Commit Graph

18 Commits

Author SHA1 Message Date
matt 77f07e0bd7 Use the thumb1 versions of sev/wfe for thumb && armv6+.
if using armv5t don't do anything for thumb.
2013-08-15 22:37:29 +00:00
matt 8837651bdf Use .inst instead of wfe/sev to shut up gas. 2012-09-19 07:57:14 +00:00
matt 2f1e74f8c5 Add a pthread__smt_wake and add support for it on arm along with
pthread__smt_pause.  These are implemented using the ARM instructions
SEV (wake) and WFE (pause).  These are treated as NOPs on ARM CPUs that
don't support them.
2012-08-16 04:49:47 +00:00
christos c5d359be42 make pthread__sp unsigned long. 2011-01-25 19:12:04 +00:00
ad a61915e94f Remove unused code that's confusing when using cscope/opengrok. 2009-05-16 22:20:40 +00:00
ad de2138164c Remove the PTHREAD_SA option. If M:N threads is reimplemented it's
better off done with a seperate library.
2007-03-02 18:53:51 +00:00
perry 4e11af46bc Remove leading __ from __(const|inline|signed|volatile) -- it is obsolete. 2005-12-24 21:11:15 +00:00
rearnsha cd8021f51e Use RET macro for returning. 2004-08-21 11:31:44 +00:00
cl 89d0cfd21f Remove possible race condition in upcall recycling. 2003-09-07 14:47:44 +00:00
skrll 795970599f Typo in comment. 2003-07-24 08:03:44 +00:00
nathanw d37a996a49 Adapt to structure name changes. 2003-07-17 20:55:25 +00:00
nathanw 9639eeaf54 Adapt to pt_trapuc: change STACK_SWITCH to check for a value in pt_trapuc
and use it preferentially to a value in pt_uc, clearing it once on the new
stack. Move stores into pt_uc back to before the stack switch; storing
after the stack switch opened a one-instruction race condition where an upcall
that had just started a chain could be preempted again, and would bomb when
restarted due to its pt_uc not yet having been updated. Now that pt_trapuc
is what the upcall code writes to, it is safe to store to pt_uc before
switching stacks.

Remove obsolete pt_sleepuc code.
2003-06-26 01:45:31 +00:00
nathanw 1414a095ac Remove PT_SLEEPUC and add PT_TRAPUC. 2003-06-26 01:29:28 +00:00
nathanw f866ba061d Two fixes:
* In switch-away cases, write PT_SWITCHTO last (after PT_SWITCHTOUC), so
   that pthread__resolve_locks() doesn't see an empty SWITCHTOUC value. This
   also permits pthread__resolve_locks() to use the presence of PT_SWITCHTO
   as a sign that the thread has done all of its necessary chain work.

 * Make the return-point of pthread__switch global and visible, so that its
   address can be compared to the PC of a thread, again as a sign that its
   chain-work is done.

(other architectures in progress, after they get the *previous* asm fix...)
2003-06-12 21:46:03 +00:00
bjh21 55cecd0f26 NetBSD/acorn26 has used APCS-32 for years, so unifdef -U__APCS_26__. 2003-04-05 23:15:10 +00:00
thorpej 04d0b802f7 Include <sys/types> before <sys/lock.h>, shuffle <ucontext.h>. 2003-03-13 19:51:33 +00:00
christos 3823415af9 add missing backslash 2003-01-18 18:40:08 +00:00
thorpej c62a74e6d5 Merge the nathanw_sa branch. 2003-01-18 10:32:11 +00:00