freebsd-dev/sys/amd64/ia32/ia32_syscall.c
David Xu 9104847f21 1. Change prototype of trapsignal and sendsig to use ksiginfo_t *, most
changes in MD code are trivial, before this change, trapsignal and
   sendsig use discrete parameters, now they uses member fields of
   ksiginfo_t structure. For sendsig, this change allows us to pass
   POSIX realtime signal value to user code.

2. Remove cpu_thread_siginfo, it is no longer needed because we now always
   generate ksiginfo_t data and feed it to libpthread.

3. Add p_sigqueue to proc structure to hold shared signals which were
   blocked by all threads in the proc.

4. Add td_sigqueue to thread structure to hold all signals delivered to
   thread.

5. i386 and amd64 now return POSIX standard si_code, other arches will
   be fixed.

6. In this sigqueue implementation, pending signal set is kept as before,
   an extra siginfo list holds additional siginfo_t data for signals.
   kernel code uses psignal() still behavior as before, it won't be failed
   even under memory pressure, only exception is when deleting a signal,
   we should call sigqueue_delete to remove signal from sigqueue but
   not SIGDELSET. Current there is no kernel code will deliver a signal
   with additional data, so kernel should be as stable as before,
   a ksiginfo can carry more information, for example, allow signal to
   be delivered but throw away siginfo data if memory is not enough.
   SIGKILL and SIGSTOP have fast path in sigqueue_add, because they can
   not be caught or masked.
   The sigqueue() syscall allows user code to queue a signal to target
   process, if resource is unavailable, EAGAIN will be returned as
   specification said.
   Just before thread exits, signal queue memory will be freed by
   sigqueue_flush.
   Current, all signals are allowed to be queued, not only realtime signals.

Earlier patch reviewed by: jhb, deischen
Tested on: i386, amd64
2005-10-14 12:43:47 +00:00

278 lines
7.0 KiB
C

/*-
* Copyright (C) 1994, David Greenman
* Copyright (c) 1990, 1993
* The Regents of the University of California. All rights reserved.
*
* 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.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
/*
* 386 Trap and System call handling
*/
#include "opt_clock.h"
#include "opt_cpu.h"
#include "opt_isa.h"
#include "opt_ktrace.h"
#include <sys/param.h>
#include <sys/bus.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/pioctl.h>
#include <sys/kernel.h>
#include <sys/ktr.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/syscall.h>
#include <sys/sysctl.h>
#include <sys/sysent.h>
#include <sys/uio.h>
#include <sys/vmmeter.h>
#ifdef KTRACE
#include <sys/ktrace.h>
#endif
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/pmap.h>
#include <vm/vm_kern.h>
#include <vm/vm_map.h>
#include <vm/vm_page.h>
#include <vm/vm_extern.h>
#include <machine/cpu.h>
#include <machine/intr_machdep.h>
#include <machine/md_var.h>
#define IDTVEC(name) __CONCAT(X,name)
extern inthand_t IDTVEC(int0x80_syscall), IDTVEC(rsvd);
extern const char *freebsd32_syscallnames[];
void ia32_syscall(struct trapframe frame); /* Called from asm code */
void
ia32_syscall(struct trapframe frame)
{
caddr_t params;
int i;
struct sysent *callp;
struct thread *td = curthread;
struct proc *p = td->td_proc;
register_t orig_tf_rflags;
u_int sticks;
int error;
int narg;
u_int32_t args[8];
u_int64_t args64[8];
u_int code;
ksiginfo_t ksi;
/*
* note: PCPU_LAZY_INC() can only be used if we can afford
* occassional inaccuracy in the count.
*/
PCPU_LAZY_INC(cnt.v_syscall);
sticks = td->td_sticks;
td->td_frame = &frame;
if (td->td_ucred != p->p_ucred)
cred_update_thread(td);
params = (caddr_t)frame.tf_rsp + sizeof(u_int32_t);
code = frame.tf_rax;
orig_tf_rflags = frame.tf_rflags;
if (p->p_sysent->sv_prepsyscall) {
/*
* The prep code is MP aware.
*/
(*p->p_sysent->sv_prepsyscall)(&frame, args, &code, &params);
} else {
/*
* Need to check if this is a 32 bit or 64 bit syscall.
* fuword is MP aware.
*/
if (code == SYS_syscall) {
/*
* Code is first argument, followed by actual args.
*/
code = fuword32(params);
params += sizeof(int);
} else if (code == SYS___syscall) {
/*
* Like syscall, but code is a quad, so as to maintain
* quad alignment for the rest of the arguments.
* We use a 32-bit fetch in case params is not
* aligned.
*/
code = fuword32(params);
params += sizeof(quad_t);
}
}
if (p->p_sysent->sv_mask)
code &= p->p_sysent->sv_mask;
if (code >= p->p_sysent->sv_size)
callp = &p->p_sysent->sv_table[0];
else
callp = &p->p_sysent->sv_table[code];
narg = callp->sy_narg & SYF_ARGMASK;
/*
* copyin and the ktrsyscall()/ktrsysret() code is MP-aware
*/
if (params != NULL && narg != 0)
error = copyin(params, (caddr_t)args,
(u_int)(narg * sizeof(int)));
else
error = 0;
for (i = 0; i < narg; i++)
args64[i] = args[i];
#ifdef KTRACE
if (KTRPOINT(td, KTR_SYSCALL))
ktrsyscall(code, narg, args64);
#endif
/*
* Try to run the syscall without Giant if the syscall
* is MP safe.
*/
if ((callp->sy_narg & SYF_MPSAFE) == 0)
mtx_lock(&Giant);
if (error == 0) {
td->td_retval[0] = 0;
td->td_retval[1] = frame.tf_rdx;
STOPEVENT(p, S_SCE, narg);
error = (*callp->sy_call)(td, args64);
}
switch (error) {
case 0:
frame.tf_rax = td->td_retval[0];
frame.tf_rdx = td->td_retval[1];
frame.tf_rflags &= ~PSL_C;
break;
case ERESTART:
/*
* Reconstruct pc, assuming lcall $X,y is 7 bytes,
* int 0x80 is 2 bytes. We saved this in tf_err.
*/
frame.tf_rip -= frame.tf_err;
break;
case EJUSTRETURN:
break;
default:
if (p->p_sysent->sv_errsize) {
if (error >= p->p_sysent->sv_errsize)
error = -1; /* XXX */
else
error = p->p_sysent->sv_errtbl[error];
}
frame.tf_rax = error;
frame.tf_rflags |= PSL_C;
break;
}
/*
* Release Giant if we previously set it.
*/
if ((callp->sy_narg & SYF_MPSAFE) == 0)
mtx_unlock(&Giant);
/*
* Traced syscall.
*/
if (orig_tf_rflags & PSL_T) {
frame.tf_rflags &= ~PSL_T;
ksiginfo_init_trap(&ksi);
ksi.ksi_signo = SIGTRAP;
ksi.ksi_code = TRAP_TRACE;
ksi.ksi_addr = (void *)frame.tf_rip;
trapsignal(td, &ksi);
}
/*
* Handle reschedule and other end-of-syscall issues
*/
userret(td, &frame, sticks);
#ifdef KTRACE
if (KTRPOINT(td, KTR_SYSRET))
ktrsysret(code, error, td->td_retval[0]);
#endif
/*
* This works because errno is findable through the
* register set. If we ever support an emulation where this
* is not the case, this code will need to be revisited.
*/
STOPEVENT(p, S_SCX, code);
WITNESS_WARN(WARN_PANIC, NULL, "System call %s returning",
(code >= 0 && code < SYS_MAXSYSCALL) ? freebsd32_syscallnames[code] : "???");
mtx_assert(&sched_lock, MA_NOTOWNED);
mtx_assert(&Giant, MA_NOTOWNED);
}
static void
ia32_syscall_enable(void *dummy)
{
setidt(IDT_SYSCALL, &IDTVEC(int0x80_syscall), SDT_SYSIGT, SEL_UPL, 0);
}
static void
ia32_syscall_disable(void *dummy)
{
setidt(IDT_SYSCALL, &IDTVEC(rsvd), SDT_SYSIGT, SEL_KPL, 0);
}
SYSINIT(ia32_syscall, SI_SUB_EXEC, SI_ORDER_ANY, ia32_syscall_enable, NULL);
SYSUNINIT(ia32_syscall, SI_SUB_EXEC, SI_ORDER_ANY, ia32_syscall_disable, NULL);