aboutsummaryrefslogtreecommitdiff
path: root/sys/i386/include/atomic.h
Commit message (Expand)AuthorAgeFilesLines
* x86 atomics: Remove unused WANT_FUNCTIONSOlivier Certner2025-01-171-15/+0
* atomics: Constify loadsOlivier Certner2025-01-171-12/+16
* i386: Fix a typo in a source code commentGordon Bergling2024-04-271-1/+1
* sys: Remove $FreeBSD$: two-line .h patternWarner Losh2023-08-231-2/+0
* spdx: The BSD-2-Clause-FreeBSD identifier is obsolete, drop -FreeBSDWarner Losh2023-07-251-1/+1
* x86 atomic.h: remove obsoleted commentKonstantin Belousov2022-02-111-8/+0
* x86 atomics: use lock prefix unconditionallyKonstantin Belousov2022-02-111-36/+16
* x86 atomic.h: cleanup comments for preprocessor directivesKonstantin Belousov2022-02-111-2/+2
* Expand generic subword atomic primitivesConrad Meyer2020-03-251-0/+1
* i386: hide more of atomic 64-bit definitions under _KERNELAndriy Gapon2019-10-081-0/+2
* i386: Implement atomic_load_64(9) and atomic_store_64(9).Konstantin Belousov2019-08-181-0/+2
* Implement missing atomic_fcmpset_XXX() support for i386.Hans Petter Selasky2018-08-091-0/+51
* Make sure kernel modules built by default are portable between UP andHans Petter Selasky2018-07-061-2/+2
* inline atomics and allow tied modules to inline locksMatt Macy2018-07-021-1/+1
* Implement atomic_add_64() and atomic_subtract_64() for the i386 target.Hans Petter Selasky2018-05-291-0/+36
* Add atomic_load(9) and atomic_store(9) operations.Konstantin Belousov2017-12-191-0/+2
* sys/i386: further adoption of SPDX licensing ID tags.Pedro F. Giffuni2017-11-271-0/+2
* Implement atomic_fetchadd_64() for i386. This function is needed by theHans Petter Selasky2017-11-241-0/+12
* - Remove 'struct vmmeter' from 'struct pcpu', leaving only global vmmeterGleb Smirnoff2017-04-171-1/+1
* Adjust the constraint for "src" in atomic_(f)cmpset_8.Mark Johnston2017-03-271-6/+6
* Add support for 8- and 16-bit atomic_(f)cmpset to x86.Mark Johnston2017-03-221-37/+74
* For i386, remove config options CPU_DISABLE_CMPXCHG, CPU_DISABLE_SSEKonstantin Belousov2017-02-031-29/+0
* i386: fixup fcmpsetMateusz Guzik2017-02-021-2/+2
* i386: add atomic_fcmpsetMateusz Guzik2017-01-301-0/+34
* atomic: Add testandclear on i386/amd64Sepherosa Ziehau2016-05-161-0/+26
* Improve comments.Konstantin Belousov2015-07-301-3/+3
* Use private cache line for the locked nop in *mb() on i386.Konstantin Belousov2015-07-301-32/+39
* MFamd64 r285934: Remove store/load (= full) barrier from the i386Konstantin Belousov2015-07-291-17/+7
* Add the atomic_thread_fence() family of functions with intent toKonstantin Belousov2015-07-081-0/+32
* Add a comment about too strong semantic of atomic_load_acq() on x86.Konstantin Belousov2015-06-291-0/+9
* Remove unneeded data dependency, currently imposed byKonstantin Belousov2015-06-281-49/+74
* Implement atomic_cmpset_64() and atomic_swap_64() for i386.Jung-uk Kim2013-08-211-0/+113
* Reimplement atomic_load_acq_64() and atomic_store_rel_64() for i386. TheseJung-uk Kim2013-08-211-82/+110
* Remove empty lines before return statements for style consistency.Jung-uk Kim2013-08-211-6/+0
* Implement atomic_swap() and atomic_testandset().Jung-uk Kim2013-08-211-19/+43
* - Remove the "a" constraint from main output operand for atomic_cmpset().Jung-uk Kim2013-08-211-5/+5
* Use '+' modifier for a memory operand that is both an input and an output.Jung-uk Kim2013-08-211-29/+21
* Remove bogus labels. No functional change.Jung-uk Kim2013-08-211-1/+0
* Use consistent style. No functional change.Jung-uk Kim2013-08-211-10/+10
* Add an unified macro to deny ability from the compiler to reorderAttilio Rao2012-10-091-2/+2
* Use plain store for atomic_store_rel on x86, instead of implicitlyKonstantin Belousov2012-06-021-39/+39
* Implement atomic_load_acq_64(9) and atomic_store_rel_64(9) for i386. TheseJung-uk Kim2011-04-061-0/+86
* Inform a compiler which asm statements in the x86 implementation ofKonstantin Belousov2010-12-181-6/+7
* Rename an argument from "exp" to "expect" since the former makes FlexeLintPoul-Henning Kamp2010-05-201-8/+8
* atomic_cmpset_barr_* was added in order to cope with compilers willing toAttilio Rao2009-10-091-64/+48
* - All the functions in atomic.h needs to be in "physical" form (likeAttilio Rao2009-10-061-45/+50
* Per their definition, atomic instructions used in conjuction withAttilio Rao2009-10-061-46/+73
* Restore memory clobber, to cause mb on the compiler level too.Konstantin Belousov2008-12-061-3/+3
* Unconditionally use locked addition of zero to tip of the stack forKonstantin Belousov2008-12-051-14/+3
* - bump __FreeBSD version to reflect added buf_ring, memory barriers,Kip Macy2008-11-221-0/+15