2d4524dd3e
ck_spinlock: Retab (whitespace).
...
Accidentally had Haskell vim modeline set.
12 years ago
07aab518f6
ck_spinlock: Retab (whitespace).
12 years ago
ce142f17f8
ck_spinlock: Add ck_spinlock_mcs_init operation.
12 years ago
6bc9f7a485
ck_spinlock: Get rid of MCS context initializers.
...
They are unnecessary, legacy from older versions.
12 years ago
ec58f5dcf7
ck_spinlock: Add ck_spinlock_dec_init operation.
12 years ago
2f52ace54c
ck_spinlock: Fix strict aliasing issue in unlock (no-op).
...
For builds with -Werror. Not pointed out by Wez Furlong <wez@f....>.
12 years ago
f214d9419e
ck_spinlock: Move elision prototype to end of file.
12 years ago
59a1b53e86
ck_spinlock: Migrate to ck_elide.h.
...
Pending unit test updates.
12 years ago
0517a51b06
ck_spinlock: Weaken volatile store in clh_lock.
12 years ago
64b1201dcc
ck_spinlock: Acquire semantics for old locked operations.
...
Even though the intended use-case is for testing, developers
may want correctness guarantees in other situations.
12 years ago
a51c8c7aa6
ck_spinlock: Add ck_spinlock_clh_locked.
12 years ago
46d61ccd46
ck_spinlock: Add ck_spinlock_ticket_locked.
12 years ago
55decd0b38
ck_spinlock: Add ck_spinlock_anderson_locked.
12 years ago
a8a74b9f57
ck_spinlock: Remove erroneous mask usage for non-x86 targets.
12 years ago
045d0e1053
ck_spinlock: Apply modulo arithmetic to proportional back-off ticket lock.
12 years ago
a5e8d6ad45
ck_spinlock: Only enable trylock for ck_spinlock_ticket on x86*.
...
trylock algorithm semantics are not cleanly defined outside of x86.
12 years ago
2ba3f59374
ck_spinlock: Migrate MCS to ck_pr_fence_X_Y.
...
This includes fixing acquire semantics on mcs_lock fast path.
This represents an additional fence on the fast path for
acquire semantics post-acquisition.
12 years ago
8540821f3f
ck_spinlock: Minor style changes to return statement.
12 years ago
8face51e0d
ck_spinlock: Acquire semantics for anderson spinlock.
12 years ago
d09e48daed
ck_spinlock: Only enable trylock path for TSO architectures at the moment.
12 years ago
27d454248d
ck_spinlock: Add ticket lock with trylock operation.
...
Upon popular request, added a variant of the ticket spinlock
with trylock support. This is pending additional verification
on other architectures besides x86*. It is still unclear whether
this implementation will be the default as it is has slower
fast path.
Add trylock support to the ck_spinlock validation tests.
It currently only tests ck_spinlock_ticket_t trylock
functionality if available.
12 years ago
0598307186
whitespace: Various style changes.
12 years ago
33a9222923
legal: Update Copyright statements.
12 years ago
65ebf86799
ck_spinlock: Switch to full semantics across all implementations.
...
More importantly, trylock previously didn't have full semantics.
12 years ago
1d61147c01
ck_spinlock/mcs: Remove unnecessary fences, serialize unload.
12 years ago
79e336cfbc
ck_spinlock: Clarify ticket spinlock code.
...
Some people might be confused as far as lack of
fencing in the lock. Add a comment to clarify that
old values should not be equal to new values
of current position (where acquiring the current position
already has a global ordering).
12 years ago
27ed5f78fe
ck_spinlock: Remove unnecessary fence in DEC-based spinlock.
12 years ago
a7c4b9df65
ck_spinlock: Adopt RMO for anderson spinlock.
12 years ago
ce4cdd45c8
ck_spinlock: Adopt RMO semantics for CLH.
12 years ago
3cf265cba0
all: Strip trailing whitespaces.
13 years ago
706fd07de7
legal: Update Copyright statements.
13 years ago
1cefea7eb6
ck_spinlock: Provide a default implementation.
...
Several users in the past have noted it was difficult for them
to decide what spinlock implementation to use. In light of this,
a light-weight greedy default is chosen (currently ck_spinlock_fas).
13 years ago
0231b68a8b
ck_spinlock: Add ck_spinlock_*_locked.
...
This class of functions detects whether or not the
lock is currently acquired.
13 years ago
4e7c6ee270
Add full barrier for anderson spinlock.
13 years ago
38c614222a
ck_spinlock: Avoid modulus on unlock for power of 2 count.
14 years ago
492faed9a3
Reformatting changes for my new laptop.
14 years ago
66ebe1a874
Drop usage of CK_CC_PACKED, prefer natural alignment.
...
CK_CC_PACKED will drop structures to one-byte alignment in certain
cases. Obviously, this will mean bad performance on most architectures.
Thanks to Matt Johnson from https://rigel.crhc.illinois.edu/ for
reporting this problem.
14 years ago
d3a033237a
Avoid modulus for wrap-around calculation in ck_anderson.
...
This change has shown a 32% reduction in latency for the reference
SPARCv9 platform.
14 years ago
cbd30b2206
Initial import.
14 years ago
Samy Al Bahra
Samy Al Bahra
Samy Al Bahra