Cross Reference: /src/lib/libpthread/arch

History log of /src/lib/libpthread/arch
Revision	Date	Author	Comments
1.2	25-May-2023	riastradh	libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437 XXX pullup-10
1.1	10-Aug-2014	matt	branches: 1.1.4; 1.1.18; 1.1.28; 1.1.36; Preliminary files for AARCH64 (64-bit ARM) support. Enough for a distribution build.
1.1.36.1	01-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #296): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.1.28.1	04-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #1700): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.1.18.1	04-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #1878): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.1.4.2	20-Aug-2014	tls	Rebase to HEAD as of a few days ago.
1.1.4.1	10-Aug-2014	tls	file pthread_md.h was added on branch tls-maxphys on 2014-08-20 00:02:20 +0000
1.5	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.4	28-Apr-2008	martin	branches: 1.4.8; Remove clause 3 and 4 from TNF licenses
1.3	08-Oct-2007	skrll	branches: 1.3.6; Provide PTHREAD__ASM_RASOPS for alpha. The gcc generated lock try RAS is broken as the store needs to be the last instruction.
1.2	18-Jan-2003	thorpej	branches: 1.2.24; Merge the nathanw_sa branch.
1.1	25-Sep-2001	nathanw	branches: 1.1.2; file _context_u.S was initially added on branch nathanw_sa.
1.1.2.3	14-Jan-2003	nathanw	Save and restore process-unique value.
1.1.2.2	17-Dec-2001	nathanw	Update to work with Klaus's mcontext code. Save and restore FP registers.
1.1.2.1	25-Sep-2001	nathanw	Alpha MD files for the pthread lib.
1.2.24.1	06-Nov-2007	matt	sync with HEAD
1.3.6.1	18-May-2008	yamt	sync with head.
1.4.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.4.8.1	28-Apr-2008	martin	file _context_u.S was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.8	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.7	28-Apr-2008	martin	branches: 1.7.8; Remove clause 3 and 4 from TNF licenses
1.6	02-Mar-2007	ad	branches: 1.6.12; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.5	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.4	17-Jul-2003	nathanw	Adapt to structure name changes.
1.3	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	25-Sep-2001	nathanw	branches: 1.1.2; file genassym.cf was initially added on branch nathanw_sa.
1.1.2.3	14-Jan-2003	nathanw	Save and restore process-unique value.
1.1.2.2	17-Dec-2001	nathanw	Update to work with Klaus's mcontext code.
1.1.2.1	25-Sep-2001	nathanw	Alpha MD files for the pthread lib.
1.6.12.1	18-May-2008	yamt	sync with head.
1.7.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.7.8.1	28-Apr-2008	martin	file genassym.cf was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.1	18-May-2009	njoly	Restore PTHREAD__ASM_RASOPS for alpha (from _context_u.S), that was lost in previous cleanup. ok by ad@.
1.1	22-Nov-2024	riastradh	branches: 1.1.4; libpthread: Fix expected symbols on alpha and hppa. These have PTHREAD__ASM_RASOPS and define a different subset of symbols which get exported. None of these pthread__ras_* and pthread__lock_* symbols _should_ be exported but we can fix that in a future revbump. PR lib/58838: shared libraries in base should all have expsym lists
1.1.4.2	02-Aug-2025	perseant	Sync with HEAD
1.1.4.1	22-Nov-2024	perseant	file pthread_md.expsym was added on branch perseant-exfatfs on 2025-08-02 05:54:56 +0000
1.7	25-Jan-2011	christos	make pthread__sp unsigned long.
1.6	16-May-2009	ad	branches: 1.6.2; Remove unused code that's confusing when using cscope/opengrok.
1.5	28-Apr-2008	martin	branches: 1.5.8; Remove clause 3 and 4 from TNF licenses
1.4	08-Oct-2007	skrll	branches: 1.4.6; Provide PTHREAD__ASM_RASOPS for alpha. The gcc generated lock try RAS is broken as the store needs to be the last instruction.
1.3	24-Dec-2005	perry	branches: 1.3.12; Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	25-Sep-2001	nathanw	branches: 1.1.2; file pthread_md.h was initially added on branch nathanw_sa.
1.1.2.7	16-Jan-2003	thorpej	* Move the pthread_sigmask() prototype to <signal.h>. * Don't include <signal.h> in <pthread.h>. * Add code to the signal trampoline to convert from the ucontext to a sigcontext, and back again (XXX though, only callee-save regs for _UC_USER contexts). This is necessary in order to support e.g. GCC's libjava, which depends on the traditional Unix semantics of changes made to the sigcontext being visible when the handler returns.
1.1.2.6	06-Dec-2002	nathanw	ucontext/sigcontext glue.
1.1.2.5	22-Oct-2002	nathanw	Define _INITCONTEXT_U_MD() to set the status register to a reasonable value.
1.1.2.4	06-Aug-2002	nathanw	Add struct reg/mcontext conversion glue.
1.1.2.3	17-Dec-2001	nathanw	Update to work with Klaus's mcontext code.
1.1.2.2	14-Nov-2001	briggs	Add pthread__uc_pc() to pthread_md.h instead of making assumptions about the contents of the m.d. mcontext.
1.1.2.1	25-Sep-2001	nathanw	Alpha MD files for the pthread lib.
1.3.12.1	06-Nov-2007	matt	sync with HEAD
1.4.6.1	18-May-2008	yamt	sync with head.
1.5.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.5.8.1	28-Apr-2008	martin	file pthread_md.h was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.6.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.6	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.5	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.4	26-Jun-2003	nathanw	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.
1.3	12-Jun-2003	nathanw	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...)
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	25-Sep-2001	nathanw	branches: 1.1.2; file pthread_switch.S was initially added on branch nathanw_sa.
1.1.2.3	13-Jan-2003	nathanw	Rewrite pthread__switch() and adjust pthread__locked_switch() to avoid storing the new saved-context pointer while still using the old stack. This avoids a race condition with pthread__find_interrupted() where a thread could lose its old state if it was interrupted in a certain window in pthread__switch().
1.1.2.2	17-Dec-2001	nathanw	Update to work with Klaus's mcontext code.
1.1.2.1	25-Sep-2001	nathanw	Alpha MD files for the pthread lib.
1.5	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.4	21-Aug-2004	rearnsha	Use RET macro for returning.
1.3	05-Apr-2003	bjh21	NetBSD/acorn26 has used APCS-32 for years, so unifdef -U__APCS_26__.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	16-Nov-2001	thorpej	branches: 1.1.2; file _context_u.S was initially added on branch nathanw_sa.
1.1.2.8	27-Nov-2001	bjh21	In GETC(), rather than faking a CPSR, save the real one if we're can, and zero otherwise (ie if we're on a 26-bit CPU). I suspect this isn't actually necessary, but it's cheap, and it should make it easier for debuggers and suchlike to work out what's going on.
1.1.2.7	22-Nov-2001	bjh21	_UC_USER \| _UC_CPU happens to be a valid ARM constant, so we can load it in a single cycle.
1.1.2.6	22-Nov-2001	thorpej	In the GETC() macro, don't actually save r14 (lr) and r15 (pc). r14 is caller-save, so we don't need to save it in the _REG_LR slot. Instead, we save it in the _REG_PC slot so that when the context is resumed, we end up at the insn after the call site. Fixes the "cu6" test in Nathan's test suite. "cu1" - "cu5" also function correctly (as they did before this change).
1.1.2.5	21-Nov-2001	thorpej	ome improvements, based on suggestions from Ben Harris: * Don't need to save CPSR in GETC(), since it's a caller-saved register. However, stuff a fake one (that indicates USR32 mode) into the ucontext in case it is used later in a setcontext(2) system call (as is done in one of Nathan's regression tests; this last bit from me). * Only restore CPSR if ! _UC_USER (i.e. context was created by getcontext(2)). * Determine at run-time if we're in USR26 or USR32 by forcing the Z flag to be set and then comparing the PC portion of R15 to all of R15 (if they're not equal, we're in 26-bit mode). * Restore banked regs properly in 26-bit mode. Plus one from me: Don't or _UC_USER \| _UC_CPU into uc_flags; set uc_flags to that value instead.
1.1.2.4	20-Nov-2001	thorpej	Clean up SAVE_FLAGS/RESTORE_FLAGS, and make sure to fetch the flags from the correct place in the ucontext (not past the END of the ucontext) in the SETC() macro.
1.1.2.3	20-Nov-2001	thorpej	Make sure to set _UC_CPU in _getcontext_u().
1.1.2.2	18-Nov-2001	thorpej	Note that we need to think about what to do regarding hard and soft FP context.
1.1.2.1	16-Nov-2001	thorpej	First cut at machine-dependent pthread bits for ARM.
1.8	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.7	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.6	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.5	17-Jul-2003	nathanw	Adapt to structure name changes.
1.4	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.3	13-Mar-2003	thorpej	Include <sys/types> before <sys/lock.h>, shuffle <ucontext.h>.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	16-Nov-2001	thorpej	branches: 1.1.2; file genassym.cf was initially added on branch nathanw_sa.
1.1.2.2	22-Nov-2001	thorpej	Move the _REG_PC definition up with the other _REG_* definitions.
1.1.2.1	16-Nov-2001	thorpej	First cut at machine-dependent pthread bits for ARM.
1.13	25-May-2023	riastradh	libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437 XXX pullup-10
1.12	25-May-2023	riastradh	libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) XXX pullup-10
1.11	22-Nov-2018	skrll	branches: 1.11.2; 1.11.10; G/C __APCS_26__ support
1.10	17-Jul-2017	skrll	branches: 1.10.2; 1.10.4; 1.10.6; Typo in comment
1.9	15-Aug-2013	matt	branches: 1.9.18; Use the thumb1 versions of sev/wfe for thumb && armv6+. if using armv5t don't do anything for thumb.
1.8	19-Sep-2012	matt	Use .inst instead of wfe/sev to shut up gas.
1.7	16-Aug-2012	matt	branches: 1.7.2; 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.
1.6	25-Jan-2011	christos	branches: 1.6.4; make pthread__sp unsigned long.
1.5	16-May-2009	ad	branches: 1.5.2; Remove unused code that's confusing when using cscope/opengrok.
1.4	24-Dec-2005	perry	Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.3	18-Jan-2003	christos	add missing backslash
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	16-Nov-2001	thorpej	branches: 1.1.2; file pthread_md.h was initially added on branch nathanw_sa.
1.1.2.4	17-Jan-2003	nathanw	Add _INITCONTEXT_U_MD() code that sets up the PC or CPSR. Adjust PTHREAD_UCONTEXT_TO_REG() to set a plausable value in reg->r_cpsr when _UC_USER is set in the ucontext; otherwise, GDB gets very confused and thinks it's dealing with 26-bit ARM state.
1.1.2.3	20-Dec-2002	thorpej	Update for mcontext_t changes.
1.1.2.2	06-Aug-2002	thorpej	Add glue for libpthread_dbg.
1.1.2.1	16-Nov-2001	thorpej	First cut at machine-dependent pthread bits for ARM.
1.5.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.6.4.2	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")
1.6.4.1	30-Oct-2012	yamt	sync with head
1.7.2.2	20-Aug-2014	tls	Rebase to HEAD as of a few days ago.
1.7.2.1	20-Nov-2012	tls	Resync to 2012-11-19 00:00:00 UTC
1.9.18.1	04-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #1878): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.10.6.1	10-Jun-2019	christos	Sync with HEAD
1.10.4.1	26-Nov-2018	pgoyette	Sync with HEAD, resolve a couple of conflicts
1.10.2.2	17-Jul-2017	skrll	2167115
1.10.2.1	17-Jul-2017	skrll	file pthread_md.h was added on branch perseant-stdc-iso10646 on 2017-07-17 20:24:08 +0000
1.11.10.1	01-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #296): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.11.2.1	04-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #1700): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.9	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.8	21-Aug-2004	rearnsha	Use RET macro for returning.
1.7	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.6	24-Jul-2003	skrll	Typo in comment.
1.5	26-Jun-2003	nathanw	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.
1.4	12-Jun-2003	nathanw	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...)
1.3	05-Apr-2003	bjh21	NetBSD/acorn26 has used APCS-32 for years, so unifdef -U__APCS_26__.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	16-Nov-2001	thorpej	branches: 1.1.2; file pthread_switch.S was initially added on branch nathanw_sa.
1.1.2.3	14-Jan-2003	nathanw	Rewrite pthread__switch() to avoid storing the new saved-context pointer while still using the old stack. This avoids a race condition with pthread__find_interrupted() where a thread could lose its old state if it was interrupted in a certain window in pthread__switch().
1.1.2.2	22-Nov-2001	bjh21	Correct a typo in STACK_SWITCH(), where it used the wrong register to compute the stack pointer. This patch gets test "cond2" working on ARM.
1.1.2.1	16-Nov-2001	thorpej	First cut at machine-dependent pthread bits for ARM.
1.5	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.4	11-Aug-2008	skrll	branches: 1.4.6; Remove unnecessary include.
1.3	28-Apr-2008	martin	branches: 1.3.2; Remove clause 3 and 4 from TNF licenses
1.2	24-Sep-2007	skrll	branches: 1.2.6; Resurrect the function pointers for lock operations and allow each architecture to provide asm versions of the RAS operations. We do this because relying on the compiler to get the RAS right is not sensible. (It gets alpha wrong and hppa is suboptimal) Provide asm RAS ops for hppa. (A slightly different version) reviewed by Andrew Doran.
1.1	19-Jul-2004	chs	branches: 1.1.18; add hppa MD libpthread bits. translated from MIPS.
1.1.18.1	06-Nov-2007	matt	sync with HEAD
1.2.6.1	18-May-2008	yamt	sync with head.
1.3.2.1	18-Sep-2008	wrstuden	Sync with wrstuden-revivesa-base-2.
1.4.6.2	11-Aug-2008	skrll	Remove unnecessary include.
1.4.6.1	11-Aug-2008	skrll	file _context_u.S was added on branch christos-time_t on 2008-08-11 21:45:25 +0000
1.4	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.3	28-Apr-2008	martin	branches: 1.3.8; Remove clause 3 and 4 from TNF licenses
1.2	02-Mar-2007	ad	branches: 1.2.12; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.1	19-Jul-2004	chs	add hppa MD libpthread bits. translated from MIPS.
1.2.12.1	18-May-2008	yamt	sync with head.
1.3.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.3.8.1	28-Apr-2008	martin	file genassym.cf was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.2	19-May-2022	skrll	Use RAS_{START,END}_ASM_HIDDEN
1.1	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.1	22-Nov-2024	riastradh	branches: 1.1.4; libpthread: Fix expected symbols on alpha and hppa. These have PTHREAD__ASM_RASOPS and define a different subset of symbols which get exported. None of these pthread__ras_* and pthread__lock_* symbols _should_ be exported but we can fix that in a future revbump. PR lib/58838: shared libraries in base should all have expsym lists
1.1.4.2	02-Aug-2025	perseant	Sync with HEAD
1.1.4.1	22-Nov-2024	perseant	file pthread_md.expsym was added on branch perseant-exfatfs on 2025-08-02 05:54:56 +0000
1.8	25-Jan-2011	christos	make pthread__sp unsigned long.
1.7	16-May-2009	ad	branches: 1.7.2; Remove unused code that's confusing when using cscope/opengrok.
1.6	28-Apr-2008	martin	branches: 1.6.8; Remove clause 3 and 4 from TNF licenses
1.5	10-Feb-2008	ad	branches: 1.5.4; - Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.4	24-Sep-2007	skrll	Resurrect the function pointers for lock operations and allow each architecture to provide asm versions of the RAS operations. We do this because relying on the compiler to get the RAS right is not sensible. (It gets alpha wrong and hppa is suboptimal) Provide asm RAS ops for hppa. (A slightly different version) reviewed by Andrew Doran.
1.3	24-Dec-2005	perry	branches: 1.3.12; __asm__ -> __asm
1.2	24-Dec-2005	perry	Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.1	19-Jul-2004	chs	add hppa MD libpthread bits. translated from MIPS.
1.3.12.2	23-Mar-2008	matt	sync with HEAD
1.3.12.1	06-Nov-2007	matt	sync with HEAD
1.5.4.1	18-May-2008	yamt	sync with head.
1.6.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.6.8.1	28-Apr-2008	martin	file pthread_md.h was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.7.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.2	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.1	19-Jul-2004	chs	add hppa MD libpthread bits. translated from MIPS.
1.3	08-Oct-1997	scottr	This incarnation of the pthreads library is ancient and not useful, and should have been mothballed some time ago...
1.2	07-Jan-1994	mycroft	Delete special rules for syscall.S; they are not needed, and one of them is wrong anyway.
1.1	14-Nov-1993	proven	branches: 1.1.1; Initial revision
1.1.1.1	14-Nov-1993	proven	Initial release of the POSIX 1003.4a Draft 7 thread implementation.
1.10	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.9	28-Apr-2008	martin	branches: 1.9.8; Remove clause 3 and 4 from TNF licenses
1.8	10-Feb-2008	ad	branches: 1.8.4; - Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.7	13-Nov-2007	ad	Mutexes: - Play scrooge again and chop more cycles off acquire/release. - Spin while the lock holder is running on another CPU (adaptive mutexes). - Do non-atomic release. Threadreg: - Add the necessary hooks to use a thread register. - Add the code for i386, using %gs. - Leave i386 code disabled until xen and COMPAT_NETBSD32 have the changes.
1.6	13-Nov-2007	ad	For PR bin/37347: - Override __libc_thr_init() instead of using our own constructor. - Add pthread__getenv() and use instead of getenv(). This is used before we are up and running and unfortunatley getenv() takes locks. Other changes: - Cache the spinlock vectors in pthread__st. Internal spinlock operations now take 1 function call instead of 3 (i386). - Use pthread__self() internally, not pthread_self(). - Use __attribute__ ((visibility("hidden"))) in some places. - Kill PTHREAD_MAIN_DEBUG.
1.5	08-Sep-2007	ad	- Get rid of self->pt_mutexhint and use pthread__mutex_owned() instead. - Update some comments and fix minor bugs. Minor cosmetic changes. - Replace some spinlocks with mutexes and rwlocks. - Change the process private semaphores to use mutexes and condition variables instead of doing the synchronization directly. Spinlocks are no longer used by the semaphore code.
1.4	07-Sep-2007	ad	- Don't take the mutex's spinlock (ptr_interlock) in pthread_cond_wait(). Instead, make the deferred wakeup list a per-thread array and pass down the lwpid_t's that way. - In pthread_cond_wait(), take the mutex before dealing with early wakeup. In this way there should never be contention on the CV's spinlock if the app follows POSIX rules (there should only be contention on the user-provided mutex). - Add a port of the kernel's rwlocks. The rwlock's spinlock is only taken if there is contention. This is enabled where atomic ops are available. Right now that is only i386 and amd64 because I don't have other hardware to test with. It's trivial to add stubs for other architectures as long as they have compare-and-swap. When we have proper atomic ops the old rwlock code can be removed. - Add a new mutex implementation that's similar to the kernel's mutexes, but uses compare-and-swap to maintain the waiters list, so no spinlocks are involved. Same caveats apply as for the rwlocks.
1.3	07-Sep-2007	ad	Add: pthread__atomic_cas_ptr, pthread__atomic_swap_ptr, pthread__membar_full This is a stopgap until the thorpej-atomic branch is complete.
1.2	18-Jan-2003	thorpej	branches: 1.2.20; 1.2.24; Merge the nathanw_sa branch.
1.1	13-Jul-2001	nathanw	branches: 1.1.2; file _context_u.S was initially added on branch nathanw_sa.
1.1.2.10	06-Sep-2002	nathanw	In the xmm case, FPSAVE should be "fxsave", and FPLOAD should be "fxrstor", not the other way around. Note to self: Lay off the crack.
1.1.2.9	14-Aug-2002	nathanw	Define, initialize, and use function pointers for _{set,get,swap}context_u routines, with different versions for saving FP state with fnsave or fxsave, depending on the machdep.osfxsr sysctl.
1.1.2.8	24-Apr-2002	nathanw	Save FP state in user context switches. XXX1: doing something clever about lazy-FP-switching would be good. XXX2: coping with SSE/SSE2 regsisters would also be good.
1.1.2.7	01-Mar-2002	nathanw	Restore FP state if the kernel handed us any. [xmms no longer sounds like it's playing Play-Skool LPs]
1.1.2.6	11-Feb-2002	nathanw	Implement _UC_USER for i386: only save callee-save registers, and set a flag saying so; on restore, if that flag is set, only restore the callee-save registers. Speeds up the user-only version of these routines by 35-40% on a Pentium MMX 233.
1.1.2.5	04-Sep-2001	nathanw	Generate and use symbolic constants for register offsets in mcontext_t, instead of hand-coding offset numbers.
1.1.2.4	02-Aug-2001	nathanw	Don't bother even storing 0s into the fields for the caller-save registers (eax, ecx, edx) and unused fields (esp, trapno, err). Still need to deal more sanely with segment registers.
1.1.2.3	02-Aug-2001	nathanw	Adjust SETC (used by _setcontext_u and _getcontext_u) to not set the new stack pointer until all the possibly-interesting data below the new SP has been preserved. Unfortunately, it's about 3% slower.
1.1.2.2	31-Jul-2001	nathanw	Whitespace cleanup.
1.1.2.1	13-Jul-2001	nathanw	Make userlevel-only *context functions part of libpthread rather than libc.
1.2.24.3	23-Mar-2008	matt	sync with HEAD
1.2.24.2	09-Jan-2008	matt	sync with HEAD
1.2.24.1	06-Nov-2007	matt	sync with HEAD
1.2.20.1	10-Sep-2007	skrll	Sync with HEAD.
1.8.4.1	18-May-2008	yamt	sync with head.
1.9.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.9.8.1	28-Apr-2008	martin	file _context_u.S was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.9	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.8	07-Jul-2008	gmcgarry	branches: 1.8.6; Selector registers are 16-bit and binutils 2.18 insists that only 16-bit accesses are permitted on them. Therefore, change movl to movw. No change to machine code generated.
1.7	28-Apr-2008	martin	branches: 1.7.2; Remove clause 3 and 4 from TNF licenses
1.6	20-Jan-2007	christos	branches: 1.6.12; fix warning about indirect call without *
1.5	30-Nov-2004	nathanw	Punt to setcontext() system call if the PSL_T bit (single-step trap) is set, so that the single-step trap happens in the thread's context and not in the middle of _setcontext_u. XXX might be able to do something here with iret, too, but it needs more testing.
1.4	10-Nov-2004	kent	save&restore %fs and %gs registers for USER_LDT applications. PR#26900
1.3	30-Oct-2003	yamt	branches: 1.3.2; use explicit "l" suffixes. (eg. lea -> leal)
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	14-Aug-2002	nathanw	branches: 1.1.2; file _getsetc.S was initially added on branch nathanw_sa.
1.1.2.4	22-Oct-2002	skrll	RCSId police.
1.1.2.3	04-Sep-2002	nathanw	The _UC_USER_BIT case of SETC (currently) needs to load FP state. Found by inspection.
1.1.2.2	15-Aug-2002	nathanw	Bit values are not the same as bit positions; fix the test for the _UC_FPU flag.
1.1.2.1	14-Aug-2002	nathanw	Define, initialize, and use function pointers for _{set,get,swap}context_u routines, with different versions for saving FP state with fnsave or fxsave, depending on the machdep.osfxsr sysctl.
1.3.2.1	12-Nov-2004	jmc	Pullup rev 1.4 (requested by kent in ticket #969) save&restore %fs and %gs registers for USER_LDT applications. PR#26900
1.6.12.1	18-May-2008	yamt	sync with head.
1.7.2.1	18-Sep-2008	wrstuden	Sync with wrstuden-revivesa-base-2.
1.8.6.2	07-Jul-2008	gmcgarry	Selector registers are 16-bit and binutils 2.18 insists that only 16-bit accesses are permitted on them. Therefore, change movl to movw. No change to machine code generated.
1.8.6.1	07-Jul-2008	gmcgarry	file _getsetc.S was added on branch christos-time_t on 2008-07-07 13:07:56 +0000
1.8	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.7	28-Apr-2008	martin	branches: 1.7.8; Remove clause 3 and 4 from TNF licenses
1.6	02-Mar-2007	ad	branches: 1.6.12; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.5	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.4	17-Jul-2003	nathanw	Adapt to structure name changes.
1.3	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	05-Mar-2001	nathanw	branches: 1.1.2; file genassym.cf was initially added on branch nathanw_sa.
1.1.2.9	14-Aug-2002	nathanw	Define, initialize, and use function pointers for _{set,get,swap}context_u routines, with different versions for saving FP state with fnsave or fxsave, depending on the machdep.osfxsr sysctl.
1.1.2.8	25-Mar-2002	nathanw	Define a couple of constants for FP register use.
1.1.2.7	11-Feb-2002	nathanw	Implement _UC_USER for i386: only save callee-save registers, and set a flag saying so; on restore, if that flag is set, only restore the callee-save registers. Speeds up the user-only version of these routines by 35-40% on a Pentium MMX 233.
1.1.2.6	04-Sep-2001	nathanw	Generate and use symbolic constants for register offsets in mcontext_t, instead of hand-coding offset numbers.
1.1.2.5	04-Sep-2001	nathanw	Define STACKSPACE in pthread_md.h, not directly in pthread_switch.S
1.1.2.4	01-Aug-2001	nathanw	Create an offset for pt_sleepuc.
1.1.2.3	31-Jul-2001	nathanw	Create an asm symbol for the offset of EIP in the ucontext.
1.1.2.2	13-Jul-2001	nathanw	Note copyright. Standardize RCS IDs.
1.1.2.1	05-Mar-2001	nathanw	The beginnings of a scheduler activations-based pthread library.
1.6.12.1	18-May-2008	yamt	sync with head.
1.7.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.7.8.1	28-Apr-2008	martin	file genassym.cf was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.4	08-Oct-1997	scottr	This incarnation of the pthreads library is ancient and not useful, and should have been mothballed some time ago...
1.3	07-Feb-1994	proven	More wrapper functions, and some hacks for machine independent sleep mechanisms.
1.2	20-Dec-1993	proven	Copyrights added to each file.
1.1	14-Nov-1993	proven	branches: 1.1.1; Initial revision
1.1.1.1	14-Nov-1993	proven	Initial release of the POSIX 1003.4a Draft 7 thread implementation.
1.4	08-Oct-1997	scottr	This incarnation of the pthreads library is ancient and not useful, and should have been mothballed some time ago...
1.3	20-Dec-1993	proven	Copyrights added to each file.
1.2	15-Nov-1993	proven	OK one more try at getting it right ...
1.1	14-Nov-1993	proven	branches: 1.1.1; Initial revision
1.1.1.1	14-Nov-1993	proven	Initial release of the POSIX 1003.4a Draft 7 thread implementation.
1.7	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.6	29-Mar-2009	ad	- Make the threadreg code use _lwp_setprivate() instead of MD hooks. XXX This must not be enabled by default because the LWP private mechanism is reserved for TLS. It is provided only as a test/demo. XXX Since ucontext_t does not contain the thread private variable, for a short time after threads are created their thread specific data is unset. If a signal arrives during that time we are screwed. - No longer need pthread__osrev. - Rearrange _lwp_ctl() calls slightly.
1.5	28-Apr-2008	martin	branches: 1.5.8; 1.5.10; Remove clause 3 and 4 from TNF licenses
1.4	13-Nov-2007	ad	branches: 1.4.6; Mutexes: - Play scrooge again and chop more cycles off acquire/release. - Spin while the lock holder is running on another CPU (adaptive mutexes). - Do non-atomic release. Threadreg: - Add the necessary hooks to use a thread register. - Add the code for i386, using %gs. - Leave i386 code disabled until xen and COMPAT_NETBSD32 have the changes.
1.3	08-Mar-2003	lukem	branches: 1.3.24; add __RCSID()
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	15-Aug-2002	nathanw	branches: 1.1.2; file pthread_md.c was initially added on branch nathanw_sa.
1.1.2.1	15-Aug-2002	nathanw	Actually add this file.
1.3.24.1	09-Jan-2008	matt	sync with HEAD
1.4.6.1	18-May-2008	yamt	sync with head.
1.5.10.1	13-May-2009	jym	Sync with HEAD. Third (and last) commit. See http://mail-index.netbsd.org/source-changes/2009/05/13/msg221222.html
1.5.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.5.8.1	28-Apr-2008	martin	file pthread_md.c was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.21	25-May-2023	riastradh	libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437 XXX pullup-10
1.20	02-Mar-2012	joerg	branches: 1.20.24; 1.20.34; 1.20.42; Avoid getcontext() as it triggers clobbering warnings. Use inline assembler to get the fields directly. Saves a system call as side effect.
1.19	24-Feb-2011	joerg	branches: 1.19.4; Allow storing and receiving the LWP private pointer via ucontext_t on all platforms except VAX and IA64. Add fast access via register for AMD64, i386 and SH3 ports. Use this fast access in libpthread to replace the stack based pthread_self(). Implement skeleton support for Alpha, HPPA, PowerPC, SPARC and SPARC64, but leave it disabled. Ports that support this feature provide __HAVE____LWP_GETPRIVATE_FAST in machine/types.h and a corresponding __lwp_getprivate_fast in machine/mcontext.h. This material is based upon work partially supported by The NetBSD Foundation under a contract with Joerg Sonnenberger.
1.18	25-Jan-2011	christos	make pthread__sp unsigned long.
1.17	16-May-2009	ad	branches: 1.17.2; Remove unused code that's confusing when using cscope/opengrok.
1.16	29-Mar-2009	ad	- Make the threadreg code use _lwp_setprivate() instead of MD hooks. XXX This must not be enabled by default because the LWP private mechanism is reserved for TLS. It is provided only as a test/demo. XXX Since ucontext_t does not contain the thread private variable, for a short time after threads are created their thread specific data is unset. If a signal arrives during that time we are screwed. - No longer need pthread__osrev. - Rearrange _lwp_ctl() calls slightly.
1.15	23-Jun-2008	ad	branches: 1.15.6; 1.15.8; pthread__threadreg_get: mark it const.
1.14	28-Apr-2008	martin	branches: 1.14.2; Remove clause 3 and 4 from TNF licenses
1.13	22-Mar-2008	ad	branches: 1.13.2; Cheat and add inlines for _atomic_cas_ptr() to work around gcc emitting unneeded PIC stuff in mutex_lock() and mutex_unlock(), when a thread register is used.
1.12	10-Feb-2008	ad	- Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.11	13-Nov-2007	ad	Mutexes: - Play scrooge again and chop more cycles off acquire/release. - Spin while the lock holder is running on another CPU (adaptive mutexes). - Do non-atomic release. Threadreg: - Add the necessary hooks to use a thread register. - Add the code for i386, using %gs. - Leave i386 code disabled until xen and COMPAT_NETBSD32 have the changes.
1.10	24-Sep-2007	skrll	Resurrect the function pointers for lock operations and allow each architecture to provide asm versions of the RAS operations. We do this because relying on the compiler to get the RAS right is not sensible. (It gets alpha wrong and hppa is suboptimal) Provide asm RAS ops for hppa. (A slightly different version) reviewed by Andrew Doran.
1.9	08-Sep-2007	ad	- Get rid of self->pt_mutexhint and use pthread__mutex_owned() instead. - Update some comments and fix minor bugs. Minor cosmetic changes. - Replace some spinlocks with mutexes and rwlocks. - Change the process private semaphores to use mutexes and condition variables instead of doing the synchronization directly. Spinlocks are no longer used by the semaphore code.
1.8	07-Sep-2007	ad	Add: pthread__atomic_cas_ptr, pthread__atomic_swap_ptr, pthread__membar_full This is a stopgap until the thorpej-atomic branch is complete.
1.7	29-Mar-2006	cube	branches: 1.7.8; 1.7.12; Instead of using hard-coded values for various registers, get them from the current context. Valid values can change depending on how the kernel is setup. i386 and amd64 happen to be setup differently.
1.6	24-Dec-2005	perry	Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.5	11-Feb-2004	nathanw	branches: 1.5.4; 1.5.6; Add ucontext conversion macros for an "extra" register set.
1.4	18-Jan-2003	christos	delint
1.3	18-Jan-2003	christos	de-lint
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	05-Mar-2001	nathanw	branches: 1.1.2; file pthread_md.h was initially added on branch nathanw_sa.
1.1.2.11	17-Jan-2003	thorpej	Include <sys/ucontext.h> to get ucontext_t for prototypes.
1.1.2.10	16-Jan-2003	thorpej	* Move the pthread_sigmask() prototype to <signal.h>. * Don't include <signal.h> in <pthread.h>. * Add code to the signal trampoline to convert from the ucontext to a sigcontext, and back again (XXX though, only callee-save regs for _UC_USER contexts). This is necessary in order to support e.g. GCC's libjava, which depends on the traditional Unix semantics of changes made to the sigcontext being visible when the handler returns.
1.1.2.9	06-Dec-2002	nathanw	Clear _UC_USER bit when converting from sigcontext to ucontext.
1.1.2.8	22-Oct-2002	nathanw	Define _INITCONTEXT_U_MD() to set segment registers and flag register to sensible values.
1.1.2.7	21-Oct-2002	nathanw	Add some macros to convert between ucontext_t and struct sigcontext.
1.1.2.6	14-Aug-2002	nathanw	Define, initialize, and use function pointers for _{set,get,swap}context_u routines, with different versions for saving FP state with fnsave or fxsave, depending on the machdep.osfxsr sysctl.
1.1.2.5	24-Apr-2002	nathanw	Add macros to convert between struct ucontext and struct reg/fpreg.
1.1.2.4	14-Nov-2001	briggs	Add pthread__uc_pc() to pthread_md.h instead of making assumptions about the contents of the m.d. mcontext.
1.1.2.3	04-Sep-2001	nathanw	Define STACKSPACE in pthread_md.h, not directly in pthread_switch.S
1.1.2.2	13-Jul-2001	nathanw	Note copyright. Standardize RCS IDs.
1.1.2.1	05-Mar-2001	nathanw	The beginnings of a scheduler activations-based pthread library.
1.5.6.1	19-Apr-2006	tron	Pull up following revision(s) (requested by cube in ticket #1265): lib/libpthread/arch/i386/pthread_md.h: revision 1.7 Instead of using hard-coded values for various registers, get them from the current context. Valid values can change depending on how the kernel is setup. i386 and amd64 happen to be setup differently.
1.5.4.1	21-Apr-2006	tron	Pull up following revision(s) (requested by cube in ticket #10448): lib/libpthread/arch/i386/pthread_md.h: revision 1.7 Instead of using hard-coded values for various registers, get them from the current context. Valid values can change depending on how the kernel is setup. i386 and amd64 happen to be setup differently.
1.7.12.3	23-Mar-2008	matt	sync with HEAD
1.7.12.2	09-Jan-2008	matt	sync with HEAD
1.7.12.1	06-Nov-2007	matt	sync with HEAD
1.7.8.1	10-Sep-2007	skrll	Sync with HEAD.
1.13.2.1	18-May-2008	yamt	sync with head.
1.14.2.1	18-Sep-2008	wrstuden	Sync with wrstuden-revivesa-base-2.
1.15.8.1	13-May-2009	jym	Sync with HEAD. Third (and last) commit. See http://mail-index.netbsd.org/source-changes/2009/05/13/msg221222.html
1.15.6.2	23-Jun-2008	ad	pthread__threadreg_get: mark it const.
1.15.6.1	23-Jun-2008	ad	file pthread_md.h was added on branch christos-time_t on 2008-06-23 10:39:39 +0000
1.17.2.2	05-Mar-2011	bouyer	Sync with HEAD
1.17.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.19.4.1	17-Apr-2012	yamt	sync with head
1.20.42.1	01-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #296): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.20.34.1	04-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #1700): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.20.24.1	04-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #1878): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.10	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.9	04-Jan-2006	skrll	A couple of fixes to make libpthread really shared, i.e. not have text re- locations: - Don't declare pthread__switch_away global - Do the PIC dance for pthread__switch_return_point and pthread__locked_switch. Ideally these (and other) symbols would be hidden. Thanks to uwe@, dyoung@ and elad@ for help. XXX sh3 is still to be done. XXX vax does strange things.
1.8	23-Apr-2004	simonb	branches: 1.8.2; s/the the/the/ (only in sources that aren't regularly imported from elsewhere).
1.7	30-Oct-2003	yamt	use explicit "l" suffixes. (eg. lea -> leal)
1.6	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.5	26-Jun-2003	nathanw	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.
1.4	12-Jun-2003	nathanw	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...)
1.3	10-Feb-2003	fvdl	Continue at the plain switch return point in pthread__switch, not the locked one, in the !PIC case. From Tor Egge via Havard Eidnes.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	05-Mar-2001	nathanw	branches: 1.1.2; file pthread_switch.S was initially added on branch nathanw_sa.
1.1.2.18	02-Jan-2003	nathanw	Rewrite pthread__switch() and adjust pthread__locked_switch() to avoid storing the new saved-context pointer while still using the old stack. This avoids a race condition with pthread__find_interrupted() where a thread could lose its old state if it was interrupted in a certain window in pthread__switch() or pthread__locked_switch() (the latter was never actually observed, but appeared possible).
1.1.2.17	18-Dec-2002	nathanw	Comment whitespace.
1.1.2.16	18-Dec-2002	nathanw	Tweak ucontext-alignment code so that it consumes at most 12 bytes of stack space instead of 16, leaving 20 bytes avaliable.
1.1.2.15	16-Sep-2002	skrll	Fix typo in comment.
1.1.2.14	06-Sep-2002	nathanw	Ensure that stack regions allocated for storing ucontext_t's are aligned to 16-byte boundaries; this ensures that the XMM save areas are also 16-byte aligned, which is a requirement for use of the fxsave and fxrstor instructions.
1.1.2.13	14-Aug-2002	nathanw	Define, initialize, and use function pointers for _{set,get,swap}context_u routines, with different versions for saving FP state with fnsave or fxsave, depending on the machdep.osfxsr sysctl.
1.1.2.12	04-Sep-2001	nathanw	Define STACKSPACE in pthread_md.h, not directly in pthread_switch.S
1.1.2.11	01-Aug-2001	nathanw	Rework the whole" ucontext vs. temporary crud on the bottom of the stack" thing again, placing the burden of weirdness on STACK_SWITCH. Add a lot of comments to explain why this is so tricky, and document which functions are external. In the old_preempt case of pthread__locked switch, save the thread's real context so we don't try to switch back into the middle of this code more than once.
1.1.2.10	31-Jul-2001	nathanw	Increase paranoia about keeping the ucontext on the bottom of the stack: Find the location to put it, but don't move $esp there, so that subsequent caller-save arguments and return addresses are above it rather than below it.
1.1.2.9	31-Jul-2001	nathanw	Actually, we do need pthread__switch in assembler, in order that the ucontext_t be the last thing on the stack. Otherwise, the switch code will overwrite stack data, since it sets the stack to pt_uc. Use the UT_EIP symbolic constant. When performing a new_preempt, store into pt_switchto and pt_switchtouc of the new thread, so that resolve_locks stands a chance of finding the switchto victim.
1.1.2.8	26-Jul-2001	nathanw	pthread__switch() no longer needs to be implemeted in assembler, and doesn't have a lock parameter.
1.1.2.7	24-Jul-2001	nathanw	Substantial rework: - Make pthread__switch() just a plain switch, and move the switch-to-next code to pthread__switch_away. Saves a stack switch, test, and branch in the pthread_switch case, a _getcontext_u() and associated stack frobbing in the switch_away case, and several points of sanity. - Remove a poorly-thought-out ucontext-dodge in STACK_SWITCH. - Fill in PT_SWITCHTO and PT_SWITCHTOUC in the new_preempt path as well as the old_preempt path in pthread__locked_switch() and pthread__upcall_switch().
1.1.2.6	23-Jul-2001	nathanw	Pushing parameters on the stack is not the same as preserving their values.
1.1.2.5	20-Jul-2001	nathanw	The %esi and %edi registers are callee-save, not caller-save.
1.1.2.4	16-Jul-2001	nathanw	Make pthread__switch() actually decrement fake spinlock counts when told to do so by pthread__upcall_switch() or pthread__lock_switch().
1.1.2.3	13-Jul-2001	nathanw	Note copyright. Standardize RCS IDs.
1.1.2.2	29-Mar-2001	nathanw	Don't frob pt_spinlocks in pthread__switch; we don't use it for switching with locks held.
1.1.2.1	05-Mar-2001	nathanw	The beginnings of a scheduler activations-based pthread library.
1.8.2.1	08-Jan-2006	riz	Pull up following revision(s) (requested by skrll in ticket #1093): lib/libpthread/arch/sparc/pthread_switch.S: revision 1.8 lib/libpthread/arch/x86_64/pthread_switch.S: revision 1.11 lib/libpthread/arch/sparc64/pthread_switch.S: revision 1.9 lib/libpthread/arch/i386/pthread_switch.S: revision 1.9 A couple of fixes to make libpthread really shared, i.e. not have text re- locations: - Don't declare pthread__switch_away global - Do the PIC dance for pthread__switch_return_point and pthread__locked_switch. Ideally these (and other) symbols would be hidden. Thanks to uwe@, dyoung@ and elad@ for help. XXX sh3 is still to be done. XXX vax does strange things.
1.4	08-Oct-1997	scottr	This incarnation of the pthreads library is ancient and not useful, and should have been mothballed some time ago...
1.3	07-Feb-1994	proven	More wrapper functions, and some hacks for machine independent sleep mechanisms.
1.2	27-Jan-1994	mycroft	Stylistic change.
1.1	14-Nov-1993	proven	branches: 1.1.1; Initial revision
1.1.1.1	14-Nov-1993	proven	Initial release of the POSIX 1003.4a Draft 7 thread implementation.
1.1	17-Apr-2015	martin	Dummy ia64 support
1.6	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.5	28-Apr-2008	martin	branches: 1.5.8; Remove clause 3 and 4 from TNF licenses
1.4	12-Oct-2003	chs	branches: 1.4.32; fix typo in previous.
1.3	01-Mar-2003	scw	Don't use FP instructions when building for m68010. Fixes broken sun2 build. G/C some unused code.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	18-Nov-2001	scw	branches: 1.1.2; file _context_u.S was initially added on branch nathanw_sa.
1.1.2.7	01-Dec-2001	scw	Small cleanup of FP register context goo.
1.1.2.6	25-Nov-2001	scw	Checkpoint user-land context switch glue. This code still needs some more thought, specifically for FPU context save/restore. On m68k, it is not possible to completely save/restore full FPU context from user-mode.
1.1.2.5	21-Nov-2001	scw	Don't bother stashing the CCR in the saved context; it's effectively a caller saved register. Instead, clear the full 32-bit REG_PS value in the context since the kernel's setcontext() call validates all 32-bits. Also overwrite uc_flags with _UC_CPU instead of a logical OR.
1.1.2.4	20-Nov-2001	scw	Can't "rts" at the end of _getcontext_u() since we've already popped the return address. Fortunately, it's in %a1 so just jmp to it.
1.1.2.3	19-Nov-2001	scw	Set the UC_CPU bit in UC_FLAGS for the GETC case. Pointed out by Nathan Williams.
1.1.2.2	19-Nov-2001	scw	Tweak the context save/restore code; the first cut was a bit too simplistic.
1.1.2.1	18-Nov-2001	scw	Initial cut of m68k-specific pthreads backend. Compiles, but testing will have to wait until I've had some sleep.
1.4.32.1	18-May-2008	yamt	sync with head.
1.5.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.5.8.1	28-Apr-2008	martin	file _context_u.S was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.8	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.7	28-Apr-2008	martin	branches: 1.7.8; Remove clause 3 and 4 from TNF licenses
1.6	02-Mar-2007	ad	branches: 1.6.12; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.5	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.4	17-Jul-2003	nathanw	Adapt to structure name changes.
1.3	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	18-Nov-2001	scw	branches: 1.1.2; file genassym.cf was initially added on branch nathanw_sa.
1.1.2.4	01-Dec-2001	scw	Small cleanup of FP register context goo.
1.1.2.3	25-Nov-2001	scw	Add defines for FP registers and for some more uc_flags values. Ditch CONTEXTSIZE in favour of RND_CTXSIZE which ensure the stack is always longword aligned (and it brings m68k into line with most other ports).
1.1.2.2	19-Nov-2001	scw	Tweak the context save/restore code; the first cut was a bit too simplistic.
1.1.2.1	18-Nov-2001	scw	Initial cut of m68k-specific pthreads backend. Compiles, but testing will have to wait until I've had some sleep.
1.6.12.1	18-May-2008	yamt	sync with head.
1.7.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.7.8.1	28-Apr-2008	martin	file genassym.cf was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.6	25-Nov-2003	christos	This is not needed anymore.
1.5	22-Sep-2003	cl	SA_SIGINFO support for m68k (libpthread)
1.4	26-Jul-2003	mrg	need <string.h>
1.3	08-Mar-2003	lukem	add __RCSID()
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	16-Jan-2003	thorpej	branches: 1.1.2; file pthread_md.c was initially added on branch nathanw_sa.
1.1.2.1	16-Jan-2003	thorpej	* Move the pthread_sigmask() prototype to <signal.h>. * Don't include <signal.h> in <pthread.h>. * Add code to the signal trampoline to convert from the ucontext to a sigcontext, and back again (XXX though, only callee-save regs for _UC_USER contexts). This is necessary in order to support e.g. GCC's libjava, which depends on the traditional Unix semantics of changes made to the sigcontext being visible when the handler returns.
1.8	25-Jan-2011	christos	make pthread__sp unsigned long.
1.7	16-May-2009	ad	branches: 1.7.2; Remove unused code that's confusing when using cscope/opengrok.
1.6	28-Apr-2008	martin	branches: 1.6.8; Remove clause 3 and 4 from TNF licenses
1.5	10-Feb-2008	ad	branches: 1.5.4; - Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.4	24-Dec-2005	perry	branches: 1.4.12; Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.3	25-Nov-2003	christos	m68k does not sigcontext<->mcontext anymore.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	18-Nov-2001	scw	branches: 1.1.2; file pthread_md.h was initially added on branch nathanw_sa.
1.1.2.5	16-Jan-2003	thorpej	* Move the pthread_sigmask() prototype to <signal.h>. * Don't include <signal.h> in <pthread.h>. * Add code to the signal trampoline to convert from the ucontext to a sigcontext, and back again (XXX though, only callee-save regs for _UC_USER contexts). This is necessary in order to support e.g. GCC's libjava, which depends on the traditional Unix semantics of changes made to the sigcontext being visible when the handler returns.
1.1.2.4	06-Aug-2002	nathanw	struct reg/ucontext conversion glue.
1.1.2.3	28-Jul-2002	gmcgarry	_REG_SP -> _REG_A7 to match definition in mcontext.h.
1.1.2.2	19-Nov-2001	scw	The right value for STACKSPACE is 12, for 3 integer values in this implementation. (Actually, we only need 10; 2 ints, 1 short, but best to keep the stack long-word aligned).
1.1.2.1	18-Nov-2001	scw	Initial cut of m68k-specific pthreads backend. Compiles, but testing will have to wait until I've had some sleep.
1.4.12.1	23-Mar-2008	matt	sync with HEAD
1.5.4.1	18-May-2008	yamt	sync with head.
1.6.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.6.8.1	28-Apr-2008	martin	file pthread_md.h was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.7.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.8	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.7	23-Apr-2004	simonb	s/the the/the/ (only in sources that aren't regularly imported from elsewhere).
1.6	17-Sep-2003	cl	fix pt_trapuc handling errors: - movl to address register doesn't set flags (add explicit test) - clr only clears a word (use clrl)
1.5	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.4	26-Jun-2003	nathanw	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.
1.3	13-Jun-2003	scw	Apply Nathan's switch-away fix and previous save-PT_UC from new stack fix. Compile-tested only.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	18-Nov-2001	scw	branches: 1.1.2; file pthread_switch.S was initially added on branch nathanw_sa.
1.1.2.4	01-Dec-2001	scw	G/C a superfluous assignment, and fix a PT_SWITCHTOUC bogon which managed to creep in with the last change...
1.1.2.3	25-Nov-2001	scw	Cleanup of the thread switching MD glue. With these changes, m68k now passes all Nathan's pthreads tests.
1.1.2.2	20-Nov-2001	scw	Fix a botched reference to a local label.
1.1.2.1	18-Nov-2001	scw	Initial cut of m68k-specific pthreads backend. Compiles, but testing will have to wait until I've had some sleep.
1.4	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.3	07-Aug-2003	agc	branches: 1.3.48; Move UCB-licensed code from 4-clause to 3-clause licence. Patches provided by Joel Baker in PR 22280, verified by myself.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	28-Nov-2001	wdk	branches: 1.1.2; file SYS.h was initially added on branch nathanw_sa.
1.1.2.5	01-Dec-2002	wdk	Remove nop
1.1.2.4	24-Nov-2002	wdk	Use __ABICALLS__
1.1.2.3	23-Nov-2002	wdk	PIC_CALL macros had a major side effect - last instruction has a jump with an unfilled bdslot. Add nop instruction to ensure no side effect and let the assembler try and remove it.
1.1.2.2	20-Nov-2002	wdk	Jump could not represent target in direct addressing mode. Error discovered by current toolchain.
1.1.2.1	28-Nov-2001	wdk	Initial pthread support for Mips processors.
1.3.48.1	16-Aug-2009	matt	Make ABI agonstic (first pass).
1.4	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.3	28-Apr-2008	martin	branches: 1.3.8; 1.3.14; Remove clause 3 and 4 from TNF licenses
1.2	18-Jan-2003	thorpej	branches: 1.2.34; Merge the nathanw_sa branch.
1.1	28-Nov-2001	wdk	branches: 1.1.2; file _context_u.S was initially added on branch nathanw_sa.
1.1.2.3	01-Dec-2002	wdk	- Use LEAF functions when nexted calls are not used. - Reorder branch-delay slots and let teh assembler do the hard work.
1.1.2.2	29-Nov-2001	wdk	setcontext macro incorrectly used the RA (return address) as the target PC to start the new context (RA == PC in getcontext so one may be lead to believe it wouldn't matter). Since the pthread__locked_switch() function updates the PC value we must use the PC value in the context. While we are the use T9 register for target PC value to maintain calling conventions.
1.1.2.1	28-Nov-2001	wdk	Initial pthread support for Mips processors.
1.2.34.1	18-May-2008	yamt	sync with head.
1.3.14.3	29-Apr-2011	matt	Pull in fixes from -current.
1.3.14.2	24-Aug-2009	matt	Fix typo
1.3.14.1	16-Aug-2009	matt	Make ABI agonstic (first pass).
1.3.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.3.8.1	28-Apr-2008	martin	file _context_u.S was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.8	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.7	28-Apr-2008	martin	branches: 1.7.8; 1.7.14; Remove clause 3 and 4 from TNF licenses
1.6	02-Mar-2007	ad	branches: 1.6.14; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.5	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.4	17-Jul-2003	nathanw	Adapt to structure name changes.
1.3	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	28-Nov-2001	wdk	branches: 1.1.2; file genassym.cf was initially added on branch nathanw_sa.
1.1.2.1	28-Nov-2001	wdk	Initial pthread support for Mips processors.
1.6.14.1	18-May-2008	yamt	sync with head.
1.7.14.1	16-Aug-2009	matt	Make ABI agonstic (first pass).
1.7.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.7.8.1	28-Apr-2008	martin	file genassym.cf was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.9	25-Jan-2011	christos	make pthread__sp unsigned long.
1.8	16-May-2009	ad	branches: 1.8.2; Remove unused code that's confusing when using cscope/opengrok.
1.7	28-Apr-2008	martin	branches: 1.7.8; Remove clause 3 and 4 from TNF licenses
1.6	24-Dec-2005	perry	branches: 1.6.22; Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.5	03-Jul-2004	simonb	Catch up with changes to __fpregset_t. In __longjmp14(), copy the FP CSR from the correct array and array slot. Completes fix for PR port-mips/25942.
1.4	26-Nov-2003	he	branches: 1.4.2; Hide the register number constants behind an _R_ prefix, and also rename FPBASE to _FPBASE, so that we avoid polluting the user's name space when e.g. <sys/ptrace.h> is included. Previously, the PC symbol in mips/regnum.h would conflict with the declaration of the external variable by the same name in termcap.h, as discovered by the ``okheaders'' regression test.
1.3	12-Jun-2003	nathanw	STACKSPACE of 16 is too small, given the use of CALLFRAME_SIZ; increase to match.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	28-Nov-2001	wdk	branches: 1.1.2; file pthread_md.h was initially added on branch nathanw_sa.
1.1.2.5	20-Dec-2002	thorpej	Update for mcontext_t changes.
1.1.2.4	05-Dec-2002	thorpej	Fix the reg <--> mcontext conversion macros. The reg structure is equivalent to the frame structure, which has a slightly different layout from the mcontext.
1.1.2.3	01-Dec-2002	wdk	Implement libpthread_dbg conversion macros.
1.1.2.2	29-Nov-2001	wdk	Drop STACKSPACE to 16 bytes
1.1.2.1	28-Nov-2001	wdk	Initial pthread support for Mips processors.
1.4.2.1	04-Jul-2004	he	Pull up revision 1.5 (requested by simonb in ticket #591): Changes fixing PR#25942: o Catch up with changes to __fpregset_t. In __longjmp14(), copy the FP CSR from the correct array and array slot.
1.6.22.1	18-May-2008	yamt	sync with head.
1.7.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.7.8.1	28-Apr-2008	martin	file pthread_md.h was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.8.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.7	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.6	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.5	26-Jun-2003	nathanw	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.
1.4	12-Jun-2003	nathanw	Oops, that's switch_return_point, not locked_return_point. The perils of cut-and-paste.
1.3	12-Jun-2003	nathanw	Apply switch-away fix and previous save-PT_UC from new stack fix.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	28-Nov-2001	wdk	branches: 1.1.2; file pthread_switch.S was initially added on branch nathanw_sa.
1.1.2.4	01-Dec-2002	wdk	Reorder branch-delay slot usage, and remove nop's cond5 test with type 5 upcalls now work!!
1.1.2.3	24-Nov-2002	wdk	Use __ABICALLS__
1.1.2.2	20-Nov-2002	wdk	Use CALLFRAME_RA and CALLFRAME_SIZ instead of static contants.
1.1.2.1	28-Nov-2001	wdk	Initial pthread support for Mips processors.
1.1	03-Sep-2014	matt	New files for OR1K support
1.6	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.5	10-Jul-2004	nathanw	When _SOFT_FLOAT is defined, don't save or restore user FP context. (note: still needs some mk rules tweaking for MKSOFTFLOAT=yes to pass -msoft-float to asm builds).
1.4	02-Jun-2004	nathanw	Remove a comment made obsolete by the previous commit.
1.3	12-Jun-2003	nathanw	branches: 1.3.4; Don't need to set the MSR field here; _INITCONTEXT_U_MD() takes care of that where necessary.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	13-Nov-2001	briggs	branches: 1.1.2; file _context_u.S was initially added on branch nathanw_sa.
1.1.2.7	08-Aug-2002	nathanw	Use register prefixes everywhere, now that asm.h no longer provides the intermediate-format macros.
1.1.2.6	21-Nov-2001	briggs	Preserve LR and use CTR to hold new PC when setting new context.
1.1.2.5	21-Nov-2001	briggs	Save FP state as well as integer state. Save reasonable constant in MSR (supervisor-only).
1.1.2.4	20-Nov-2001	briggs	Some cleanup.
1.1.2.3	19-Nov-2001	briggs	Use r prefixes for registers.
1.1.2.2	17-Nov-2001	briggs	Change SETC to use a fixed register (r4).
1.1.2.1	13-Nov-2001	briggs	Initial stab at pthread support for PPC.
1.3.4.1	18-May-2005	riz	Pull up revision 1.4 (requested by matt in ticket #1526): Remove a comment made obsolete by the previous commit.
1.8	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.7	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.6	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.5	17-Jul-2003	nathanw	Adapt to structure name changes.
1.4	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.3	20-Jan-2003	matt	Add _REG_foo to ppc mcontext and use them instead of constants.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	13-Nov-2001	briggs	branches: 1.1.2; file genassym.cf was initially added on branch nathanw_sa.
1.1.2.2	21-Nov-2001	briggs	Save FP state as well as integer state. Save reasonable constant in MSR (supervisor-only).
1.1.2.1	13-Nov-2001	briggs	Initial stab at pthread support for PPC.
1.9	11-Apr-2020	rin	Revert previous: http://mail-index.netbsd.org/source-changes/2020/02/20/msg114173.html Comment turned out to be wrong, and KASSERT fires for oea. XXX Need to revisit shortly...
1.8	20-Feb-2020	rin	libpthread sets initial value of MSR for lwp's. However, appropriate value differs b/w oea/booke/ibm4xx, and there's no way to obtain it from userland. Therefore, this initial value should be corrected by cpu_setmcontext(). - Comment this in libpthread - Add KASSERT in cpu_mcontext_validate()
1.7	25-Jan-2011	christos	branches: 1.7.44; 1.7.46; make pthread__sp unsigned long.
1.6	16-May-2009	ad	branches: 1.6.2; Remove unused code that's confusing when using cscope/opengrok.
1.5	24-Dec-2005	perry	Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.4	11-Feb-2004	nathanw	Add ucontext conversion macros for an "extra" register set.
1.3	20-Jan-2003	matt	Add _REG_foo to ppc mcontext and use them instead of constants.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	13-Nov-2001	briggs	branches: 1.1.2; file pthread_md.h was initially added on branch nathanw_sa.
1.1.2.8	16-Jan-2003	thorpej	* Move the pthread_sigmask() prototype to <signal.h>. * Don't include <signal.h> in <pthread.h>. * Add code to the signal trampoline to convert from the ucontext to a sigcontext, and back again (XXX though, only callee-save regs for _UC_USER contexts). This is necessary in order to support e.g. GCC's libjava, which depends on the traditional Unix semantics of changes made to the sigcontext being visible when the handler returns.
1.1.2.7	06-Dec-2002	nathanw	sigcontext/ucontext glue.
1.1.2.6	22-Oct-2002	nathanw	Define _INITCONTEXT_U_MD() to set the MSR to a reasonable value.
1.1.2.5	24-Apr-2002	nathanw	Add macros to convert between struct ucontext and struct reg/fpreg.
1.1.2.4	23-Mar-2002	nathanw	Change operand constraint of "mr %0,1" from "=g" to "=r", since mr really wants a register. This fixes -g powerpc builds.
1.1.2.3	20-Nov-2001	briggs	Some cleanup.
1.1.2.2	14-Nov-2001	briggs	Add pthread__uc_pc() to pthread_md.h instead of making assumptions about the contents of the m.d. mcontext.
1.1.2.1	13-Nov-2001	briggs	Initial stab at pthread support for PPC.
1.6.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.7.46.2	12-Apr-2020	martin	Pull up following revision(s) (requested by rin in ticket #826): lib/libpthread/arch/powerpc/pthread_md.h: revision 1.9 sys/arch/powerpc/powerpc/sig_machdep.c: revision 1.48 Revert previous: http://mail-index.netbsd.org/source-changes/2020/02/20/msg114173.html Comment turned out to be wrong, and KASSERT fires for oea. XXX Need to revisit shortly...
1.7.46.1	27-Feb-2020	martin	Pull up following revision(s) (requested by rin in ticket #736): lib/libpthread/arch/powerpc/pthread_md.h: revision 1.8 sys/arch/powerpc/powerpc/sig_machdep.c: revision 1.47 libpthread sets initial value of MSR for lwp's. However, appropriate value differs b/w oea/booke/ibm4xx, and there's no way to obtain it from userland. Therefore, this initial value should be corrected by cpu_setmcontext(). - Comment this in libpthread - Add KASSERT in cpu_mcontext_validate()
1.7.44.2	13-Apr-2020	martin	Mostly merge changes from HEAD upto 20200411
1.7.44.1	08-Apr-2020	martin	Merge changes from current as of 20200406
1.11	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.10	08-Jul-2006	ross	remove unreferenced temporary label
1.9	07-Jul-2004	nathanw	Fix a comment to say "Edit" instead of "Exit".
1.8	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.7	26-Jun-2003	nathanw	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.
1.6	24-Jun-2003	nathanw	Oops, reordering the PT_STATE/PT_SWITCHTOUC/PT_SWITCHTO assembly killed a live value too soon. Fix by using a different register for the PT_STATE immediate.
1.5	23-Jun-2003	nathanw	Update the switch_return point name in the static case.
1.4	12-Jun-2003	nathanw	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...)
1.3	06-Jun-2003	nathanw	Fix typo in comment.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	13-Nov-2001	briggs	branches: 1.1.2; file pthread_switch.S was initially added on branch nathanw_sa.
1.1.2.10	14-Jan-2003	nathanw	Rewrite pthread__switch() and adjust pthread__locked_switch() to avoid storing the new saved-context pointer while still using the old stack. This avoids a race condition with pthread__find_interrupted() where a thread could lose its old state if it was interrupted in a certain window in pthread__switch().
1.1.2.9	09-Nov-2002	nathanw	Make pthread__locked_switch() work in a PIC world, now that the linker is less lenient. XXX the stack usage is probably overkill for the required alignment.
1.1.2.8	08-Aug-2002	nathanw	Use register prefixes everywhere, now that asm.h no longer provides the intermediate-format macros.
1.1.2.7	02-May-2002	nathanw	Restore all three registers that are saved before the call to pthread__sa_recycle. Fixes a problem where pt_switchtouc would end up containing a small integer, rather than the ucontext pointer.
1.1.2.6	26-Nov-2001	briggs	Correct offset of ucontext on stack in pthread__switch(). Correct saved ucontext in PT_SLEEPUC in pthread__locked_switch().
1.1.2.5	21-Nov-2001	briggs	Update a couple of offsets I missed in earlier stack alignment.
1.1.2.4	20-Nov-2001	briggs	Some cleanup.
1.1.2.3	19-Nov-2001	briggs	Use r prefixes for registers.
1.1.2.2	16-Nov-2001	briggs	What crack was I on to use reg 0 in an addi instruction?
1.1.2.1	13-Nov-2001	briggs	Initial stab at pthread support for PPC.
1.3	07-May-2023	skrll	RISC-V support that works on QEMU with a single hart. Thanks for Simon Burge for plic(4).
1.2	31-Mar-2015	matt	We have _REG_SP so use it.
1.1	19-Sep-2014	matt	New files for Userland support of UCB RISC-V (both 32-bit and 64-bit)
1.7	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.6	01-Jun-2008	uwe	branches: 1.6.6; Recycle unused _REG_EXPEVT slot in mcontext for _REG_GBR. As the size of mcontext is not changed, we avoid the hassle of versioning all the calls that use it. _REG_EXPEVT was never used by any code in the tree. Reporting EXPEVT makes sense only for signals and in that case we pass it to userland in ksi_trap already which is official MI way to get this (MD) information. Old binaries running on new kernels will now have their GBR set from new mcontext, but that's ok too, as GBR was not properly supported by old kernels (not saved in trapframe), so old binaries couldn't have possibly used it anyway.
1.5	04-Jan-2006	uwe	branches: 1.5.20; 1.5.22; In PIC code call setcontext(2) via PLT to avoid text reloc in the shared library.
1.4	17-Nov-2003	uwe	branches: 1.4.6; Cause SIGTRAP if NOTREACHED code is reached.
1.3	05-Jul-2003	uwe	Not that the branch in SETC doens't have a delay slot, remove the .empty comment as it's no longer pertinent.
1.2	05-Jul-2003	marcus	PIC patch from Valeriy E. Ushakov applied. Also, removed bogus delay slot flag from branch instruction.
1.1	23-Jun-2003	uwe	First bits of SH3 support. Only _context_u.S is implemented (passess cu[1-6] tests), the pthread_switch.S is stubbed out for now. Code posted by Christian Groessler (cpg at aladdin dot de) to port-sh3.
1.4.6.1	11-Jan-2006	tron	Pull up following revision(s) (requested by uwe in ticket #1095): lib/libpthread/arch/sh3/_context_u.S: revision 1.5 In PIC code call setcontext(2) via PLT to avoid text reloc in the shared library.
1.5.22.1	23-Jun-2008	wrstuden	Sync w/ -current. 34 merge conflicts to follow.
1.5.20.1	04-Jun-2008	yamt	sync with head
1.6.6.2	01-Jun-2008	uwe	Recycle unused _REG_EXPEVT slot in mcontext for _REG_GBR. As the size of mcontext is not changed, we avoid the hassle of versioning all the calls that use it. _REG_EXPEVT was never used by any code in the tree. Reporting EXPEVT makes sense only for signals and in that case we pass it to userland in ksi_trap already which is official MI way to get this (MD) information. Old binaries running on new kernels will now have their GBR set from new mcontext, but that's ok too, as GBR was not properly supported by old kernels (not saved in trapframe), so old binaries couldn't have possibly used it anyway.
1.6.6.1	01-Jun-2008	uwe	file _context_u.S was added on branch christos-time_t on 2008-06-01 23:07:21 +0000
1.9	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.8	01-Jun-2008	uwe	branches: 1.8.6; Recycle unused _REG_EXPEVT slot in mcontext for _REG_GBR. As the size of mcontext is not changed, we avoid the hassle of versioning all the calls that use it. _REG_EXPEVT was never used by any code in the tree. Reporting EXPEVT makes sense only for signals and in that case we pass it to userland in ksi_trap already which is official MI way to get this (MD) information. Old binaries running on new kernels will now have their GBR set from new mcontext, but that's ok too, as GBR was not properly supported by old kernels (not saved in trapframe), so old binaries couldn't have possibly used it anyway.
1.7	28-Apr-2008	martin	branches: 1.7.2; Remove clause 3 and 4 from TNF licenses
1.6	02-Mar-2007	ad	branches: 1.6.12; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.5	18-Nov-2003	uwe	Add necessary symbols.
1.4	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.3	17-Jul-2003	nathanw	Adapt to structure name changes.
1.2	05-Jul-2003	marcus	The field "pt_sleepuc" doesn't exist in struct pthread_st.
1.1	23-Jun-2003	uwe	First bits of SH3 support. Only _context_u.S is implemented (passess cu[1-6] tests), the pthread_switch.S is stubbed out for now. Code posted by Christian Groessler (cpg at aladdin dot de) to port-sh3.
1.6.12.2	04-Jun-2008	yamt	sync with head
1.6.12.1	18-May-2008	yamt	sync with head.
1.7.2.1	23-Jun-2008	wrstuden	Sync w/ -current. 34 merge conflicts to follow.
1.8.6.2	01-Jun-2008	uwe	Recycle unused _REG_EXPEVT slot in mcontext for _REG_GBR. As the size of mcontext is not changed, we avoid the hassle of versioning all the calls that use it. _REG_EXPEVT was never used by any code in the tree. Reporting EXPEVT makes sense only for signals and in that case we pass it to userland in ksi_trap already which is official MI way to get this (MD) information. Old binaries running on new kernels will now have their GBR set from new mcontext, but that's ok too, as GBR was not properly supported by old kernels (not saved in trapframe), so old binaries couldn't have possibly used it anyway.
1.8.6.1	01-Jun-2008	uwe	file genassym.cf was added on branch christos-time_t on 2008-06-01 23:07:21 +0000
1.8	25-Jan-2011	christos	make pthread__sp unsigned long.
1.7	16-May-2009	ad	branches: 1.7.2; Remove unused code that's confusing when using cscope/opengrok.
1.6	27-Oct-2008	uwe	branches: 1.6.4; Fix typo in comment.
1.5	27-Oct-2008	uwe	Pull down revision 1.3.6.1 by skrll@ (adapted to include reg::r_gbr). struct mcontext != struct reg on sh3. Fix PTHREAD_UCONTEXT_TO_REG / PTHREAD_REG_TO_UCONTEXT to deal with this.
1.4	10-Feb-2008	ad	- Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.3	24-Dec-2005	perry	branches: 1.3.4; 1.3.6; 1.3.12; Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.2	20-Nov-2003	uwe	Add _INITCONTEXT_U_MD, we need to clean _REG_SR.
1.1	23-Jun-2003	uwe	First bits of SH3 support. Only _context_u.S is implemented (passess cu[1-6] tests), the pthread_switch.S is stubbed out for now. Code posted by Christian Groessler (cpg at aladdin dot de) to port-sh3.
1.3.12.1	23-Mar-2008	matt	sync with HEAD
1.3.6.1	26-Feb-2008	skrll	struct mcontext != struct reg on sh3. Fix PTHREAD_UCONTEXT_TO_REG / PTHREAD_REG_TO_UCONTEXT to deal with this.
1.3.4.1	16-Sep-2008	bouyer	Sync with the following revisions (requested by skrll in ticket #1196): gnu/dist/gdb removed gnu/usr.bin/gdb53 removed distrib/cats/instkernel/Makefile 1.14.6.1 gnu/dist/gdb6/bfd/config.bfd 1.3.6.1 gnu/dist/gdb6/bfd/elfxx-sparc.c 1.1.1.2.6.1 gnu/dist/gdb6/bfd/elfxx-sparc.h 1.1.1.2.6.1 gnu/dist/gdb6/gdb/Makefile.in 1.2.2.1.2.2 gnu/dist/gdb6/gdb/alpha-tdep.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/alpha-tdep.h 1.1.1.2.6.1 gnu/dist/gdb6/gdb/alphabsd-nat.c 1.1.1.2.6.2 gnu/dist/gdb6/gdb/alphabsd-nat.h 1.1.2.1 gnu/dist/gdb6/gdb/alphabsd-tdep.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/alphabsd-tdep.h 1.1.1.2.6.1 gnu/dist/gdb6/gdb/alphanbsd-nat.c 1.1.2.1 gnu/dist/gdb6/gdb/alphanbsd-tdep.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/amd64-nat.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/amd64bsd-nat.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/amd64nbsd-nat.c 1.1.1.2.6.3 gnu/dist/gdb6/gdb/amd64nbsd-tdep.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/arm-tdep.h 1.1.1.2.6.1 gnu/dist/gdb6/gdb/armbsd-tdep.c 1.1.2.1 gnu/dist/gdb6/gdb/armnbsd-nat.c 1.1.1.2.6.2 gnu/dist/gdb6/gdb/armnbsd-tdep.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/configure 1.1.1.2.6.1 gnu/dist/gdb6/gdb/configure.ac 1.1.1.2.6.1 gnu/dist/gdb6/gdb/i386bsd-nat.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/i386nbsd-tdep.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/m68kbsd-nat.c 1.1.1.2.6.2 gnu/dist/gdb6/gdb/mipsnbsd-nat.c 1.1.1.2.6.2 gnu/dist/gdb6/gdb/nbsd-thread.c 1.1.2.3 gnu/dist/gdb6/gdb/ppcnbsd-nat.c 1.1.1.2.6.2 gnu/dist/gdb6/gdb/ppcnbsd-tdep.c 1.3.6.1 gnu/dist/gdb6/gdb/sh-tdep.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/shnbsd-nat.c 1.1.1.2.6.3 gnu/dist/gdb6/gdb/shnbsd-tdep.c 1.1.1.2.6.4 gnu/dist/gdb6/gdb/shnbsd-tdep.h 1.1.1.2.6.1 gnu/dist/gdb6/gdb/sparc-nat.c 1.1.1.2.6.1 gnu/dist/gdb6/gdb/sparc64nbsd-nat.c 1.1.1.2.6.2 gnu/dist/gdb6/gdb/sparcnbsd-nat.c 1.1.1.2.6.2 gnu/dist/gdb6/gdb/tramp-frame.h 1.1.1.2.6.1 gnu/dist/gdb6/gdb/vaxbsd-nat.c 1.1.1.2.6.2 gnu/dist/gdb6/gdb/config/alpha/nbsd.mh 1.1.1.2.6.1 gnu/dist/gdb6/gdb/config/arm/nbsd.mt 1.1.1.1.6.1 gnu/dist/gdb6/gdb/config/arm/nbsdelf.mh 1.1.1.1.6.1 gnu/dist/gdb6/gdb/config/i386/nbsd64.mh 1.1.1.1.6.1 gnu/dist/gdb6/gdb/config/m68k/nbsdelf.mh 1.1.1.1.6.1 gnu/dist/gdb6/gdb/config/mips/nbsd.mh 1.1.1.1.6.1 gnu/dist/gdb6/gdb/config/powerpc/nbsd.mh 1.1.1.2.6.1 gnu/dist/gdb6/gdb/config/sh/nbsd.mh 1.1.1.1.6.2 gnu/dist/gdb6/gdb/config/sh/tm-nbsd.h 1.1.1.1.6.1 gnu/dist/gdb6/gdb/config/sparc/nbsd64.mh 1.1.1.1.6.1 gnu/dist/gdb6/gdb/config/sparc/nbsdelf.mh 1.1.1.1.6.1 gnu/dist/gdb6/gdb/config/vax/nbsdelf.mh 1.1.1.1.6.1 gnu/dist/gdb6/opcodes/configure 1.1.1.2.6.1 gnu/dist/gdb6/opcodes/configure.in 1.1.1.2.6.1 gnu/usr.bin/Makefile 1.126.4.1 gnu/usr.bin/gdb6/arch/alpha/config.h 1.3.4.1 gnu/usr.bin/gdb6/arch/alpha/defs.mk 1.2.6.1 gnu/usr.bin/gdb6/arch/alpha/init.c 1.2.6.1 gnu/usr.bin/gdb6/arch/alpha/nm.h 1.2.6.1 gnu/usr.bin/gdb6/arch/arm/defs.mk 1.2.6.2 gnu/usr.bin/gdb6/arch/arm/init.c 1.1.6.1 gnu/usr.bin/gdb6/arch/armeb/config.h 1.1.6.2 gnu/usr.bin/gdb6/arch/armeb/defs.mk 1.1.6.3 gnu/usr.bin/gdb6/arch/armeb/init.c 1.1.6.2 gnu/usr.bin/gdb6/arch/armeb/tm.h 1.1.6.2 gnu/usr.bin/gdb6/arch/armeb/version.c 1.1.6.2 gnu/usr.bin/gdb6/arch/i386/defs.mk 1.4.4.1 gnu/usr.bin/gdb6/arch/i386/init.c 1.3.6.1 gnu/usr.bin/gdb6/arch/m68000/config.h 1.1.6.2 gnu/usr.bin/gdb6/arch/m68000/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/arch/m68000/init.c 1.1.6.2 gnu/usr.bin/gdb6/arch/m68000/tm.h 1.1.6.2 gnu/usr.bin/gdb6/arch/m68000/version.c 1.1.6.2 gnu/usr.bin/gdb6/arch/m68k/defs.mk 1.1.4.1 gnu/usr.bin/gdb6/arch/m68k/init.c 1.1.4.1 gnu/usr.bin/gdb6/arch/mipseb/config.h 1.3.4.1 gnu/usr.bin/gdb6/arch/mipseb/defs.mk 1.2.6.2 gnu/usr.bin/gdb6/arch/mipseb/init.c 1.2.6.2 gnu/usr.bin/gdb6/arch/mipsel/config.h 1.2.6.3 gnu/usr.bin/gdb6/arch/mipsel/defs.mk 1.2.6.3 gnu/usr.bin/gdb6/arch/mipsel/init.c 1.2.6.3 gnu/usr.bin/gdb6/arch/mipsel/tm.h 1.2.6.2 gnu/usr.bin/gdb6/arch/mipsel/version.c 1.2.6.2 gnu/usr.bin/gdb6/arch/powerpc/defs.mk 1.3.6.1 gnu/usr.bin/gdb6/arch/powerpc/init.c 1.3.6.1 gnu/usr.bin/gdb6/arch/sh3eb/config.h 1.2.2.2 gnu/usr.bin/gdb6/arch/sh3eb/defs.mk 1.2.8.3 gnu/usr.bin/gdb6/arch/sh3eb/init.c 1.1.8.3 gnu/usr.bin/gdb6/arch/sh3eb/nm.h 1.1.8.2 gnu/usr.bin/gdb6/arch/sh3eb/tm.h 1.1.8.2 gnu/usr.bin/gdb6/arch/sh3eb/version.c 1.1.8.2 gnu/usr.bin/gdb6/arch/sh3el/config.h 1.2.2.2 gnu/usr.bin/gdb6/arch/sh3el/defs.mk 1.2.8.3 gnu/usr.bin/gdb6/arch/sh3el/init.c 1.1.8.3 gnu/usr.bin/gdb6/arch/sh3el/nm.h 1.1.8.2 gnu/usr.bin/gdb6/arch/sh3el/tm.h 1.1.8.2 gnu/usr.bin/gdb6/arch/sh3el/version.c 1.1.8.2 gnu/usr.bin/gdb6/arch/sparc/defs.mk 1.2.6.1 gnu/usr.bin/gdb6/arch/sparc/init.c 1.1.6.1 gnu/usr.bin/gdb6/arch/sparc64/defs.mk 1.2.6.1 gnu/usr.bin/gdb6/arch/sparc64/init.c 1.1.6.1 gnu/usr.bin/gdb6/arch/vax/config.h 1.1.6.2 gnu/usr.bin/gdb6/arch/vax/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/arch/vax/init.c 1.1.6.2 gnu/usr.bin/gdb6/arch/vax/tm.h 1.1.6.2 gnu/usr.bin/gdb6/arch/vax/version.c 1.1.6.2 gnu/usr.bin/gdb6/arch/x86_64/defs.mk 1.2.6.1 gnu/usr.bin/gdb6/arch/x86_64/init.c 1.1.6.1 gnu/usr.bin/gdb6/bfd/arch/armeb/bfd.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/armeb/bfdver.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/armeb/config.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/armeb/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/m68000/bfd.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/m68000/bfdver.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/m68000/config.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/m68000/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/mipsel/bfd.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/mipsel/bfdver.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/mipsel/config.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/mipsel/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/sh3eb/bfd.h 1.1.8.3 gnu/usr.bin/gdb6/bfd/arch/sh3eb/bfdver.h 1.1.8.2 gnu/usr.bin/gdb6/bfd/arch/sh3eb/config.h 1.1.8.2 gnu/usr.bin/gdb6/bfd/arch/sh3eb/defs.mk 1.1.8.3 gnu/usr.bin/gdb6/bfd/arch/sh3el/bfd.h 1.1.8.3 gnu/usr.bin/gdb6/bfd/arch/sh3el/bfdver.h 1.1.8.2 gnu/usr.bin/gdb6/bfd/arch/sh3el/config.h 1.1.8.2 gnu/usr.bin/gdb6/bfd/arch/sh3el/defs.mk 1.1.8.3 gnu/usr.bin/gdb6/bfd/arch/vax/bfd.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/vax/bfdver.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/vax/config.h 1.1.6.2 gnu/usr.bin/gdb6/bfd/arch/vax/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/gdb/Makefile 1.5.2.1.2.2 gnu/usr.bin/gdb6/gdbtui/Makefile 1.2.6.1 gnu/usr.bin/gdb6/libiberty/arch/armeb/config.h 1.1.6.2 gnu/usr.bin/gdb6/libiberty/arch/armeb/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/libiberty/arch/m68000/config.h 1.1.6.2 gnu/usr.bin/gdb6/libiberty/arch/m68000/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/libiberty/arch/mipsel/config.h 1.1.6.2 gnu/usr.bin/gdb6/libiberty/arch/mipsel/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/libiberty/arch/sh3eb/config.h 1.1.8.2 gnu/usr.bin/gdb6/libiberty/arch/sh3eb/defs.mk 1.1.8.2 gnu/usr.bin/gdb6/libiberty/arch/sh3el/config.h 1.1.8.2 gnu/usr.bin/gdb6/libiberty/arch/sh3el/defs.mk 1.1.8.2 gnu/usr.bin/gdb6/libiberty/arch/vax/config.h 1.1.6.2 gnu/usr.bin/gdb6/libiberty/arch/vax/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/opcodes/arch/armeb/config.h 1.1.6.2 gnu/usr.bin/gdb6/opcodes/arch/armeb/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/opcodes/arch/m68000/config.h 1.1.6.2 gnu/usr.bin/gdb6/opcodes/arch/m68000/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/opcodes/arch/mipsel/config.h 1.1.6.2 gnu/usr.bin/gdb6/opcodes/arch/mipsel/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/opcodes/arch/sh3eb/config.h 1.1.8.2 gnu/usr.bin/gdb6/opcodes/arch/sh3eb/defs.mk 1.1.8.3 gnu/usr.bin/gdb6/opcodes/arch/sh3el/config.h 1.1.8.2 gnu/usr.bin/gdb6/opcodes/arch/sh3el/defs.mk 1.1.8.3 gnu/usr.bin/gdb6/opcodes/arch/vax/config.h 1.1.6.2 gnu/usr.bin/gdb6/opcodes/arch/vax/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/readline/arch/armeb/config.h 1.1.6.2 gnu/usr.bin/gdb6/readline/arch/armeb/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/readline/arch/m68000/config.h 1.1.6.2 gnu/usr.bin/gdb6/readline/arch/m68000/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/readline/arch/mipsel/config.h 1.1.6.2 gnu/usr.bin/gdb6/readline/arch/mipsel/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/readline/arch/sh3eb/config.h 1.1.8.2 gnu/usr.bin/gdb6/readline/arch/sh3eb/defs.mk 1.1.8.2 gnu/usr.bin/gdb6/readline/arch/sh3el/config.h 1.1.8.2 gnu/usr.bin/gdb6/readline/arch/sh3el/defs.mk 1.1.8.2 gnu/usr.bin/gdb6/readline/arch/vax/config.h 1.1.6.2 gnu/usr.bin/gdb6/readline/arch/vax/defs.mk 1.1.6.2 gnu/usr.bin/gdb6/sim/arch/mipseb/cconfig.h 1.1.2.1 gnu/usr.bin/gdb6/sim/arch/mipseb/config.h 1.1.2.1 gnu/usr.bin/gdb6/sim/arch/mipseb/defs.mk 1.1.2.1 gnu/usr.bin/gdb6/sim/arch/mipsel/cconfig.h 1.1.2.1 gnu/usr.bin/gdb6/sim/arch/mipsel/config.h 1.1.2.1 gnu/usr.bin/gdb6/sim/arch/mipsel/defs.mk 1.1.2.1 lib/libkvm/kvm_sparc64.c 1.10.18.2 lib/libpthread/pthread.c 1.48.6.4 lib/libpthread/pthread_barrier.c 1.6.18.1 lib/libpthread/pthread_cond.c 1.18.12.2 lib/libpthread/pthread_debug.h 1.8.18.1 lib/libpthread/pthread_int.h 1.34.4.5 lib/libpthread/pthread_lock.c 1.14.6.1 lib/libpthread/pthread_mutex.c 1.22.4.2 lib/libpthread/pthread_run.c 1.18.12.4 lib/libpthread/pthread_rwlock.c 1.13.6.2 lib/libpthread/pthread_sa.c 1.37.6.5 lib/libpthread/pthread_sig.c 1.47.4.8 lib/libpthread/pthread_sleep.c 1.7.6.2 lib/libpthread/sem.c 1.9.6.2 lib/libpthread/arch/sh3/pthread_md.h 1.3.6.1 regress/lib/libpthread/resolv/Makefile 1.1.12.1 regress/lib/libpthread/sigrunning/Makefile 1.1.2.1 regress/lib/libpthread/sigrunning/sigrunning.c 1.1.2.1 share/mk/bsd.own.mk 1.489.4.3 sys/arch/amd64/amd64/locore.S 1.18.14.1 sys/arch/amd64/amd64/machdep.c 1.44.2.3.2.1 sys/arch/amd64/conf/kern.ldscript 1.1.70.1 sys/arch/cats/conf/Makefile.cats.inc 1.17.30.1 sys/arch/shark/conf/Makefile.shark.inc 1.6.30.1 sys/arch/sparc64/conf/kern.ldscript 1.7.26.2 sys/arch/sparc64/conf/kern32.ldscript 1.6.26.2 sys/arch/sparc64/include/kcore.h 1.4.92.2 sys/arch/sparc64/sparc64/locore.s 1.232.4.4 sys/arch/sparc64/sparc64/machdep.c 1.193.4.3 sys/arch/sparc64/sparc64/pmap.c 1.184.2.1.2.4 sys/conf/newvers.sh 1.42.26.2 sys/kern/kern_sa.c 1.87.4.11 sys/kern/kern_synch.c 1.173.4.2 sys/sys/savar.h 1.20.10.2 tools/gdb/Makefile 1.9.4.1 tools/gdb/mknative-gdb 1.1.6.1 pullup the wrstuden-fixsa CVS branch to netbsd-4: toolchain/35540 - GDB 6 support for pthreads. port-sparc64/37534 - ktrace firefox gives kernel trap 30: data access expection GDB changes: - delete gdb53 - enable gdb6 on all architectures - add support for amd64 crash dumps - add support for sparc64 crash dumps - add support for /proc pid to executable filename for all archs - enable thread support for all architectures - add a note section to kernels to all platforms - support detection/unwinding of signals for most architectures. - Fix PTHREAD_UCONTEXT_TO_REG / PTHREAD_REG_TO_UCONTEXT on sh3. - Apply fix from binutils-current so that sparc gdb can be cross built on a 64bit host. SA/pthread changes: Pre-allocate memory needed for event delivery. Eliminates dropped interrupts under load. Deliver intra-process signals to running threads Eliminate some deadlock scenarios Fix intra-process signal delivery when delivering to a thread waiting for signals. Makes afs work again!
1.6.4.2	27-Oct-2008	uwe	Fix typo in comment.
1.6.4.1	27-Oct-2008	uwe	file pthread_md.h was added on branch christos-time_t on 2008-10-27 00:52:08 +0000
1.7.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.8	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.7	06-Jan-2006	uwe	Use PLT for PIC calls to avoid text relocs in the shared library.
1.6	31-Dec-2005	uwe	Adapt to new PIC macros that are now in <machine/asm.h>. Same binary code is generated (still with text relocs, but eliminating them is the next step).
1.5	28-May-2004	uwe	branches: 1.5.2; Fix typo in comment.
1.4	20-Nov-2003	uwe	Do not move incoming paramters to callee-save registers when not necessary. Saves about a dozen of instructions.
1.3	20-Nov-2003	uwe	In pthread__locked_switch set self->pt_uc only when the context is inited. In STACK_SWITCH subtract STACKSPACE, not add it (it's zero for now anyway).
1.2	18-Nov-2003	uwe	First cut at pthreads MD code for sh3. Based on m68k version. Regression tests still failing: sem, sigalarm.
1.1	23-Jun-2003	uwe	First bits of SH3 support. Only _context_u.S is implemented (passess cu[1-6] tests), the pthread_switch.S is stubbed out for now. Code posted by Christian Groessler (cpg at aladdin dot de) to port-sh3.
1.5.2.2	11-Jan-2006	tron	Pull up following revision(s) (requested by uwe in ticket #1099): lib/libpthread/arch/sh3/pthread_switch.S: revision 1.7 Use PLT for PIC calls to avoid text relocs in the shared library.
1.5.2.1	11-Jan-2006	tron	Pull up following revision(s) (requested by uwe in ticket #1094): lib/libpthread/arch/sh3/pthread_switch.S: revision 1.6 Adapt to new PIC macros that are now in <machine/asm.h>. Same binary code is generated (still with text relocs, but eliminating them is the next step).
1.4	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.3	28-Apr-2008	martin	branches: 1.3.8; Remove clause 3 and 4 from TNF licenses
1.2	18-Jan-2003	thorpej	branches: 1.2.32; Merge the nathanw_sa branch.
1.1	23-Nov-2002	martin	branches: 1.1.2; file _context_u.S was initially added on branch nathanw_sa.
1.1.2.4	07-Jan-2003	thorpej	UC_GREG -> UC_GREGS
1.1.2.3	29-Nov-2002	uwe	Add _UC_USER to genassym.cf and use it instead of hardcoded magic number.
1.1.2.2	28-Nov-2002	uwe	Save nPC in _getcontext_u() too, so that we can setcontext(2) it. Cosmetic changes. All context tests now work.
1.1.2.1	23-Nov-2002	martin	Port of Andrey Petrovs sparc64 support to sparc. With input from Valeriy E. Ushakov. Not yet tested.
1.2.32.1	18-May-2008	yamt	sync with head.
1.3.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.3.8.1	28-Apr-2008	martin	file _context_u.S was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.9	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.8	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.7	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.6	29-Jul-2003	kleink	Remove PT_SLEEPUC, which somehow wasn't.
1.5	17-Jul-2003	nathanw	Adapt to structure name changes.
1.4	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.3	31-Jan-2003	pk	Include <sys/types.h> Remove v9 register defs.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	23-Nov-2002	martin	branches: 1.1.2; file genassym.cf was initially added on branch nathanw_sa.
1.1.2.3	18-Dec-2002	skrll	Fix up after change to mcontext.h
1.1.2.2	29-Nov-2002	uwe	Add _UC_USER to genassym.cf and use it instead of hardcoded magic number.
1.1.2.1	23-Nov-2002	martin	Port of Andrey Petrovs sparc64 support to sparc. With input from Valeriy E. Ushakov. Not yet tested.
1.8	25-Jan-2011	christos	make pthread__sp unsigned long.
1.7	16-May-2009	ad	branches: 1.7.2; Remove unused code that's confusing when using cscope/opengrok.
1.6	28-Apr-2008	martin	branches: 1.6.8; Remove clause 3 and 4 from TNF licenses
1.5	10-Feb-2008	ad	branches: 1.5.4; - Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.4	24-Dec-2005	perry	branches: 1.4.12; Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.3	10-Nov-2003	martin	All the ucontext <-> {fp}reg macros were slightly simplistic and untested before (old gdb support on sparc did not use this). Pointed out by Christian Limpach.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	23-Nov-2002	martin	branches: 1.1.2; file pthread_md.h was initially added on branch nathanw_sa.
1.1.2.2	18-Dec-2002	skrll	Fix up after change to mcontext.h
1.1.2.1	23-Nov-2002	martin	Port of Andrey Petrovs sparc64 support to sparc. With input from Valeriy E. Ushakov. Not yet tested.
1.4.12.1	23-Mar-2008	matt	sync with HEAD
1.5.4.1	18-May-2008	yamt	sync with head.
1.6.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.6.8.1	28-Apr-2008	martin	file pthread_md.h was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.7.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.9	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.8	04-Jan-2006	skrll	A couple of fixes to make libpthread really shared, i.e. not have text re- locations: - Don't declare pthread__switch_away global - Do the PIC dance for pthread__switch_return_point and pthread__locked_switch. Ideally these (and other) symbols would be hidden. Thanks to uwe@, dyoung@ and elad@ for help. XXX sh3 is still to be done. XXX vax does strange things.
1.7	07-Sep-2003	cl	branches: 1.7.6; Remove possible race condition in upcall recycling.
1.6	07-Sep-2003	uwe	Use delay slot in STACK_SWITCH (catching up with sparc64 changes).
1.5	07-Sep-2003	uwe	Use correct context to switch to. From sparc64 fix by Andrey Petrov <petrov@netbsd>.
1.4	26-Jun-2003	nathanw	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.
1.3	17-Jun-2003	martin	Catch up with Nathan's changes to other archs.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	23-Nov-2002	martin	branches: 1.1.2; file pthread_switch.S was initially added on branch nathanw_sa.
1.1.2.3	07-Jan-2003	thorpej	UC_GREG -> UC_GREGS
1.1.2.2	28-Nov-2002	uwe	Remove few remaining sparc64'isms. Some cosmetic changes.
1.1.2.1	23-Nov-2002	martin	Port of Andrey Petrovs sparc64 support to sparc. With input from Valeriy E. Ushakov. Not yet tested.
1.7.6.1	08-Jan-2006	riz	Pull up following revision(s) (requested by skrll in ticket #1093): lib/libpthread/arch/sparc/pthread_switch.S: revision 1.8 lib/libpthread/arch/x86_64/pthread_switch.S: revision 1.11 lib/libpthread/arch/sparc64/pthread_switch.S: revision 1.9 lib/libpthread/arch/i386/pthread_switch.S: revision 1.9 A couple of fixes to make libpthread really shared, i.e. not have text re- locations: - Don't declare pthread__switch_away global - Do the PIC dance for pthread__switch_return_point and pthread__locked_switch. Ideally these (and other) symbols would be hidden. Thanks to uwe@, dyoung@ and elad@ for help. XXX sh3 is still to be done. XXX vax does strange things.
1.4	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.3	28-Apr-2008	martin	branches: 1.3.8; Remove clause 3 and 4 from TNF licenses
1.2	18-Jan-2003	thorpej	branches: 1.2.32; Merge the nathanw_sa branch.
1.1	22-Feb-2002	petrov	branches: 1.1.2; file _context_u.S was initially added on branch nathanw_sa.
1.1.2.5	23-Nov-2002	martin	Minor style nits, express frame size by apropriate macro and reorder one load sequence to avoid pipeline interlocks. From Valeriy E. Ushakov.
1.1.2.4	19-Sep-2002	petrov	PIC aware, remove debug cruft.
1.1.2.3	21-May-2002	petrov	STACK_SWITCH fix, added debug.
1.1.2.2	26-Apr-2002	petrov	round 2: simplify _get(set)context_u, add pthread__locked_switch.
1.1.2.1	22-Feb-2002	petrov	Initial pthreads support
1.2.32.1	18-May-2008	yamt	sync with head.
1.3.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.3.8.1	28-Apr-2008	martin	file _context_u.S was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.9	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.8	28-Apr-2008	martin	branches: 1.8.8; Remove clause 3 and 4 from TNF licenses
1.7	02-Mar-2007	ad	branches: 1.7.12; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.6	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.5	17-Jul-2003	nathanw	Adapt to structure name changes.
1.4	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.3	07-May-2003	petrov	Add missing include and copyright.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	22-Feb-2002	petrov	branches: 1.1.2; file genassym.cf was initially added on branch nathanw_sa.
1.1.2.1	22-Feb-2002	petrov	Initial pthreads support
1.7.12.1	18-May-2008	yamt	sync with head.
1.8.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.8.8.1	28-Apr-2008	martin	file genassym.cf was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.7	25-Jan-2011	christos	make pthread__sp unsigned long.
1.6	16-May-2009	ad	branches: 1.6.2; Remove unused code that's confusing when using cscope/opengrok.
1.5	28-Apr-2008	martin	branches: 1.5.8; Remove clause 3 and 4 from TNF licenses
1.4	24-Dec-2005	perry	branches: 1.4.20; Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.3	11-Nov-2003	martin	Fix ucontext conversion macros. From Christian Limpach.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	22-Feb-2002	petrov	branches: 1.1.2; file pthread_md.h was initially added on branch nathanw_sa.
1.1.2.4	16-Jan-2003	thorpej	* Move the pthread_sigmask() prototype to <signal.h>. * Don't include <signal.h> in <pthread.h>. * Add code to the signal trampoline to convert from the ucontext to a sigcontext, and back again (XXX though, only callee-save regs for _UC_USER contexts). This is necessary in order to support e.g. GCC's libjava, which depends on the traditional Unix semantics of changes made to the sigcontext being visible when the handler returns.
1.1.2.3	10-Sep-2002	petrov	regs/mcontext conversion macros.
1.1.2.2	26-Apr-2002	petrov	round 2: simplify _get(set)context_u, add pthread__locked_switch.
1.1.2.1	22-Feb-2002	petrov	Initial pthreads support
1.4.20.1	18-May-2008	yamt	sync with head.
1.5.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.5.8.1	28-Apr-2008	martin	file pthread_md.h was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.6.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.10	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.9	04-Jan-2006	skrll	A couple of fixes to make libpthread really shared, i.e. not have text re- locations: - Don't declare pthread__switch_away global - Do the PIC dance for pthread__switch_return_point and pthread__locked_switch. Ideally these (and other) symbols would be hidden. Thanks to uwe@, dyoung@ and elad@ for help. XXX sh3 is still to be done. XXX vax does strange things.
1.8	07-Sep-2003	cl	branches: 1.8.6; Remove possible race condition in upcall recycling.
1.7	26-Aug-2003	petrov	typo in previous commit, annul isn't good there, noticed by Eduardo Horvath.
1.6	25-Aug-2003	petrov	Use branch-slot in STACK_SWITCH, suggested by Martin Husemann.
1.5	25-Aug-2003	petrov	Use correct context to switch to.
1.4	26-Jun-2003	nathanw	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.
1.3	15-Jun-2003	martin	Catch up with changes Nathan did to other archs.
1.2	18-Jan-2003	thorpej	Merge the nathanw_sa branch.
1.1	22-Feb-2002	petrov	branches: 1.1.2; file pthread_switch.S was initially added on branch nathanw_sa.
1.1.2.6	20-Sep-2002	petrov	minor clean-up.
1.1.2.5	19-Sep-2002	petrov	PIC aware, remove debug cruft.
1.1.2.4	22-May-2002	petrov	more fixes.
1.1.2.3	21-May-2002	petrov	STACK_SWITCH fix, added debug.
1.1.2.2	26-Apr-2002	petrov	round 2: simplify _get(set)context_u, add pthread__locked_switch.
1.1.2.1	22-Feb-2002	petrov	Implementation of pthread__switch only so far.
1.8.6.1	08-Jan-2006	riz	Pull up following revision(s) (requested by skrll in ticket #1093): lib/libpthread/arch/sparc/pthread_switch.S: revision 1.8 lib/libpthread/arch/x86_64/pthread_switch.S: revision 1.11 lib/libpthread/arch/sparc64/pthread_switch.S: revision 1.9 lib/libpthread/arch/i386/pthread_switch.S: revision 1.9 A couple of fixes to make libpthread really shared, i.e. not have text re- locations: - Don't declare pthread__switch_away global - Do the PIC dance for pthread__switch_return_point and pthread__locked_switch. Ideally these (and other) symbols would be hidden. Thanks to uwe@, dyoung@ and elad@ for help. XXX sh3 is still to be done. XXX vax does strange things.
1.5	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.4	28-Apr-2008	martin	branches: 1.4.8; Remove clause 3 and 4 from TNF licenses
1.3	09-Apr-2005	matt	branches: 1.3.20; Rework and cleanup. Don't use REI, fake a call frame instead.
1.2	19-Jan-2003	matt	Set _UC_USER in ucontext. Call setcontext if _UC_USER is not in _setcontext_u
1.1	19-Jan-2003	matt	VAX versions of _getcontext_u/_setcontext_u/_swapcontext_u
1.3.20.1	18-May-2008	yamt	sync with head.
1.4.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.4.8.1	28-Apr-2008	martin	file _context_u.S was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.9	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.8	28-Apr-2008	martin	branches: 1.8.8; Remove clause 3 and 4 from TNF licenses
1.7	02-Mar-2007	ad	branches: 1.7.12; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.6	09-Apr-2005	matt	Add STACKSPACE
1.5	01-Dec-2004	skrll	pt_sleepuc was removed a long time ago.
1.4	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.3	25-Aug-2003	ragge	Add PT_TRAPUC and pthread__switch_return_point. Not tested (as most of the pthread stuff on vax) but at least allow the system to compile.
1.2	17-Jul-2003	nathanw	Adapt to structure name changes.
1.1	19-Jan-2003	matt	Add of pthread support for VAX.
1.7.12.1	18-May-2008	yamt	sync with head.
1.8.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.8.8.1	28-Apr-2008	martin	file genassym.cf was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.8	25-Jan-2011	christos	make pthread__sp unsigned long.
1.7	16-May-2009	ad	branches: 1.7.2; Remove unused code that's confusing when using cscope/opengrok.
1.6	28-Apr-2008	martin	branches: 1.6.8; Remove clause 3 and 4 from TNF licenses
1.5	10-Feb-2008	ad	branches: 1.5.4; - Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.4	24-Dec-2005	perry	branches: 1.4.12; Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.3	20-Jan-2003	matt	Define FPREG macros even though we don't have any.
1.2	19-Jan-2003	matt	Need to define STACKSIZE (even though we don't need any).
1.1	19-Jan-2003	matt	Add of pthread support for VAX.
1.4.12.1	23-Mar-2008	matt	sync with HEAD
1.5.4.1	18-May-2008	yamt	sync with head.
1.6.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.6.8.1	28-Apr-2008	martin	file pthread_md.h was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.7.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.7	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.6	09-Apr-2005	matt	Merge updates to algorithms from i386 switch code.
1.5	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.4	25-Aug-2003	ragge	Add PT_TRAPUC and pthread__switch_return_point. Not tested (as most of the pthread stuff on vax) but at least allow the system to compile.
1.3	09-Jul-2003	matt	Update to new world order. not tested But will allow builds to finish.
1.2	20-Jan-2003	matt	Add myself to the authors list.
1.1	19-Jan-2003	matt	Add of pthread support for VAX.
1.12	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.11	28-Apr-2008	martin	branches: 1.11.8; Remove clause 3 and 4 from TNF licenses
1.10	10-Feb-2008	ad	branches: 1.10.4; - Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.9	13-Nov-2007	ad	Mutexes: - Play scrooge again and chop more cycles off acquire/release. - Spin while the lock holder is running on another CPU (adaptive mutexes). - Do non-atomic release. Threadreg: - Add the necessary hooks to use a thread register. - Add the code for i386, using %gs. - Leave i386 code disabled until xen and COMPAT_NETBSD32 have the changes.
1.8	13-Nov-2007	ad	For PR bin/37347: - Override __libc_thr_init() instead of using our own constructor. - Add pthread__getenv() and use instead of getenv(). This is used before we are up and running and unfortunatley getenv() takes locks. Other changes: - Cache the spinlock vectors in pthread__st. Internal spinlock operations now take 1 function call instead of 3 (i386). - Use pthread__self() internally, not pthread_self(). - Use __attribute__ ((visibility("hidden"))) in some places. - Kill PTHREAD_MAIN_DEBUG.
1.7	11-Sep-2007	ad	Fix a dodgy bit of assembly.
1.6	07-Sep-2007	ad	- Don't take the mutex's spinlock (ptr_interlock) in pthread_cond_wait(). Instead, make the deferred wakeup list a per-thread array and pass down the lwpid_t's that way. - In pthread_cond_wait(), take the mutex before dealing with early wakeup. In this way there should never be contention on the CV's spinlock if the app follows POSIX rules (there should only be contention on the user-provided mutex). - Add a port of the kernel's rwlocks. The rwlock's spinlock is only taken if there is contention. This is enabled where atomic ops are available. Right now that is only i386 and amd64 because I don't have other hardware to test with. It's trivial to add stubs for other architectures as long as they have compare-and-swap. When we have proper atomic ops the old rwlock code can be removed. - Add a new mutex implementation that's similar to the kernel's mutexes, but uses compare-and-swap to maintain the waiters list, so no spinlocks are involved. Same caveats apply as for the rwlocks.
1.5	07-Sep-2007	ad	Add: pthread__atomic_cas_ptr, pthread__atomic_swap_ptr, pthread__membar_full This is a stopgap until the thorpej-atomic branch is complete.
1.4	21-Oct-2004	fvdl	branches: 1.4.14; 1.4.18; Fix thread context switching to take the stack ABI into account. From Wolfgang Solfrank.
1.3	08-Nov-2003	fvdl	branches: 1.3.2; Restore %rax correctly during a full context restore (oops).
1.2	26-Jul-2003	salo	netbsd.org->NetBSD.org
1.1	30-Jan-2003	fvdl	libpthread support for x86_64.
1.3.2.1	12-Nov-2004	jmc	Pullup rev 1.4 (requested by fvdl in ticket #956) Fix thread context switching to take the stack ABI into account.
1.4.18.3	23-Mar-2008	matt	sync with HEAD
1.4.18.2	09-Jan-2008	matt	sync with HEAD
1.4.18.1	06-Nov-2007	matt	sync with HEAD
1.4.14.1	10-Sep-2007	skrll	Sync with HEAD.
1.10.4.1	18-May-2008	yamt	sync with head.
1.11.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.11.8.1	28-Apr-2008	martin	file _context_u.S was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.7	16-May-2009	ad	Remove unused code that's confusing when using cscope/opengrok.
1.6	28-Apr-2008	martin	branches: 1.6.8; Remove clause 3 and 4 from TNF licenses
1.5	02-Mar-2007	ad	branches: 1.5.12; Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.4	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.3	17-Jul-2003	nathanw	Adapt to structure name changes.
1.2	26-Jun-2003	nathanw	Remove PT_SLEEPUC and add PT_TRAPUC.
1.1	30-Jan-2003	fvdl	libpthread support for x86_64.
1.5.12.1	18-May-2008	yamt	sync with head.
1.6.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.6.8.1	28-Apr-2008	martin	file genassym.cf was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.13	25-May-2023	riastradh	libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437 XXX pullup-10
1.12	25-Jan-2011	christos	branches: 1.12.36; 1.12.46; 1.12.54; make pthread__sp unsigned long.
1.11	16-May-2009	ad	branches: 1.11.2; Remove unused code that's confusing when using cscope/opengrok.
1.10	28-Apr-2008	martin	branches: 1.10.8; Remove clause 3 and 4 from TNF licenses
1.9	22-Mar-2008	ad	branches: 1.9.2; Cheat and add inlines for _atomic_cas_ptr() to work around gcc emitting unneeded PIC stuff in mutex_lock() and mutex_unlock(), when a thread register is used.
1.8	10-Feb-2008	ad	- Remove libpthread's atomic ops. - Remove the old spinlock-based mutex and rwlock implementations. - Use the atomic ops from libc.
1.7	13-Nov-2007	ad	Mutexes: - Play scrooge again and chop more cycles off acquire/release. - Spin while the lock holder is running on another CPU (adaptive mutexes). - Do non-atomic release. Threadreg: - Add the necessary hooks to use a thread register. - Add the code for i386, using %gs. - Leave i386 code disabled until xen and COMPAT_NETBSD32 have the changes.
1.6	24-Sep-2007	skrll	Resurrect the function pointers for lock operations and allow each architecture to provide asm versions of the RAS operations. We do this because relying on the compiler to get the RAS right is not sensible. (It gets alpha wrong and hppa is suboptimal) Provide asm RAS ops for hppa. (A slightly different version) reviewed by Andrew Doran.
1.5	07-Sep-2007	ad	Add: pthread__atomic_cas_ptr, pthread__atomic_swap_ptr, pthread__membar_full This is a stopgap until the thorpej-atomic branch is complete.
1.4	24-Dec-2005	perry	branches: 1.4.8; 1.4.12; Remove leading __ from __(const\|inline\|signed\|volatile) -- it is obsolete.
1.3	26-Jul-2003	salo	netbsd.org->NetBSD.org
1.2	17-Apr-2003	fvdl	Catch up with changed struct reg (same as gregs in mcontext now).
1.1	30-Jan-2003	fvdl	libpthread support for x86_64.
1.4.12.3	23-Mar-2008	matt	sync with HEAD
1.4.12.2	09-Jan-2008	matt	sync with HEAD
1.4.12.1	06-Nov-2007	matt	sync with HEAD
1.4.8.1	10-Sep-2007	skrll	Sync with HEAD.
1.9.2.1	18-May-2008	yamt	sync with head.
1.10.8.2	28-Apr-2008	martin	Remove clause 3 and 4 from TNF licenses
1.10.8.1	28-Apr-2008	martin	file pthread_md.h was added on branch christos-time_t on 2008-04-28 20:23:03 +0000
1.11.2.1	08-Feb-2011	bouyer	Sync with HEAD
1.12.54.1	01-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #296): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.12.46.1	04-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #1700): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.12.36.1	04-Aug-2023	martin	Pull up following revision(s) (requested by riastradh in ticket #1878): lib/libpthread/arch/x86_64/pthread_md.h: revision 1.13 lib/libpthread/pthread_int.h: revision 1.110 lib/libpthread/pthread_int.h: revision 1.111 lib/libpthread/arch/i386/pthread_md.h: revision 1.21 lib/libpthread/arch/arm/pthread_md.h: revision 1.12 lib/libpthread/arch/arm/pthread_md.h: revision 1.13 lib/libpthread/pthread_spin.c: revision 1.11 lib/libpthread/arch/aarch64/pthread_md.h: revision 1.2 libpthread: Use __nothing, not /* nothing */, for empty macros. No functional change intended -- just safer to do it this way in case the macros are used in if branches or comma expressions. PR port-arm/57437 (pthread__smt_pause/wake issue) libpthread: New pthread__smt_wait to put CPU in low power for spin. This is now distinct from pthread__smt_pause, which is for spin lock backoff with no paired wakeup. On Arm, there is a single-bit event register per CPU, and there are two instructions to manage it: - wfe, wait for event -- if event register is clear, enter low power mode and wait until event register is set; then exit low power mode and clear event register - sev, signal event -- sets event register on all CPUs (other circumstances like interrupts also set the event register and cause wfe to wake) These can be used to reduce the power consumption of spinning for a lock, but only if they are actually paired -- if there's no sev, wfe might hang indefinitely. Currently only pthread_spin(3) actually pairs them; the other lock primitives (internal lock, mutex, rwlock) do not -- they have spin lock backoff loops, but no corresponding wakeup to cancel a wfe. It may be worthwhile to teach the other lock primitives to pair wfe/sev, but that requires some performance measurement to verify it's actually worthwhile. So for now, we just make sure not to use wfe when there's no sev, and keep everything else the same -- this should fix severe performance degredation in libpthread on Arm without hurting anything else. No change in the generated code on amd64 and i386. No change in the generated code for pthread_spin.c on arm and aarch64 -- changes only the generated code for pthread_lock.c, pthread_mutex.c, and pthread_rwlock.c, as intended. PR port-arm/57437
1.13	02-Mar-2007	ad	Remove the PTHREAD_SA option. If M:N threads is reimplemented it's better off done with a seperate library.
1.12	09-Jan-2006	skrll	I was a bit over zealous with my last change so revert the locked_return_point change. Loading the instruction at locked_return_point as a return value didn't work so well. Thanks to uwe, cube, and dsl.
1.11	04-Jan-2006	skrll	A couple of fixes to make libpthread really shared, i.e. not have text re- locations: - Don't declare pthread__switch_away global - Do the PIC dance for pthread__switch_return_point and pthread__locked_switch. Ideally these (and other) symbols would be hidden. Thanks to uwe@, dyoung@ and elad@ for help. XXX sh3 is still to be done. XXX vax does strange things.
1.10	23-Apr-2004	simonb	branches: 1.10.2; s/the the/the/ (only in sources that aren't regularly imported from elsewhere).
1.9	08-Nov-2003	fvdl	Make register usage more consistent, also in comparison with the i386 version, for easier maintenance.
1.8	20-Oct-2003	fvdl	Correct and simplify computing the return point; just use PC-relative addressing.
1.7	19-Oct-2003	fvdl	Make sure the stack stays aligned.
1.6	07-Sep-2003	cl	Remove possible race condition in upcall recycling.
1.5	26-Jul-2003	salo	netbsd.org->NetBSD.org
1.4	26-Jun-2003	nathanw	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.
1.3	12-Jun-2003	fvdl	Apply Nathan's switch-away fix.
1.2	10-Feb-2003	fvdl	Continue at the plain switch return point in pthread__switch, not the locked one, in the !PIC case. From Tor Egge via Havard Eidnes.
1.1	30-Jan-2003	fvdl	libpthread support for x86_64.
1.10.2.2	11-Jan-2006	tron	Pull up following revision(s) (requested by skrll in ticket #1115): lib/libpthread/arch/x86_64/pthread_switch.S: revision 1.12 I was a bit over zealous with my last change so revert the locked_return_point change. Loading the instruction at locked_return_point as a return value didn't work so well. Thanks to uwe, cube, and dsl.
1.10.2.1	08-Jan-2006	riz	Pull up following revision(s) (requested by skrll in ticket #1093): lib/libpthread/arch/sparc/pthread_switch.S: revision 1.8 lib/libpthread/arch/x86_64/pthread_switch.S: revision 1.11 lib/libpthread/arch/sparc64/pthread_switch.S: revision 1.9 lib/libpthread/arch/i386/pthread_switch.S: revision 1.9 A couple of fixes to make libpthread really shared, i.e. not have text re- locations: - Don't declare pthread__switch_away global - Do the PIC dance for pthread__switch_return_point and pthread__locked_switch. Ideally these (and other) symbols would be hidden. Thanks to uwe@, dyoung@ and elad@ for help. XXX sh3 is still to be done. XXX vax does strange things.

OpenGrok