aboutsummaryrefslogtreecommitdiff
path: root/sys/sys/smp.h
Commit message (Expand)AuthorAgeFilesLines
* Allow a rendezvous with just a specified CPU too.John Birrell2008-05-231-1/+6
* - Remove the old smp cpu topology specification with a new, more flexibleJeff Roberson2008-03-021-9/+32
* Initial checkin for rmlock (read mostly lock) a multi reader single writerStephan Uphoff2007-11-081-0/+1
* Rename the KDB_STOP_NMI kernel option to STOP_NMI and make it apply to allJohn Baldwin2005-10-241-3/+0
* Implement an alternate method to stop CPUs when entering DDB. Normally we useDoug White2005-04-301-0/+4
* /* -> /*- for license, minor formatting changesWarner Losh2005-01-071-1/+1
* ooops finish last commit.Julian Elischer2004-09-031-3/+4
* Move 4bsd specific experimental IP code into the 4bsd file.Julian Elischer2004-09-031-1/+0
* Give the 4bsd scheduler the ability to wake up idle processorsJulian Elischer2004-09-011-1/+6
* s/smp_rv_mtx/smp_ipi_mtx/gDavid E. O'Brien2004-08-281-1/+1
* Commit Doug White and Alan Cox's fix for the cross-ipi smp deadlock.Peter Wemm2004-08-231-0/+1
* Change the type of the various CPU masks to cpumask_t. Note that asMarcel Moolenaar2004-03-271-6/+6
* Fix all users of mp_maxid to use the same semantics, namely:John Baldwin2003-12-031-1/+1
* Export a few SMP related symbols in UP kernels as well. This is needed toJohn Baldwin2003-12-031-6/+7
* - Split cpu_mp_probe() into two parts. cpu_mp_setmaxid() is still calledJohn Baldwin2003-11-211-0/+6
* - Add structures for defining cpu topologies more complex than SMP.Jeff Roberson2003-06-281-0/+27
* Forward declare struct thread.Jake Burkholder2002-05-201-0/+2
* Add needed includes of machine/smp.h, remove nested include in sys/smp.hJake Burkholder2002-03-071-1/+0
* Add a new variable mp_maxid. This is used so that per cpu datastructures mayJeff Roberson2002-03-051-0/+1
* Make smp_started volatile in sys/smp.h and remove the volatileMarcel Moolenaar2001-10-311-1/+1
* KSE Milestone 2Julian Elischer2001-09-121-1/+1
* Move CPU_ABSENT() macro to smp.h, where it belongs anyway. It will beBosko Milekic2001-08-011-1/+9
* - Split out the support for per-CPU data from the SMP code. UP kernelsJohn Baldwin2001-05-101-6/+0
* Overhaul of the SMP code. Several portions of the SMP kernel support haveJohn Baldwin2001-04-271-137/+46
* Remove the BETTER_CLOCK #ifdef's. The code is on by default and is hereJohn Baldwin2001-04-101-2/+0
* Defer assignment of low level interrupt handlers for PCI interruptsTor Egge2001-01-281-0/+1
* Move io_apic_{read,write} from apic_ipl.s (where they do not belong) intoPeter Wemm2000-12-061-4/+3
* GC unused assembler function apic_eoi()Peter Wemm2000-12-061-1/+0
* Cleanup some leftover lint from the old interrupt system.Peter Wemm2000-12-041-6/+1
* Move MAXCPU from machine/smp.h to machine/param.h to fix breakagePaul Saab2000-09-231-10/+0
* Remove the NCPU, NAPIC, NBUS, NINTR config options. Make NAPIC,Paul Saab2000-09-221-12/+11
* Make LINT compile.Poul-Henning Kamp2000-09-161-1/+1
* Test for both SMP and I386_CPU being set before generating an error.John Baldwin2000-09-071-1/+1
* Major update to the way synchronization is done in the kernel. HighlightsJason Evans2000-09-071-34/+4
* Increase the default NAPIC from 1 to 2 as a bandaid until we allocateMike Smith2000-08-181-1/+1
* Be more verbose when changing APIC ID on an IO APIC.Tor Egge2000-08-061-0/+1
* Further fixes for multiple-IO-APIC systems from Tor Egge:Mike Smith2000-05-311-0/+1
* The SMP cleanup commit broke UP compiles. Make UP compiles work again.Matthew Dillon2000-03-281-1/+18
* ISA device drivers use the ISA source interrupt number in locations whereTor Egge2000-01-041-0/+2
* Change #ifdef KERNEL to #ifdef _KERNEL in the public headers. "KERNEL"Peter Wemm1999-12-291-2/+2
* Fix from Tor so that if we enter the debugger in the tristate going toMatt Jacob1999-09-251-0/+1
* $Id$ -> $FreeBSD$Peter Wemm1999-08-281-1/+1
* Implement an all-CPU shootdown-style rendezvous facility. This allowsMike Smith1999-07-201-1/+6
* Enable vmspace sharing on SMP. Major changes are,Luoqi Chen1999-04-281-8/+1
* Maintain a mapping from irq number to (ioapic number, int pin) tuple,Tor Egge1998-09-061-9/+13
* Add forwarding of roundrobin to other cpus. This gives a more regularTor Egge1998-05-171-1/+5
* Add two workarounds for broken MP tables:Tor Egge1998-04-011-1/+2
* Declare some variables modified by interrupt handlers as volatile.Tor Egge1998-04-011-3/+3
* This mega-commit is meant to fix numerous interrelated problems. ThereJohn Dyson1998-03-071-3/+3
* Remove special handling for resuming clock interrupt when using APIC_IO.Tor Egge1998-03-051-8/+1