Julian Elischer ed062c8d66 Refactor a bunch of scheduler code to give basically the same behaviour ... but with slightly cleaned up interfaces. The KSE structure has become the same as the "per thread scheduler private data" structure. In order to not make the diffs too great one is #defined as the other at this time. The KSE (or td_sched) structure is now allocated per thread and has no allocation code of its own. Concurrency for a KSEGRP is now kept track of via a simple pair of counters rather than using KSE structures as tokens. Since the KSE structure is different in each scheduler, kern_switch.c is now included at the end of each scheduler. Nothing outside the scheduler knows the contents of the KSE (aka td_sched) structure. The fields in the ksegrp structure that are to do with the scheduler's queueing mechanisms are now moved to the kg_sched structure. (per ksegrp scheduler private data structure). In other words how the scheduler queues and keeps track of threads is no-one's business except the scheduler's. This should allow people to write experimental schedulers with completely different internal structuring. A scheduler call sched_set_concurrency(kg, N) has been added that notifies teh scheduler that no more than N threads from that ksegrp should be allowed to be on concurrently scheduled. This is also used to enforce 'fainess' at this time so that a ksegrp with 10000 threads can not swamp a the run queue and force out a process with 1 thread, since the current code will not set the concurrency above NCPU, and both schedulers will not allow more than that many onto the system run queue at a time. Each scheduler should eventualy develop their own methods to do this now that they are effectively separated. Rejig libthr's kernel interface to follow the same code paths as linkse for scope system threads. This has slightly hurt libthr's performance but I will work to recover as much of it as I can. Thread exit code has been cleaned up greatly. exit and exec code now transitions a process back to 'standard non-threaded mode' before taking the next step. Reviewed by: scottl, peter MFC after: 1 week		2004-09-05 02:09:54 +00:00
..
bus_if.m	Minor formatting fixes for lines > 80 characters	2004-08-12 17:26:22 +00:00
clock_if.m
device_if.m	Minor formatting fixes for lines > 80 characters	2004-08-12 17:26:22 +00:00
genassym.sh
imgact_aout.c	Change the types of vn_rdwr_inchunks()'s len and aresid arguments to	2004-06-05 02:18:28 +00:00
imgact_elf.c	Add __elfN(dump_thread). This function is called from __elfN(coredump)	2004-08-11 02:35:06 +00:00
imgact_elf32.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
imgact_elf64.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
imgact_gzip.c	Locking for the per-process resource limits structure.	2004-02-04 21:52:57 +00:00
imgact_shell.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
inflate.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
init_main.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
init_sysent.c	Give kldunload a -f(orce) argument.	2004-07-13 19:36:59 +00:00
kern_acct.c	Second half of the dev_t cleanup.	2004-06-17 17:16:53 +00:00
kern_acl.c	Rename suser_cred()'s PRISON_ROOT flag to SUSER_ALLOWJAIL. This is	2004-07-26 07:24:04 +00:00
kern_alq.c	Allow MAC policies to block/revoke kern_alq write access to a file.	2003-10-25 16:10:41 +00:00
kern_clock.c	Update for the KDB framework:	2004-07-10 21:36:01 +00:00
kern_condvar.c	Now that the return value semantics of cv's for multithreaded processes	2004-08-19 11:31:42 +00:00
kern_conf.c	Add a missing '\n'.	2004-08-30 01:10:20 +00:00
kern_context.c	Change the clear_ret argument of get_mcontext() to be a flags argument.	2003-11-09 20:31:04 +00:00
kern_descrip.c	Remove GIANT_REQUIRED from setugidsafety() as knote_fdclose() no longer	2004-08-19 14:59:51 +00:00
kern_environment.c	If the buffer supplied to kenv(KENV_DUMP, ...) isn't big enough,	2004-04-28 01:27:33 +00:00
kern_event.c	Allocate the marker, when scanning a kqueue, from the "heap" instead of the	2004-08-16 03:08:38 +00:00
kern_exec.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_exit.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_fork.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_idle.c	Give the 4bsd scheduler the ability to wake up idle processors	2004-09-01 06:42:02 +00:00
kern_intr.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_jail.c	Add two missing includes and remove two uneeded.	2004-06-27 09:03:22 +00:00
kern_kse.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_kthread.c	Give setrunqueue() and sched_add() more of a clue as to	2004-09-01 02:11:28 +00:00
kern_ktr.c	Export KTR_COMPILE as a sysctl so you can easily check from user space	2004-07-23 17:41:44 +00:00
kern_ktrace.c	Rename suser_cred()'s PRISON_ROOT flag to SUSER_ALLOWJAIL. This is	2004-07-26 07:24:04 +00:00
kern_linker.c	When trying each linker class in turn with a preloaded module, exit	2004-08-27 01:20:26 +00:00
kern_lock.c	Reintroduce slightly modified patch from kern/69964. Check for	2004-08-27 01:41:28 +00:00
kern_lockf.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
kern_mac.c	Do a pass over all modules in the kernel and make them return EOPNOTSUPP	2004-07-15 08:26:07 +00:00
kern_malloc.c	Reimplement contigmalloc(9) with an algorithm which stands a greatly-	2004-07-19 06:21:27 +00:00
kern_mbuf.c	* Add a "how" argument to uma_zone constructors and initialization functions	2004-08-02 00:18:36 +00:00
kern_mib.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
kern_module.c	Don't bother calling the module event handlers from module_shutdown()	2004-08-20 21:47:48 +00:00
kern_mtxpool.c	Rearrange the SYSINIT order to call lockmgr_init() earlier so that	2003-07-16 01:00:39 +00:00
kern_mutex.c	Turn PREEMPTION into a kernel option. Make sure that it's defined if	2004-09-02 18:59:15 +00:00
kern_ntptime.c	Annual NTP kernel code spring-cleaning:	2004-03-14 15:23:05 +00:00
kern_physio.c	Eliminate the acquisition and release of Giant within physio(). Remove	2004-08-10 21:47:11 +00:00
kern_poll.c	Add a NULL param to an mi_switch() that I missed.	2004-07-03 02:38:03 +00:00
kern_proc.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_prot.c	Remove sched_free_thread() which was only used	2004-08-31 06:12:13 +00:00
kern_resource.c	Push UIDINFO_UNLOCK() slightly earlier in chgsbize(), as it's not	2004-08-06 22:04:33 +00:00
kern_sema.c	Change the return value of sema_timedwait() so it returns 0 on	2004-06-14 18:19:05 +00:00
kern_shutdown.c	Turn PREEMPTION into a kernel option. Make sure that it's defined if	2004-09-02 18:59:15 +00:00
kern_sig.c	Remove an unneeded argument..	2004-08-31 07:34:54 +00:00
kern_subr.c	Clean up and wash struct iovec and struct uio handling.	2004-07-10 15:42:16 +00:00
kern_switch.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_sx.c	Fix _sx_assert() to panic() rather than printf() when an assertion fails	2004-02-27 16:13:44 +00:00
kern_synch.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_syscalls.c	Do a pass over all modules in the kernel and make them return EOPNOTSUPP	2004-07-15 08:26:07 +00:00
kern_sysctl.c	Avoid casts as lvalues.	2004-07-28 06:42:41 +00:00
kern_tc.c	Add some KASSERTS.	2004-08-14 08:33:49 +00:00
kern_thr.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_thread.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
kern_time.c	Update previous commit to:	2004-06-21 22:34:57 +00:00
kern_timeout.c	Cut a KTR record whenever a callout is invoked. Mark whether it runs	2004-08-06 21:49:00 +00:00
kern_umtx.c	writers must hold both sched_lock and the process lock; therefore, readers	2004-07-12 15:28:31 +00:00
kern_uuid.c	Fix generation of random multicast MAC address.	2004-01-22 13:34:11 +00:00
kern_xxx.c	Rename suser_cred()'s PRISON_ROOT flag to SUSER_ALLOWJAIL. This is	2004-07-26 07:24:04 +00:00
ksched.c	sched_setscheduler: Return EINVAL when a invalid policy is specified,	2003-09-13 18:46:24 +00:00
link_elf.c	Normalize the VM wiring done with SPARSE_MAPPING: check for errors, and	2004-08-09 18:46:13 +00:00
link_elf_obj.c	Add support for completing the installation of ELF relocatable	2004-08-29 01:21:51 +00:00
linker_if.m	The method link_preload_finish is not static.	2003-09-20 17:39:32 +00:00
Make.tags.inc	Finish driving a stake through the heart of netns and the associated	2003-03-05 19:24:24 +00:00
Makefile	Finish driving a stake through the heart of netns and the associated	2003-03-05 19:24:24 +00:00
makesyscalls.sh	Remove the namespace column from the syscalls tables. We don't actually	2003-12-23 03:50:43 +00:00
md4c.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
md5c.c	Revert stuff which accidentally ended up in the previous commit.	2003-07-22 10:36:36 +00:00
p1003_1b.c	Use __FBSDID().	2003-06-11 06:34:30 +00:00
posix4_mib.c	Use __FBSDID().	2003-06-11 06:34:30 +00:00
sched_4bsd.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
sched_ule.c	Refactor a bunch of scheduler code to give basically the same behaviour	2004-09-05 02:09:54 +00:00
subr_acl_posix1e.c	Rename suser_cred()'s PRISON_ROOT flag to SUSER_ALLOWJAIL. This is	2004-07-26 07:24:04 +00:00
subr_autoconf.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
subr_blist.c	Move the definitions of SWAPBLK_NONE and SWAPBLK_MASK from vm_page.h to	2004-06-04 04:03:26 +00:00
subr_bus.c	Fix BUS_DEBUG case	2004-08-30 05:48:49 +00:00
subr_clist.c	Preparation commit for the tty cleanups that will follow in the near	2004-07-15 20:47:41 +00:00
subr_clock.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
subr_devstat.c	Do the dreaded s/dev_t/struct cdev */	2004-06-16 09:47:26 +00:00
subr_disk.c	Add bioq_takefirst().	2004-08-19 19:51:51 +00:00
subr_eventhandler.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
subr_hints.c	Add a resource_disabled() helper function that returns true (non-zero) if	2003-07-02 16:01:38 +00:00
subr_kdb.c	Make debug.kdb.stop_cpus also a TUNABLE() so it can be set prior to boot	2004-08-22 15:10:52 +00:00
subr_kobj.c	* Add multiple inheritance to kobj. Each class can have zero or more base	2003-10-16 09:16:28 +00:00
subr_log.c	Do the dreaded s/dev_t/struct cdev */	2004-06-16 09:47:26 +00:00
subr_mbpool.c	Pass MTX_DEF as the last argument to mtx_init() instead of 0. This	2003-12-07 21:53:41 +00:00
subr_mchain.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
subr_module.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
subr_msgbuf.c	Put the message about msgbuf cksum mismatch under bootverbose and tell	2003-09-05 11:12:00 +00:00
subr_param.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
subr_pcpu.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
subr_power.c	Move the kernel power change printf under bootverbose since the	2004-01-02 18:24:13 +00:00
subr_prf.c	Update for the KDB framework:	2004-07-10 21:43:23 +00:00
subr_prof.c	- Move TDF_OWEPREEMPT, TDF_OWEUPC, and TDF_USTATCLOCK over to td_pflags	2004-07-16 21:04:55 +00:00
subr_rman.c	Add a newline.	2004-08-19 20:16:09 +00:00
subr_rtc.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
subr_sbuf.c	Cosmetic adjustment to previous commit: name the second argument to	2004-07-09 11:37:44 +00:00
subr_scanf.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
subr_sleepqueue.c	Now that the return value semantics of cv's for multithreaded processes	2004-08-19 11:31:42 +00:00
subr_smp.c	Move 4bsd specific experimental IP code into the 4bsd file.	2004-09-03 07:42:31 +00:00
subr_taskqueue.c	rearange some code that handles the thread taskqueue so that it is more	2004-08-08 02:37:22 +00:00
subr_trap.c	Remove an unneeded argument..	2004-08-31 07:34:54 +00:00
subr_turnstile.c	Give setrunqueue() and sched_add() more of a clue as to	2004-09-01 02:11:28 +00:00
subr_witness.c	Remove a potential deadlock on i386 SMP by changing the lazypmap ipi and	2004-08-04 20:31:19 +00:00
sys_generic.c	Poll() uses the array smallbits that is big enough to hold 32 struct	2004-08-27 21:23:50 +00:00
sys_pipe.c	Major enhancements to pipe memory usage:	2004-08-16 01:27:24 +00:00
sys_process.c	Add pl_flags to ptrace_lwpinfo, two flags PL_FLAG_SA and PL_FLAG_BOUND	2004-08-08 22:26:11 +00:00
sys_socket.c	Push Giant acquisition down into fo_stat() from most callers. Acquire	2004-07-22 20:40:23 +00:00
syscalls.c	Give kldunload a -f(orce) argument.	2004-07-13 19:36:59 +00:00
syscalls.master	Add kldunloadf() system call. Stay tuned for follwing commit messages.	2004-07-13 19:35:11 +00:00
sysv_ipc.c	Use __FBSDID().	2003-06-11 00:56:59 +00:00
sysv_msg.c	Add missing #include <sys/module.h>	2004-05-30 20:34:58 +00:00
sysv_sem.c	Add missing #include <sys/module.h>	2004-05-30 20:34:58 +00:00
sysv_shm.c	Push Giant deep into vm_forkproc(), acquiring it only if the process has	2004-09-03 05:11:32 +00:00
tty.c	Add locking to the kqueue subsystem. This also makes the kqueue subsystem	2004-08-15 06:24:42 +00:00
tty_compat.c	Put the pre FreeBSD-2.x tty compat code under BURN_BRIDGES.	2004-06-21 22:57:16 +00:00
tty_conf.c	Preparation commit for the tty cleanups that will follow in the near	2004-07-15 20:47:41 +00:00
tty_cons.c	Add locking to the kqueue subsystem. This also makes the kqueue subsystem	2004-08-15 06:24:42 +00:00
tty_pty.c	Preparation commit for the tty cleanups that will follow in the near	2004-07-15 20:47:41 +00:00
tty_subr.c	Preparation commit for the tty cleanups that will follow in the near	2004-07-15 20:47:41 +00:00
tty_tty.c	Second half of the dev_t cleanup.	2004-06-17 17:16:53 +00:00
uipc_accf.c	Add a global mutex, accept_filter_mtx, to protect the global list of	2004-06-01 04:08:48 +00:00
uipc_cow.c	In some cases, sf_buf_alloc() should sleep with pri PCATCH; in others, it	2004-04-03 09:16:27 +00:00
uipc_domain.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
uipc_jumbo.c	Use kmem_alloc_nofault() rather than kmem_alloc_pageable() for allocating	2004-07-23 19:36:18 +00:00
uipc_mbuf.c	Back out just a portion of Alfred's last commit. Remove the MBUF_CHECK	2004-07-21 21:03:01 +00:00
uipc_mbuf2.c	Make sure we don't call mbuf allocation functions with mutexes held.	2004-07-21 07:12:24 +00:00
uipc_proto.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
uipc_sem.c	Add missing #include <sys/module.h>	2004-05-30 20:34:58 +00:00
uipc_sockbuf.c	Add locking to the kqueue subsystem. This also makes the kqueue subsystem	2004-08-15 06:24:42 +00:00
uipc_socket.c	Conditional acquisition of socket buffer mutexes when testing socket	2004-08-24 05:28:18 +00:00
uipc_socket2.c	Add locking to the kqueue subsystem. This also makes the kqueue subsystem	2004-08-15 06:24:42 +00:00
uipc_syscalls.c	Add locking to the kqueue subsystem. This also makes the kqueue subsystem	2004-08-15 06:24:42 +00:00
uipc_usrreq.c	Don't hold the UNIX domain socket subsystem lock over the body of the	2004-08-25 21:24:36 +00:00
vfs_acl.c	Rename suser_cred()'s PRISON_ROOT flag to SUSER_ALLOWJAIL. This is	2004-07-26 07:24:04 +00:00
vfs_aio.c	Tag AIO as requiring Giant over the network stack using	2004-09-03 03:19:14 +00:00
vfs_bio.c	Eliminate unused second argument to reassignbuf() and simplify it	2004-07-25 21:24:23 +00:00
vfs_cache.c	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00
vfs_cluster.c	Eliminate unused second argument to reassignbuf() and simplify it	2004-07-25 21:24:23 +00:00
vfs_default.c	Make VFS_ROOT() and vflush() take a thread argument.	2004-07-12 08:14:09 +00:00
vfs_export.c	Make VFS_ROOT() and vflush() take a thread argument.	2004-07-12 08:14:09 +00:00
vfs_extattr.c	Rename suser_cred()'s PRISON_ROOT flag to SUSER_ALLOWJAIL. This is	2004-07-26 07:24:04 +00:00
vfs_init.c	Put a version element in the VFS filesystem configuration structure	2004-07-30 22:08:52 +00:00
vfs_lookup.c	Assert Giant in namei(). Bugs have been reported in which, following	2004-08-04 18:39:07 +00:00
vfs_mount.c	Put a version element in the VFS filesystem configuration structure	2004-07-30 22:08:52 +00:00
vfs_subr.c	Don't attempt to trigger the syncer thread final sync code in the	2004-08-20 19:21:47 +00:00
vfs_syscalls.c	Rename suser_cred()'s PRISON_ROOT flag to SUSER_ALLOWJAIL. This is	2004-07-26 07:24:04 +00:00
vfs_vnops.c	Add locking to the kqueue subsystem. This also makes the kqueue subsystem	2004-08-15 06:24:42 +00:00
vnode_if.src	Remove advertising clause from University of California Regent's license,	2004-04-05 21:03:37 +00:00