| History log of /src/sys/rump/librump/rumpkern/threads.c |
| Revision | | Date | Author | Comments |
| 1.28 |
| 04-Oct-2023 |
ad | rump now needs lwp_need_userret()
|
| 1.27 |
| 01-Aug-2020 |
riastradh | Define kthread_fpu_enter/exit for rump.
XXX Not 100% sure that it's safe to touch curlwp->l_flag in this
context, but this change will make progress, at least.
|
| 1.26 |
| 21-Apr-2017 |
kamil | Fix build of rump after change in lwp_create's signature
|
| 1.25 |
| 21-Apr-2017 |
christos | - Propagate the signal mask from the ucontext_t to the newly created thread
as specified by _lwp_create(2)
- Reset the signal stack for threads created with _lwp_create(2)
|
| 1.24 |
| 26-Jan-2016 |
pooka | branches: 1.24.2; 1.24.4;
Put the kernelside rump kernel headers into <rump-sys> instead of
sprinkling them around the faction directories. Avoids having
to add a CPPFLAGS (or several) to pretty much every component
Makefile.
Leave compat headers around in the old locations.
The commit changes some autogenerated files, but I'll fix the
generators shortly and regen.
|
| 1.23 |
| 09-Apr-2014 |
pooka | branches: 1.23.4;
implement lwp_create() and a few related interfaces.
main raison d'impalerment: the aio driver
|
| 1.22 |
| 15-Mar-2014 |
pooka | branches: 1.22.2;
Allow compile-time optimizations to curlwp. This can have a pretty
staggering impact on performance. When running sendto() in a loop,
the improvement is 200k more calls per second with an inlined __thread
curlwp as opposed to the default. In other words, it shaves off hundreds
of CPU cycles per call (~20%). Even just eliminating the x86_curlwp()
call in favor of an inline gives an improvement of 60k calls per second.
|
| 1.21 |
| 02-May-2013 |
pooka | branches: 1.21.4;
Inform the rump kernel hypervisor of valid thread contexts so
that the implementation can allocate and release storage for them
in an optimal fashion, if necessary.
|
| 1.20 |
| 30-Apr-2013 |
pooka | In kthread_create(), pass the priority and cpu index down to the
rump kernel hypervisor (though the current implementation doesn't take
advantage of them).
|
| 1.19 |
| 27-Apr-2013 |
pooka | roll mutex init hypercalls into one (one of them already took a flag anyway)
|
| 1.18 |
| 10-Mar-2013 |
pooka | Don't allow kernel threads to run before all CPUs have been initialized
to avoid them getting scheduled on non-initialized CPUs.
|
| 1.17 |
| 04-Nov-2012 |
pooka | Add vdrain to the list of kernel threads.
|
| 1.16 |
| 04-Nov-2012 |
pooka | Use a table to check for kernel threads.
|
| 1.15 |
| 07-Aug-2011 |
rmind | branches: 1.15.2; 1.15.12;
Rename slightly misleading KTHREAD_JOINABLE to KTHREAD_MUSTJOIN.
|
| 1.14 |
| 17-Jul-2011 |
joerg | Retire varargs.h support. Move machine/stdarg.h logic into MI
sys/stdarg.h and expect compiler to provide proper builtins, defaulting
to the GCC interface. lint still has a special fallback.
Reduce abuse of _BSD_VA_LIST_ by defining __va_list by default and
derive va_list as required by standards.
|
| 1.13 |
| 29-Oct-2010 |
pooka | Attach implicit threads to initproc instead of proc0. This way
applications which alter, by purpose or by accident, the uid in an
implicit thread are don't affect kernel threads.
from discussion with njoly
|
| 1.12 |
| 01-Sep-2010 |
pooka | Implement rump_lwproc: the new lwp/proc management routines for
rump. These move the management of the pid/lwpid space from the
application into the kernel, make code more robust, and make it
possible to attach multiple lwp's to non-proc0 processes.
|
| 1.11 |
| 03-Jun-2010 |
pooka | Don't use rumpuser_malloc() directly.
|
| 1.10 |
| 31-May-2010 |
pooka | Support KTHREAD_JOINABLE/kthread_join(). Also fixes earlier bug
where all pthreads were created non-detached.
|
| 1.9 |
| 28-May-2010 |
pooka | Improve the CPU scheduler for a host MP system with multithreaded
access. The old scheduler had a global freelist which caused a
cache crisis with multiple host threads trying to schedule a virtual
CPU simultaneously.
The rump scheduler is different from a normal thread scheduler, so
it has different requirements. First, we schedule a CPU for a
thread (which we get from the host scheduler) instead of scheduling
a thread onto a CPU. Second, scheduling points are at every
entry/exit to/from the rump kernel, including (but not limited to)
syscall entry points and hypercalls. This means scheduling happens
a lot more frequently than in a normal kernel.
For every lwp, cache the previously used CPU. When scheduling,
attempt to reuse the same CPU. If we get it, we can use it directly
without any memory barriers or expensive locks. If the CPU is
taken, migrate. Use a lock/wait only in the slowpath. Be very
wary of walking the entire CPU array because that does not lead to
a happy cacher.
The migration algorithm could probably benefit from improved
heuristics and tuning. Even as such, with the new scheduler an
application which has two threads making rlimit syscalls in a tight
loop experiences almost 400% speedup. The exact speedup is difficult
to pinpoint, though, since the old scheduler caused very jittery
results due to cache contention. Also, the rump version is now
70% faster than the counterpart which calls the host kernel.
|
| 1.8 |
| 09-Feb-2010 |
pooka | branches: 1.8.2; 1.8.4;
Store l_name for kernel threads.
|
| 1.7 |
| 27-Jan-2010 |
pooka | branches: 1.7.2;
ignore pmf threads if RUMP_THREADS == 0
|
| 1.6 |
| 05-Dec-2009 |
pooka | KERNEL_UNLOCK_LAST in non-mpsafe kthread exit.
|
| 1.5 |
| 03-Dec-2009 |
pooka | Soft-fail xcall thread creation to make RUMP_THREADS=0 work again.
|
| 1.4 |
| 01-Dec-2009 |
pooka | Almost there for virtual CPU MP support:
* support bound kernel threads
* bind softint threads to specific virtual cpus
+ remove now-unnecessary locks from softint code
Now, if we only had MI CPU_INFO_FOREACH() .... (hi rmind ;)
|
| 1.3 |
| 09-Nov-2009 |
pooka | adjust comment for previous
|
| 1.2 |
| 09-Nov-2009 |
pooka | set LP_INTR for KTHREAD_INTR
|
| 1.1 |
| 04-Nov-2009 |
pooka | Give the kthread->pthread interface emulation its own module.
|
| 1.7.2.4 |
| 06-Nov-2010 |
uebayasi | Sync with HEAD.
|
| 1.7.2.3 |
| 22-Oct-2010 |
uebayasi | Sync with HEAD (-D20101022).
|
| 1.7.2.2 |
| 17-Aug-2010 |
uebayasi | Sync with HEAD.
|
| 1.7.2.1 |
| 30-Apr-2010 |
uebayasi | Sync with HEAD.
|
| 1.8.4.3 |
| 05-Mar-2011 |
rmind | sync with head
|
| 1.8.4.2 |
| 03-Jul-2010 |
rmind | sync with head
|
| 1.8.4.1 |
| 30-May-2010 |
rmind | sync with head
|
| 1.8.2.4 |
| 09-Oct-2010 |
yamt | sync with head
|
| 1.8.2.3 |
| 11-Aug-2010 |
yamt | sync with head.
|
| 1.8.2.2 |
| 11-Mar-2010 |
yamt | sync with head
|
| 1.8.2.1 |
| 09-Feb-2010 |
yamt | file threads.c was added on branch yamt-nfs-mp on 2010-03-11 15:04:38 +0000
|
| 1.15.12.4 |
| 03-Dec-2017 |
jdolecek | update from HEAD
|
| 1.15.12.3 |
| 20-Aug-2014 |
tls | Rebase to HEAD as of a few days ago.
|
| 1.15.12.2 |
| 23-Jun-2013 |
tls | resync from head
|
| 1.15.12.1 |
| 20-Nov-2012 |
tls | Resync to 2012-11-19 00:00:00 UTC
|
| 1.15.2.2 |
| 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")
|
| 1.15.2.1 |
| 16-Jan-2013 |
yamt | sync with (a bit old) head
|
| 1.21.4.1 |
| 18-May-2014 |
rmind | sync with head
|
| 1.22.2.1 |
| 10-Aug-2014 |
tls | Rebase.
|
| 1.23.4.2 |
| 28-Aug-2017 |
skrll | Sync with HEAD
|
| 1.23.4.1 |
| 19-Mar-2016 |
skrll | Sync with HEAD
|
| 1.24.4.2 |
| 23-Apr-2017 |
bouyer | Sync with HEAD
|
| 1.24.4.1 |
| 21-Apr-2017 |
bouyer | Sync with HEAD
|
| 1.24.2.1 |
| 26-Apr-2017 |
pgoyette | Sync with HEAD
|
