| Commit message (Expand) | Author | Age | Files | Lines |
* | Add the atomic_thread_fence() family of functions with intent to | kib | 2015-07-08 | 1 | -0/+41 |
* | Small performance optimization. Clobber only cr0, rather than the entire CR. | jhibbits | 2014-04-11 | 1 | -18/+18 |
* | Described in the man page but not implemented. Here it comes, | andreast | 2014-01-13 | 1 | -0/+37 |
* | Add a missing " to get closer to compiling. | bz | 2012-05-24 | 1 | -1/+1 |
* | Atomic operation acquire barriers also need to be isync on 64-bit systems. | nwhitehorn | 2012-05-24 | 1 | -1/+1 |
* | Revert isync for ILP32 to sync as per my original change that I discussed | marcel | 2012-05-24 | 1 | -4/+4 |
* | Fix the memory barriers for CPUs that do not like lwsync and wedge or cause | marcel | 2012-05-24 | 1 | -12/+22 |
* | Fix final bugs in memory barriers on PowerPC: | nwhitehorn | 2012-05-04 | 1 | -5/+0 |
* | Provide a clearer split between read/write and acquire/release barriers. | nwhitehorn | 2012-04-22 | 1 | -19/+24 |
* | Clarify what we are doing in r234583 a little better: eieio and isync do | nwhitehorn | 2012-04-22 | 1 | -15/+23 |
* | On non-64-bit systems (which generally don't have lwsync), use eieio and | nwhitehorn | 2012-04-22 | 1 | -0/+5 |
* | Use lwsync to provide memory barriers on systems that support it instead | nwhitehorn | 2012-04-22 | 1 | -20/+18 |
* | Merge r221614,221696,221737,221840 from largeSMP project branch: | attilio | 2011-05-22 | 1 | -258/+262 |
* | MFppc64: | nwhitehorn | 2010-07-13 | 1 | -21/+158 |
* | Unbreak previous commit. | marcel | 2008-11-22 | 1 | -2/+0 |
* | - bump __FreeBSD version to reflect added buf_ring, memory barriers, | kmacy | 2008-11-22 | 1 | -0/+4 |
* | Fix copy-n-paste typos in free text. | marcel | 2008-04-10 | 1 | -3/+3 |
* | Reimplement atomic_add, atomic_clear, atomic_set and atomic_subtract | marcel | 2008-04-09 | 1 | -272/+294 |
* | Quick fix for the kernel build breakage in netgraph and the | marcel | 2008-04-08 | 1 | -2/+4 |
* | Implement atomic_fetchadd_long() for all architectures and document it. | pjd | 2008-03-16 | 1 | -0/+2 |
* | Define atomic_readandclear_ptr. | jasone | 2007-11-27 | 1 | -0/+1 |
* | Implement the _long functions using u_long rather than trying to | jb | 2007-11-26 | 1 | -5/+43 |
* | Define atomic_cmpset_acq_long and atomic_cmpset_rel_long so that | jb | 2007-11-19 | 1 | -2/+4 |
* | Cast the arguments to atomic_*_ptr() when mapping it to atomic_*_32() | marcel | 2007-07-10 | 1 | -3/+8 |
* | Add a new atomic_fetchadd() primitive that atomically adds a value to a | jhb | 2005-09-27 | 1 | -0/+13 |
* | Stop using the '+' constraint modifier with inline assembly. The '+' | jhb | 2005-09-15 | 1 | -12/+12 |
* | Convert the atomic_ptr() operations over to operating on uintptr_t | jhb | 2005-07-15 | 1 | -63/+20 |
* | netchild's mega-patch to isolate compiler dependencies into a central | joerg | 2005-03-02 | 1 | -6/+10 |
* | - change all u_int_XX to uint_XX | grehan | 2005-02-01 | 1 | -39/+39 |
* | Fix bugs with operand ordering and unnecessary sync/eieio ops. Mostly | grehan | 2003-01-18 | 1 | -59/+71 |
* | Fixed branch labels | grehan | 2002-09-19 | 1 | -5/+5 |
* | Make atomic_cmpset_32 correctly return 0 on failure. | benno | 2002-02-24 | 1 | -0/+3 |
* | Fix the atomic_*_32 operations. These were written before I had the ability | benno | 2001-06-27 | 1 | -19/+19 |
* | Don't initialise ret in atomic_cmpset_32. | benno | 2001-06-26 | 1 | -2/+1 |
* | Fix asm constraints for atomic_cmpset_32. This fix may also be needed | benno | 2001-06-24 | 1 | -1/+1 |
* | This commit (along with one pending in sys/dev/ofw and one in sys/conf) give | benno | 2001-06-16 | 1 | -25/+27 |
* | PowerPC atomic operation functions. | benno | 2001-01-07 | 1 | -56/+298 |
* | Shells for the atomic operations FreeBSD needs. | obrien | 2001-01-01 | 1 | -0/+228 |