summaryrefslogtreecommitdiffstats
path: root/sys/amd64/include/atomic.h
Commit message (Expand)AuthorAgeFilesLines
* Add an unified macro to deny ability from the compiler to reorderattilio2012-10-091-2/+2
* Use plain store for atomic_store_rel on x86, instead of implicitlykib2012-06-021-37/+37
* Inform a compiler which asm statements in the x86 implementation ofkib2010-12-181-9/+10
* Rename an argument from "exp" to "expect" since the former makes FlexeLintphk2010-05-201-7/+7
* atomic_cmpset_barr_* was added in order to cope with compilers willing toattilio2009-10-091-32/+44
* - All the functions in atomic.h needs to be in "physical" form (likeattilio2009-10-061-46/+29
* Per their definition, atomic instructions used in conjuction withattilio2009-10-061-46/+67
* - bump __FreeBSD version to reflect added buf_ring, memory barriers,kmacy2008-11-221-0/+4
* Implement atomic_fetchadd_long() for all architectures and document it.pjd2008-03-161-0/+20
* Fixed some style bugs (mainly assorted errors in comments, and inconsistentbde2006-12-291-23/+23
* Fixed some style bugs (whitespace only).bde2006-12-291-30/+31
* Try harder to garbage-collect the "LOCORE" (really asm) version ofbde2006-12-291-6/+6
* Removed gratuitous cosmetic differences with the i386 version. Thisbde2006-12-281-7/+7
* Avoid an instruction in atomic_cmpset_{int_long)() in most cases.bde2006-12-271-10/+10
* Add a new atomic_fetchadd() primitive that atomically adds a value to ajhb2005-09-271-0/+21
* Stop using the '+' constraint modifier with inline assembly. The '+'jhb2005-09-151-22/+27
* Add aliases for atomic operations on 64-bit integers just like otherjhb2005-08-181-0/+20
* Like on i386, bypass lock prefix for atomic ops on !SMP kernels.peter2005-07-211-0/+27
* Convert the atomic_ptr() operations over to operating on uintptr_tjhb2005-07-151-52/+18
* Some cleanups and tweaks to some of the atomic.h files in preparation forjhb2005-07-091-79/+63
* netchild's mega-patch to isolate compiler dependencies into a centraljoerg2005-03-021-11/+15
* Cosmetic and/or trivial sync up with i386.peter2003-11-211-4/+10
* Initial landing of SMP support for FreeBSD/amd64.peter2003-11-171-1/+1
* Commit MD parts of a loosely functional AMD64 port. This is based onpeter2003-05-011-67/+29
* Add a knob to turn on and off the CMPXCHG instruction on > i386 IA32 systems.pirzyk2002-10-141-1/+1
* Beautify. This has the side effect of improving portability andmarkm2002-07-181-39/+31
* Clean up the syntax WRT semicolons at the end of function-like-macros, and pr...markm2002-07-171-23/+74
* Make MPLOCKED work again in asm files and stringify it explicitlybmilekic2002-02-281-4/+4
* Garbage-collect the "LOCORE" version of MPLOCKED.bde2002-02-111-10/+2
* Allow the ATOMIC_ASM() macro to pass in the constraints on the V parameterjhb2001-12-181-23/+23
* Use newer constraints for atomic_cmpset().jhb2001-11-121-11/+9
* Use newer constraints for inline assembly for an operand that is both anjhb2001-11-121-21/+21
* Allow atomic ops to be somewhat safely used in userland. We always usejhb2001-10-081-3/+7
* RIP <machine/lock.h>.markm2001-02-111-4/+9
* - Sort of lie and say that %eax is an output only and not an input for thejhb2001-01-171-2/+2
* - Fix atomic_load_* and atomic_store_* to generate functions for atomic.cjhb2001-01-161-168/+123
* Fix the atomic_load_acq() and atomic_store_rel() functions to properlyjhb2001-01-141-5/+43
* The x86 atomic operations are already locked, so they do not need anjhb2000-10-281-2/+0
* - Add atomic_cmpset_{acq_,rel_,}_longjhb2000-10-251-0/+52
* - Expand the set of atomic operations to optionally include memory barriersjhb2000-10-201-2/+108
* Add atomic_readandclear_int and atomic_readandclear_long.jhb2000-10-051-2/+34
* Introduce atomic_cmpset_int() and atomic_cmpset_long() from SMPng aphk2000-09-061-0/+72
* When using _asm{} in GCC, one must specify the operand's size if oneobrien2000-05-101-9/+9
* Use the rev 1.1.2.1 code from RELENG_3 for atomic operations ratherpeter1999-10-041-19/+38
* Typo: s/__GNUC_MINOR_/__GNUC_MINOR__/peter1999-10-041-1/+1
* Allow compilation with older versions of GCC, in order to make it possibleeivind1999-10-031-0/+23
* $Id$ -> $FreeBSD$peter1999-08-281-1/+1
* Create callable (non-inline) versions of the atomic_OP_TYPE functionsalc1999-08-181-3/+14
* atomic.h:alc1999-07-231-4/+4
* Commit the correct patch, i.e., the one that actually correspondsalc1999-07-131-35/+55
OpenPOWER on IntegriCloud