d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
e86c09ff09
freebsd-nq/sys/kern/subr_trap.c

267 lines
7.2 KiB
C
Raw Normal View History

Initial import, 0.1 + pk 0.2.4-B1
1993-06-12 14:58:17 +00:00
/*-
trap.c: Vastly improved trap.c from me. This rewritten version has a variety of features, amoung them: higher performance and much higher code quality. support.s, cpufunc.h: No longer use gs override to enforce range limits - compare directly against VM_MAXUSER_ADDRESS instead. The old way caused problems in preserving the gs selector...and this method is just as fast or faster.
1994-06-06 14:54:41 +00:00
* Copyright (C) 1994, David Greenman
* Copyright (c) 1990, 1993
* The Regents of the University of California. All rights reserved.
Initial import, 0.1 + pk 0.2.4-B1
1993-06-12 14:58:17 +00:00
*
* This code is derived from software contributed to Berkeley by
* the University of Utah, and William Jolitz.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
genassym.c: Remove NKMEMCLUSTERS, it is no longer define or used. locores.s: Fix comment on PTDpde and APTDpde to be pde instead of pte Add new equation for calculating location of Sysmap Remove Bill's old #ifdef garbage for counting up memory, that stuff will never be made to work and was just cluttering up the file. Add code that places the PTD, page table pages, and kernel stack below the 640k ISA hole if there is room for it, otherwise put this stuff all at 1MB. This fixes the 28K bogusity in the boot blocks, that can now go away! Fix the caclulation of where first is to be dependent on NKPDE so that we can skip over the above mentioned areas. The 28K thing is now 44K in size due to the increase in kernel virtual memory space, but since we no longer have to worry about that this is no big deal. Use if NNPX > 0 instead of ifdef NPX for floating point code. machdep.c Change the calculation of for the buffer cache to be 20% of all memory above 2MB and add back the upper limit of 2/5's of the VM_KMEM_SIZE so that we do not eat ALL of the kernel memory space on large memory machines, note that this will not even come into effect unless you have more than 32MB. The current buffer cache limit is 6.7MB due to this caclulation. It seems that we where erroniously allocating bufpages pages for buffer_map. buffer_map is UNUSED in this implementation of the buffer cache, but since the map is referenced in several if statements a quick fix was to simply allocate 1 vm page (but no real memory) to it. pmap.h Remove rcsid, don't want them in the kernel files! Removed some cruft inside an #ifdef DEBUGx that caused compiler errors if you where compiling this for debug. Use the #defines for PD_SHIFT and PG_SHIFT in place of constants. trap.c: Remove patch kit header and rcsid, fix $Id$. Now include "npx.h" and use NNPX for controlling the floating point code. Remove a now completly invalid check for a maximum virtual address, the virtual address now ends at 0xFFFFFFFF so there is no more MAX!! (Thanks David, I completly missed that one!) vm_machdep.c Remove patch kit header and rcsid, fix $Id$. Now include "npx.h" and use NNPX for controlling the floating point code. Replace several 0xFE00000 constants with KERNBASE
1993-10-15 10:34:29 +00:00
* from: @(#)trap.c 7.4 (Berkeley) 5/13/91
Initial import, 0.1 + pk 0.2.4-B1
1993-06-12 14:58:17 +00:00
*/
Use __FBSDID().
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
When ktracing context switches, make sure we record involuntary switches. Otherwise, when we get a evicted from the cpu, there is no record of it. This is not a default ktrace flag.
2003-07-31 01:36:24 +00:00
#include "opt_ktrace.h"
Add a new MAC entry point, mac_thread_userret(td), which permits policy modules to perform MAC-related events when a thread returns to user space. This is required for policies that have floating process labels, as it's not always possible to acquire the process lock at arbitrary points in the stack during system call processing; process labels might represent traditional authentication data, process history information, or other data. LOMAC will use this entry point to perform the process label update prior to the thread returning to userspace, when plugged into the MAC framework. Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2002-10-02 02:42:38 +00:00
#include "opt_mac.h"
Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.
2001-06-29 19:51:37 +00:00
#ifdef __i386__
Use #ifdef DEV_NPX from opt_npx.h instead of #if NNPX > 0 from npx.h
2001-01-19 13:19:02 +00:00
#include "opt_npx.h"
Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.
2001-06-29 19:51:37 +00:00
#endif
Converted two options over to the new scheme: USER_LDT and KTRACE.
1996-01-03 21:42:35 +00:00
The big 4.4BSD Lite to FreeBSD 2.0.0 (Development) patch. Reviewed by: Rodney W. Grimes Submitted by: John Dyson and David Greenman
1994-05-25 09:21:21 +00:00
#include <sys/param.h>
Major update to the way synchronization is done in the kernel. Highlights include: * Mutual exclusion is used instead of spl*(). See mutex(9). (Note: The alpha port is still in transition and currently uses both.) * Per-CPU idle processes. * Interrupts are run in their own separate kernel threads and can be preempted (i386 only). Partially contributed by: BSDi (BSD/OS) Submissions by (at least): cp, dfr, dillon, grog, jake, jhb, sheldonh
2000-09-07 01:33:02 +00:00
#include <sys/bus.h>
The big 4.4BSD Lite to FreeBSD 2.0.0 (Development) patch. Reviewed by: Rodney W. Grimes Submitted by: John Dyson and David Greenman
1994-05-25 09:21:21 +00:00
#include <sys/kernel.h>
Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.
2001-06-29 19:51:37 +00:00
#include <sys/lock.h>
Add a new MAC entry point, mac_thread_userret(td), which permits policy modules to perform MAC-related events when a thread returns to user space. This is required for policies that have floating process labels, as it's not always possible to acquire the process lock at arbitrary points in the stack during system call processing; process labels might represent traditional authentication data, process history information, or other data. LOMAC will use this entry point to perform the process label update prior to the thread returning to userspace, when plugged into the MAC framework. Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2002-10-02 02:42:38 +00:00
#include <sys/mac.h>
Catch up to moving headers: - machine/ipl.h -> sys/ipl.h - machine/mutex.h -> sys/mutex.h
2000-10-20 07:58:15 +00:00
#include <sys/mutex.h>
Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.
2001-06-29 19:51:37 +00:00
#include <sys/proc.h>
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
#include <sys/ktr.h>
Fixed some #include messes. Hid the check of the user %cs in syscall() under `#ifdef DIAGNOSTIC'.
1997-11-24 13:25:37 +00:00
#include <sys/resourcevar.h>
- Create a new scheduler api that is defined in sys/sched.h - Begin moving scheduler specific functionality into sched_4bsd.c - Replace direct manipulation of scheduler data with hooks provided by the new api. - Remove KSE specific state modifications and single runq assumptions from kern_switch.c Reviewed by: -arch
2002-10-12 05:32:24 +00:00
#include <sys/sched.h>
Fixed some #include messes. Hid the check of the user %cs in syscall() under `#ifdef DIAGNOSTIC'.
1997-11-24 13:25:37 +00:00
#include <sys/signalvar.h>
Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.
2001-06-29 19:51:37 +00:00
#include <sys/systm.h>
Untangled the vm.h include file spaghetti.
1995-12-07 12:48:31 +00:00
#include <sys/vmmeter.h>
When ktracing context switches, make sure we record involuntary switches. Otherwise, when we get a evicted from the cpu, there is no record of it. This is not a default ktrace flag.
2003-07-31 01:36:24 +00:00
#ifdef KTRACE
#include <sys/uio.h>
#include <sys/ktrace.h>
#endif
The big 4.4BSD Lite to FreeBSD 2.0.0 (Development) patch. Reviewed by: Rodney W. Grimes Submitted by: John Dyson and David Greenman
1994-05-25 09:21:21 +00:00
#include <machine/cpu.h>
Fixed some #include messes. Hid the check of the user %cs in syscall() under `#ifdef DIAGNOSTIC'.
1997-11-24 13:25:37 +00:00
#include <machine/pcb.h>
- Add code to detect if a system call returns with locks other than Giant held and panic if so (conditional on witness). - Change witness_list to return the number of locks held so this is easier. - Add kern/syscalls.c to the kernel build if witness is defined so that the panic message can contain the name of the offending system call. - Add assertions that Giant and sched_lock are not held when returning from a system call, which were missing for alpha and ia64.
2000-12-12 01:14:32 +00:00
Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.
2001-06-29 19:51:37 +00:00
/*
* Define the code needed before returning to user mode, for
* trap and syscall.
Remove the MPSAFE keyword from the parser for syscalls.master. Instead introduce the [M] prefix to existing keywords. e.g. MSTD is the MP SAFE version of STD. This is prepatory for a massive Giant lock pushdown. The old MPSAFE keyword made syscalls.master too messy. Begin comments MP-Safe procedures with the comment: /* * MPSAFE */ This comments means that the procedure may be called without Giant held (The procedure itself may still need to obtain Giant temporarily to do its thing). sv_prepsyscall() is now MP SAFE and assumed to be MP SAFE sv_transtrap() is now MP SAFE and assumed to be MP SAFE ktrsyscall() and ktrsysret() are now MP SAFE (Giant Pushdown) trapsignal() is now MP SAFE (Giant Pushdown) Places which used to do the if (mtx_owned(&Giant)) mtx_unlock(&Giant) test in syscall[2]() in */*/trap.c now do not. Instead they explicitly unlock Giant if they previously obtained it, and then assert that it is no longer held to catch broken system calls. Rebuild syscall tables.
2001-08-30 18:50:57 +00:00
*
* MPSAFE
Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.
2001-06-29 19:51:37 +00:00
*/
- Kill the have_giant parameter to userret() along with all instances of that name as a variable. Use mtx_owned(&Giant) where appropriate instead. - Proc locking. - P_FOO -> PS_FOO. - Update comments about enable interrupts during trap and why this may be bad if we trap while holding a spin mutex. - Don't bother resetting p to curproc in syscall() in case we are the child returning from fork. The child hasn't returned from fork through syscall in a while. - Remove fork_return() as it has been superseded by the MI version.
2001-01-24 09:53:49 +00:00
void
KSE Milestone 2 Note ALL MODULES MUST BE RECOMPILED make the kernel aware that there are smaller units of scheduling than the process. (but only allow one thread per process at this time). This is functionally equivalent to teh previousl -current except that there is a thread associated with each process. Sorry john! (your next MFC will be a doosie!) Reviewed by: peter@freebsd.org, dillon@freebsd.org X-MFC after: ha ha ha ha
2001-09-12 08:38:13 +00:00
userret(td, frame, oticks)
struct thread *td;
trap.c: Vastly improved trap.c from me. This rewritten version has a variety of features, amoung them: higher performance and much higher code quality. support.s, cpufunc.h: No longer use gs override to enforce range limits - compare directly against VM_MAXUSER_ADDRESS instead. The old way caused problems in preserving the gs selector...and this method is just as fast or faster.
1994-06-06 14:54:41 +00:00
struct trapframe *frame;
- Close races with signals and other AST's being triggered while we are in the process of exiting the kernel. The ast() function now loops as long as the PS_ASTPENDING or PS_NEEDRESCHED flags are set. It returns with preemption disabled so that any further AST's that arrive via an interrupt will be delayed until the low-level MD code returns to user mode. - Use u_int's to store the tick counts for profiling purposes so that we do not need sched_lock just to read p_sticks. This also closes a problem where the call to addupc_task() could screw up the arithmetic due to non-atomic reads of p_sticks. - Axe need_proftick(), aston(), astoff(), astpending(), need_resched(), clear_resched(), and resched_wanted() in favor of direct bit operations on p_sflag. - Fix up locking with sched_lock some. In addupc_intr(), use sched_lock to ensure pr_addr and pr_ticks are updated atomically with setting PS_OWEUPC. In ast() we clear pr_ticks atomically with clearing PS_OWEUPC. We also do not grab the lock just to test a flag. - Simplify the handling of Giant in ast() slightly. Reviewed by: bde (mostly)
2001-08-10 22:53:32 +00:00
u_int oticks;
trap.c: Vastly improved trap.c from me. This rewritten version has a variety of features, amoung them: higher performance and much higher code quality. support.s, cpufunc.h: No longer use gs override to enforce range limits - compare directly against VM_MAXUSER_ADDRESS instead. The old way caused problems in preserving the gs selector...and this method is just as fast or faster.
1994-06-06 14:54:41 +00:00
{
KSE Milestone 2 Note ALL MODULES MUST BE RECOMPILED make the kernel aware that there are smaller units of scheduling than the process. (but only allow one thread per process at this time). This is functionally equivalent to teh previousl -current except that there is a thread associated with each process. Sorry john! (your next MFC will be a doosie!) Reviewed by: peter@freebsd.org, dillon@freebsd.org X-MFC after: ha ha ha ha
2001-09-12 08:38:13 +00:00
struct proc *p = td->td_proc;
trap.c: Vastly improved trap.c from me. This rewritten version has a variety of features, amoung them: higher performance and much higher code quality. support.s, cpufunc.h: No longer use gs override to enforce range limits - compare directly against VM_MAXUSER_ADDRESS instead. The old way caused problems in preserving the gs selector...and this method is just as fast or faster.
1994-06-06 14:54:41 +00:00
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
CTR3(KTR_SYSC, "userret: thread %p (pid %d, %s)", td, p->p_pid,
p->p_comm);
Put "failed to set signal flags properly for ast()" check under DIAGNOSTIC instead of INVARIANTS. INVARIANTS is intended for tests that don't substantially change code flow or behavior (passive), but this test required locking both the proc lock and scheduler lock in order to execute. It also appears to be a very advisory diagnostic as opposed to an invariant violation. Following discussion with: bde
2004-03-05 17:35:28 +00:00
#ifdef DIAGNOSTIC
Reversion of commit by Davidxu plus fixes since applied. I'm not convinced there is anything major wrong with the patch but them's the rules.. I am using my "David's mentor" hat to revert this as he's offline for a while.
2003-02-01 12:17:09 +00:00
/* Check that we called signotify() enough. */
- Grab the proc lock around CURSIG and postsig(). Don't release the proc lock until after grabbing the sched_lock to avoid CURSIG racing with psignal. - Don't grab Giant for addupc_task() as it isn't needed. Reported by: tegge (signal race), bde (addupc_task a while back)
2001-06-22 23:05:11 +00:00
PROC_LOCK(p);
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
mtx_lock_spin(&sched_lock);
- Move p->p_sigmask to td->td_sigmask. Signal masks will be per thread with a follow on commit to kern_sig.c - signotify() now operates on a thread since unmasked pending signals are stored in the thread. - PS_NEEDSIGCHK moves to TDF_NEEDSIGCHK.
2003-03-31 22:49:17 +00:00
if (SIGPENDING(td) && ((td->td_flags & TDF_NEEDSIGCHK) == 0 ||
Move a bunch of flags from the KSE to the thread. I was in two minds as to where to put them in the first case.. I should have listenned to the other mind. Submitted by: parts by davidxu@ Reviewed by: jeff@ mini@
2003-02-17 09:55:10 +00:00
(td->td_flags & TDF_ASTPENDING) == 0))
Spell proprly properly: failed to set signal flags proprly for ast() failed to set signal flags proprly for ast() failed to set signal flags proprly for ast() failed to set signal flags proprly for ast()
2002-08-22 14:36:03 +00:00
printf("failed to set signal flags properly for ast()\n");
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
mtx_unlock_spin(&sched_lock);
- Close races with signals and other AST's being triggered while we are in the process of exiting the kernel. The ast() function now loops as long as the PS_ASTPENDING or PS_NEEDRESCHED flags are set. It returns with preemption disabled so that any further AST's that arrive via an interrupt will be delayed until the low-level MD code returns to user mode. - Use u_int's to store the tick counts for profiling purposes so that we do not need sched_lock just to read p_sticks. This also closes a problem where the call to addupc_task() could screw up the arithmetic due to non-atomic reads of p_sticks. - Axe need_proftick(), aston(), astoff(), astpending(), need_resched(), clear_resched(), and resched_wanted() in favor of direct bit operations on p_sflag. - Fix up locking with sched_lock some. In addupc_intr(), use sched_lock to ensure pr_addr and pr_ticks are updated atomically with setting PS_OWEUPC. In ast() we clear pr_ticks atomically with clearing PS_OWEUPC. We also do not grab the lock just to test a flag. - Simplify the handling of Giant in ast() slightly. Reviewed by: bde (mostly)
2001-08-10 22:53:32 +00:00
PROC_UNLOCK(p);
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
#endif
Commit major SMP cleanups and move the BGL (big giant lock) in the syscall path inward. A system call may select whether it needs the MP lock or not (the default being that it does need it). A great deal of conditional SMP code for various deadended experiments has been removed. 'cil' and 'cml' have been removed entirely, and the locking around the cpl has been removed. The conditional separately-locked fast-interrupt code has been removed, meaning that interrupts must hold the CPL now (but they pretty much had to anyway). Another reason for doing this is that the original separate-lock for interrupts just doesn't apply to the interrupt thread mechanism being contemplated. Modifications to the cpl may now ONLY occur while holding the MP lock. For example, if an otherwise MP safe syscall needs to mess with the cpl, it must hold the MP lock for the duration and must (as usual) save/restore the cpl in a nested fashion. This is precursor work for the real meat coming later: avoiding having to hold the MP lock for common syscalls and I/O's and interrupt threads. It is expected that the spl mechanisms and new interrupt threading mechanisms will be able to run in tandem, allowing a slow piecemeal transition to occur. This patch should result in a moderate performance improvement due to the considerable amount of code that has been removed from the critical path, especially the simplification of the spl*() calls. The real performance gains will come later. Approved by: jkh Reviewed by: current, bde (exception.s) Some work taken from: luoqi's patch
2000-03-28 07:16:37 +00:00
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
/*
- Create a new scheduler api that is defined in sys/sched.h - Begin moving scheduler specific functionality into sched_4bsd.c - Replace direct manipulation of scheduler data with hooks provided by the new api. - Remove KSE specific state modifications and single runq assumptions from kern_switch.c Reviewed by: -arch
2002-10-12 05:32:24 +00:00
* Let the scheduler adjust our priority etc.
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
*/
- Create a new scheduler api that is defined in sys/sched.h - Begin moving scheduler specific functionality into sched_4bsd.c - Replace direct manipulation of scheduler data with hooks provided by the new api. - Remove KSE specific state modifications and single runq assumptions from kern_switch.c Reviewed by: -arch
2002-10-12 05:32:24 +00:00
sched_userret(td);
- Kill the have_giant parameter to userret() along with all instances of that name as a variable. Use mtx_owned(&Giant) where appropriate instead. - Proc locking. - P_FOO -> PS_FOO. - Update comments about enable interrupts during trap and why this may be bad if we trap while holding a spin mutex. - Don't bother resetting p to curproc in syscall() in case we are the child returning from fork. The child hasn't returned from fork through syscall in a while. - Remove fork_return() as it has been superseded by the MI version.
2001-01-24 09:53:49 +00:00
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
/*
iBack out david's last commit. the suspension code needs to be called for non KSE processes too.
2002-10-26 04:44:17 +00:00
* We need to check to see if we have to exit or wait due to a
* single threading requirement or some other STOP condition.
* Don't bother doing all the work if the stop bits are not set
* at this time.. If we miss it, we miss it.. no big deal.
*/
if (P_SHOULDSTOP(p)) {
PROC_LOCK(p);
thread_suspend_check(0); /* Can suspend or kill */
PROC_UNLOCK(p);
}
/*
* Do special thread processing, e.g. upcall tweaking and such.
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
*/
Push Giant down a little further: - no longer serialize on Giant for thread_single*() and family in fork, exit and exec - thread_wait() is mpsafe, assert no Giant - reduce scope of Giant in exit to not cover thread_wait and just do vm_waitproc(). - assert that thread_single() family are not called with Giant - remove the DROP/PICKUP_GIANT macros from thread_single() family - assert that thread_suspend_check() s not called with Giant - remove manual drop_giant hack in thread_suspend_check since we know it isn't held. - remove the DROP/PICKUP_GIANT macros from thread_suspend_check() family - mark kse_create() mpsafe
2004-03-13 22:31:39 +00:00
if (p->p_flag & P_SA)
slightly clean up the thread_userret() and thread_consider_upcall() calls. also some slight changes for TDF_BOUND testing and small style changes Should ONLY affect KSE programs Submitted by: davidxu
2002-09-23 06:14:30 +00:00
thread_userret(td, frame);
Reversion of commit by Davidxu plus fixes since applied. I'm not convinced there is anything major wrong with the patch but them's the rules.. I am using my "David's mentor" hat to revert this as he's offline for a while.
2003-02-01 12:17:09 +00:00
/*
* Charge system time if profiling.
*/
- Move PS_PROFIL and its new cousin PS_STOPPROF back over to p_flag and rename them appropriately. Protect both flags with both the proc lock and the sched_lock. - Protect p_profthreads with the proc lock. - Remove Giant from profil(2).
2003-04-22 20:54:04 +00:00
if (p->p_flag & P_PROFIL) {
Reversion of commit by Davidxu plus fixes since applied. I'm not convinced there is anything major wrong with the patch but them's the rules.. I am using my "David's mentor" hat to revert this as he's offline for a while.
2003-02-01 12:17:09 +00:00
quad_t ticks;
mtx_lock_spin(&sched_lock);
- Move ke_sticks, ke_iticks, ke_uticks, ke_uu, ke_su, and ke_iu back into the proc. These counters are only examined through calcru. Submitted by: davidxu Tested on: x86, alpha, UP/SMP
2003-02-17 02:19:58 +00:00
ticks = td->td_sticks - oticks;
Reversion of commit by Davidxu plus fixes since applied. I'm not convinced there is anything major wrong with the patch but them's the rules.. I am using my "David's mentor" hat to revert this as he's offline for a while.
2003-02-01 12:17:09 +00:00
mtx_unlock_spin(&sched_lock);
Move a bunch of flags from the KSE to the thread. I was in two minds as to where to put them in the first case.. I should have listenned to the other mind. Submitted by: parts by davidxu@ Reviewed by: jeff@ mini@
2003-02-17 09:55:10 +00:00
addupc_task(td, TRAPF_PC(frame), (u_int)ticks * psratio);
Reversion of commit by Davidxu plus fixes since applied. I'm not convinced there is anything major wrong with the patch but them's the rules.. I am using my "David's mentor" hat to revert this as he's offline for a while.
2003-02-01 12:17:09 +00:00
}
trap.c: Vastly improved trap.c from me. This rewritten version has a variety of features, amoung them: higher performance and much higher code quality. support.s, cpufunc.h: No longer use gs override to enforce range limits - compare directly against VM_MAXUSER_ADDRESS instead. The old way caused problems in preserving the gs selector...and this method is just as fast or faster.
1994-06-06 14:54:41 +00:00
}
Initial import, 0.1 + pk 0.2.4-B1
1993-06-12 14:58:17 +00:00
/*
Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.
2001-06-29 19:51:37 +00:00
* Process an asynchronous software trap.
* This is relatively easy.
- Close races with signals and other AST's being triggered while we are in the process of exiting the kernel. The ast() function now loops as long as the PS_ASTPENDING or PS_NEEDRESCHED flags are set. It returns with preemption disabled so that any further AST's that arrive via an interrupt will be delayed until the low-level MD code returns to user mode. - Use u_int's to store the tick counts for profiling purposes so that we do not need sched_lock just to read p_sticks. This also closes a problem where the call to addupc_task() could screw up the arithmetic due to non-atomic reads of p_sticks. - Axe need_proftick(), aston(), astoff(), astpending(), need_resched(), clear_resched(), and resched_wanted() in favor of direct bit operations on p_sflag. - Fix up locking with sched_lock some. In addupc_intr(), use sched_lock to ensure pr_addr and pr_ticks are updated atomically with setting PS_OWEUPC. In ast() we clear pr_ticks atomically with clearing PS_OWEUPC. We also do not grab the lock just to test a flag. - Simplify the handling of Giant in ast() slightly. Reviewed by: bde (mostly)
2001-08-10 22:53:32 +00:00
* This function will return with preemption disabled.
Initial import, 0.1 + pk 0.2.4-B1
1993-06-12 14:58:17 +00:00
*/
Major update to the way synchronization is done in the kernel. Highlights include: * Mutual exclusion is used instead of spl*(). See mutex(9). (Note: The alpha port is still in transition and currently uses both.) * Per-CPU idle processes. * Interrupts are run in their own separate kernel threads and can be preempted (i386 only). Partially contributed by: BSDi (BSD/OS) Submissions by (at least): cp, dfr, dillon, grog, jake, jhb, sheldonh
2000-09-07 01:33:02 +00:00
void
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
ast(struct trapframe *framep)
Major update to the way synchronization is done in the kernel. Highlights include: * Mutual exclusion is used instead of spl*(). See mutex(9). (Note: The alpha port is still in transition and currently uses both.) * Per-CPU idle processes. * Interrupts are run in their own separate kernel threads and can be preempted (i386 only). Partially contributed by: BSDi (BSD/OS) Submissions by (at least): cp, dfr, dillon, grog, jake, jhb, sheldonh
2000-09-07 01:33:02 +00:00
{
Various style fixups. Submitted by: bde (mostly)
2002-10-01 14:16:50 +00:00
struct thread *td;
struct proc *p;
struct ksegrp *kg;
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
struct rlimit rlim;
Tidy up uprof locking. Mostly the fields are protected by both the proc lock and sched_lock so they can be read with either lock held. Document the locking as well. The one remaining bogosity is that pr_addr and pr_ticks should be per-thread but profiling of multithreaded apps is currently undefined.
2004-07-02 03:50:48 +00:00
u_int sticks;
- Close races with signals and other AST's being triggered while we are in the process of exiting the kernel. The ast() function now loops as long as the PS_ASTPENDING or PS_NEEDRESCHED flags are set. It returns with preemption disabled so that any further AST's that arrive via an interrupt will be delayed until the low-level MD code returns to user mode. - Use u_int's to store the tick counts for profiling purposes so that we do not need sched_lock just to read p_sticks. This also closes a problem where the call to addupc_task() could screw up the arithmetic due to non-atomic reads of p_sticks. - Axe need_proftick(), aston(), astoff(), astpending(), need_resched(), clear_resched(), and resched_wanted() in favor of direct bit operations on p_sflag. - Fix up locking with sched_lock some. In addupc_intr(), use sched_lock to ensure pr_addr and pr_ticks are updated atomically with setting PS_OWEUPC. In ast() we clear pr_ticks atomically with clearing PS_OWEUPC. We also do not grab the lock just to test a flag. - Simplify the handling of Giant in ast() slightly. Reviewed by: bde (mostly)
2001-08-10 22:53:32 +00:00
int sflag;
KSE Milestone 2 Note ALL MODULES MUST BE RECOMPILED make the kernel aware that there are smaller units of scheduling than the process. (but only allow one thread per process at this time). This is functionally equivalent to teh previousl -current except that there is a thread associated with each process. Sorry john! (your next MFC will be a doosie!) Reviewed by: peter@freebsd.org, dillon@freebsd.org X-MFC after: ha ha ha ha
2001-09-12 08:38:13 +00:00
int flags;
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
int sig;
Convert npx interrupts into traps instead of vice versa. This is much simpler for npx exceptions that start as traps (no assembly required...) and works better for npx exceptions that start as interrupts (there is no longer a problem for nested interrupts). Submitted by: original (pre-SMPng) version by luoqi
2001-05-22 21:20:49 +00:00
#if defined(DEV_NPX) && !defined(SMP)
int ucode;
#endif
Major update to the way synchronization is done in the kernel. Highlights include: * Mutual exclusion is used instead of spl*(). See mutex(9). (Note: The alpha port is still in transition and currently uses both.) * Per-CPU idle processes. * Interrupts are run in their own separate kernel threads and can be preempted (i386 only). Partially contributed by: BSDi (BSD/OS) Submissions by (at least): cp, dfr, dillon, grog, jake, jhb, sheldonh
2000-09-07 01:33:02 +00:00
Various style fixups. Submitted by: bde (mostly)
2002-10-01 14:16:50 +00:00
td = curthread;
p = td->td_proc;
De-obfuscate local use of members of 'struct thread', for which we have local variables, and group assignment.
2002-10-02 16:39:39 +00:00
kg = td->td_ksegrp;
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
CTR3(KTR_SYSC, "ast: thread %p (pid %d, %s)", td, p->p_pid,
p->p_comm);
- Change ast() to take a pointer to a trapframe like other architectures. - Don't use an atomic operation to update cnt.v_soft in ast(). This is the only place the variable is written to, and sched_lock is always held when it is written, so it is already protected and the mutex release of sched_lock asserts a memory barrier that ensures the value will be updated in a timely fashion.
2001-02-22 18:05:15 +00:00
KASSERT(TRAPF_USERMODE(framep), ("ast in kernel mode"));
Replace calls to WITNESS_SLEEP() and witness_list() with equivalent calls to WITNESS_WARN().
2003-03-04 21:03:05 +00:00
WITNESS_WARN(WARN_PANIC, NULL, "Returning to user mode");
- Close races with signals and other AST's being triggered while we are in the process of exiting the kernel. The ast() function now loops as long as the PS_ASTPENDING or PS_NEEDRESCHED flags are set. It returns with preemption disabled so that any further AST's that arrive via an interrupt will be delayed until the low-level MD code returns to user mode. - Use u_int's to store the tick counts for profiling purposes so that we do not need sched_lock just to read p_sticks. This also closes a problem where the call to addupc_task() could screw up the arithmetic due to non-atomic reads of p_sticks. - Axe need_proftick(), aston(), astoff(), astpending(), need_resched(), clear_resched(), and resched_wanted() in favor of direct bit operations on p_sflag. - Fix up locking with sched_lock some. In addupc_intr(), use sched_lock to ensure pr_addr and pr_ticks are updated atomically with setting PS_OWEUPC. In ast() we clear pr_ticks atomically with clearing PS_OWEUPC. We also do not grab the lock just to test a flag. - Simplify the handling of Giant in ast() slightly. Reviewed by: bde (mostly)
2001-08-10 22:53:32 +00:00
mtx_assert(&Giant, MA_NOTOWNED);
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
mtx_assert(&sched_lock, MA_NOTOWNED);
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
td->td_frame = framep;
Various style fixups. Submitted by: bde (mostly)
2002-10-01 14:16:50 +00:00
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
/*
* This updates the p_sflag's for the checks below in one
* "atomic" operation with turning off the astpending flag.
* If another AST is triggered while we are handling the
* AST's saved in sflag, the astpending flag will be set and
* ast() will be called again.
*/
mtx_lock_spin(&sched_lock);
- Move ke_sticks, ke_iticks, ke_uticks, ke_uu, ke_su, and ke_iu back into the proc. These counters are only examined through calcru. Submitted by: davidxu Tested on: x86, alpha, UP/SMP
2003-02-17 02:19:58 +00:00
sticks = td->td_sticks;
Move a bunch of flags from the KSE to the thread. I was in two minds as to where to put them in the first case.. I should have listenned to the other mind. Submitted by: parts by davidxu@ Reviewed by: jeff@ mini@
2003-02-17 09:55:10 +00:00
flags = td->td_flags;
Various style fixups. Submitted by: bde (mostly)
2002-10-01 14:16:50 +00:00
sflag = p->p_sflag;
- Move p->p_sigmask to td->td_sigmask. Signal masks will be per thread with a follow on commit to kern_sig.c - signotify() now operates on a thread since unmasked pending signals are stored in the thread. - PS_NEEDSIGCHK moves to TDF_NEEDSIGCHK.
2003-03-31 22:49:17 +00:00
p->p_sflag &= ~(PS_ALRMPEND | PS_PROFPEND | PS_XCPU);
To reduce per-return overhead of userret(), call into mac_thread_userret() only if PS_MACPEND is set in the process AST mask. This avoids the cost of the entry point in the common case, but requires policies interested in the userret event to set the flag (protected by the scheduler lock) if they do want the event. Since all the policies that we're working with which use mac_thread_userret() use the entry point only selectively to perform operations deferred for locking reasons, this maintains the desired semantics. Approved by: re Requested by: bde Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2002-11-08 19:00:17 +00:00
#ifdef MAC
p->p_sflag &= ~PS_MACPEND;
#endif
- Move p->p_sigmask to td->td_sigmask. Signal masks will be per thread with a follow on commit to kern_sig.c - signotify() now operates on a thread since unmasked pending signals are stored in the thread. - PS_NEEDSIGCHK moves to TDF_NEEDSIGCHK.
2003-03-31 22:49:17 +00:00
td->td_flags &= ~(TDF_ASTPENDING | TDF_NEEDSIGCHK |
- Move TDF_OWEPREEMPT, TDF_OWEUPC, and TDF_USTATCLOCK over to td_pflags since they are only accessed by curthread and thus do not need any locking. - Move pr_addr and pr_ticks out of struct uprof (which is per-process) and directly into struct thread as td_profil_addr and td_profil_ticks as these variables are really per-thread. (They are used to defer an addupc_intr() that was too "hard" until ast()).
2004-07-16 21:04:55 +00:00
TDF_NEEDRESCHED | TDF_INTERRUPT);
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
cnt.v_soft++;
mtx_unlock_spin(&sched_lock);
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
/*
* XXXKSE While the fact that we owe a user profiling
* tick is stored per KSE in this code, the statistics
* themselves are still stored per process.
* This should probably change, by which I mean that
* possibly the location of both might change.
*/
Add some DIAGNOSTIC code. While in userland, keep the thread's ucred reference in a shadow field so that the usual place to store it is NULL. If DIAGNOSTIC is not set, the thread ucred is kept valid until the next kernel entry, at which time it is checked against the process cred and possibly corrected. Produces a BIG speedup in kernels with INVARIANTS set. (A previous commit corrected it for the non INVARIANTS case already) Reviewed by: dillon@freebsd.org
2002-02-22 23:58:22 +00:00
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
if (td->td_ucred != p->p_ucred)
cred_update_thread(td);
- Move TDF_OWEPREEMPT, TDF_OWEUPC, and TDF_USTATCLOCK over to td_pflags since they are only accessed by curthread and thus do not need any locking. - Move pr_addr and pr_ticks out of struct uprof (which is per-process) and directly into struct thread as td_profil_addr and td_profil_ticks as these variables are really per-thread. (They are used to defer an addupc_intr() that was too "hard" until ast()).
2004-07-16 21:04:55 +00:00
if (td->td_pflags & TDP_OWEUPC && p->p_flag & P_PROFIL) {
addupc_task(td, td->td_profil_addr, td->td_profil_ticks);
td->td_profil_ticks = 0;
td->td_pflags &= ~TDP_OWEUPC;
Tidy up uprof locking. Mostly the fields are protected by both the proc lock and sched_lock so they can be read with either lock held. Document the locking as well. The one remaining bogosity is that pr_addr and pr_ticks should be per-thread but profiling of multithreaded apps is currently undefined.
2004-07-02 03:50:48 +00:00
}
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
if (sflag & PS_ALRMPEND) {
PROC_LOCK(p);
psignal(p, SIGVTALRM);
PROC_UNLOCK(p);
}
Convert npx interrupts into traps instead of vice versa. This is much simpler for npx exceptions that start as traps (no assembly required...) and works better for npx exceptions that start as interrupts (there is no longer a problem for nested interrupts). Submitted by: original (pre-SMPng) version by luoqi
2001-05-22 21:20:49 +00:00
#if defined(DEV_NPX) && !defined(SMP)
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
if (PCPU_GET(curpcb)->pcb_flags & PCB_NPXTRAP) {
atomic_clear_int(&PCPU_GET(curpcb)->pcb_flags,
PCB_NPXTRAP);
ucode = npxtrap();
if (ucode != -1) {
- Change trapsignal() to accept a thread and not a proc. - Change all consumers to pass in a thread. Right now this does not cause any functional changes but it will be important later when signals can be delivered to specific threads.
2003-03-31 22:02:38 +00:00
trapsignal(td, SIGFPE, ucode);
Convert npx interrupts into traps instead of vice versa. This is much simpler for npx exceptions that start as traps (no assembly required...) and works better for npx exceptions that start as interrupts (there is no longer a problem for nested interrupts). Submitted by: original (pre-SMPng) version by luoqi
2001-05-22 21:20:49 +00:00
}
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
}
Convert npx interrupts into traps instead of vice versa. This is much simpler for npx exceptions that start as traps (no assembly required...) and works better for npx exceptions that start as interrupts (there is no longer a problem for nested interrupts). Submitted by: original (pre-SMPng) version by luoqi
2001-05-22 21:20:49 +00:00
#endif
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
if (sflag & PS_PROFPEND) {
PROC_LOCK(p);
psignal(p, SIGPROF);
PROC_UNLOCK(p);
}
- Add a new per-process flag PS_XCPU to indicate that at least one thread has exceeded its CPU time limit. - In mi_switch(), set PS_XCPU when the CPU time limit is exceeded. - Perform actual CPU time limit exceeded work in ast() when PS_XCPU is set. Requested by: many
2002-09-30 21:13:54 +00:00
if (sflag & PS_XCPU) {
PROC_LOCK(p);
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
lim_rlimit(p, RLIMIT_CPU, &rlim);
Tweak locking in the PS_XCPU handler to hold the sched_lock while reading p_runtime.
2003-04-17 22:33:04 +00:00
mtx_lock_spin(&sched_lock);
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
if (p->p_runtime.sec >= rlim.rlim_max) {
Tweak locking in the PS_XCPU handler to hold the sched_lock while reading p_runtime.
2003-04-17 22:33:04 +00:00
mtx_unlock_spin(&sched_lock);
- Add a new per-process flag PS_XCPU to indicate that at least one thread has exceeded its CPU time limit. - In mi_switch(), set PS_XCPU when the CPU time limit is exceeded. - Perform actual CPU time limit exceeded work in ast() when PS_XCPU is set. Requested by: many
2002-09-30 21:13:54 +00:00
killproc(p, "exceeded maximum CPU limit");
Tweak locking in the PS_XCPU handler to hold the sched_lock while reading p_runtime.
2003-04-17 22:33:04 +00:00
} else {
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
if (p->p_cpulimit < rlim.rlim_max)
- Move p_cpulimit to struct proc from struct plimit and protect it with sched_lock. This means that we no longer access p_limit in mi_switch() and the p_limit pointer can be protected by the proc lock. - Remove PRS_ZOMBIE check from CPU limit test in mi_switch(). PRS_ZOMBIE processes don't call mi_switch(), and even if they did there is no longer the danger of p_limit being NULL (which is what the original zombie check was added for). - When we bump the current processes soft CPU limit in ast(), just bump the private p_cpulimit instead of the shared rlimit. This fixes an XXX for some value of fix. There is still a (probably benign) bug in that this code doesn't check that the new soft limit exceeds the hard limit. Inspired by: bde (2)
2002-10-09 17:17:24 +00:00
p->p_cpulimit += 5;
mtx_unlock_spin(&sched_lock);
Tweak locking in the PS_XCPU handler to hold the sched_lock while reading p_runtime.
2003-04-17 22:33:04 +00:00
psignal(p, SIGXCPU);
- Add a new per-process flag PS_XCPU to indicate that at least one thread has exceeded its CPU time limit. - In mi_switch(), set PS_XCPU when the CPU time limit is exceeded. - Perform actual CPU time limit exceeded work in ast() when PS_XCPU is set. Requested by: many
2002-09-30 21:13:54 +00:00
}
PROC_UNLOCK(p);
}
To reduce per-return overhead of userret(), call into mac_thread_userret() only if PS_MACPEND is set in the process AST mask. This avoids the cost of the entry point in the common case, but requires policies interested in the userret event to set the flag (protected by the scheduler lock) if they do want the event. Since all the policies that we're working with which use mac_thread_userret() use the entry point only selectively to perform operations deferred for locking reasons, this maintains the desired semantics. Approved by: re Requested by: bde Obtained from: TrustedBSD Project Sponsored by: DARPA, Network Associates Laboratories
2002-11-08 19:00:17 +00:00
#ifdef MAC
if (sflag & PS_MACPEND)
mac_thread_userret(td);
#endif
Move a bunch of flags from the KSE to the thread. I was in two minds as to where to put them in the first case.. I should have listenned to the other mind. Submitted by: parts by davidxu@ Reviewed by: jeff@ mini@
2003-02-17 09:55:10 +00:00
if (flags & TDF_NEEDRESCHED) {
When ktracing context switches, make sure we record involuntary switches. Otherwise, when we get a evicted from the cpu, there is no record of it. This is not a default ktrace flag.
2003-07-31 01:36:24 +00:00
#ifdef KTRACE
if (KTRPOINT(td, KTR_CSW))
Log involuntary context switches correctly.
2003-09-05 22:15:26 +00:00
ktrcsw(1, 1);
When ktracing context switches, make sure we record involuntary switches. Otherwise, when we get a evicted from the cpu, there is no record of it. This is not a default ktrace flag.
2003-07-31 01:36:24 +00:00
#endif
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
mtx_lock_spin(&sched_lock);
- Create a new scheduler api that is defined in sys/sched.h - Begin moving scheduler specific functionality into sched_4bsd.c - Replace direct manipulation of scheduler data with hooks provided by the new api. - Remove KSE specific state modifications and single runq assumptions from kern_switch.c Reviewed by: -arch
2002-10-12 05:32:24 +00:00
sched_prio(td, kg->kg_user_pri);
- Change mi_switch() and sched_switch() to accept an optional thread to switch to. If a non-NULL thread pointer is passed in, then the CPU will switch to that thread directly rather than calling choosethread() to pick a thread to choose to. - Make sched_switch() aware of idle threads and know to do TD_SET_CAN_RUN() instead of sticking them on the run queue rather than requiring all callers of mi_switch() to know to do this if they can be called from an idlethread. - Move constants for arguments to mi_switch() and thread_single() out of the middle of the function prototypes and up above into their own section.
2004-07-02 19:09:50 +00:00
mi_switch(SW_INVOL, NULL);
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
mtx_unlock_spin(&sched_lock);
When ktracing context switches, make sure we record involuntary switches. Otherwise, when we get a evicted from the cpu, there is no record of it. This is not a default ktrace flag.
2003-07-31 01:36:24 +00:00
#ifdef KTRACE
if (KTRPOINT(td, KTR_CSW))
Log involuntary context switches correctly.
2003-09-05 22:15:26 +00:00
ktrcsw(0, 1);
When ktracing context switches, make sure we record involuntary switches. Otherwise, when we get a evicted from the cpu, there is no record of it. This is not a default ktrace flag.
2003-07-31 01:36:24 +00:00
#endif
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
}
- Move p->p_sigmask to td->td_sigmask. Signal masks will be per thread with a follow on commit to kern_sig.c - signotify() now operates on a thread since unmasked pending signals are stored in the thread. - PS_NEEDSIGCHK moves to TDF_NEEDSIGCHK.
2003-03-31 22:49:17 +00:00
if (flags & TDF_NEEDSIGCHK) {
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
PROC_LOCK(p);
- Merge struct procsig with struct sigacts. - Move struct sigacts out of the u-area and malloc() it using the M_SUBPROC malloc bucket. - Add a small sigacts_*() API for managing sigacts structures: sigacts_alloc(), sigacts_free(), sigacts_copy(), sigacts_share(), and sigacts_shared(). - Remove the p_sigignore, p_sigacts, and p_sigcatch macros. - Add a mutex to struct sigacts that protects all the members of the struct. - Add sigacts locking. - Remove Giant from nosys(), kill(), killpg(), and kern_sigaction() now that sigacts is locked. - Several in-kernel functions such as psignal(), tdsignal(), trapsignal(), and thread_stopped() are now MP safe. Reviewed by: arch@ Approved by: re (rwatson)
2003-05-13 20:36:02 +00:00
mtx_lock(&p->p_sigacts->ps_mtx);
o Change kse_thr_interrupt to allow send a signal to a specified thread, or unblock a thread in kernel, and allow UTS to specify whether syscall should be restarted. o Add ability for UTS to monitor signal comes in and removed from process, the flag PS_SIGEVENT is used to indicate the events. o Add a KMF_WAITSIGEVENT for KSE mailbox flag, UTS call kse_release with this flag set to wait for above signal event. o For SA based thread, kernel masks all signal in its signal mask, let UTS to use kse_thr_interrupt interrupt a thread, and install a signal frame in userland for the thread. o Add a tm_syncsig in thread mailbox, when a hardware trap occurs, it is used to deliver synchronous signal to userland, and upcall is schedule, so UTS can process the synchronous signal for the thread. Reviewed by: julian (mentor)
2003-06-28 08:29:05 +00:00
while ((sig = cursig(td)) != 0)
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
postsig(sig);
- Merge struct procsig with struct sigacts. - Move struct sigacts out of the u-area and malloc() it using the M_SUBPROC malloc bucket. - Add a small sigacts_*() API for managing sigacts structures: sigacts_alloc(), sigacts_free(), sigacts_copy(), sigacts_share(), and sigacts_shared(). - Remove the p_sigignore, p_sigacts, and p_sigcatch macros. - Add a mutex to struct sigacts that protects all the members of the struct. - Add sigacts locking. - Remove Giant from nosys(), kill(), killpg(), and kern_sigaction() now that sigacts is locked. - Several in-kernel functions such as psignal(), tdsignal(), trapsignal(), and thread_stopped() are now MP safe. Reviewed by: arch@ Approved by: re (rwatson)
2003-05-13 20:36:02 +00:00
mtx_unlock(&p->p_sigacts->ps_mtx);
Moved signal handling and rescheduling from userret() to ast() so that they aren't in the usual path of execution for syscalls and traps. The main complication for this is that we have to set flags to control ast() everywhere that changes the signal mask. Avoid locking in userret() in most of the remaining cases. Submitted by: luoqi (first part only, long ago, reorganized by me) Reminded by: dillon
2002-04-04 17:49:48 +00:00
PROC_UNLOCK(p);
}
The biggie: Get rid of the UPAGES from the top of the per-process address space. (!) Have each process use the kernel stack and pcb in the kvm space. Since the stacks are at a different address, we cannot copy the stack at fork() and allow the child to return up through the function call tree to return to user mode - create a new execution context and have the new process begin executing from cpu_switch() and go to user mode directly. In theory this should speed up fork a bit. Context switch the tss_esp0 pointer in the common tss. This is a lot simpler since than swithching the gdt[GPROC0_SEL].sd.sd_base pointer to each process's tss since the esp0 pointer is a 32 bit pointer, and the sd_base setting is split into three different bit sections at non-aligned boundaries and requires a lot of twiddling to reset. The 8K of memory at the top of the process space is now empty, and unmapped (and unmappable, it's higher than VM_MAXUSER_ADDRESS). Simplity the pmap code to manage process contexts, we no longer have to double map the UPAGES, this simplifies and should measuably speed up fork(). The following parts came from John Dyson: Set PG_G on the UPAGES that are now in kernel context, and invalidate them when swapping them out. Move the upages object (upobj) from the vmspace to the proc structure. Now that the UPAGES (pcb and kernel stack) are out of user space, make rfork(..RFMEM..) do what was intended by sharing the vmspace entirely via reference counting rather than simply inheriting the mappings.
1997-04-07 07:16:06 +00:00
Style fixes purposefully left out of last commit. I checked the kse tree and didn't see any changes that this conflicts with.
2002-03-29 16:45:03 +00:00
userret(td, framep, sticks);
Revert removal of cred_free_thread(): It is used to ensure that a thread's credentials are not improperly borrowed when the thread is not current in the kernel. Requested by: jhb, alfred
2002-07-11 02:18:33 +00:00
#ifdef DIAGNOSTIC
cred_free_thread(td);
#endif
- Close races with signals and other AST's being triggered while we are in the process of exiting the kernel. The ast() function now loops as long as the PS_ASTPENDING or PS_NEEDRESCHED flags are set. It returns with preemption disabled so that any further AST's that arrive via an interrupt will be delayed until the low-level MD code returns to user mode. - Use u_int's to store the tick counts for profiling purposes so that we do not need sched_lock just to read p_sticks. This also closes a problem where the call to addupc_task() could screw up the arithmetic due to non-atomic reads of p_sticks. - Axe need_proftick(), aston(), astoff(), astpending(), need_resched(), clear_resched(), and resched_wanted() in favor of direct bit operations on p_sflag. - Fix up locking with sched_lock some. In addupc_intr(), use sched_lock to ensure pr_addr and pr_ticks are updated atomically with setting PS_OWEUPC. In ast() we clear pr_ticks atomically with clearing PS_OWEUPC. We also do not grab the lock just to test a flag. - Simplify the handling of Giant in ast() slightly. Reviewed by: bde (mostly)
2001-08-10 22:53:32 +00:00
mtx_assert(&Giant, MA_NOTOWNED);
The biggie: Get rid of the UPAGES from the top of the per-process address space. (!) Have each process use the kernel stack and pcb in the kvm space. Since the stacks are at a different address, we cannot copy the stack at fork() and allow the child to return up through the function call tree to return to user mode - create a new execution context and have the new process begin executing from cpu_switch() and go to user mode directly. In theory this should speed up fork a bit. Context switch the tss_esp0 pointer in the common tss. This is a lot simpler since than swithching the gdt[GPROC0_SEL].sd.sd_base pointer to each process's tss since the esp0 pointer is a 32 bit pointer, and the sd_base setting is split into three different bit sections at non-aligned boundaries and requires a lot of twiddling to reset. The 8K of memory at the top of the process space is now empty, and unmapped (and unmappable, it's higher than VM_MAXUSER_ADDRESS). Simplity the pmap code to manage process contexts, we no longer have to double map the UPAGES, this simplifies and should measuably speed up fork(). The following parts came from John Dyson: Set PG_G on the UPAGES that are now in kernel context, and invalidate them when swapping them out. Move the upages object (upobj) from the vmspace to the proc structure. Now that the UPAGES (pcb and kernel stack) are out of user space, make rfork(..RFMEM..) do what was intended by sharing the vmspace entirely via reference counting rather than simply inheriting the mappings.
1997-04-07 07:16:06 +00:00
}
Reference in New Issue Copy Permalink