aboutsummaryrefslogtreecommitdiff
path: root/sys/i386/include/cpufunc.h
Commit message (Expand)AuthorAgeFilesLines
* $Id$ -> $FreeBSD$Peter Wemm1999-08-281-1/+1
* Undo my previous commit and do it differently. Break the ffs() etc macrosPeter Wemm1999-08-191-14/+27
* Try using the builtin ffs() for egcs, it (by random inspection)Peter Wemm1999-08-191-1/+5
* atomic.h:Alan Cox1999-07-231-12/+1
* loadandclear() uses an atomic instruction (even on SMP, where it's anPeter Wemm1999-05-091-2/+2
* Enable vmspace sharing on SMP. Major changes are,Luoqi Chen1999-04-281-1/+33
* Don't put operands in clobber lists, since this is dubious for oldBruce Evans1999-01-091-13/+16
* Fixed some style bugs. Clarified a comment.Bruce Evans1999-01-081-13/+12
* Unspammed includes in <machine/cpufunc.h> in the !SMP case. PartiallyBruce Evans1999-01-081-10/+13
* Moved declarations related to copying and zeroing to the right place.Bruce Evans1999-01-081-2/+1
* Add macros for accessing device memory.Doug Rabson1998-08-171-1/+9
* Don't pretend to support ix86's with 16-bit ints by using longsBruce Evans1998-07-111-32/+32
* For SMP, use prv_PPAGE1/prv_PMAP1 instead of PADDR1/PMAP1.Tor Egge1998-05-171-1/+15
* Fix alot of silly LINT that I left in the code.John Dyson1998-05-121-2/+2
* Support better performance with P6 architectures and in SMPJohn Dyson1998-05-111-3/+11
* Undo previous commit. The cpuid symbol has been already used by SMPKATO Takenori1998-01-251-10/+1
* Added cpuid instruction.KATO Takenori1998-01-251-1/+10
* Implementation of Bus Space for FreeBSD-x86.Justin T. Gibbs1998-01-151-4/+4
* After one of my analysis passes to evaluate methods for SMP TLB mgmt, IJohn Dyson1997-12-141-1/+7
* General cleanup of the lock pushdown code. They are grouped and enabledSteve Passe1997-09-071-7/+3
* General cleanup of the sub-system locking macros.Steve Passe1997-09-011-3/+7
* Another round of lock pushdown.Steve Passe1997-08-301-1/+6
* Add support for 4MB pages. This includes the .text, .data, .data partsJohn Dyson1997-07-171-1/+3
* remove #include of <machine/spl.h> - they are externed nowPeter Wemm1997-05-311-3/+1
* Make setbits() SMP-safe. Eliminate the SETBITS() macro, and replaceJohn Polstra1997-05-211-2/+6
* remove #include "opt_smp.h" and <machine/smp.h>. Slightly elaborate onPeter Wemm1997-05-071-7/+3
* remove all the SMP_INVLTLB defines, making the code default for APIC_IO.Steve Passe1997-04-281-5/+7
* Try and make these usermode safe, Steve beat me in finding these..Peter Wemm1997-04-261-3/+5
* Man the liferafts! Here comes the long awaited SMP -> -current merge!Peter Wemm1997-04-261-1/+16
* Improved CPU identification and initialization routines. ThisKATO Takenori1997-03-221-1/+15
* Back out part 1 of the MCFH that changed $Id$ to $FreeBSD$. We are notPeter Wemm1997-02-221-1/+1
* Make the long-awaited change from $Id$ to $FreeBSD$Jordan K. Hubbard1997-01-141-1/+1
* Added "memory" to clobber list in invlpg(). It needs it if invltlb()Bruce Evans1996-09-291-20/+21
* Essentially rename pmap_update to be invltlb. It is a very machineJohn Dyson1996-09-281-4/+3
* Move pmap_update_1pg to cpufunc.h. Additionally,John Dyson1996-09-281-1/+7
* Fixed a few hundred warnings (2400 in LINT) for signed vs unsignedBruce Evans1996-09-241-6/+13
* Another round of merge/update.Satoshi Asami1996-09-121-49/+1
* Add an fls() inline function which does the opposite operation toGarrett Wollman1996-08-011-1/+12
* Update to current state of PC98 world.Satoshi Asami1996-07-231-1/+3
* Fixed lots of warnings about unportable casts of pointers to volatileBruce Evans1996-07-011-3/+10
* Moved declarations of non-cpu things from <machine/cpufunc.h> to betterBruce Evans1996-07-011-19/+1
* The Great PC98 Merge.Satoshi Asami1996-06-141-1/+48
* Changed bdb() to breakpoint() and always enable it.Bruce Evans1996-04-071-34/+30
* Moved rtcin() to clock.c.Bruce Evans1996-03-311-2/+1
* >Blush<. Use the correct opcode for the WRMSR instruction.Garrett Wollman1996-03-281-2/+2
* Add support for Pentium and Pentium Pro performance counters.Garrett Wollman1996-03-261-1/+35
* Removed declarations of nonexistent functions.Bruce Evans1996-01-161-10/+2
* Made bzero a function vector and added a 586/686 optimized version ofDavid Greenman1995-12-281-61/+1
* Implemented a (sorely needed for years) double fault handler to catch stackDavid Greenman1995-12-191-2/+2
* Moved inline functions for insque() and remque() to <sys/queue.h>.Bruce Evans1995-12-031-33/+1