The Design and Implementation of the FreeBSD Operating System, Second Edition
Now available: The Design and Implementation of the FreeBSD Operating System (Second Edition)


[ source navigation ] [ diff markup ] [ identifier search ] [ freetext search ] [ file search ] [ list types ] [ track identifier ]

FreeBSD/Linux Kernel Cross Reference
sys/kern/subr_syscall.c

Version: -  FREEBSD  -  FREEBSD-13-STABLE  -  FREEBSD-13-0  -  FREEBSD-12-STABLE  -  FREEBSD-12-0  -  FREEBSD-11-STABLE  -  FREEBSD-11-0  -  FREEBSD-10-STABLE  -  FREEBSD-10-0  -  FREEBSD-9-STABLE  -  FREEBSD-9-0  -  FREEBSD-8-STABLE  -  FREEBSD-8-0  -  FREEBSD-7-STABLE  -  FREEBSD-7-0  -  FREEBSD-6-STABLE  -  FREEBSD-6-0  -  FREEBSD-5-STABLE  -  FREEBSD-5-0  -  FREEBSD-4-STABLE  -  FREEBSD-3-STABLE  -  FREEBSD22  -  l41  -  OPENBSD  -  linux-2.6  -  MK84  -  PLAN9  -  xnu-8792 
SearchContext: -  none  -  3  -  10 

    1 /*-
    2  * SPDX-License-Identifier: BSD-4-Clause
    3  *
    4  * Copyright (C) 1994, David Greenman
    5  * Copyright (c) 1990, 1993
    6  *      The Regents of the University of California.  All rights reserved.
    7  * Copyright (C) 2010 Konstantin Belousov <kib@freebsd.org>
    8  *
    9  * This code is derived from software contributed to Berkeley by
   10  * the University of Utah, and William Jolitz.
   11  *
   12  * Redistribution and use in source and binary forms, with or without
   13  * modification, are permitted provided that the following conditions
   14  * are met:
   15  * 1. Redistributions of source code must retain the above copyright
   16  *    notice, this list of conditions and the following disclaimer.
   17  * 2. Redistributions in binary form must reproduce the above copyright
   18  *    notice, this list of conditions and the following disclaimer in the
   19  *    documentation and/or other materials provided with the distribution.
   20  * 3. All advertising materials mentioning features or use of this software
   21  *    must display the following acknowledgement:
   22  *      This product includes software developed by the University of
   23  *      California, Berkeley and its contributors.
   24  * 4. Neither the name of the University nor the names of its contributors
   25  *    may be used to endorse or promote products derived from this software
   26  *    without specific prior written permission.
   27  *
   28  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
   29  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
   30  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
   31  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
   32  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
   33  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
   34  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
   35  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
   36  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
   37  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
   38  * SUCH DAMAGE.
   39  *
   40  *      from: @(#)trap.c        7.4 (Berkeley) 5/13/91
   41  */
   42 
   43 #include "opt_capsicum.h"
   44 #include "opt_ktrace.h"
   45 
   46 __FBSDID("$FreeBSD$");
   47 
   48 #include <sys/capsicum.h>
   49 #include <sys/ktr.h>
   50 #include <sys/vmmeter.h>
   51 #ifdef KTRACE
   52 #include <sys/uio.h>
   53 #include <sys/ktrace.h>
   54 #endif
   55 #include <security/audit/audit.h>
   56 
   57 static inline void
   58 syscallenter(struct thread *td)
   59 {
   60         struct proc *p;
   61         struct syscall_args *sa;
   62         struct sysent *se;
   63         int error, traced;
   64         bool sy_thr_static;
   65 
   66         VM_CNT_INC(v_syscall);
   67         p = td->td_proc;
   68         sa = &td->td_sa;
   69 
   70         td->td_pticks = 0;
   71         if (__predict_false(td->td_cowgen != p->p_cowgen))
   72                 thread_cow_update(td);
   73         traced = (p->p_flag & P_TRACED) != 0;
   74         if (__predict_false(traced || td->td_dbgflags & TDB_USERWR)) {
   75                 PROC_LOCK(p);
   76                 td->td_dbgflags &= ~TDB_USERWR;
   77                 if (traced)
   78                         td->td_dbgflags |= TDB_SCE;
   79                 PROC_UNLOCK(p);
   80         }
   81         error = (p->p_sysent->sv_fetch_syscall_args)(td);
   82         se = sa->callp;
   83 #ifdef KTRACE
   84         if (KTRPOINT(td, KTR_SYSCALL))
   85                 ktrsyscall(sa->code, se->sy_narg, sa->args);
   86 #endif
   87         KTR_START4(KTR_SYSC, "syscall", syscallname(p, sa->code),
   88             (uintptr_t)td, "pid:%d", td->td_proc->p_pid, "arg0:%p", sa->args[0],
   89             "arg1:%p", sa->args[1], "arg2:%p", sa->args[2]);
   90 
   91         if (__predict_false(error != 0)) {
   92                 td->td_errno = error;
   93                 goto retval;
   94         }
   95 
   96         if (__predict_false(traced)) {
   97                 PROC_LOCK(p);
   98                 if (p->p_ptevents & PTRACE_SCE)
   99                         ptracestop((td), SIGTRAP, NULL);
  100                 PROC_UNLOCK(p);
  101 
  102                 if ((td->td_dbgflags & TDB_USERWR) != 0) {
  103                         /*
  104                          * Reread syscall number and arguments if debugger
  105                          * modified registers or memory.
  106                          */
  107                         error = (p->p_sysent->sv_fetch_syscall_args)(td);
  108                         se = sa->callp;
  109 #ifdef KTRACE
  110                         if (KTRPOINT(td, KTR_SYSCALL))
  111                                 ktrsyscall(sa->code, se->sy_narg, sa->args);
  112 #endif
  113                         if (error != 0) {
  114                                 td->td_errno = error;
  115                                 goto retval;
  116                         }
  117                 }
  118         }
  119 
  120 #ifdef CAPABILITY_MODE
  121         /*
  122          * In capability mode, we only allow access to system calls
  123          * flagged with SYF_CAPENABLED.
  124          */
  125         if (__predict_false(IN_CAPABILITY_MODE(td) &&
  126             (se->sy_flags & SYF_CAPENABLED) == 0)) {
  127                 td->td_errno = error = ECAPMODE;
  128                 goto retval;
  129         }
  130 #endif
  131 
  132         /*
  133          * Fetch fast sigblock value at the time of syscall entry to
  134          * handle sleepqueue primitives which might call cursig().
  135          */
  136         if (__predict_false(sigfastblock_fetch_always))
  137                 (void)sigfastblock_fetch(td);
  138 
  139         /* Let system calls set td_errno directly. */
  140         KASSERT((td->td_pflags & TDP_NERRNO) == 0,
  141             ("%s: TDP_NERRNO set", __func__));
  142 
  143         sy_thr_static = (se->sy_thrcnt & SY_THR_STATIC) != 0;
  144 
  145         if (__predict_false(SYSTRACE_ENABLED() ||
  146             AUDIT_SYSCALL_ENTER(sa->code, td) ||
  147             !sy_thr_static)) {
  148                 if (!sy_thr_static) {
  149                         error = syscall_thread_enter(td, se);
  150                         if (error != 0) {
  151                                 td->td_errno = error;
  152                                 goto retval;
  153                         }
  154                 }
  155 
  156 #ifdef KDTRACE_HOOKS
  157                 /* Give the syscall:::entry DTrace probe a chance to fire. */
  158                 if (__predict_false(se->sy_entry != 0))
  159                         (*systrace_probe_func)(sa, SYSTRACE_ENTRY, 0);
  160 #endif
  161                 error = (se->sy_call)(td, sa->args);
  162                 /* Save the latest error return value. */
  163                 if (__predict_false((td->td_pflags & TDP_NERRNO) != 0))
  164                         td->td_pflags &= ~TDP_NERRNO;
  165                 else
  166                         td->td_errno = error;
  167 
  168                 /*
  169                  * Note that some syscall implementations (e.g., sys_execve)
  170                  * will commit the audit record just before their final return.
  171                  * These were done under the assumption that nothing of interest
  172                  * would happen between their return and here, where we would
  173                  * normally commit the audit record.  These assumptions will
  174                  * need to be revisited should any substantial logic be added
  175                  * above.
  176                  */
  177                 AUDIT_SYSCALL_EXIT(error, td);
  178 
  179 #ifdef KDTRACE_HOOKS
  180                 /* Give the syscall:::return DTrace probe a chance to fire. */
  181                 if (__predict_false(se->sy_return != 0))
  182                         (*systrace_probe_func)(sa, SYSTRACE_RETURN,
  183                             error ? -1 : td->td_retval[0]);
  184 #endif
  185 
  186                 if (!sy_thr_static)
  187                         syscall_thread_exit(td, se);
  188         } else {
  189                 error = (se->sy_call)(td, sa->args);
  190                 /* Save the latest error return value. */
  191                 if (__predict_false((td->td_pflags & TDP_NERRNO) != 0))
  192                         td->td_pflags &= ~TDP_NERRNO;
  193                 else
  194                         td->td_errno = error;
  195         }
  196 
  197  retval:
  198         KTR_STOP4(KTR_SYSC, "syscall", syscallname(p, sa->code),
  199             (uintptr_t)td, "pid:%d", td->td_proc->p_pid, "error:%d", error,
  200             "retval0:%#lx", td->td_retval[0], "retval1:%#lx",
  201             td->td_retval[1]);
  202         if (__predict_false(traced)) {
  203                 PROC_LOCK(p);
  204                 td->td_dbgflags &= ~TDB_SCE;
  205                 PROC_UNLOCK(p);
  206         }
  207         (p->p_sysent->sv_set_syscall_retval)(td, error);
  208 }
  209 
  210 static inline void
  211 syscallret(struct thread *td)
  212 {
  213         struct proc *p;
  214         struct syscall_args *sa;
  215         ksiginfo_t ksi;
  216         int traced;
  217 
  218         KASSERT((td->td_pflags & TDP_FORKING) == 0,
  219             ("fork() did not clear TDP_FORKING upon completion"));
  220         KASSERT(td->td_errno != ERELOOKUP,
  221             ("ERELOOKUP not consumed syscall %d", td->td_sa.code));
  222 
  223         p = td->td_proc;
  224         sa = &td->td_sa;
  225         if (__predict_false(td->td_errno == ENOTCAPABLE ||
  226             td->td_errno == ECAPMODE)) {
  227                 if ((trap_enotcap ||
  228                     (p->p_flag2 & P2_TRAPCAP) != 0) && IN_CAPABILITY_MODE(td)) {
  229                         ksiginfo_init_trap(&ksi);
  230                         ksi.ksi_signo = SIGTRAP;
  231                         ksi.ksi_errno = td->td_errno;
  232                         ksi.ksi_code = TRAP_CAP;
  233                         trapsignal(td, &ksi);
  234                 }
  235         }
  236 
  237         /*
  238          * Handle reschedule and other end-of-syscall issues
  239          */
  240         userret(td, td->td_frame);
  241 
  242 #ifdef KTRACE
  243         if (KTRPOINT(td, KTR_SYSRET)) {
  244                 ktrsysret(sa->code, td->td_errno, td->td_retval[0]);
  245         }
  246 #endif
  247 
  248         traced = 0;
  249         if (__predict_false(p->p_flag & P_TRACED)) {
  250                 traced = 1;
  251                 PROC_LOCK(p);
  252                 td->td_dbgflags |= TDB_SCX;
  253                 PROC_UNLOCK(p);
  254         }
  255         if (__predict_false(traced ||
  256             (td->td_dbgflags & (TDB_EXEC | TDB_FORK)) != 0)) {
  257                 PROC_LOCK(p);
  258                 /*
  259                  * If tracing the execed process, trap to the debugger
  260                  * so that breakpoints can be set before the program
  261                  * executes.  If debugger requested tracing of syscall
  262                  * returns, do it now too.
  263                  */
  264                 if (traced &&
  265                     ((td->td_dbgflags & (TDB_FORK | TDB_EXEC)) != 0 ||
  266                     (p->p_ptevents & PTRACE_SCX) != 0))
  267                         ptracestop(td, SIGTRAP, NULL);
  268                 td->td_dbgflags &= ~(TDB_SCX | TDB_EXEC | TDB_FORK);
  269                 PROC_UNLOCK(p);
  270         }
  271 
  272         if (__predict_false(td->td_pflags & TDP_RFPPWAIT))
  273                 fork_rfppwait(td);
  274 }

Cache object: bfcb46a176e061ca96515665a8407375


[ source navigation ] [ diff markup ] [ identifier search ] [ freetext search ] [ file search ] [ list types ] [ track identifier ]


This page is part of the FreeBSD/Linux Linux Kernel Cross-Reference, and was automatically generated using a modified version of the LXR engine.