freebsd-skq/sys/kern/subr_trap.c

271 lines
7.3 KiB
C
Raw Normal View History

1993-06-12 14:58:17 +00:00
/*-
* Copyright (C) 1994, David Greenman
* Copyright (c) 1990, 1993
* The Regents of the University of California. All rights reserved.
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
1993-06-12 14:58:17 +00:00
*/
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_ktrace.h"
#include "opt_mac.h"
#ifdef __i386__
#include "opt_npx.h"
#endif
#include <sys/param.h>
#include <sys/bus.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/mac.h>
#include <sys/mutex.h>
#include <sys/proc.h>
#include <sys/ktr.h>
#include <sys/resourcevar.h>
#include <sys/sched.h>
#include <sys/signalvar.h>
#include <sys/systm.h>
#include <sys/vmmeter.h>
#ifdef KTRACE
#include <sys/uio.h>
#include <sys/ktrace.h>
#endif
#include <machine/cpu.h>
#include <machine/pcb.h>
/*
* Define the code needed before returning to user mode, for
* trap and syscall.
*
* MPSAFE
*/
void
userret(td, frame, oticks)
struct thread *td;
struct trapframe *frame;
u_int oticks;
{
struct proc *p = td->td_proc;
CTR3(KTR_SYSC, "userret: thread %p (pid %d, %s)", td, p->p_pid,
p->p_comm);
#ifdef DIAGNOSTIC
/* Check that we called signotify() enough. */
PROC_LOCK(p);
mtx_lock_spin(&sched_lock);
if (SIGPENDING(td) && ((td->td_flags & TDF_NEEDSIGCHK) == 0 ||
(td->td_flags & TDF_ASTPENDING) == 0))
printf("failed to set signal flags properly for ast()\n");
mtx_unlock_spin(&sched_lock);
PROC_UNLOCK(p);
#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
/*
* Let the scheduler adjust our priority etc.
*/
sched_userret(td);
/*
* 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.
*/
if (p->p_flag & P_SA)
thread_userret(td, frame);
/*
* Charge system time if profiling.
*/
if (p->p_flag & P_PROFIL) {
quad_t ticks;
mtx_lock_spin(&sched_lock);
ticks = td->td_sticks - oticks;
mtx_unlock_spin(&sched_lock);
addupc_task(td, TRAPF_PC(frame), (u_int)ticks * psratio);
}
}
1993-06-12 14:58:17 +00:00
/*
* Process an asynchronous software trap.
* This is relatively easy.
* This function will return with preemption disabled.
1993-06-12 14:58:17 +00:00
*/
void
ast(struct trapframe *framep)
{
struct thread *td;
struct proc *p;
struct kse *ke;
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;
u_int prticks, sticks;
int sflag;
int flags;
int sig;
#if defined(DEV_NPX) && !defined(SMP)
int ucode;
#endif
td = curthread;
p = td->td_proc;
kg = td->td_ksegrp;
CTR3(KTR_SYSC, "ast: thread %p (pid %d, %s)", td, p->p_pid,
p->p_comm);
KASSERT(TRAPF_USERMODE(framep), ("ast in kernel mode"));
WITNESS_WARN(WARN_PANIC, NULL, "Returning to user mode");
mtx_assert(&Giant, MA_NOTOWNED);
mtx_assert(&sched_lock, MA_NOTOWNED);
td->td_frame = framep;
/*
* 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);
ke = td->td_kse;
sticks = td->td_sticks;
flags = td->td_flags;
sflag = p->p_sflag;
p->p_sflag &= ~(PS_ALRMPEND | PS_PROFPEND | PS_XCPU);
#ifdef MAC
p->p_sflag &= ~PS_MACPEND;
#endif
td->td_flags &= ~(TDF_ASTPENDING | TDF_NEEDSIGCHK |
TDF_NEEDRESCHED | TDF_OWEUPC | TDF_INTERRUPT);
cnt.v_soft++;
prticks = 0;
if (flags & TDF_OWEUPC && p->p_flag & P_PROFIL) {
prticks = p->p_stats->p_prof.pr_ticks;
p->p_stats->p_prof.pr_ticks = 0;
}
mtx_unlock_spin(&sched_lock);
/*
* 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.
*/
if (td->td_ucred != p->p_ucred)
cred_update_thread(td);
if (flags & TDF_OWEUPC && p->p_flag & P_PROFIL)
addupc_task(td, p->p_stats->p_prof.pr_addr, prticks);
if (sflag & PS_ALRMPEND) {
PROC_LOCK(p);
psignal(p, SIGVTALRM);
PROC_UNLOCK(p);
}
#if defined(DEV_NPX) && !defined(SMP)
if (PCPU_GET(curpcb)->pcb_flags & PCB_NPXTRAP) {
atomic_clear_int(&PCPU_GET(curpcb)->pcb_flags,
PCB_NPXTRAP);
ucode = npxtrap();
if (ucode != -1) {
trapsignal(td, SIGFPE, ucode);
}
}
#endif
if (sflag & PS_PROFPEND) {
PROC_LOCK(p);
psignal(p, SIGPROF);
PROC_UNLOCK(p);
}
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);
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) {
mtx_unlock_spin(&sched_lock);
killproc(p, "exceeded maximum CPU limit");
} 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)
p->p_cpulimit += 5;
mtx_unlock_spin(&sched_lock);
psignal(p, SIGXCPU);
}
PROC_UNLOCK(p);
}
#ifdef MAC
if (sflag & PS_MACPEND)
mac_thread_userret(td);
#endif
if (flags & TDF_NEEDRESCHED) {
#ifdef KTRACE
if (KTRPOINT(td, KTR_CSW))
ktrcsw(1, 1);
#endif
mtx_lock_spin(&sched_lock);
sched_prio(td, kg->kg_user_pri);
mi_switch(SW_INVOL);
mtx_unlock_spin(&sched_lock);
#ifdef KTRACE
if (KTRPOINT(td, KTR_CSW))
ktrcsw(0, 1);
#endif
}
if (flags & TDF_NEEDSIGCHK) {
PROC_LOCK(p);
mtx_lock(&p->p_sigacts->ps_mtx);
while ((sig = cursig(td)) != 0)
postsig(sig);
mtx_unlock(&p->p_sigacts->ps_mtx);
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
userret(td, framep, sticks);
#ifdef DIAGNOSTIC
cred_free_thread(td);
#endif
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
}