1. For ck_pr_cas_foo_value, let the inline assembly save the observed
value in a register, and store to the output reference in C.
This lets the C optimiser eliminate the memory access once the
CAS function is inlined.
2. Specify the result of the CAS as a condition code in EFLAGS instead
of executing SETcc in inline assembly, when possible. GCC gained
this functionality in GCC 6; CAS loops can now directly branch on
the condition code, without SETcc / TEST.
TESTED=existing regression tests.
On FreeBSD, atomic operations in the kernel must access the nucleus
address space. Userland may use either the atomic instruction set
which goes without an ASI (address space identifier) or specify the
primary address space.
To avoid hardcoding the address space here, we grab the corresponding
identifier from the appropriate machine header but also only for the
kernel so the namespace doesn't get polluted for userland.
* Implement ck_pr_dec_is_zero family of functions
* include/ck_pr.h: add ck_pr_{dec,inc}_is_zero and implement ck_pr_{dec,inc}_zero in terms of the new functions. Convert the architecture-specific implementations of ck_pr_foo_zero for x86 and x86-64 to ck_pr_foo_is_zero.
* regressions/ck_pr/validate: add smoke tests for ck_pr_dec_{,is_}zero and ck_pr_inc_{,is_}zero
* doc: document ck_pr_inc_is_zero
In an attempt to prevent gcc from emiting warnings, ck_pr_md_load_ptr and
ck_pr_md_store_ptr were made wrong in commit
5ae12a19d0.
load_ptr would return target instead of *target, and store would store the
value in target instead of in *target.
This is an attempt at fixing this, while still trying to avoid warnings.
This primarily affects the FreeBSD kernel, where the popcount builtin
can be problematic (relies on compiler-provided libraries). See the
history of __POPCNT__ for details [1].
- A new flag, CK_MD_CC_BUILTIN_DISABLE, can be set to indicate that CK
should not rely on compiler builtins when possible.
- ck_cc_clz has been removed, it was unused.
- ck_internal_bsf has been removed, it was duplicate of ck_cc_ffs but broken,
replaced in favor of ck_cc_ffs. Previous consumers were using the bsf
instruction, eitherway.
- ck_{rhs,hs,ht} have been updated to use ck_cc_ffs*.
If FreeBSD requires the builtins for performance reasons, we will lift the
appropriate detection into ck_md (at least, bt* bs* family of functions don't
have the same problems on most targets unlike popcount).
1: https://lists.freebsd.org/pipermail/svn-src-head/2015-March/069663.html
A note has also been added around some ambiguity with respect to WC
memory and relaxed memory semantics (so, heavier-weight mfence semantics
for strict acquire-release interface).
All fences related to atomic operations have been removed as they were
just unnecessary, and so, confusing.
Add a new configure option, --enable-lse, which is only effective for
the AArch64 architecture. When used, most ck_pr_* atomics will use Large
System Extensions instructions as per the ARMv8.1 specification, rather
then LL/SC instruction pairs.
We don't have to claim we will read the value from variables when we do not,
this was only done to work around a bug on some versions of gcc for arm
a while ago, hopefully this won't be needed here.
This should fix the (harmless) warnings described in issue #83.
These primitives are meant to be used in lock implementations
where control dependency ordering is sufficient to enforce
ordering of critical section. At the moment, this only affects
PPC. Currently, we rely on lwsync for entry into critical sections
which is insufficient. sync is rather heavy-weight, and assuming
we aren't falling victim into compiler re-ordering, isync should
be sufficient.
There is follow-up work to be done in ARM, as we may have cheaper
(but target-specialized) ISB-tricks for load-load ordering.
DECONST_PTR is a hack to deconstify void pointer values
that is safe in presence of -Wcast-qual. CK_CC_RESTRICT
is restrict qualifier that can be disabled for only
partially C99 compliant compilers.
We use some macro trickery to enforce that ck_pr_store_* is actually
storing the correct type into the target variable, without any actual
side effects--by making the assignment into an rvalue and using a
comma expression, the compiler should optimize it away.
On the load side, we simply cast the result to the type of the target
variable for pointer loads.
There is an unsafe version of the store_ptr macro called
ck_pr_store_ptr_unsafe for those times when you are _really_ sure that
you know what you're doing.
This commit also updates some of the source files (ck_ht, ck_hs,
ck_rhs): ck_ht now uses the unsafe macro, as its conversion between
uintptr_t and void * is invalid under the new macros. ck_hs and ck_rhs
have had some casts added to preserve validity.
Paul Khuong
Paul Khuong
Marius Strobl
Kevin Bowling
Theo Schlossnagle
Olivier Houchard
Samy Al Bahra
Neale Ferguson
Alexey Kopytov
alfredo
Michael Haberler
Samy Al Bahra
John Wittrock