| History log of /src/lib/libc/atomic |
| Revision | Date | Author | Comments |
| 1.5 | 09-Apr-2022 |
riastradh | Introduce membar_acquire/release. Deprecate membar_enter/exit.
The names membar_enter/exit were unclear, and the documentation of
membar_enter has disagreed with the implementations on sparc,
powerpc, and even x86(!) for the entire time it has been in NetBSD.
The terms `acquire' and `release' are ubiquitous in the literature
today, and have been adopted in the C and C++ standards to mean
load-before-load/store and load/store-before-store, respectively,
which are exactly the orderings required by acquiring and releasing a
mutex, as well as other useful applications like decrementing a
reference count and then freeing the underlying object if it went to
zero.
Originally I proposed changing one word in the documentation for
membar_enter to make it load-before-load/store instead of
store-before-load/store, i.e., to make it an acquire barrier. I
proposed this on the grounds that
(a) all implementations guarantee load-before-load/store,
(b) some implementations fail to guarantee store-before-load/store,
and
(c) all uses in-tree assume load-before-load/store.
I verified parts (a) and (b) (except, for (a), powerpc didn't even
guarantee load-before-load/store -- isync isn't necessarily enough;
need lwsync in general -- but it _almost_ did, and it certainly didn't
guarantee store-before-load/store).
Part (c) might not be correct, however: under the mistaken assumption
that atomic-r/m/w then membar-w/rw is equivalent to atomic-r/m/w then
membar-r/rw, I only audited the cases of membar_enter that _aren't_
immediately after an atomic-r/m/w. All of those cases assume
load-before-load/store. But my assumption was wrong -- there are
cases of atomic-r/m/w then membar-w/rw that would be broken by
changing to atomic-r/m/w then membar-r/rw:
https://mail-index.netbsd.org/tech-kern/2022/03/29/msg028044.html
Furthermore, the name membar_enter has been adopted in other places
like OpenBSD where it actually does follow the documentation and
guarantee store-before-load/store, even if that order is not useful.
So the name membar_enter currently lives in a bad place where it
means either of two things -- r/rw or w/rw.
With this change, we deprecate membar_enter/exit, introduce
membar_acquire/release as better names for the useful pair (r/rw and
rw/w), and make sure the implementation of membar_enter guarantees
both what was documented _and_ what was implemented, making it an
alias for membar_sync.
While here, rework all of the membar_* definitions and aliases. The
new logic follows a rule to make it easier to audit:
membar_X is defined as an alias for membar_Y iff membar_X is
guaranteed by membar_Y.
The `no stronger than' relation is (the transitive closure of):
- membar_consumer (r/r) is guaranteed by membar_acquire (r/rw)
- membar_producer (w/w) is guaranteed by membar_release (rw/w)
- membar_acquire (r/rw) is guaranteed by membar_sync (rw/rw)
- membar_release (rw/w) is guaranteed by membar_sync (rw/rw)
And, for the deprecated membars:
- membar_enter (whether r/rw, w/rw, or rw/rw) is guaranteed by
membar_sync (rw/rw)
- membar_exit (rw/w) is guaranteed by membar_release (rw/w)
(membar_exit is identical to membar_release, but the name is
deprecated.)
Finally, while here, annotate some of the instructions with their
semantics. For powerpc, leave an essay with citations on the
unfortunate but -- as far as I can tell -- necessary decision to use
lwsync, not isync, for membar_acquire and membar_consumer.
Also add membar(3) and atomic(3) man page links.
|
| 1.4 | 07-Dec-2019 |
riastradh | Add missing MLINK for membar_datadep_consumer(3).
Detected by the indefatigable wizd.
|
| 1.3 | 27-Aug-2016 |
dholland | branches: 1.3.14;
Add MLINKS for atomic_add_nv, atomic_cas_ni, and so forth - otherwise
you have to remember that they're the same page as plain atomic_add and
atomic_cas, or remember one of the types that they're defined on.
PR 51033.
|
| 1.2 | 12-Feb-2010 |
dyoung | Link atomic_cas.3 to atomic_cas_{32,64,ptr,uint,ulong}_ni.3.
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8;
Install manual pages for the atomic ops.
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file Makefile.inc was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file Makefile.inc was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.3.14.1 | 08-Apr-2020 |
martin | Merge changes from current as of 20200406
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8;
Install manual pages for the atomic ops.
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file atomic_add.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file atomic_add.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.2 | 16-Jun-2018 |
dholland | atomic_and/atomic_or do bitwise ops, not logical ops.
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8; 1.1.62;
Install manual pages for the atomic ops.
|
| 1.1.62.1 | 25-Jun-2018 |
pgoyette | Sync with HEAD
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file atomic_and.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file atomic_and.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.5 | 02-Feb-2014 |
dholland | bump date for previous
|
| 1.4 | 02-Feb-2014 |
dholland | Reorg second paragraph too, to group related info together.
|
| 1.3 | 02-Feb-2014 |
dholland | Rework description for clarity; prompted by chat comments from bad@.
|
| 1.2 | 12-Feb-2010 |
dyoung | branches: 1.2.6; 1.2.12;
With help from rmind@, describe the non-interlocked (*_ni) variants of
the standard atomic compare-and-swap operations. Tell some caveats.
Manual page links, *_ni.3 -> atomic_cas.3 are coming up after a
successful 'build.sh distribution'.
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8;
Install manual pages for the atomic ops.
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file atomic_cas.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file atomic_cas.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.2.12.1 | 20-Aug-2014 |
tls | Rebase to HEAD as of a few days ago.
|
| 1.2.6.1 | 22-May-2014 |
yamt | sync with head.
for a reference, the tree before this commit was tagged
as yamt-pagecache-tag8.
this commit was splitted into small chunks to avoid
a limitation of cvs. ("Protocol error: too many arguments")
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8;
Install manual pages for the atomic ops.
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file atomic_dec.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file atomic_dec.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8;
Install manual pages for the atomic ops.
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file atomic_inc.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file atomic_inc.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.9 | 06-Sep-2023 |
ad | Node that aarch64 implements CAS.
|
| 1.8 | 16-Jun-2018 |
dholland | branches: 1.8.12;
atomic_and/atomic_or do bitwise ops, not logical ops.
|
| 1.7 | 07-Feb-2018 |
martin | branches: 1.7.2;
Bump date for previous
|
| 1.6 | 07-Feb-2018 |
martin | Fix typo, from Eitan Adler.
|
| 1.5 | 14-Apr-2010 |
jruoho | Bump date for previous. (How hard can it be to remember this.)
|
| 1.4 | 14-Apr-2010 |
jruoho | Use subtitles instead of a list.
|
| 1.3 | 18-May-2009 |
wiz | Punctuation nit. Remove superfluous .Pp.
|
| 1.2 | 18-May-2009 |
wiz | Fix typo in Dd argument.
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8;
Install manual pages for the atomic ops.
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file atomic_ops.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file atomic_ops.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.7.2.1 | 25-Jun-2018 |
pgoyette | Sync with HEAD
|
| 1.8.12.1 | 20-Jul-2024 |
martin | Pull up following revision(s) (requested by rin in ticket #748):
lib/libc/atomic/atomic_ops.3: revision 1.9
Note that aarch64 implements CAS.
|
| 1.2 | 16-Jun-2018 |
dholland | atomic_and/atomic_or do bitwise ops, not logical ops.
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8; 1.1.62;
Install manual pages for the atomic ops.
|
| 1.1.62.1 | 25-Jun-2018 |
pgoyette | Sync with HEAD
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file atomic_or.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file atomic_or.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8;
Install manual pages for the atomic ops.
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file atomic_swap.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file atomic_swap.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.10 | 09-Apr-2022 |
riastradh | Introduce membar_acquire/release. Deprecate membar_enter/exit.
The names membar_enter/exit were unclear, and the documentation of
membar_enter has disagreed with the implementations on sparc,
powerpc, and even x86(!) for the entire time it has been in NetBSD.
The terms `acquire' and `release' are ubiquitous in the literature
today, and have been adopted in the C and C++ standards to mean
load-before-load/store and load/store-before-store, respectively,
which are exactly the orderings required by acquiring and releasing a
mutex, as well as other useful applications like decrementing a
reference count and then freeing the underlying object if it went to
zero.
Originally I proposed changing one word in the documentation for
membar_enter to make it load-before-load/store instead of
store-before-load/store, i.e., to make it an acquire barrier. I
proposed this on the grounds that
(a) all implementations guarantee load-before-load/store,
(b) some implementations fail to guarantee store-before-load/store,
and
(c) all uses in-tree assume load-before-load/store.
I verified parts (a) and (b) (except, for (a), powerpc didn't even
guarantee load-before-load/store -- isync isn't necessarily enough;
need lwsync in general -- but it _almost_ did, and it certainly didn't
guarantee store-before-load/store).
Part (c) might not be correct, however: under the mistaken assumption
that atomic-r/m/w then membar-w/rw is equivalent to atomic-r/m/w then
membar-r/rw, I only audited the cases of membar_enter that _aren't_
immediately after an atomic-r/m/w. All of those cases assume
load-before-load/store. But my assumption was wrong -- there are
cases of atomic-r/m/w then membar-w/rw that would be broken by
changing to atomic-r/m/w then membar-r/rw:
https://mail-index.netbsd.org/tech-kern/2022/03/29/msg028044.html
Furthermore, the name membar_enter has been adopted in other places
like OpenBSD where it actually does follow the documentation and
guarantee store-before-load/store, even if that order is not useful.
So the name membar_enter currently lives in a bad place where it
means either of two things -- r/rw or w/rw.
With this change, we deprecate membar_enter/exit, introduce
membar_acquire/release as better names for the useful pair (r/rw and
rw/w), and make sure the implementation of membar_enter guarantees
both what was documented _and_ what was implemented, making it an
alias for membar_sync.
While here, rework all of the membar_* definitions and aliases. The
new logic follows a rule to make it easier to audit:
membar_X is defined as an alias for membar_Y iff membar_X is
guaranteed by membar_Y.
The `no stronger than' relation is (the transitive closure of):
- membar_consumer (r/r) is guaranteed by membar_acquire (r/rw)
- membar_producer (w/w) is guaranteed by membar_release (rw/w)
- membar_acquire (r/rw) is guaranteed by membar_sync (rw/rw)
- membar_release (rw/w) is guaranteed by membar_sync (rw/rw)
And, for the deprecated membars:
- membar_enter (whether r/rw, w/rw, or rw/rw) is guaranteed by
membar_sync (rw/rw)
- membar_exit (rw/w) is guaranteed by membar_release (rw/w)
(membar_exit is identical to membar_release, but the name is
deprecated.)
Finally, while here, annotate some of the instructions with their
semantics. For powerpc, leave an essay with citations on the
unfortunate but -- as far as I can tell -- necessary decision to use
lwsync, not isync, for membar_acquire and membar_consumer.
Also add membar(3) and atomic(3) man page links.
|
| 1.9 | 15-Feb-2022 |
riastradh | membar_ops(3): xref bus_dma, bus_space in SEE ALSO section too
|
| 1.8 | 09-Oct-2020 |
uwe | Add italic correction to _Atomic-qualified.
|
| 1.7 | 09-Oct-2020 |
riastradh | Reword advice about when not to use membar_exit.
With help from skrll and pgoyette.
While here, change the example so it doesn't violate the advice just
given. Still not a great example -- abusing UINT_MAX for a reference
count is kinda sketchy, but it'll serve for now.
|
| 1.6 | 03-Sep-2020 |
riastradh | Update membar_ops(3) man page with examples and relation to C11.
Add exhortation to always always always document how membars come in
pairs for synchronization between two CPUs when you use them.
|
| 1.5 | 24-Oct-2017 |
abhinav | branches: 1.5.6;
Add membar_datadep_consumer to the NAME section
Remove Pp before Bl
|
| 1.4 | 08-Jan-2015 |
riastradh | Introduce membar_datadep_consumer.
Discussed briefly on tech-kern without objection:
https://mail-index.netbsd.org/tech-kern/2014/11/20/msg018054.html
https://mail-index.netbsd.org/tech-kern/2015/01/07/msg018326.html
|
| 1.3 | 28-Apr-2011 |
wiz | branches: 1.3.22;
Fix a typo.
|
| 1.2 | 18-May-2009 |
wiz | Fix typo in Dd argument. Remove superfluous .Pp.
|
| 1.1 | 23-Jun-2008 |
ad | branches: 1.1.2; 1.1.8;
Install manual pages for the atomic ops.
|
| 1.1.8.2 | 23-Jun-2008 |
ad | Install manual pages for the atomic ops.
|
| 1.1.8.1 | 23-Jun-2008 |
ad | file membar_ops.3 was added on branch christos-time_t on 2008-06-23 10:22:41 +0000
|
| 1.1.2.2 | 18-Sep-2008 |
wrstuden | Sync with wrstuden-revivesa-base-2.
|
| 1.1.2.1 | 23-Jun-2008 |
wrstuden | file membar_ops.3 was added on branch wrstuden-revivesa on 2008-09-18 04:39:20 +0000
|
| 1.3.22.1 | 18-Mar-2015 |
snj | Pull up following revision(s) (requested by riastradh in ticket #600):
common/lib/libc/arch/alpha/atomic/membar_ops.S: revision 1.7
lib/libc/atomic/membar_ops.3: revision 1.4
sys/arch/alpha/include/types.h: revision 1.50
sys/sys/atomic.h: revision 1.13
Introduce membar_datadep_consumer.
Discussed briefly on tech-kern without objection:
https://mail-index.netbsd.org/tech-kern/2014/11/20/msg018054.html
https://mail-index.netbsd.org/tech-kern/2015/01/07/msg018326.html
|
| 1.5.6.1 | 13-Sep-2020 |
martin | Pull up following revision(s) (requested by riastradh in ticket #1082):
share/man/man9/atomic_loadstore.9: revision 1.6
share/man/man9/ipi.9: revision 1.5
lib/libc/atomic/membar_ops.3: revision 1.6
Spell out acronyms in title for clarity.
Update membar_ops(3) man page with examples and relation to C11.
Add exhortation to always always always document how membars come in
pairs for synchronization between two CPUs when you use them.
atomic_load/store_* appeared in NetBSD 9, not 10.
Pullup preceded release of 9.0.
|
