summaryrefslogtreecommitdiffstats
path: root/sys/amd64/amd64/swtch.s
Commit message (Expand)AuthorAgeFilesLines
* Move SWTCH_OPTIM_STATS related code out of cpufunc.h. (This sort of statpeter2002-07-211-3/+3
* Set the thread state of the newly chosen to run thread to TDS_RUNNING injhb2002-07-121-14/+0
* Part 1 of KSE-IIIjulian2002-06-291-2/+11
* Compromise for critical*()/cpu_critical*() recommit. Cleanup the interruptdillon2002-03-271-0/+6
* revert last commit temporarily due to whining on the lists.dillon2002-02-261-6/+0
* STAGE-1 of 3 commit - allow (but do not require) interrupts to remaindillon2002-02-261-0/+6
* Attempt to patch up some style bugs introduced in the previous commitpeter2002-02-071-5/+9
* Pre-KSE/M3 commit.julian2002-02-071-13/+16
* Changed the type of pcb_flags from u_char to u_int and adjusted things.bde2002-01-171-5/+3
* Overhaul the per-CPU support a bit:jhb2001-12-111-5/+5
* Fix a typo in comment and #ifdef fixes: GRAP_PRIO -> GRAB_PRIO so thatjhb2001-10-301-1/+1
* - More whitespace and comment cleanups.jhb2001-10-281-35/+46
* Currently no code does a CROSSJUMP() to sw1a, so we don't need ajhb2001-10-251-2/+0
* Use %ecx instead of %ebx for the scratch register while updating %dr7 sincejhb2001-10-251-5/+3
* - Fix typo in comment from previous revision.jhb2001-10-251-3/+4
* Whitespace, comment, and string fixes.jhb2001-10-251-43/+39
* Split the per-process Local Descriptor Table out of the PCB and intojhb2001-10-251-4/+7
* Fix a mistake I made with the pcb movement relative to the stack in thepeter2001-09-191-2/+2
* KSE Milestone 2julian2001-09-121-35/+43
* swtch.s: During context save, use the correct bit mask for clearingbsd2001-07-191-2/+8
* Use a critical region to protect saving of the npx state in savectx().bde2001-05-201-1/+4
* Remove unneeded includes of sys/ipl.h and machine/ipl.h.jhb2001-05-151-1/+0
* Remove the leading underscore from all symbols defined in x86 asmjake2001-02-251-21/+21
* Activate USER_LDT by default. The new thread libraries are going topeter2001-02-231-3/+0
* - Don't call clear_resched() in userret(), instead, clear the resched flagjhb2001-02-201-22/+0
* Implement a unified run queue and adjust priority levels accordingly.jake2001-02-121-17/+3
* RIP <machine/lock.h>.markm2001-02-111-1/+0
* - Make astpending and need_resched process attributes rather than CPUjhb2001-02-101-3/+0
* Rename the ASSYM MTX_RECURSE to MTX_RECURSECNT in order to not conflictjake2001-01-201-2/+2
* Use #ifdef DEV_NPX from opt_npx.h instead of #if NNPX > 0 from npx.hpeter2001-01-191-5/+5
* Use %fs to access per-cpu variables in uni-processor kernels the samejake2001-01-061-6/+1
* Use _lapic+offset to access the local apic from assembly languagejake2000-12-141-2/+2
* Introduce a new potientially cleaner interface for accessing per-cpujake2000-12-131-19/+19
* Revert the previous change I made to cpu_switch. It doesn't help asjake2000-12-081-2/+4
* Change cpu_switch to explicitly popl the callers program counter andjake2000-12-031-4/+2
* - Change extra sanity checks in cpu_switch() to be conditional on INVARIANTSjhb2000-11-171-31/+3
* savectx() is now used exclusively by the crash dump system. Move thepeter2000-10-131-0/+3
* Unremoved used include of <machine/ipl.h>. Removing it in rev.1.95bde2000-10-091-0/+1
* - Change fast interrupts on x86 to push a full interrupt frame and tojhb2000-10-061-1/+0
* - Heavyweight interrupt threads on the alpha for device I/O interrupts.jhb2000-10-051-1/+0
* Implement halt-on-idle in the !SMP case, which should significantlymsmith2000-09-221-10/+0
* Major update to the way synchronization is done in the kernel. Highlightsjasone2000-09-071-208/+61
* Move <machine/ipl.h> outside #ifdef SMP because it supplies AST_RESCHED.peter2000-05-111-1/+1
* The SMP cleanup commit broke need_resched, this fixes that and alsodillon2000-03-291-1/+1
* Commit major SMP cleanups and move the BGL (big giant lock) in thedillon2000-03-281-9/+16
* Move the "sti" instruction to right before the "hlt" to close a tinyphk2000-01-021-2/+1
* $Id$ -> $FreeBSD$peter1999-08-281-1/+1
* Use the MI process selection. We use a quick routine to decide whetherpeter1999-08-191-269/+15
* Go back to the old (icu.s rev.1.7 1993) way of keeping the AST-pendingbde1999-07-101-11/+1
* Implement support for hardware debug registers on the i386.jlemon1999-07-091-1/+39
OpenPOWER on IntegriCloud