aboutsummaryrefslogtreecommitdiff
path: root/sys/kern/subr_syscall.c
blob: 292b942d4d94006f79f5da8142a83bbd60a25b3f (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
/*-
 * Copyright (C) 1994, David Greenman
 * Copyright (c) 1990, 1993
 *	The Regents of the University of California.  All rights reserved.
 * Copyright (C) 2010 Konstantin Belousov <kib@freebsd.org>
 *
 * 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.
 *
 *	from: @(#)trap.c	7.4 (Berkeley) 5/13/91
 */

#include "opt_capsicum.h"
#include "opt_ktrace.h"

__FBSDID("$FreeBSD$");

#include <sys/capsicum.h>
#include <sys/ktr.h>
#ifdef KTRACE
#include <sys/uio.h>
#include <sys/ktrace.h>
#endif
#include <security/audit/audit.h>

static inline int
syscallenter(struct thread *td, struct syscall_args *sa)
{
	struct proc *p;
	int error, traced;

	PCPU_INC(cnt.v_syscall);
	p = td->td_proc;

	td->td_pticks = 0;
	if (td->td_cowgen != p->p_cowgen)
		thread_cow_update(td);
	if (p->p_flag & P_TRACED) {
		traced = 1;
		PROC_LOCK(p);
		td->td_dbgflags &= ~TDB_USERWR;
		td->td_dbgflags |= TDB_SCE;
		PROC_UNLOCK(p);
	} else
		traced = 0;
	error = (p->p_sysent->sv_fetch_syscall_args)(td, sa);
#ifdef KTRACE
	if (KTRPOINT(td, KTR_SYSCALL))
		ktrsyscall(sa->code, sa->narg, sa->args);
#endif
	KTR_START4(KTR_SYSC, "syscall", syscallname(p, sa->code),
	    (uintptr_t)td, "pid:%d", td->td_proc->p_pid, "arg0:%p", sa->args[0],
	    "arg1:%p", sa->args[1], "arg2:%p", sa->args[2]);

	if (error == 0) {

		STOPEVENT(p, S_SCE, sa->narg);
		if (p->p_flag & P_TRACED && p->p_stops & S_PT_SCE) {
			PROC_LOCK(p);
			td->td_dbg_sc_code = sa->code;
			td->td_dbg_sc_narg = sa->narg;
			ptracestop((td), SIGTRAP);
			PROC_UNLOCK(p);
		}
		if (td->td_dbgflags & TDB_USERWR) {
			/*
			 * Reread syscall number and arguments if
			 * debugger modified registers or memory.
			 */
			error = (p->p_sysent->sv_fetch_syscall_args)(td, sa);
			PROC_LOCK(p);
			td->td_dbg_sc_code = sa->code;
			td->td_dbg_sc_narg = sa->narg;
			PROC_UNLOCK(p);
#ifdef KTRACE
			if (KTRPOINT(td, KTR_SYSCALL))
				ktrsyscall(sa->code, sa->narg, sa->args);
#endif
			if (error != 0)
				goto retval;
		}

#ifdef CAPABILITY_MODE
		/*
		 * In capability mode, we only allow access to system calls
		 * flagged with SYF_CAPENABLED.
		 */
		if (IN_CAPABILITY_MODE(td) &&
		    !(sa->callp->sy_flags & SYF_CAPENABLED)) {
			error = ECAPMODE;
			goto retval;
		}
#endif

		error = syscall_thread_enter(td, sa->callp);
		if (error != 0)
			goto retval;

#ifdef KDTRACE_HOOKS
		/*
		 * If the systrace module has registered it's probe
		 * callback and if there is a probe active for the
		 * syscall 'entry', process the probe.
		 */
		if (systrace_probe_func != NULL && sa->callp->sy_entry != 0)
			(*systrace_probe_func)(sa->callp->sy_entry, sa->code,
			    sa->callp, sa->args, 0);
#endif

		AUDIT_SYSCALL_ENTER(sa->code, td);
		error = (sa->callp->sy_call)(td, sa->args);
		AUDIT_SYSCALL_EXIT(error, td);

		/* Save the latest error return value. */
		if ((td->td_pflags & TDP_NERRNO) == 0)
			td->td_errno = error;

#ifdef KDTRACE_HOOKS
		/*
		 * If the systrace module has registered it's probe
		 * callback and if there is a probe active for the
		 * syscall 'return', process the probe.
		 */
		if (systrace_probe_func != NULL && sa->callp->sy_return != 0)
			(*systrace_probe_func)(sa->callp->sy_return, sa->code,
			    sa->callp, NULL, (error) ? -1 : td->td_retval[0]);
#endif
		syscall_thread_exit(td, sa->callp);
	}
 retval:
	KTR_STOP4(KTR_SYSC, "syscall", syscallname(p, sa->code),
	    (uintptr_t)td, "pid:%d", td->td_proc->p_pid, "error:%d", error,
	    "retval0:%#lx", td->td_retval[0], "retval1:%#lx",
	    td->td_retval[1]);
	if (traced) {
		PROC_LOCK(p);
		td->td_dbgflags &= ~TDB_SCE;
		PROC_UNLOCK(p);
	}
	(p->p_sysent->sv_set_syscall_retval)(td, error);
	return (error);
}

static inline void
syscallret(struct thread *td, int error, struct syscall_args *sa __unused)
{
	struct proc *p, *p2;
	int traced;

	p = td->td_proc;

	/*
	 * Handle reschedule and other end-of-syscall issues
	 */
	userret(td, td->td_frame);

#ifdef KTRACE
	if (KTRPOINT(td, KTR_SYSRET)) {
		ktrsysret(sa->code, (td->td_pflags & TDP_NERRNO) == 0 ?
		    error : td->td_errno, td->td_retval[0]);
	}
#endif
	td->td_pflags &= ~TDP_NERRNO;

	if (p->p_flag & P_TRACED) {
		traced = 1;
		PROC_LOCK(p);
		td->td_dbgflags |= TDB_SCX;
		PROC_UNLOCK(p);
	} else
		traced = 0;
	/*
	 * 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, sa->code);
	if (traced || (td->td_dbgflags & (TDB_EXEC | TDB_FORK)) != 0) {
		PROC_LOCK(p);
		/*
		 * If tracing the execed process, trap to the debugger
		 * so that breakpoints can be set before the program
		 * executes.  If debugger requested tracing of syscall
		 * returns, do it now too.
		 */
		if (traced &&
		    ((td->td_dbgflags & (TDB_FORK | TDB_EXEC)) != 0 ||
		    (p->p_stops & S_PT_SCX) != 0))
			ptracestop(td, SIGTRAP);
		td->td_dbgflags &= ~(TDB_SCX | TDB_EXEC | TDB_FORK);
		PROC_UNLOCK(p);
	}

	if (td->td_pflags & TDP_RFPPWAIT) {
		/*
		 * Preserve synchronization semantics of vfork.  If
		 * waiting for child to exec or exit, fork set
		 * P_PPWAIT on child, and there we sleep on our proc
		 * (in case of exit).
		 *
		 * Do it after the ptracestop() above is finished, to
		 * not block our debugger until child execs or exits
		 * to finish vfork wait.
		 */
		td->td_pflags &= ~TDP_RFPPWAIT;
		p2 = td->td_rfppwait_p;
again:
		PROC_LOCK(p2);
		while (p2->p_flag & P_PPWAIT) {
			PROC_LOCK(p);
			if (thread_suspend_check_needed()) {
				PROC_UNLOCK(p2);
				thread_suspend_check(0);
				PROC_UNLOCK(p);
				goto again;
			} else {
				PROC_UNLOCK(p);
			}
			cv_timedwait(&p2->p_pwait, &p2->p_mtx, hz);
		}
		PROC_UNLOCK(p2);
	}
}