mdf bbc3957715 Fix a bug with sched_affinity() where it checks td_pinned of another ...

thread in a racy manner, which can lead to attempting to migrate a
thread that is pinned to a CPU.  Instead, have sched_switch() determine
which CPU a thread should run on if the current one is not allowed.

KASSERT in sched_bind() that the thread is not yet pinned to a CPU.

KASSERT in sched_switch() that only migratable threads or those moving
due to a sched_bind() are changing CPUs.

sched_affinity code came from jhb@.

MFC after:	2 weeks

2010-09-01 20:32:47 +00:00

..

bus_if.m

…

clock_if.m

…

cpufreq_if.m

…

device_if.m

…

genassym.sh

…

imgact_aout.c

…

imgact_elf32.c

…

imgact_elf64.c

…

imgact_elf.c

Supply some useful information to the started image using ELF aux vectors.

2010-08-17 08:55:45 +00:00

imgact_gzip.c

…

imgact_shell.c

…

inflate.c

…

init_main.c

…

init_sysent.c

Regen

2010-08-30 14:26:02 +00:00

kern_acct.c

…

kern_alq.c

…

kern_clock.c

…

kern_clocksource.c

…

kern_condvar.c

…

kern_conf.c

…

kern_cons.c

…

kern_context.c

…

kern_cpu.c

…

kern_cpuset.c

…

kern_ctf.c

…

kern_descrip.c

…

kern_dtrace.c

Bump KDTRACE_THREAD_ZERO and use M_ZERO as a malloc flag instead of

2010-08-22 11:09:53 +00:00

kern_environment.c

…

kern_et.c

…

kern_event.c

…

kern_exec.c

execve(2) has a special check for file permissions: a file must have at

2010-08-30 16:30:18 +00:00

kern_exit.c

Add an extra comment to the SDT probes definition. This allows us to get

2010-08-22 11:18:57 +00:00

kern_fail.c

…

kern_fork.c

Add an extra comment to the SDT probes definition. This allows us to get

2010-08-22 11:18:57 +00:00

kern_gzio.c

…

kern_idle.c

…

kern_intr.c

…

kern_jail.c

…

kern_kthread.c

…

kern_ktr.c

…

kern_ktrace.c

Fix a whitespace nit and remove a questioning comment. STAILQ_CONCAT()

2010-08-19 16:38:58 +00:00

kern_linker.c

…

kern_lock.c

Add dedicated routines to toggle lockmgr flags such as LK_NOSHARE and

2010-08-20 19:46:50 +00:00

kern_lockf.c

…

kern_lockstat.c

…

kern_malloc.c

The realloc case for memguard(9) will copy too many bytes when

2010-08-31 16:57:58 +00:00

kern_mbuf.c

…

kern_mib.c

…

kern_module.c

…

kern_mtxpool.c

…

kern_mutex.c

…

kern_ntptime.c

…

kern_osd.c

…

kern_physio.c

…

kern_pmc.c

…

kern_poll.c

…

kern_priv.c

Add an extra comment to the SDT probes definition. This allows us to get

2010-08-22 11:18:57 +00:00

kern_proc.c

Add an extra comment to the SDT probes definition. This allows us to get

2010-08-22 11:18:57 +00:00

kern_prot.c

…

kern_resource.c

…

kern_rmlock.c

rmlock(9) two additions and one change/fix:

2010-09-01 19:50:03 +00:00

kern_rwlock.c

…

kern_sdt.c

…

kern_sema.c

…

kern_shutdown.c

…

kern_sig.c

rescure comments from RELENG_4.

2010-09-01 01:26:07 +00:00

kern_switch.c

…

kern_sx.c

…

kern_synch.c

…

kern_syscalls.c

…

kern_sysctl.c

…

kern_tc.c

…

kern_thr.c

Optimize thr_suspend, if timeout is zero, don't call msleep, just

2010-08-24 07:29:55 +00:00

kern_thread.c

…

kern_time.c

…

kern_timeout.c

Add an extra comment to the SDT probes definition. This allows us to get

2010-08-22 11:18:57 +00:00

kern_umtx.c

If a thread is removed from umtxq while sleeping, reset error code

2010-08-25 03:14:32 +00:00

kern_uuid.c

…

kern_xxx.c

…

ksched.c

…

link_elf_obj.c

…

link_elf.c

…

linker_if.m

…

Make.tags.inc

…

Makefile

This should really be MACHINE not MACHINE_ARCH, and is this Makefile even used?

2010-08-23 06:22:35 +00:00

makesyscalls.sh

…

md4c.c

…

md5c.c

…

p1003_1b.c

…

posix4_mib.c

…

sched_4bsd.c

…

sched_ule.c

Fix a bug with sched_affinity() where it checks td_pinned of another

2010-09-01 20:32:47 +00:00

serdev_if.m

…

stack_protector.c

…

subr_acl_nfs4.c

execve(2) has a special check for file permissions: a file must have at

2010-08-30 16:30:18 +00:00

subr_acl_posix1e.c

execve(2) has a special check for file permissions: a file must have at

2010-08-30 16:30:18 +00:00

subr_autoconf.c

Allow interrupt driven config hooks to be registered from config hook callbacks.

2010-08-12 19:50:40 +00:00

subr_blist.c

…

subr_bufring.c

…

subr_bus.c

Properly indent a continue statement. No functional changes.

2010-08-12 19:26:27 +00:00

subr_clock.c

…

subr_devstat.c

…

subr_disk.c

…

subr_eventhandler.c

…

subr_fattime.c

…

subr_firmware.c

…

subr_hash.c

…

subr_hints.c

…

subr_kdb.c

…

subr_kobj.c

…

subr_lock.c

…

subr_log.c

…

subr_mbpool.c

…

subr_mchain.c

…

subr_module.c

…

subr_msgbuf.c

…

subr_param.c

…

subr_pcpu.c

…

subr_power.c

…

subr_prf.c

…

subr_prof.c

…

subr_rman.c

…

subr_rtc.c

Add the half of time-of-day clock resolution when we adjust system time from

2010-08-12 17:17:05 +00:00

subr_sbuf.c

…

subr_scanf.c

…

subr_sglist.c

…

subr_sleepqueue.c

make sure thread lock is locked.

2010-08-20 23:51:34 +00:00

subr_smp.c

…

subr_stack.c

…

subr_taskqueue.c

Run all tasks from a proper context, with proper priority, etc.

2010-08-28 08:38:03 +00:00

subr_trap.c

Call the systrace_probe_func() when the error value.

2010-08-22 11:30:49 +00:00

subr_turnstile.c

…

subr_uio.c

…

subr_unit.c

…

subr_witness.c

…

sys_generic.c

For some file types, select code registers two selfd structures. E.g.,

2010-08-28 17:42:08 +00:00

sys_pipe.c

…

sys_process.c

…

sys_socket.c

…

syscalls.c

Regen

2010-08-30 14:26:02 +00:00

syscalls.master

Make the syscalls reserved for AFS usable by OpenAFS port.

2010-08-30 14:24:44 +00:00

systrace_args.c

Regen

2010-08-30 14:26:02 +00:00

sysv_ipc.c

…

sysv_msg.c

…

sysv_sem.c

…

sysv_shm.c

…

tty_compat.c

…

tty_info.c

…

tty_inq.c

…

tty_outq.c

…

tty_pts.c

…

tty_tty.c

…

tty_ttydisc.c

…

tty.c

…

uipc_accf.c

…

uipc_cow.c

…

uipc_debug.c

…

uipc_domain.c

…

uipc_mbuf2.c

…

uipc_mbuf.c

…

uipc_mqueue.c

…

uipc_sem.c

…

uipc_shm.c

…

uipc_sockbuf.c

…

uipc_socket.c

…

uipc_syscalls.c

…

uipc_usrreq.c

…

vfs_acl.c

…

vfs_aio.c

…

vfs_bio.c

…

vfs_cache.c

Add an extra comment to the SDT probes definition. This allows us to get

2010-08-22 11:18:57 +00:00

vfs_cluster.c

…

vfs_default.c

If we read zero bytes from the directory, early out with ENOENT

2010-08-25 18:09:51 +00:00

vfs_export.c

…

vfs_extattr.c

…

vfs_hash.c

…

vfs_init.c

…

vfs_lookup.c

Add an extra comment to the SDT probes definition. This allows us to get

2010-08-22 11:18:57 +00:00

vfs_mount.c

There is a bug in vfs_allocate_syncvnode() failure handling in mount code.

2010-08-28 08:57:15 +00:00

vfs_subr.c

As long as we are going to panic anyway, there's no need to hide additional

2010-09-01 13:47:11 +00:00

vfs_syscalls.c

Add an extra comment to the SDT probes definition. This allows us to get

2010-08-22 11:18:57 +00:00

vfs_vnops.c

…

vnode_if.src

…