wireguard-openbsd/sys/arch, branch jd/queueboosts WireGuard implementation for the OpenBSD kernel https://git.zx2c4.com/wireguard-openbsd/atom/sys/arch?h=jd%2Fqueueboosts 2020-06-23T01:21:29Z Implement pci_intr_establish_cpu() for pyro(4) and vpci(4) based sparc64 2020-06-23T01:21:29Z jmatthew jmatthew@openbsd.org 2020-06-23T01:21:29Z urn:sha1:1d9e937e45405d8fccbf06a258cd97fbc51591ce systems. MSIs on these systems are delivered to event queues, which trigger interrupts when non-empty. The interrupt handler dequeues the MSIs and converts them into soft interrupts, which run on the same cpu as the event queue interrupt. To target pci device interrupts to different cpus, we set up an event queue per cpu in the system, or as many as we can, if there are fewer event queues available. For now, we don't have a way to feed this information back to intrmap, so instead we just map interrupts for cpus that don't have an event queue to another cpu that does have one. Tested on V215 (pyro), T5120, T4-1, S7-2 (vpci). dlg@ got the pyro side of it working for me. ok dlg@ kettenis@ Add opalcons(4), a driver for the OPAL console. 2020-06-22T21:13:40Z kettenis kettenis@openbsd.org 2020-06-22T21:13:40Z urn:sha1:9cff15ef82ea860b6c29be0e577000460a15a956 The minimum frame size for the ELFv2 ABI is 32 bytes. Using this value 2020-06-22T18:49:36Z kettenis kettenis@openbsd.org 2020-06-22T18:49:36Z urn:sha1:4d943fd61ab7ebc3390510da6f072b3fbd6ff841 instead of 48 in the trap setup functions makes it possible to get rid of the magic offset in proc_trampoline. Suggested by gkoehler@ Enable interrupts when they were enabled before the trap (except when we 2020-06-22T18:15:50Z kettenis kettenis@openbsd.org 2020-06-22T18:15:50Z urn:sha1:be00ebe64ffda37c7ac803f330b1c897f12b55ea are handling "genuine" interrupts like the decrementer and hypervisor virtualization interrupts). Handle data storage and data segment interrupts from userland as well. 2020-06-22T18:03:22Z kettenis kettenis@openbsd.org 2020-06-22T18:03:22Z urn:sha1:c0e8dfc26859acc5c80a7cd731a9232aad396d94 Make return-to-user and kernel re-entry work. This adds a per-pmap SLB 2020-06-22T16:58:20Z kettenis kettenis@openbsd.org 2020-06-22T16:58:20Z urn:sha1:37d56e14ef1a0db6f4d11db0ecc4e6ce6dbee7df cache. We might want to turn that in a per-proc cache at some point, but this gets us to the point where we can sucessfully have init(1) do its first system call. Fix previous commit; pasted instructed in the wrong spot. 2020-06-22T16:47:10Z kettenis kettenis@openbsd.org 2020-06-22T16:47:10Z urn:sha1:ebbbb1399a0803cd282701c7145a2416733aed07 Add magic offset to make the frames line up. 2020-06-22T16:22:58Z kettenis kettenis@openbsd.org 2020-06-22T16:22:58Z urn:sha1:286b57f10e8b965d73d463d8f6fb53e3e1839071 Implement setregs(). 2020-06-22T16:09:33Z kettenis kettenis@openbsd.org 2020-06-22T16:09:33Z urn:sha1:aaaa4eb26a2f615e1506ab12948314c8db7eb051 Provide working definitions of PROC_STACK() and PROC_PC(). 2020-06-22T13:52:40Z kettenis kettenis@openbsd.org 2020-06-22T13:52:40Z urn:sha1:717af3c7dd8043a8a6063e7ee0c7c5d9a7f79459