| 1 |
.\" Copyright 1999, ike Coleman <[email protected]> |
| 2 |
.\" Copyright 2011, Denys Vlasenko <[email protected]> |
| 3 |
.\" Copyright 2015-2016, Michael Kerrisk <[email protected]> |
| 4 |
.\" Copyright, the authors of the Linux man-pages project |
| 5 |
.\" |
| 6 |
.\" SPDX-License-Identifier: GPL-2.0-or-later |
| 7 |
.\" |
| 8 |
.\" FIXME The following are undocumented: |
| 9 |
.\" |
| 10 |
.\" PTRACE_GETWMMXREGS |
| 11 |
.\" PTRACE_SETWMMXREGS |
| 12 |
.\" ARM |
| 13 |
.\" Linux 2.6.12 |
| 14 |
.\" |
| 15 |
.\" PTRACE_SET_SYSCALL |
| 16 |
.\" ARM and ARM64 |
| 17 |
.\" Linux 2.6.16 |
| 18 |
.\" commit 3f471126ee53feb5e9b210ea2f525ed3bb9b7a7f |
| 19 |
.\" Author: Nicolas Pitre <[email protected]> |
| 20 |
.\" Date: Sat Jan 14 19:30:04 2006 +0000 |
| 21 |
.\" |
| 22 |
.\" PTRACE_GETCRUNCHREGS |
| 23 |
.\" PTRACE_SETCRUNCHREGS |
| 24 |
.\" ARM |
| 25 |
.\" Linux 2.6.18 |
| 26 |
.\" commit 3bec6ded282b331552587267d67a06ed7fd95ddd |
| 27 |
.\" Author: Lennert Buytenhek <[email protected]> |
| 28 |
.\" Date: Tue Jun 27 22:56:18 2006 +0100 |
| 29 |
.\" |
| 30 |
.\" PTRACE_GETVFPREGS |
| 31 |
.\" PTRACE_SETVFPREGS |
| 32 |
.\" ARM and ARM64 |
| 33 |
.\" Linux 2.6.30 |
| 34 |
.\" commit 3d1228ead618b88e8606015cbabc49019981805d |
| 35 |
.\" Author: Catalin Marinas <[email protected]> |
| 36 |
.\" Date: Wed Feb 11 13:12:56 2009 +0100 |
| 37 |
.\" |
| 38 |
.\" PTRACE_GETHBPREGS |
| 39 |
.\" PTRACE_SETHBPREGS |
| 40 |
.\" ARM and ARM64 |
| 41 |
.\" Linux 2.6.37 |
| 42 |
.\" commit 864232fa1a2f8dfe003438ef0851a56722740f3e |
| 43 |
.\" Author: Will Deacon <[email protected]> |
| 44 |
.\" Date: Fri Sep 3 10:42:55 2010 +0100 |
| 45 |
.\" |
| 46 |
.\" PTRACE_SINGLEBLOCK |
| 47 |
.\" Since at least Linux 2.4.0 on various architectures |
| 48 |
.\" Since Linux 2.6.25 on x86 (and others?) |
| 49 |
.\" commit 5b88abbf770a0e1975c668743100f42934f385e8 |
| 50 |
.\" Author: Roland McGrath <[email protected]> |
| 51 |
.\" Date: Wed Jan 30 13:30:53 2008 +0100 |
| 52 |
.\" ptrace: generic PTRACE_SINGLEBLOCK |
| 53 |
.\" |
| 54 |
.\" PTRACE_GETFPXREGS |
| 55 |
.\" PTRACE_SETFPXREGS |
| 56 |
.\" Since at least Linux 2.4.0 on various architectures |
| 57 |
.\" |
| 58 |
.\" PTRACE_GETFDPIC |
| 59 |
.\" PTRACE_GETFDPIC_EXEC |
| 60 |
.\" PTRACE_GETFDPIC_INTERP |
| 61 |
.\" blackfin, c6x, frv, sh |
| 62 |
.\" First appearance in Linux 2.6.11 on frv |
| 63 |
.\" |
| 64 |
.\" and others that can be found in the arch/*/include/uapi/asm/ptrace files |
| 65 |
.\" |
| 66 |
.TH ptrace 2 2026-02-10 "Linux man-pages 6.18" |
| 67 |
.SH NAME |
| 68 |
ptrace \- process trace |
| 69 |
.SH LIBRARY |
| 70 |
Standard C library |
| 71 |
.RI ( libc ,\~ \-lc ) |
| 72 |
.SH SYNOPSIS |
| 73 |
.nf |
| 74 |
.B #include <sys/ptrace.h> |
| 75 |
.P |
| 76 |
.BI "long ptrace(enum __ptrace_request " op ", pid_t " pid , |
| 77 |
.BI " void *" addr ", void *" data ); |
| 78 |
.fi |
| 79 |
.SH DESCRIPTION |
| 80 |
The |
| 81 |
.BR ptrace () |
| 82 |
system call provides a means by which one process (the "tracer") |
| 83 |
may observe and control the execution of another process (the "tracee"), |
| 84 |
and examine and change the tracee's memory and registers. |
| 85 |
It is primarily used to implement breakpoint debugging and system |
| 86 |
call tracing. |
| 87 |
.P |
| 88 |
A tracee first needs to be attached to the tracer. |
| 89 |
Attachment and subsequent commands are per thread: |
| 90 |
in a multithreaded process, |
| 91 |
every thread can be individually attached to a |
| 92 |
(potentially different) tracer, |
| 93 |
or left not attached and thus not debugged. |
| 94 |
Therefore, "tracee" always means "(one) thread", |
| 95 |
never "a (possibly multithreaded) process". |
| 96 |
Ptrace commands are always sent to |
| 97 |
a specific tracee using a call of the form |
| 98 |
.P |
| 99 |
.in +4n |
| 100 |
.EX |
| 101 |
ptrace(PTRACE_foo, pid, ...) |
| 102 |
.EE |
| 103 |
.in |
| 104 |
.P |
| 105 |
where |
| 106 |
.I pid |
| 107 |
is the thread ID of the corresponding Linux thread. |
| 108 |
.P |
| 109 |
(Note that in this page, a "multithreaded process" |
| 110 |
means a thread group consisting of threads created using the |
| 111 |
.BR clone (2) |
| 112 |
.B CLONE_THREAD |
| 113 |
flag.) |
| 114 |
.P |
| 115 |
A process can initiate a trace by calling |
| 116 |
.BR fork (2) |
| 117 |
and having the resulting child do a |
| 118 |
.BR PTRACE_TRACEME , |
| 119 |
followed (typically) by an |
| 120 |
.BR execve (2). |
| 121 |
Alternatively, one process may commence tracing another process using |
| 122 |
.B PTRACE_ATTACH |
| 123 |
or |
| 124 |
.BR PTRACE_SEIZE . |
| 125 |
.P |
| 126 |
While being traced, the tracee will stop each time a signal is delivered, |
| 127 |
even if the signal is being ignored. |
| 128 |
(An exception is |
| 129 |
.BR SIGKILL , |
| 130 |
which has its usual effect.) |
| 131 |
The tracer will be notified at its next call to |
| 132 |
.BR waitpid (2) |
| 133 |
(or one of the related "wait" system calls); |
| 134 |
that call will return a |
| 135 |
.I status |
| 136 |
value containing information that indicates |
| 137 |
the cause of the stop in the tracee. |
| 138 |
While the tracee is stopped, |
| 139 |
the tracer can use various ptrace operations to inspect and modify the tracee. |
| 140 |
The tracer then causes the tracee to continue, |
| 141 |
optionally ignoring the delivered signal |
| 142 |
(or even delivering a different signal instead). |
| 143 |
.P |
| 144 |
If the |
| 145 |
.B PTRACE_O_TRACEEXEC |
| 146 |
option is not in effect, all successful calls to |
| 147 |
.BR execve (2) |
| 148 |
by the traced process will cause it to be sent a |
| 149 |
.B SIGTRAP |
| 150 |
signal, |
| 151 |
giving the parent a chance to gain control before the new program |
| 152 |
begins execution. |
| 153 |
.P |
| 154 |
When the tracer is finished tracing, it can cause the tracee to continue |
| 155 |
executing in a normal, untraced mode via |
| 156 |
.BR PTRACE_DETACH . |
| 157 |
.P |
| 158 |
The value of |
| 159 |
.I op |
| 160 |
determines the operation to be performed: |
| 161 |
.TP |
| 162 |
.B PTRACE_TRACEME |
| 163 |
Indicate that this process is to be traced by its parent. |
| 164 |
A process probably shouldn't make this operation if its parent |
| 165 |
isn't expecting to trace it. |
| 166 |
.RI ( pid , |
| 167 |
.IR addr , |
| 168 |
and |
| 169 |
.I data |
| 170 |
are ignored.) |
| 171 |
.IP |
| 172 |
The |
| 173 |
.B PTRACE_TRACEME |
| 174 |
operation is used only by the tracee; |
| 175 |
the remaining operations are used only by the tracer. |
| 176 |
In the following operations, |
| 177 |
.I pid |
| 178 |
specifies the thread ID of the tracee to be acted on. |
| 179 |
For operations other than |
| 180 |
.BR PTRACE_ATTACH , |
| 181 |
.BR PTRACE_SEIZE , |
| 182 |
.BR PTRACE_INTERRUPT , |
| 183 |
and |
| 184 |
.BR PTRACE_KILL , |
| 185 |
the tracee must be stopped. |
| 186 |
.TP |
| 187 |
.B PTRACE_PEEKTEXT |
| 188 |
.TQ |
| 189 |
.B PTRACE_PEEKDATA |
| 190 |
Read a word at the address |
| 191 |
.I addr |
| 192 |
in the tracee's memory, returning the word as the result of the |
| 193 |
.BR ptrace () |
| 194 |
call. |
| 195 |
Linux does not have separate text and data address spaces, |
| 196 |
so these two operations are currently equivalent. |
| 197 |
.RI ( data |
| 198 |
is ignored; |
| 199 |
but see NOTES.) |
| 200 |
.TP |
| 201 |
.B PTRACE_PEEKUSER |
| 202 |
.\" PTRACE_PEEKUSR in kernel source, but glibc uses PTRACE_PEEKUSER, |
| 203 |
.\" and that is the name that seems common on other systems. |
| 204 |
Read a word at offset |
| 205 |
.I addr |
| 206 |
in the tracee's USER area, |
| 207 |
which holds the registers and other information about the process |
| 208 |
(see |
| 209 |
.IR <sys/user.h> ). |
| 210 |
The word is returned as the result of the |
| 211 |
.BR ptrace () |
| 212 |
call. |
| 213 |
Typically, the offset must be word-aligned, though this might vary by |
| 214 |
architecture. |
| 215 |
See NOTES. |
| 216 |
.RI ( data |
| 217 |
is ignored; |
| 218 |
but see NOTES.) |
| 219 |
.TP |
| 220 |
.B PTRACE_POKETEXT |
| 221 |
.TQ |
| 222 |
.B PTRACE_POKEDATA |
| 223 |
Copy the word |
| 224 |
.I data |
| 225 |
to the address |
| 226 |
.I addr |
| 227 |
in the tracee's memory. |
| 228 |
As for |
| 229 |
.B PTRACE_PEEKTEXT |
| 230 |
and |
| 231 |
.BR PTRACE_PEEKDATA , |
| 232 |
these two operations are currently equivalent. |
| 233 |
.TP |
| 234 |
.B PTRACE_POKEUSER |
| 235 |
.\" PTRACE_POKEUSR in kernel source, but glibc uses PTRACE_POKEUSER, |
| 236 |
.\" and that is the name that seems common on other systems. |
| 237 |
Copy the word |
| 238 |
.I data |
| 239 |
to offset |
| 240 |
.I addr |
| 241 |
in the tracee's USER area. |
| 242 |
As for |
| 243 |
.BR PTRACE_PEEKUSER , |
| 244 |
the offset must typically be word-aligned. |
| 245 |
In order to maintain the integrity of the kernel, |
| 246 |
some modifications to the USER area are disallowed. |
| 247 |
.\" FIXME In the preceding sentence, which modifications are disallowed, |
| 248 |
.\" and when they are disallowed, how does user space discover that fact? |
| 249 |
.TP |
| 250 |
.B PTRACE_GETREGS |
| 251 |
.TQ |
| 252 |
.B PTRACE_GETFPREGS |
| 253 |
Copy the tracee's general-purpose or floating-point registers, |
| 254 |
respectively, to the address |
| 255 |
.I data |
| 256 |
in the tracer. |
| 257 |
See |
| 258 |
.I <sys/user.h> |
| 259 |
for information on the format of this data. |
| 260 |
.RI ( addr |
| 261 |
is ignored.) |
| 262 |
Note that SPARC systems have the meaning of |
| 263 |
.I data |
| 264 |
and |
| 265 |
.I addr |
| 266 |
reversed; |
| 267 |
that is, |
| 268 |
.I data |
| 269 |
is ignored and the registers are copied to the address |
| 270 |
.IR addr . |
| 271 |
.B PTRACE_GETREGS |
| 272 |
and |
| 273 |
.B PTRACE_GETFPREGS |
| 274 |
are not present on all architectures. |
| 275 |
.TP |
| 276 |
.BR PTRACE_GETREGSET " (since Linux 2.6.34)" |
| 277 |
Read the tracee's registers. |
| 278 |
.I addr |
| 279 |
specifies, in an architecture-dependent way, the type of registers to be read. |
| 280 |
.B NT_PRSTATUS |
| 281 |
(with numerical value 1) |
| 282 |
usually results in reading of general-purpose registers. |
| 283 |
If the CPU has, for example, |
| 284 |
floating-point and/or vector registers, they can be retrieved by setting |
| 285 |
.I addr |
| 286 |
to the corresponding |
| 287 |
.B NT_foo |
| 288 |
constant. |
| 289 |
.I data |
| 290 |
points to a |
| 291 |
.BR "struct iovec" , |
| 292 |
which describes the destination buffer's location and size. |
| 293 |
On return, the kernel modifies |
| 294 |
.B iov.len |
| 295 |
to indicate the actual number of bytes returned. |
| 296 |
.TP |
| 297 |
.B PTRACE_SETREGS |
| 298 |
.TQ |
| 299 |
.B PTRACE_SETFPREGS |
| 300 |
Modify the tracee's general-purpose or floating-point registers, |
| 301 |
respectively, from the address |
| 302 |
.I data |
| 303 |
in the tracer. |
| 304 |
As for |
| 305 |
.BR PTRACE_POKEUSER , |
| 306 |
some general-purpose register modifications may be disallowed. |
| 307 |
.\" FIXME . In the preceding sentence, which modifications are disallowed, |
| 308 |
.\" and when they are disallowed, how does user space discover that fact? |
| 309 |
.RI ( addr |
| 310 |
is ignored.) |
| 311 |
Note that SPARC systems have the meaning of |
| 312 |
.I data |
| 313 |
and |
| 314 |
.I addr |
| 315 |
reversed; |
| 316 |
that is, |
| 317 |
.I data |
| 318 |
is ignored |
| 319 |
and the registers are copied from the address |
| 320 |
.IR addr . |
| 321 |
.B PTRACE_SETREGS |
| 322 |
and |
| 323 |
.B PTRACE_SETFPREGS |
| 324 |
are not present on all architectures. |
| 325 |
.TP |
| 326 |
.BR PTRACE_SETREGSET " (since Linux 2.6.34)" |
| 327 |
Modify the tracee's registers. |
| 328 |
The meaning of |
| 329 |
.I addr |
| 330 |
and |
| 331 |
.I data |
| 332 |
is analogous to |
| 333 |
.BR PTRACE_GETREGSET . |
| 334 |
.TP |
| 335 |
.BR PTRACE_GETSIGINFO " (since Linux 2.3.99-pre6)" |
| 336 |
Retrieve information about the signal that caused the stop. |
| 337 |
Copy a |
| 338 |
.I siginfo_t |
| 339 |
structure (see |
| 340 |
.BR sigaction (2)) |
| 341 |
from the tracee to the address |
| 342 |
.I data |
| 343 |
in the tracer. |
| 344 |
.RI ( addr |
| 345 |
is ignored.) |
| 346 |
.TP |
| 347 |
.BR PTRACE_SETSIGINFO " (since Linux 2.3.99-pre6)" |
| 348 |
Set signal information: |
| 349 |
copy a |
| 350 |
.I siginfo_t |
| 351 |
structure from the address |
| 352 |
.I data |
| 353 |
in the tracer to the tracee. |
| 354 |
This will affect only signals that would normally be delivered to |
| 355 |
the tracee and were caught by the tracer. |
| 356 |
It may be difficult to tell |
| 357 |
these normal signals from synthetic signals generated by |
| 358 |
.BR ptrace () |
| 359 |
itself. |
| 360 |
.RI ( addr |
| 361 |
is ignored.) |
| 362 |
.TP |
| 363 |
.BR PTRACE_PEEKSIGINFO " (since Linux 3.10)" |
| 364 |
.\" commit 84c751bd4aebbaae995fe32279d3dba48327bad4 |
| 365 |
Retrieve |
| 366 |
.I siginfo_t |
| 367 |
structures without removing signals from a queue. |
| 368 |
.I addr |
| 369 |
points to a |
| 370 |
.I ptrace_peeksiginfo_args |
| 371 |
structure that specifies the ordinal position from which |
| 372 |
copying of signals should start, |
| 373 |
and the number of signals to copy. |
| 374 |
.I siginfo_t |
| 375 |
structures are copied into the buffer pointed to by |
| 376 |
.IR data . |
| 377 |
The return value contains the number of copied signals (zero indicates |
| 378 |
that there is no signal corresponding to the specified ordinal position). |
| 379 |
Within the returned |
| 380 |
.I siginfo |
| 381 |
structures, |
| 382 |
the |
| 383 |
.I si_code |
| 384 |
field includes information |
| 385 |
.RB ( __SI_CHLD , |
| 386 |
.BR __SI_FAULT , |
| 387 |
etc.) that are not otherwise exposed to user space. |
| 388 |
.P |
| 389 |
.in +4n |
| 390 |
.EX |
| 391 |
struct ptrace_peeksiginfo_args { |
| 392 |
u64 off; /* Ordinal position in queue at which |
| 393 |
to start copying signals */ |
| 394 |
u32 flags; /* PTRACE_PEEKSIGINFO_SHARED or 0 */ |
| 395 |
s32 nr; /* Number of signals to copy */ |
| 396 |
}; |
| 397 |
.EE |
| 398 |
.in |
| 399 |
.IP |
| 400 |
Currently, there is only one flag, |
| 401 |
.BR PTRACE_PEEKSIGINFO_SHARED , |
| 402 |
for dumping signals from the process-wide signal queue. |
| 403 |
If this flag is not set, |
| 404 |
signals are read from the per-thread queue of the specified thread. |
| 405 |
.in |
| 406 |
.TP |
| 407 |
.BR PTRACE_GETSIGMASK " (since Linux 3.11)" |
| 408 |
.\" commit 29000caecbe87b6b66f144f72111f0d02fbbf0c1 |
| 409 |
Place a copy of the mask of blocked signals (see |
| 410 |
.BR sigprocmask (2)) |
| 411 |
in the buffer pointed to by |
| 412 |
.IR data , |
| 413 |
which should be a pointer to a buffer of type |
| 414 |
.IR sigset_t . |
| 415 |
The |
| 416 |
.I addr |
| 417 |
argument contains the size of the buffer pointed to by |
| 418 |
.I data |
| 419 |
(i.e., |
| 420 |
.IR sizeof(sigset_t) ). |
| 421 |
.TP |
| 422 |
.BR PTRACE_SETSIGMASK " (since Linux 3.11)" |
| 423 |
Change the mask of blocked signals (see |
| 424 |
.BR sigprocmask (2)) |
| 425 |
to the value specified in the buffer pointed to by |
| 426 |
.IR data , |
| 427 |
which should be a pointer to a buffer of type |
| 428 |
.IR sigset_t . |
| 429 |
The |
| 430 |
.I addr |
| 431 |
argument contains the size of the buffer pointed to by |
| 432 |
.I data |
| 433 |
(i.e., |
| 434 |
.IR sizeof(sigset_t) ). |
| 435 |
.TP |
| 436 |
.BR PTRACE_SETOPTIONS " (since Linux 2.4.6; see BUGS for caveats)" |
| 437 |
Set ptrace options from |
| 438 |
.IR data . |
| 439 |
.RI ( addr |
| 440 |
is ignored.) |
| 441 |
.I data |
| 442 |
is interpreted as a bit mask of options, |
| 443 |
which are specified by the following flags: |
| 444 |
.RS |
| 445 |
.TP |
| 446 |
.BR PTRACE_O_EXITKILL " (since Linux 3.8)" |
| 447 |
.\" commit 992fb6e170639b0849bace8e49bf31bd37c4123 |
| 448 |
Send a |
| 449 |
.B SIGKILL |
| 450 |
signal to the tracee if the tracer exits. |
| 451 |
This option is useful for ptrace jailers that |
| 452 |
want to ensure that tracees can never escape the tracer's control. |
| 453 |
.TP |
| 454 |
.BR PTRACE_O_TRACECLONE " (since Linux 2.5.46)" |
| 455 |
Stop the tracee at the next |
| 456 |
.BR clone (2) |
| 457 |
and automatically start tracing the newly cloned process, |
| 458 |
which will start with a |
| 459 |
.BR SIGSTOP , |
| 460 |
or |
| 461 |
.B PTRACE_EVENT_STOP |
| 462 |
if |
| 463 |
.B PTRACE_SEIZE |
| 464 |
was used. |
| 465 |
A |
| 466 |
.BR waitpid (2) |
| 467 |
by the tracer will return a |
| 468 |
.I status |
| 469 |
value such that |
| 470 |
.IP |
| 471 |
.nf |
| 472 |
status>>8 == (SIGTRAP | (PTRACE_EVENT_CLONE<<8)) |
| 473 |
.fi |
| 474 |
.IP |
| 475 |
The PID of the new process can be retrieved with |
| 476 |
.BR PTRACE_GETEVENTMSG . |
| 477 |
.IP |
| 478 |
This option may not catch |
| 479 |
.BR clone (2) |
| 480 |
calls in all cases. |
| 481 |
If the tracee calls |
| 482 |
.BR clone (2) |
| 483 |
with the |
| 484 |
.B CLONE_VFORK |
| 485 |
flag, |
| 486 |
.B PTRACE_EVENT_VFORK |
| 487 |
will be delivered instead |
| 488 |
if |
| 489 |
.B PTRACE_O_TRACEVFORK |
| 490 |
is set; |
| 491 |
otherwise if the tracee calls |
| 492 |
.BR clone (2) |
| 493 |
with the exit signal set to |
| 494 |
.BR SIGCHLD , |
| 495 |
.B PTRACE_EVENT_FORK |
| 496 |
will be delivered if |
| 497 |
.B PTRACE_O_TRACEFORK |
| 498 |
is set. |
| 499 |
.TP |
| 500 |
.BR PTRACE_O_TRACEEXEC " (since Linux 2.5.46)" |
| 501 |
Stop the tracee at the next |
| 502 |
.BR execve (2). |
| 503 |
A |
| 504 |
.BR waitpid (2) |
| 505 |
by the tracer will return a |
| 506 |
.I status |
| 507 |
value such that |
| 508 |
.IP |
| 509 |
.nf |
| 510 |
status>>8 == (SIGTRAP | (PTRACE_EVENT_EXEC<<8)) |
| 511 |
.fi |
| 512 |
.IP |
| 513 |
If the execing thread is not a thread group leader, |
| 514 |
the thread ID is reset to thread group leader's ID before this stop. |
| 515 |
Since Linux 3.0, the former thread ID can be retrieved with |
| 516 |
.BR PTRACE_GETEVENTMSG . |
| 517 |
.TP |
| 518 |
.BR PTRACE_O_TRACEEXIT " (since Linux 2.5.60)" |
| 519 |
Stop the tracee at exit. |
| 520 |
A |
| 521 |
.BR waitpid (2) |
| 522 |
by the tracer will return a |
| 523 |
.I status |
| 524 |
value such that |
| 525 |
.IP |
| 526 |
.nf |
| 527 |
status>>8 == (SIGTRAP | (PTRACE_EVENT_EXIT<<8)) |
| 528 |
.fi |
| 529 |
.IP |
| 530 |
The tracee's exit status can be retrieved with |
| 531 |
.BR PTRACE_GETEVENTMSG . |
| 532 |
.IP |
| 533 |
The tracee is stopped early during process exit, |
| 534 |
when registers are still available, |
| 535 |
allowing the tracer to see where the exit occurred, |
| 536 |
whereas the normal exit notification is done after the process |
| 537 |
is finished exiting. |
| 538 |
Even though context is available, |
| 539 |
the tracer cannot prevent the exit from happening at this point. |
| 540 |
.TP |
| 541 |
.BR PTRACE_O_TRACEFORK " (since Linux 2.5.46)" |
| 542 |
Stop the tracee at the next |
| 543 |
.BR fork (2) |
| 544 |
and automatically start tracing the newly forked process, |
| 545 |
which will start with a |
| 546 |
.BR SIGSTOP , |
| 547 |
or |
| 548 |
.B PTRACE_EVENT_STOP |
| 549 |
if |
| 550 |
.B PTRACE_SEIZE |
| 551 |
was used. |
| 552 |
A |
| 553 |
.BR waitpid (2) |
| 554 |
by the tracer will return a |
| 555 |
.I status |
| 556 |
value such that |
| 557 |
.IP |
| 558 |
.nf |
| 559 |
status>>8 == (SIGTRAP | (PTRACE_EVENT_FORK<<8)) |
| 560 |
.fi |
| 561 |
.IP |
| 562 |
The PID of the new process can be retrieved with |
| 563 |
.BR PTRACE_GETEVENTMSG . |
| 564 |
.TP |
| 565 |
.BR PTRACE_O_TRACESYSGOOD " (since Linux 2.4.6)" |
| 566 |
When delivering system call traps, set bit 7 in the signal number |
| 567 |
(i.e., deliver |
| 568 |
.IR "SIGTRAP|0x80" ). |
| 569 |
This makes it easy for the tracer to distinguish |
| 570 |
normal traps from those caused by a system call. |
| 571 |
.TP |
| 572 |
.BR PTRACE_O_TRACEVFORK " (since Linux 2.5.46)" |
| 573 |
Stop the tracee at the next |
| 574 |
.BR vfork (2) |
| 575 |
and automatically start tracing the newly vforked process, |
| 576 |
which will start with a |
| 577 |
.BR SIGSTOP , |
| 578 |
or |
| 579 |
.B PTRACE_EVENT_STOP |
| 580 |
if |
| 581 |
.B PTRACE_SEIZE |
| 582 |
was used. |
| 583 |
A |
| 584 |
.BR waitpid (2) |
| 585 |
by the tracer will return a |
| 586 |
.I status |
| 587 |
value such that |
| 588 |
.IP |
| 589 |
.nf |
| 590 |
status>>8 == (SIGTRAP | (PTRACE_EVENT_VFORK<<8)) |
| 591 |
.fi |
| 592 |
.IP |
| 593 |
The PID of the new process can be retrieved with |
| 594 |
.BR PTRACE_GETEVENTMSG . |
| 595 |
.TP |
| 596 |
.BR PTRACE_O_TRACEVFORKDONE " (since Linux 2.5.60)" |
| 597 |
Stop the tracee at the completion of the next |
| 598 |
.BR vfork (2). |
| 599 |
A |
| 600 |
.BR waitpid (2) |
| 601 |
by the tracer will return a |
| 602 |
.I status |
| 603 |
value such that |
| 604 |
.IP |
| 605 |
.nf |
| 606 |
status>>8 == (SIGTRAP | (PTRACE_EVENT_VFORK_DONE<<8)) |
| 607 |
.fi |
| 608 |
.IP |
| 609 |
The PID of the new process can (since Linux 2.6.18) be retrieved with |
| 610 |
.BR PTRACE_GETEVENTMSG . |
| 611 |
.TP |
| 612 |
.BR PTRACE_O_TRACESECCOMP " (since Linux 3.5)" |
| 613 |
Stop the tracee when a |
| 614 |
.BR seccomp (2) |
| 615 |
.B SECCOMP_RET_TRACE |
| 616 |
rule is triggered. |
| 617 |
A |
| 618 |
.BR waitpid (2) |
| 619 |
by the tracer will return a |
| 620 |
.I status |
| 621 |
value such that |
| 622 |
.IP |
| 623 |
.nf |
| 624 |
status>>8 == (SIGTRAP | (PTRACE_EVENT_SECCOMP<<8)) |
| 625 |
.fi |
| 626 |
.IP |
| 627 |
While this triggers a |
| 628 |
.B PTRACE_EVENT |
| 629 |
stop, it is similar to a syscall-enter-stop. |
| 630 |
For details, see the note on |
| 631 |
.B PTRACE_EVENT_SECCOMP |
| 632 |
below. |
| 633 |
The seccomp event message data (from the |
| 634 |
.B SECCOMP_RET_DATA |
| 635 |
portion of the seccomp filter rule) can be retrieved with |
| 636 |
.BR PTRACE_GETEVENTMSG . |
| 637 |
.TP |
| 638 |
.BR PTRACE_O_SUSPEND_SECCOMP " (since Linux 4.3)" |
| 639 |
.\" commit 13c4a90119d28cfcb6b5bdd820c233b86c2b0237 |
| 640 |
Suspend the tracee's seccomp protections. |
| 641 |
This applies regardless of mode, and |
| 642 |
can be used when the tracee has not yet installed seccomp filters. |
| 643 |
That is, a valid use case is to suspend a tracee's seccomp protections |
| 644 |
before they are installed by the tracee, |
| 645 |
let the tracee install the filters, |
| 646 |
and then clear this flag when the filters should be resumed. |
| 647 |
Setting this option requires that the tracer have the |
| 648 |
.B CAP_SYS_ADMIN |
| 649 |
capability, |
| 650 |
not have any seccomp protections installed, and not have |
| 651 |
.B PTRACE_O_SUSPEND_SECCOMP |
| 652 |
set on itself. |
| 653 |
.RE |
| 654 |
.TP |
| 655 |
.BR PTRACE_GETEVENTMSG " (since Linux 2.5.46)" |
| 656 |
Retrieve a message (as an |
| 657 |
.IR "unsigned long" ) |
| 658 |
about the ptrace event |
| 659 |
that just happened, placing it at the address |
| 660 |
.I data |
| 661 |
in the tracer. |
| 662 |
For |
| 663 |
.BR PTRACE_EVENT_EXIT , |
| 664 |
this is the tracee's exit status. |
| 665 |
For |
| 666 |
.BR PTRACE_EVENT_FORK , |
| 667 |
.BR PTRACE_EVENT_VFORK , |
| 668 |
.BR PTRACE_EVENT_VFORK_DONE , |
| 669 |
and |
| 670 |
.BR PTRACE_EVENT_CLONE , |
| 671 |
this is the PID of the new process. |
| 672 |
For |
| 673 |
.BR PTRACE_EVENT_SECCOMP , |
| 674 |
this is the |
| 675 |
.BR seccomp (2) |
| 676 |
filter's |
| 677 |
.B SECCOMP_RET_DATA |
| 678 |
associated with the triggered rule. |
| 679 |
.RI ( addr |
| 680 |
is ignored.) |
| 681 |
.TP |
| 682 |
.B PTRACE_CONT |
| 683 |
Restart the stopped tracee process. |
| 684 |
If |
| 685 |
.I data |
| 686 |
is nonzero, |
| 687 |
it is interpreted as the number of a signal to be delivered to the tracee; |
| 688 |
otherwise, no signal is delivered. |
| 689 |
Thus, for example, the tracer can control |
| 690 |
whether a signal sent to the tracee is delivered or not. |
| 691 |
.RI ( addr |
| 692 |
is ignored.) |
| 693 |
.TP |
| 694 |
.B PTRACE_SYSCALL |
| 695 |
.TQ |
| 696 |
.B PTRACE_SINGLESTEP |
| 697 |
Restart the stopped tracee as for |
| 698 |
.BR PTRACE_CONT , |
| 699 |
but arrange for the tracee to be stopped at |
| 700 |
the next entry to or exit from a system call, |
| 701 |
or after execution of a single instruction, respectively. |
| 702 |
(The tracee will also, as usual, be stopped upon receipt of a signal.) |
| 703 |
From the tracer's perspective, the tracee will appear to have been |
| 704 |
stopped by receipt of a |
| 705 |
.BR SIGTRAP . |
| 706 |
So, for |
| 707 |
.BR PTRACE_SYSCALL , |
| 708 |
for example, the idea is to inspect |
| 709 |
the arguments to the system call at the first stop, |
| 710 |
then do another |
| 711 |
.B PTRACE_SYSCALL |
| 712 |
and inspect the return value of the system call at the second stop. |
| 713 |
The |
| 714 |
.I data |
| 715 |
argument is treated as for |
| 716 |
.BR PTRACE_CONT . |
| 717 |
.RI ( addr |
| 718 |
is ignored.) |
| 719 |
.TP |
| 720 |
.BR PTRACE_SET_SYSCALL " (since Linux 2.6.16)" |
| 721 |
.\" commit 3f471126ee53feb5e9b210ea2f525ed3bb9b7a7f |
| 722 |
When in syscall-enter-stop, |
| 723 |
change the number of the system call that is about to |
| 724 |
be executed to the number specified in the |
| 725 |
.I data |
| 726 |
argument. |
| 727 |
The |
| 728 |
.I addr |
| 729 |
argument is ignored. |
| 730 |
This operation is currently |
| 731 |
.\" As of 4.19-rc2 |
| 732 |
supported only on arm (and arm64, though only for backwards compatibility), |
| 733 |
.\" commit 27aa55c5e5123fa8b8ad0156559d34d7edff58ca |
| 734 |
but most other architectures have other means of accomplishing this |
| 735 |
(usually by changing the register that the userland code passed the |
| 736 |
system call number in). |
| 737 |
.\" see change_syscall in tools/testing/selftests/seccomp/seccomp_bpf.c |
| 738 |
.\" and also strace's linux/*/set_scno.c files. |
| 739 |
.TP |
| 740 |
.B PTRACE_SYSEMU |
| 741 |
.TQ |
| 742 |
.BR PTRACE_SYSEMU_SINGLESTEP " (since Linux 2.6.14)" |
| 743 |
For |
| 744 |
.BR PTRACE_SYSEMU , |
| 745 |
continue and stop on entry to the next system call, |
| 746 |
which will not be executed. |
| 747 |
See the documentation on syscall-stops below. |
| 748 |
For |
| 749 |
.BR PTRACE_SYSEMU_SINGLESTEP , |
| 750 |
do the same but also singlestep if not a system call. |
| 751 |
This call is used by programs like |
| 752 |
User Mode Linux that want to emulate all the tracee's system calls. |
| 753 |
The |
| 754 |
.I data |
| 755 |
argument is treated as for |
| 756 |
.BR PTRACE_CONT . |
| 757 |
The |
| 758 |
.I addr |
| 759 |
argument is ignored. |
| 760 |
These operations are currently |
| 761 |
.\" As at 3.7 |
| 762 |
supported only on x86. |
| 763 |
.TP |
| 764 |
.BR PTRACE_LISTEN " (since Linux 3.4)" |
| 765 |
Restart the stopped tracee, but prevent it from executing. |
| 766 |
The resulting state of the tracee is similar to a process which |
| 767 |
has been stopped by a |
| 768 |
.B SIGSTOP |
| 769 |
(or other stopping signal). |
| 770 |
See the "group-stop" subsection for additional information. |
| 771 |
.B PTRACE_LISTEN |
| 772 |
works only on tracees attached by |
| 773 |
.BR PTRACE_SEIZE . |
| 774 |
.TP |
| 775 |
.B PTRACE_KILL |
| 776 |
Send the tracee a |
| 777 |
.B SIGKILL |
| 778 |
to terminate it. |
| 779 |
.RI ( addr |
| 780 |
and |
| 781 |
.I data |
| 782 |
are ignored.) |
| 783 |
.IP |
| 784 |
.I This operation is deprecated; do not use it! |
| 785 |
Instead, send a |
| 786 |
.B SIGKILL |
| 787 |
directly using |
| 788 |
.BR kill (2) |
| 789 |
or |
| 790 |
.BR tgkill (2). |
| 791 |
The problem with |
| 792 |
.B PTRACE_KILL |
| 793 |
is that it requires the tracee to be in signal-delivery-stop, |
| 794 |
otherwise it may not work |
| 795 |
(i.e., may complete successfully but won't kill the tracee). |
| 796 |
By contrast, sending a |
| 797 |
.B SIGKILL |
| 798 |
directly has no such limitation. |
| 799 |
.\" [Note from Denys Vlasenko: |
| 800 |
.\" deprecation suggested by Oleg Nesterov. He prefers to deprecate it |
| 801 |
.\" instead of describing (and needing to support) PTRACE_KILL's quirks.] |
| 802 |
.TP |
| 803 |
.BR PTRACE_INTERRUPT " (since Linux 3.4)" |
| 804 |
Stop a tracee. |
| 805 |
If the tracee is running or sleeping in kernel space and |
| 806 |
.B PTRACE_SYSCALL |
| 807 |
is in effect, |
| 808 |
the system call is interrupted and syscall-exit-stop is reported. |
| 809 |
(The interrupted system call is restarted when the tracee is restarted.) |
| 810 |
If the tracee was already stopped by a signal and |
| 811 |
.B PTRACE_LISTEN |
| 812 |
was sent to it, |
| 813 |
the tracee stops with |
| 814 |
.B PTRACE_EVENT_STOP |
| 815 |
and |
| 816 |
.I WSTOPSIG(status) |
| 817 |
returns the stop signal. |
| 818 |
If any other ptrace-stop is generated at the same time (for example, |
| 819 |
if a signal is sent to the tracee), this ptrace-stop happens. |
| 820 |
If none of the above applies (for example, if the tracee is running in user |
| 821 |
space), it stops with |
| 822 |
.B PTRACE_EVENT_STOP |
| 823 |
with |
| 824 |
.I WSTOPSIG(status) |
| 825 |
== |
| 826 |
.BR SIGTRAP . |
| 827 |
.B PTRACE_INTERRUPT |
| 828 |
only works on tracees attached by |
| 829 |
.BR PTRACE_SEIZE . |
| 830 |
.TP |
| 831 |
.B PTRACE_ATTACH |
| 832 |
Attach to the process specified in |
| 833 |
.IR pid , |
| 834 |
making it a tracee of the calling process. |
| 835 |
.\" No longer true (removed by Denys Vlasenko, 2011, who remarks: |
| 836 |
.\" "I think it isn't true in non-ancient 2.4 and in Linux 2.6/3.x. |
| 837 |
.\" Basically, it's not true for any Linux in practical use. |
| 838 |
.\" the behavior of the tracee is as if it had done a |
| 839 |
.\" .BR PTRACE_TRACEME . |
| 840 |
.\" The calling process actually becomes the parent of the tracee |
| 841 |
.\" process for most purposes (e.g., it will receive |
| 842 |
.\" notification of tracee events and appears in |
| 843 |
.\" .BR ps (1) |
| 844 |
.\" output as the tracee's parent), but a |
| 845 |
.\" .BR getppid (2) |
| 846 |
.\" by the tracee will still return the PID of the original parent. |
| 847 |
The tracee is sent a |
| 848 |
.BR SIGSTOP , |
| 849 |
but will not necessarily have stopped |
| 850 |
by the completion of this call; |
| 851 |
use |
| 852 |
.BR waitpid (2) |
| 853 |
to wait for the tracee to stop. |
| 854 |
See the "Attaching and detaching" subsection for additional information. |
| 855 |
.RI ( addr |
| 856 |
and |
| 857 |
.I data |
| 858 |
are ignored.) |
| 859 |
.IP |
| 860 |
Permission to perform a |
| 861 |
.B PTRACE_ATTACH |
| 862 |
is governed by a ptrace access mode |
| 863 |
.B PTRACE_MODE_ATTACH_REALCREDS |
| 864 |
check; |
| 865 |
see below. |
| 866 |
.TP |
| 867 |
.BR PTRACE_SEIZE " (since Linux 3.4)" |
| 868 |
.\" |
| 869 |
.\" Noted by Dmitry Levin: |
| 870 |
.\" |
| 871 |
.\" PTRACE_SEIZE was introduced by commit v3.1-rc1~308^2~28, but |
| 872 |
.\" it had to be used along with a temporary flag PTRACE_SEIZE_DEVEL, |
| 873 |
.\" which was removed later by commit v3.4-rc1~109^2~20. |
| 874 |
.\" |
| 875 |
.\" That is, [before] v3.4 we had a test mode of PTRACE_SEIZE API, |
| 876 |
.\" which was not compatible with the current PTRACE_SEIZE API introduced |
| 877 |
.\" in Linux 3.4. |
| 878 |
.\" |
| 879 |
Attach to the process specified in |
| 880 |
.IR pid , |
| 881 |
making it a tracee of the calling process. |
| 882 |
Unlike |
| 883 |
.BR PTRACE_ATTACH , |
| 884 |
.B PTRACE_SEIZE |
| 885 |
does not stop the process. |
| 886 |
Group-stops are reported as |
| 887 |
.B PTRACE_EVENT_STOP |
| 888 |
and |
| 889 |
.I WSTOPSIG(status) |
| 890 |
returns the stop signal. |
| 891 |
Automatically attached children stop with |
| 892 |
.B PTRACE_EVENT_STOP |
| 893 |
and |
| 894 |
.I WSTOPSIG(status) |
| 895 |
returns |
| 896 |
.B SIGTRAP |
| 897 |
instead of having |
| 898 |
.B SIGSTOP |
| 899 |
signal delivered to them. |
| 900 |
.BR execve (2) |
| 901 |
does not deliver an extra |
| 902 |
.BR SIGTRAP . |
| 903 |
Only a |
| 904 |
.BR PTRACE_SEIZE d |
| 905 |
process can accept |
| 906 |
.B PTRACE_INTERRUPT |
| 907 |
and |
| 908 |
.B PTRACE_LISTEN |
| 909 |
commands. |
| 910 |
The "seized" behavior just described is inherited by |
| 911 |
children that are automatically attached using |
| 912 |
.BR PTRACE_O_TRACEFORK , |
| 913 |
.BR PTRACE_O_TRACEVFORK , |
| 914 |
and |
| 915 |
.BR PTRACE_O_TRACECLONE . |
| 916 |
.I addr |
| 917 |
must be zero. |
| 918 |
.I data |
| 919 |
contains a bit mask of ptrace options to activate immediately. |
| 920 |
.IP |
| 921 |
Permission to perform a |
| 922 |
.B PTRACE_SEIZE |
| 923 |
is governed by a ptrace access mode |
| 924 |
.B PTRACE_MODE_ATTACH_REALCREDS |
| 925 |
check; |
| 926 |
see below. |
| 927 |
.\" |
| 928 |
.TP |
| 929 |
.BR PTRACE_SECCOMP_GET_FILTER " (since Linux 4.4)" |
| 930 |
.\" commit f8e529ed941ba2bbcbf310b575d968159ce7e895 |
| 931 |
This operation allows the tracer to dump the tracee's |
| 932 |
classic BPF filters. |
| 933 |
.IP |
| 934 |
.I addr |
| 935 |
is an integer specifying the index of the filter to be dumped. |
| 936 |
The most recently installed filter has the index 0. |
| 937 |
If |
| 938 |
.I addr |
| 939 |
is greater than the number of installed filters, |
| 940 |
the operation fails with the error |
| 941 |
.BR ENOENT . |
| 942 |
.IP |
| 943 |
.I data |
| 944 |
is either a pointer to a |
| 945 |
.I struct sock_filter |
| 946 |
array that is large enough to store the BPF program, |
| 947 |
or NULL if the program is not to be stored. |
| 948 |
.IP |
| 949 |
Upon success, |
| 950 |
the return value is the number of instructions in the BPF program. |
| 951 |
If |
| 952 |
.I data |
| 953 |
was NULL, then this return value can be used to correctly size the |
| 954 |
.I struct sock_filter |
| 955 |
array passed in a subsequent call. |
| 956 |
.IP |
| 957 |
This operation fails with the error |
| 958 |
.B EACCES |
| 959 |
if the caller does not have the |
| 960 |
.B CAP_SYS_ADMIN |
| 961 |
capability or if the caller is in strict or filter seccomp mode. |
| 962 |
If the filter referred to by |
| 963 |
.I addr |
| 964 |
is not a classic BPF filter, the operation fails with the error |
| 965 |
.BR EMEDIUMTYPE . |
| 966 |
.IP |
| 967 |
This operation is available if the kernel was configured with both the |
| 968 |
.B CONFIG_SECCOMP_FILTER |
| 969 |
and the |
| 970 |
.B CONFIG_CHECKPOINT_RESTORE |
| 971 |
options. |
| 972 |
.TP |
| 973 |
.B PTRACE_DETACH |
| 974 |
Restart the stopped tracee as for |
| 975 |
.BR PTRACE_CONT , |
| 976 |
but first detach from it. |
| 977 |
Under Linux, a tracee can be detached in this way regardless |
| 978 |
of which method was used to initiate tracing. |
| 979 |
.RI ( addr |
| 980 |
is ignored.) |
| 981 |
.\" |
| 982 |
.TP |
| 983 |
.BR PTRACE_GET_THREAD_AREA " (since Linux 2.6.0)" |
| 984 |
This operation performs a similar task to |
| 985 |
.BR get_thread_area (2). |
| 986 |
It reads the TLS entry in the GDT whose index is given in |
| 987 |
.IR addr , |
| 988 |
placing a copy of the entry into the |
| 989 |
.I struct user_desc |
| 990 |
pointed to by |
| 991 |
.IR data . |
| 992 |
(By contrast with |
| 993 |
.BR get_thread_area (2), |
| 994 |
the |
| 995 |
.I entry_number |
| 996 |
of the |
| 997 |
.I struct user_desc |
| 998 |
is ignored.) |
| 999 |
.TP |
| 1000 |
.BR PTRACE_SET_THREAD_AREA " (since Linux 2.6.0)" |
| 1001 |
This operation performs a similar task to |
| 1002 |
.BR set_thread_area (2). |
| 1003 |
It sets the TLS entry in the GDT whose index is given in |
| 1004 |
.IR addr , |
| 1005 |
assigning it the data supplied in the |
| 1006 |
.I struct user_desc |
| 1007 |
pointed to by |
| 1008 |
.IR data . |
| 1009 |
(By contrast with |
| 1010 |
.BR set_thread_area (2), |
| 1011 |
the |
| 1012 |
.I entry_number |
| 1013 |
of the |
| 1014 |
.I struct user_desc |
| 1015 |
is ignored; |
| 1016 |
in other words, |
| 1017 |
this ptrace operation can't be used to allocate a free TLS entry.) |
| 1018 |
.TP |
| 1019 |
.BR PTRACE_GET_SYSCALL_INFO " (since Linux 5.3)" |
| 1020 |
.\" commit 201766a20e30f982ccfe36bebfad9602c3ff574a |
| 1021 |
Retrieve information about the system call that caused the stop. |
| 1022 |
The information is placed into the buffer pointed by the |
| 1023 |
.I data |
| 1024 |
argument, which should be a pointer to a buffer of type |
| 1025 |
.IR "struct ptrace_syscall_info" . |
| 1026 |
The |
| 1027 |
.I addr |
| 1028 |
argument contains the size of the buffer pointed to |
| 1029 |
by the |
| 1030 |
.I data |
| 1031 |
argument (i.e., |
| 1032 |
.IR "sizeof(struct ptrace_syscall_info)" ). |
| 1033 |
The return value contains the number of bytes available |
| 1034 |
to be written by the kernel. |
| 1035 |
If the size of the data to be written by the kernel exceeds the size |
| 1036 |
specified by the |
| 1037 |
.I addr |
| 1038 |
argument, the output data is truncated. |
| 1039 |
.IP |
| 1040 |
The |
| 1041 |
.I ptrace_syscall_info |
| 1042 |
structure contains the following fields: |
| 1043 |
.IP |
| 1044 |
.in +4n |
| 1045 |
.EX |
| 1046 |
struct ptrace_syscall_info { |
| 1047 |
__u8 op; /* Type of system call stop */ |
| 1048 |
__u8 reserved; /* Reserved for future use, must be zero */ |
| 1049 |
__u16 flags; /* Reserved for future use, must be zero */ |
| 1050 |
__u32 arch; /* AUDIT_ARCH_* value; see seccomp(2) */ |
| 1051 |
__u64 instruction_pointer; /* CPU instruction pointer */ |
| 1052 |
__u64 stack_pointer; /* CPU stack pointer */ |
| 1053 |
union { |
| 1054 |
struct { /* op == PTRACE_SYSCALL_INFO_ENTRY */ |
| 1055 |
__u64 nr; /* System call number */ |
| 1056 |
__u64 args[6]; /* System call arguments */ |
| 1057 |
} entry; |
| 1058 |
struct { /* op == PTRACE_SYSCALL_INFO_EXIT */ |
| 1059 |
__s64 rval; /* System call return value */ |
| 1060 |
__u8 is_error; /* System call error flag; |
| 1061 |
Boolean: does rval contain |
| 1062 |
an error value (\-ERRCODE) or |
| 1063 |
a nonerror return value? */ |
| 1064 |
} exit; |
| 1065 |
struct { /* op == PTRACE_SYSCALL_INFO_SECCOMP */ |
| 1066 |
__u64 nr; /* System call number */ |
| 1067 |
__u64 args[6]; /* System call arguments */ |
| 1068 |
__u32 ret_data; /* SECCOMP_RET_DATA portion |
| 1069 |
of SECCOMP_RET_TRACE |
| 1070 |
return value */ |
| 1071 |
} seccomp; |
| 1072 |
}; |
| 1073 |
}; |
| 1074 |
.EE |
| 1075 |
.in |
| 1076 |
.IP |
| 1077 |
The |
| 1078 |
.IR op , |
| 1079 |
.IR arch , |
| 1080 |
.IR instruction_pointer , |
| 1081 |
and |
| 1082 |
.I stack_pointer |
| 1083 |
fields are defined for all kinds of ptrace system call stops. |
| 1084 |
The rest of the structure is a union; |
| 1085 |
one should read only those fields |
| 1086 |
that are meaningful for the kind of system call stop specified by the |
| 1087 |
.I op |
| 1088 |
field. |
| 1089 |
.IP |
| 1090 |
The |
| 1091 |
.I op |
| 1092 |
field has one of the following values (defined in |
| 1093 |
.IR <linux/ptrace.h> ) |
| 1094 |
indicating what type of stop occurred and |
| 1095 |
which part of the union is filled: |
| 1096 |
.RS |
| 1097 |
.TP |
| 1098 |
.B PTRACE_SYSCALL_INFO_ENTRY |
| 1099 |
The |
| 1100 |
.I entry |
| 1101 |
component of the union contains information relating to a |
| 1102 |
system call entry stop. |
| 1103 |
.TP |
| 1104 |
.B PTRACE_SYSCALL_INFO_EXIT |
| 1105 |
The |
| 1106 |
.I exit |
| 1107 |
component of the union contains information relating to a |
| 1108 |
system call exit stop. |
| 1109 |
.TP |
| 1110 |
.B PTRACE_SYSCALL_INFO_SECCOMP |
| 1111 |
The |
| 1112 |
.I seccomp |
| 1113 |
component of the union contains information relating to a |
| 1114 |
.B PTRACE_EVENT_SECCOMP |
| 1115 |
stop. |
| 1116 |
.TP |
| 1117 |
.B PTRACE_SYSCALL_INFO_NONE |
| 1118 |
No component of the union contains relevant information. |
| 1119 |
.RE |
| 1120 |
.IP |
| 1121 |
In case of system call entry or exit stops, |
| 1122 |
the data returned by |
| 1123 |
.B PTRACE_GET_SYSCALL_INFO |
| 1124 |
is limited to type |
| 1125 |
.B PTRACE_SYSCALL_INFO_NONE |
| 1126 |
unless |
| 1127 |
.B PTRACE_O_TRACESYSGOOD |
| 1128 |
option is set before the corresponding system call stop has occurred. |
| 1129 |
.TP |
| 1130 |
.BR PTRACE_SET_SYSCALL_INFO " (since Linux 6.16)" |
| 1131 |
.\" commit 26bb32768fe6552de044f782a58b3272073fbfc0 |
| 1132 |
Modify information about the system call that caused the stop. |
| 1133 |
The |
| 1134 |
.I data |
| 1135 |
argument is a pointer to |
| 1136 |
.I struct ptrace_syscall_info |
| 1137 |
that specifies the system call information to be set. |
| 1138 |
The |
| 1139 |
.I addr |
| 1140 |
argument should be set to |
| 1141 |
.IR "sizeof(struct ptrace_syscall_info)" . |
| 1142 |
Only the |
| 1143 |
.IR nr , |
| 1144 |
.IR args , |
| 1145 |
and |
| 1146 |
.I rval |
| 1147 |
fields can be modified. |
| 1148 |
.\" |
| 1149 |
.SS Death under ptrace |
| 1150 |
When a (possibly multithreaded) process receives a killing signal |
| 1151 |
(one whose disposition is set to |
| 1152 |
.B SIG_DFL |
| 1153 |
and whose default action is to kill the process), |
| 1154 |
all threads exit. |
| 1155 |
Tracees report their death to their tracer(s). |
| 1156 |
Notification of this event is delivered via |
| 1157 |
.BR waitpid (2). |
| 1158 |
.P |
| 1159 |
Note that the killing signal will first cause signal-delivery-stop |
| 1160 |
(on one tracee only), |
| 1161 |
and only after it is injected by the tracer |
| 1162 |
(or after it was dispatched to a thread which isn't traced), |
| 1163 |
will death from the signal happen on |
| 1164 |
.I all |
| 1165 |
tracees within a multithreaded process. |
| 1166 |
(The term "signal-delivery-stop" is explained below.) |
| 1167 |
.P |
| 1168 |
.B SIGKILL |
| 1169 |
does not generate signal-delivery-stop and |
| 1170 |
therefore the tracer can't suppress it. |
| 1171 |
.B SIGKILL |
| 1172 |
kills even within system calls |
| 1173 |
(syscall-exit-stop is not generated prior to death by |
| 1174 |
.BR SIGKILL ). |
| 1175 |
The net effect is that |
| 1176 |
.B SIGKILL |
| 1177 |
always kills the process (all its threads), |
| 1178 |
even if some threads of the process are ptraced. |
| 1179 |
.P |
| 1180 |
When the tracee calls |
| 1181 |
.BR _exit (2), |
| 1182 |
it reports its death to its tracer. |
| 1183 |
Other threads are not affected. |
| 1184 |
.P |
| 1185 |
When any thread executes |
| 1186 |
.BR exit_group (2), |
| 1187 |
every tracee in its thread group reports its death to its tracer. |
| 1188 |
.P |
| 1189 |
If the |
| 1190 |
.B PTRACE_O_TRACEEXIT |
| 1191 |
option is on, |
| 1192 |
.B PTRACE_EVENT_EXIT |
| 1193 |
will happen before actual death. |
| 1194 |
This applies to exits via |
| 1195 |
.BR exit (2), |
| 1196 |
.BR exit_group (2), |
| 1197 |
and signal deaths (except |
| 1198 |
.BR SIGKILL , |
| 1199 |
depending on the kernel version; |
| 1200 |
see BUGS below), |
| 1201 |
and when threads are torn down on |
| 1202 |
.BR execve (2) |
| 1203 |
in a multithreaded process. |
| 1204 |
.P |
| 1205 |
The tracer cannot assume that the ptrace-stopped tracee exists. |
| 1206 |
There are many scenarios when the tracee may die while stopped (such as |
| 1207 |
.BR SIGKILL ). |
| 1208 |
Therefore, the tracer must be prepared to handle an |
| 1209 |
.B ESRCH |
| 1210 |
error on any ptrace operation. |
| 1211 |
Unfortunately, the same error is returned if the tracee |
| 1212 |
exists but is not ptrace-stopped |
| 1213 |
(for commands which require a stopped tracee), |
| 1214 |
or if it is not traced by the process which issued the ptrace call. |
| 1215 |
The tracer needs to keep track of the stopped/running state of the tracee, |
| 1216 |
and interpret |
| 1217 |
.B ESRCH |
| 1218 |
as "tracee died unexpectedly" only if it knows that the tracee has |
| 1219 |
been observed to enter ptrace-stop. |
| 1220 |
Note that there is no guarantee that |
| 1221 |
.I waitpid(WNOHANG) |
| 1222 |
will reliably report the tracee's death status if a |
| 1223 |
ptrace operation returned |
| 1224 |
.BR ESRCH . |
| 1225 |
.I waitpid(WNOHANG) |
| 1226 |
may return 0 instead. |
| 1227 |
In other words, the tracee may be "not yet fully dead", |
| 1228 |
but already refusing ptrace operations. |
| 1229 |
.P |
| 1230 |
The tracer can't assume that the tracee |
| 1231 |
.I always |
| 1232 |
ends its life by reporting |
| 1233 |
.I WIFEXITED(status) |
| 1234 |
or |
| 1235 |
.IR WIFSIGNALED(status) ; |
| 1236 |
there are cases where this does not occur. |
| 1237 |
For example, if a thread other than thread group leader does an |
| 1238 |
.BR execve (2), |
| 1239 |
it disappears; |
| 1240 |
its PID will never be seen again, |
| 1241 |
and any subsequent ptrace stops will be reported under |
| 1242 |
the thread group leader's PID. |
| 1243 |
.SS Stopped states |
| 1244 |
A tracee can be in two states: running or stopped. |
| 1245 |
For the purposes of ptrace, a tracee which is blocked in a system call |
| 1246 |
(such as |
| 1247 |
.BR read (2), |
| 1248 |
.BR pause (2), |
| 1249 |
etc.) |
| 1250 |
is nevertheless considered to be running, even if the tracee is blocked |
| 1251 |
for a long time. |
| 1252 |
The state of the tracee after |
| 1253 |
.B PTRACE_LISTEN |
| 1254 |
is somewhat of a gray area: it is not in any ptrace-stop (ptrace commands |
| 1255 |
won't work on it, and it will deliver |
| 1256 |
.BR waitpid (2) |
| 1257 |
notifications), |
| 1258 |
but it also may be considered "stopped" because |
| 1259 |
it is not executing instructions (is not scheduled), and if it was |
| 1260 |
in group-stop before |
| 1261 |
.BR PTRACE_LISTEN , |
| 1262 |
it will not respond to signals until |
| 1263 |
.B SIGCONT |
| 1264 |
is received. |
| 1265 |
.P |
| 1266 |
There are many kinds of states when the tracee is stopped, and in ptrace |
| 1267 |
discussions they are often conflated. |
| 1268 |
Therefore, it is important to use precise terms. |
| 1269 |
.P |
| 1270 |
In this manual page, any stopped state in which the tracee is ready |
| 1271 |
to accept ptrace commands from the tracer is called |
| 1272 |
.IR ptrace-stop . |
| 1273 |
Ptrace-stops can |
| 1274 |
be further subdivided into |
| 1275 |
.IR signal-delivery-stop , |
| 1276 |
.IR group-stop , |
| 1277 |
.IR syscall-stop , |
| 1278 |
.IR "PTRACE_EVENT stops" , |
| 1279 |
and so on. |
| 1280 |
These stopped states are described in detail below. |
| 1281 |
.P |
| 1282 |
When the running tracee enters ptrace-stop, it notifies its tracer using |
| 1283 |
.BR waitpid (2) |
| 1284 |
(or one of the other "wait" system calls). |
| 1285 |
Most of this manual page assumes that the tracer waits with: |
| 1286 |
.P |
| 1287 |
.in +4n |
| 1288 |
.EX |
| 1289 |
pid = waitpid(pid_or_minus_1, &status, __WALL); |
| 1290 |
.EE |
| 1291 |
.in |
| 1292 |
.P |
| 1293 |
Ptrace-stopped tracees are reported as returns with |
| 1294 |
.I pid |
| 1295 |
greater than 0 and |
| 1296 |
.I WIFSTOPPED(status) |
| 1297 |
true. |
| 1298 |
.\" Denys Vlasenko: |
| 1299 |
.\" Do we require __WALL usage, or will just using 0 be ok? (With 0, |
| 1300 |
.\" I am not 100% sure there aren't ugly corner cases.) Are the |
| 1301 |
.\" rules different if user wants to use waitid? Will waitid require |
| 1302 |
.\" WEXITED? |
| 1303 |
.\" |
| 1304 |
.P |
| 1305 |
The |
| 1306 |
.B __WALL |
| 1307 |
flag does not include the |
| 1308 |
.B WSTOPPED |
| 1309 |
and |
| 1310 |
.B WEXITED |
| 1311 |
flags, but implies their functionality. |
| 1312 |
.P |
| 1313 |
Setting the |
| 1314 |
.B WCONTINUED |
| 1315 |
flag when calling |
| 1316 |
.BR waitpid (2) |
| 1317 |
is not recommended: the "continued" state is per-process and |
| 1318 |
consuming it can confuse the real parent of the tracee. |
| 1319 |
.P |
| 1320 |
Use of the |
| 1321 |
.B WNOHANG |
| 1322 |
flag may cause |
| 1323 |
.BR waitpid (2) |
| 1324 |
to return 0 ("no wait results available yet") |
| 1325 |
even if the tracer knows there should be a notification. |
| 1326 |
Example: |
| 1327 |
.P |
| 1328 |
.in +4n |
| 1329 |
.EX |
| 1330 |
errno = 0; |
| 1331 |
ptrace(PTRACE_CONT, pid, 0L, 0L); |
| 1332 |
if (errno == ESRCH) { |
| 1333 |
/* tracee is dead */ |
| 1334 |
r = waitpid(tracee, &status, __WALL | WNOHANG); |
| 1335 |
/* r can still be 0 here! */ |
| 1336 |
} |
| 1337 |
.EE |
| 1338 |
.in |
| 1339 |
.\" FIXME . |
| 1340 |
.\" waitid usage? WNOWAIT? |
| 1341 |
.\" describe how wait notifications queue (or not queue) |
| 1342 |
.P |
| 1343 |
The following kinds of ptrace-stops exist: signal-delivery-stops, |
| 1344 |
group-stops, |
| 1345 |
.B PTRACE_EVENT |
| 1346 |
stops, syscall-stops. |
| 1347 |
They all are reported by |
| 1348 |
.BR waitpid (2) |
| 1349 |
with |
| 1350 |
.I WIFSTOPPED(status) |
| 1351 |
true. |
| 1352 |
They may be differentiated by examining the value |
| 1353 |
.IR status>>8 , |
| 1354 |
and if there is ambiguity in that value, by querying |
| 1355 |
.BR PTRACE_GETSIGINFO . |
| 1356 |
(Note: the |
| 1357 |
.I WSTOPSIG(status) |
| 1358 |
macro can't be used to perform this examination, |
| 1359 |
because it returns the value |
| 1360 |
.IR "(status>>8)\ &\ 0xff" .) |
| 1361 |
.SS Signal-delivery-stop |
| 1362 |
When a (possibly multithreaded) process receives any signal except |
| 1363 |
.BR SIGKILL , |
| 1364 |
the kernel selects an arbitrary thread which handles the signal. |
| 1365 |
(If the signal is generated with |
| 1366 |
.BR tgkill (2), |
| 1367 |
the target thread can be explicitly selected by the caller.) |
| 1368 |
If the selected thread is traced, it enters signal-delivery-stop. |
| 1369 |
At this point, the signal is not yet delivered to the process, |
| 1370 |
and can be suppressed by the tracer. |
| 1371 |
If the tracer doesn't suppress the signal, |
| 1372 |
it passes the signal to the tracee in the next ptrace restart operation. |
| 1373 |
This second step of signal delivery is called |
| 1374 |
.I "signal injection" |
| 1375 |
in this manual page. |
| 1376 |
Note that if the signal is blocked, |
| 1377 |
signal-delivery-stop doesn't happen until the signal is unblocked, |
| 1378 |
with the usual exception that |
| 1379 |
.B SIGSTOP |
| 1380 |
can't be blocked. |
| 1381 |
.P |
| 1382 |
Signal-delivery-stop is observed by the tracer as |
| 1383 |
.BR waitpid (2) |
| 1384 |
returning with |
| 1385 |
.I WIFSTOPPED(status) |
| 1386 |
true, with the signal returned by |
| 1387 |
.IR WSTOPSIG(status) . |
| 1388 |
If the signal is |
| 1389 |
.BR SIGTRAP , |
| 1390 |
this may be a different kind of ptrace-stop; |
| 1391 |
see the "Syscall-stops" and "execve" sections below for details. |
| 1392 |
If |
| 1393 |
.I WSTOPSIG(status) |
| 1394 |
returns a stopping signal, |
| 1395 |
this may be a group-stop; |
| 1396 |
see below. |
| 1397 |
.SS Signal injection and suppression |
| 1398 |
After signal-delivery-stop is observed by the tracer, |
| 1399 |
the tracer should restart the tracee with the call |
| 1400 |
.P |
| 1401 |
.in +4n |
| 1402 |
.EX |
| 1403 |
ptrace(PTRACE_restart, pid, 0, sig) |
| 1404 |
.EE |
| 1405 |
.in |
| 1406 |
.P |
| 1407 |
where |
| 1408 |
.B PTRACE_restart |
| 1409 |
is one of the restarting ptrace operations. |
| 1410 |
If |
| 1411 |
.I sig |
| 1412 |
is 0, then a signal is not delivered. |
| 1413 |
Otherwise, the signal |
| 1414 |
.I sig |
| 1415 |
is delivered. |
| 1416 |
This operation is called |
| 1417 |
.I "signal injection" |
| 1418 |
in this manual page, to distinguish it from signal-delivery-stop. |
| 1419 |
.P |
| 1420 |
The |
| 1421 |
.I sig |
| 1422 |
value may be different from the |
| 1423 |
.I WSTOPSIG(status) |
| 1424 |
value: the tracer can cause a different signal to be injected. |
| 1425 |
.P |
| 1426 |
Note that a suppressed signal still causes system calls to return |
| 1427 |
prematurely. |
| 1428 |
In this case, system calls will be restarted: the tracer will |
| 1429 |
observe the tracee to reexecute the interrupted system call (or |
| 1430 |
.BR restart_syscall (2) |
| 1431 |
system call for a few system calls which use a different mechanism |
| 1432 |
for restarting) if the tracer uses |
| 1433 |
.BR PTRACE_SYSCALL . |
| 1434 |
Even system calls (such as |
| 1435 |
.BR poll (2)) |
| 1436 |
which are not restartable after signal are restarted after |
| 1437 |
signal is suppressed; |
| 1438 |
however, kernel bugs exist which cause some system calls to fail with |
| 1439 |
.B EINTR |
| 1440 |
even though no observable signal is injected to the tracee. |
| 1441 |
.P |
| 1442 |
Restarting ptrace commands issued in ptrace-stops other than |
| 1443 |
signal-delivery-stop are not guaranteed to inject a signal, even if |
| 1444 |
.I sig |
| 1445 |
is nonzero. |
| 1446 |
No error is reported; |
| 1447 |
a nonzero |
| 1448 |
.I sig |
| 1449 |
may simply be ignored. |
| 1450 |
Ptrace users should not try to "create a new signal" this way: |
| 1451 |
use |
| 1452 |
.BR tgkill (2) |
| 1453 |
instead. |
| 1454 |
.P |
| 1455 |
The fact that signal injection operations may be ignored |
| 1456 |
when restarting the tracee after |
| 1457 |
ptrace stops that are not signal-delivery-stops |
| 1458 |
is a cause of confusion among ptrace users. |
| 1459 |
One typical scenario is that the tracer observes group-stop, |
| 1460 |
mistakes it for signal-delivery-stop, restarts the tracee with |
| 1461 |
.P |
| 1462 |
.in +4n |
| 1463 |
.EX |
| 1464 |
ptrace(PTRACE_restart, pid, 0, stopsig) |
| 1465 |
.EE |
| 1466 |
.in |
| 1467 |
.P |
| 1468 |
with the intention of injecting |
| 1469 |
.IR stopsig , |
| 1470 |
but |
| 1471 |
.I stopsig |
| 1472 |
gets ignored and the tracee continues to run. |
| 1473 |
.P |
| 1474 |
The |
| 1475 |
.B SIGCONT |
| 1476 |
signal has a side effect of waking up (all threads of) |
| 1477 |
a group-stopped process. |
| 1478 |
This side effect happens before signal-delivery-stop. |
| 1479 |
The tracer can't suppress this side effect (it can |
| 1480 |
only suppress signal injection, which only causes the |
| 1481 |
.B SIGCONT |
| 1482 |
handler to not be executed in the tracee, if such a handler is installed). |
| 1483 |
In fact, waking up from group-stop may be followed by |
| 1484 |
signal-delivery-stop for signal(s) |
| 1485 |
.I other than |
| 1486 |
.BR SIGCONT , |
| 1487 |
if they were pending when |
| 1488 |
.B SIGCONT |
| 1489 |
was delivered. |
| 1490 |
In other words, |
| 1491 |
.B SIGCONT |
| 1492 |
may be not the first signal observed by the tracee after it was sent. |
| 1493 |
.P |
| 1494 |
Stopping signals cause (all threads of) a process to enter group-stop. |
| 1495 |
This side effect happens after signal injection, and therefore can be |
| 1496 |
suppressed by the tracer. |
| 1497 |
.P |
| 1498 |
In Linux 2.4 and earlier, the |
| 1499 |
.B SIGSTOP |
| 1500 |
signal can't be injected. |
| 1501 |
.\" In the Linux 2.4 sources, in arch/i386/kernel/signal.c::do_signal(), |
| 1502 |
.\" there is: |
| 1503 |
.\" |
| 1504 |
.\" /* The debugger continued. Ignore SIGSTOP. */ |
| 1505 |
.\" if (signr == SIGSTOP) |
| 1506 |
.\" continue; |
| 1507 |
.P |
| 1508 |
.B PTRACE_GETSIGINFO |
| 1509 |
can be used to retrieve a |
| 1510 |
.I siginfo_t |
| 1511 |
structure which corresponds to the delivered signal. |
| 1512 |
.B PTRACE_SETSIGINFO |
| 1513 |
may be used to modify it. |
| 1514 |
If |
| 1515 |
.B PTRACE_SETSIGINFO |
| 1516 |
has been used to alter |
| 1517 |
.IR siginfo_t , |
| 1518 |
the |
| 1519 |
.I si_signo |
| 1520 |
field and the |
| 1521 |
.I sig |
| 1522 |
parameter in the restarting command must match, |
| 1523 |
otherwise the result is undefined. |
| 1524 |
.SS Group-stop |
| 1525 |
When a (possibly multithreaded) process receives a stopping signal, |
| 1526 |
all threads stop. |
| 1527 |
If some threads are traced, they enter a group-stop. |
| 1528 |
Note that the stopping signal will first cause signal-delivery-stop |
| 1529 |
(on one tracee only), and only after it is injected by the tracer |
| 1530 |
(or after it was dispatched to a thread which isn't traced), |
| 1531 |
will group-stop be initiated on |
| 1532 |
.I all |
| 1533 |
tracees within the multithreaded process. |
| 1534 |
As usual, every tracee reports its group-stop separately |
| 1535 |
to the corresponding tracer. |
| 1536 |
.P |
| 1537 |
Group-stop is observed by the tracer as |
| 1538 |
.BR waitpid (2) |
| 1539 |
returning with |
| 1540 |
.I WIFSTOPPED(status) |
| 1541 |
true, with the stopping signal available via |
| 1542 |
.IR WSTOPSIG(status) . |
| 1543 |
The same result is returned by some other classes of ptrace-stops, |
| 1544 |
therefore the recommended practice is to perform the call |
| 1545 |
.P |
| 1546 |
.in +4n |
| 1547 |
.EX |
| 1548 |
ptrace(PTRACE_GETSIGINFO, pid, 0, &siginfo) |
| 1549 |
.EE |
| 1550 |
.in |
| 1551 |
.P |
| 1552 |
The call can be avoided if the signal is not |
| 1553 |
.BR SIGSTOP , |
| 1554 |
.BR SIGTSTP , |
| 1555 |
.BR SIGTTIN , |
| 1556 |
or |
| 1557 |
.BR SIGTTOU ; |
| 1558 |
only these four signals are stopping signals. |
| 1559 |
If the tracer sees something else, it can't be a group-stop. |
| 1560 |
Otherwise, the tracer needs to call |
| 1561 |
.BR PTRACE_GETSIGINFO . |
| 1562 |
If |
| 1563 |
.B PTRACE_GETSIGINFO |
| 1564 |
fails with |
| 1565 |
.BR EINVAL , |
| 1566 |
then it is definitely a group-stop. |
| 1567 |
(Other failure codes are possible, such as |
| 1568 |
.B ESRCH |
| 1569 |
("no such process") if a |
| 1570 |
.B SIGKILL |
| 1571 |
killed the tracee.) |
| 1572 |
.P |
| 1573 |
If tracee was attached using |
| 1574 |
.BR PTRACE_SEIZE , |
| 1575 |
group-stop is indicated by |
| 1576 |
.BR PTRACE_EVENT_STOP : |
| 1577 |
.IR "status>>16 == PTRACE_EVENT_STOP" . |
| 1578 |
This allows detection of group-stops |
| 1579 |
without requiring an extra |
| 1580 |
.B PTRACE_GETSIGINFO |
| 1581 |
call. |
| 1582 |
.P |
| 1583 |
As of Linux 2.6.38, |
| 1584 |
after the tracer sees the tracee ptrace-stop and until it |
| 1585 |
restarts or kills it, the tracee will not run, |
| 1586 |
and will not send notifications (except |
| 1587 |
.B SIGKILL |
| 1588 |
death) to the tracer, even if the tracer enters into another |
| 1589 |
.BR waitpid (2) |
| 1590 |
call. |
| 1591 |
.P |
| 1592 |
The kernel behavior described in the previous paragraph |
| 1593 |
causes a problem with transparent handling of stopping signals. |
| 1594 |
If the tracer restarts the tracee after group-stop, |
| 1595 |
the stopping signal |
| 1596 |
is effectively ignored\[em]the tracee doesn't remain stopped, it runs. |
| 1597 |
If the tracer doesn't restart the tracee before entering into the next |
| 1598 |
.BR waitpid (2), |
| 1599 |
future |
| 1600 |
.B SIGCONT |
| 1601 |
signals will not be reported to the tracer; |
| 1602 |
this would cause the |
| 1603 |
.B SIGCONT |
| 1604 |
signals to have no effect on the tracee. |
| 1605 |
.P |
| 1606 |
Since Linux 3.4, there is a method to overcome this problem: instead of |
| 1607 |
.BR PTRACE_CONT , |
| 1608 |
a |
| 1609 |
.B PTRACE_LISTEN |
| 1610 |
command can be used to restart a tracee in a way where it does not execute, |
| 1611 |
but waits for a new event which it can report via |
| 1612 |
.BR waitpid (2) |
| 1613 |
(such as when |
| 1614 |
it is restarted by a |
| 1615 |
.BR SIGCONT ). |
| 1616 |
.SS PTRACE_EVENT stops |
| 1617 |
If the tracer sets |
| 1618 |
.B PTRACE_O_TRACE_* |
| 1619 |
options, the tracee will enter ptrace-stops called |
| 1620 |
.B PTRACE_EVENT |
| 1621 |
stops. |
| 1622 |
.P |
| 1623 |
.B PTRACE_EVENT |
| 1624 |
stops are observed by the tracer as |
| 1625 |
.BR waitpid (2) |
| 1626 |
returning with |
| 1627 |
.IR WIFSTOPPED(status) , |
| 1628 |
and |
| 1629 |
.I WSTOPSIG(status) |
| 1630 |
returns |
| 1631 |
.B SIGTRAP |
| 1632 |
(or for |
| 1633 |
.BR PTRACE_EVENT_STOP , |
| 1634 |
returns the stopping signal if tracee is in a group-stop). |
| 1635 |
An additional bit is set in the higher byte of the status word: |
| 1636 |
the value |
| 1637 |
.I status>>8 |
| 1638 |
will be |
| 1639 |
.P |
| 1640 |
.in +4n |
| 1641 |
.EX |
| 1642 |
((PTRACE_EVENT_foo<<8) | SIGTRAP). |
| 1643 |
.EE |
| 1644 |
.in |
| 1645 |
.P |
| 1646 |
The following events exist: |
| 1647 |
.TP |
| 1648 |
.B PTRACE_EVENT_VFORK |
| 1649 |
Stop before return from |
| 1650 |
.BR vfork (2) |
| 1651 |
or |
| 1652 |
.BR clone (2) |
| 1653 |
with the |
| 1654 |
.B CLONE_VFORK |
| 1655 |
flag. |
| 1656 |
When the tracee is continued after this stop, it will wait for child to |
| 1657 |
exit/exec before continuing its execution |
| 1658 |
(in other words, the usual behavior on |
| 1659 |
.BR vfork (2)). |
| 1660 |
.TP |
| 1661 |
.B PTRACE_EVENT_FORK |
| 1662 |
Stop before return from |
| 1663 |
.BR fork (2) |
| 1664 |
or |
| 1665 |
.BR clone (2) |
| 1666 |
with the exit signal set to |
| 1667 |
.BR SIGCHLD . |
| 1668 |
.TP |
| 1669 |
.B PTRACE_EVENT_CLONE |
| 1670 |
Stop before return from |
| 1671 |
.BR clone (2). |
| 1672 |
.TP |
| 1673 |
.B PTRACE_EVENT_VFORK_DONE |
| 1674 |
Stop before return from |
| 1675 |
.BR vfork (2) |
| 1676 |
or |
| 1677 |
.BR clone (2) |
| 1678 |
with the |
| 1679 |
.B CLONE_VFORK |
| 1680 |
flag, |
| 1681 |
but after the child unblocked this tracee by exiting or execing. |
| 1682 |
.P |
| 1683 |
For all four stops described above, |
| 1684 |
the stop occurs in the parent (i.e., the tracee), |
| 1685 |
not in the newly created thread. |
| 1686 |
.B PTRACE_GETEVENTMSG |
| 1687 |
can be used to retrieve the new thread's ID. |
| 1688 |
.TP |
| 1689 |
.B PTRACE_EVENT_EXEC |
| 1690 |
Stop before return from |
| 1691 |
.BR execve (2). |
| 1692 |
Since Linux 3.0, |
| 1693 |
.B PTRACE_GETEVENTMSG |
| 1694 |
returns the former thread ID. |
| 1695 |
.TP |
| 1696 |
.B PTRACE_EVENT_EXIT |
| 1697 |
Stop before exit (including death from |
| 1698 |
.BR exit_group (2)), |
| 1699 |
signal death, or exit caused by |
| 1700 |
.BR execve (2) |
| 1701 |
in a multithreaded process. |
| 1702 |
.B PTRACE_GETEVENTMSG |
| 1703 |
returns the exit status. |
| 1704 |
Registers can be examined |
| 1705 |
(unlike when "real" exit happens). |
| 1706 |
The tracee is still alive; |
| 1707 |
it needs to be |
| 1708 |
.BR PTRACE_CONT ed |
| 1709 |
or |
| 1710 |
.BR PTRACE_DETACH ed |
| 1711 |
to finish exiting. |
| 1712 |
.TP |
| 1713 |
.B PTRACE_EVENT_STOP |
| 1714 |
Stop induced by |
| 1715 |
.B PTRACE_INTERRUPT |
| 1716 |
command, or group-stop, or initial ptrace-stop when a new child is attached |
| 1717 |
(only if attached using |
| 1718 |
.BR PTRACE_SEIZE ). |
| 1719 |
.TP |
| 1720 |
.B PTRACE_EVENT_SECCOMP |
| 1721 |
Stop triggered by a |
| 1722 |
.BR seccomp (2) |
| 1723 |
rule on tracee syscall entry when |
| 1724 |
.B PTRACE_O_TRACESECCOMP |
| 1725 |
has been set by the tracer. |
| 1726 |
The seccomp event message data (from the |
| 1727 |
.B SECCOMP_RET_DATA |
| 1728 |
portion of the seccomp filter rule) can be retrieved with |
| 1729 |
.BR PTRACE_GETEVENTMSG . |
| 1730 |
The semantics of this stop are described in |
| 1731 |
detail in a separate section below. |
| 1732 |
.P |
| 1733 |
.B PTRACE_GETSIGINFO |
| 1734 |
on |
| 1735 |
.B PTRACE_EVENT |
| 1736 |
stops returns |
| 1737 |
.B SIGTRAP |
| 1738 |
in |
| 1739 |
.IR si_signo , |
| 1740 |
with |
| 1741 |
.I si_code |
| 1742 |
set to |
| 1743 |
.IR "(event<<8)\ |\ SIGTRAP" . |
| 1744 |
.SS Syscall-stops |
| 1745 |
If the tracee was restarted by |
| 1746 |
.B PTRACE_SYSCALL |
| 1747 |
or |
| 1748 |
.BR PTRACE_SYSEMU , |
| 1749 |
the tracee enters |
| 1750 |
syscall-enter-stop just prior to entering any system call (which |
| 1751 |
will not be executed if the restart was using |
| 1752 |
.BR PTRACE_SYSEMU , |
| 1753 |
regardless of any change made to registers at this point or how the |
| 1754 |
tracee is restarted after this stop). |
| 1755 |
No matter which method caused the syscall-entry-stop, |
| 1756 |
if the tracer restarts the tracee with |
| 1757 |
.BR PTRACE_SYSCALL , |
| 1758 |
the tracee enters syscall-exit-stop when the system call is finished, |
| 1759 |
or if it is interrupted by a signal. |
| 1760 |
(That is, |
| 1761 |
signal-delivery-stop never happens |
| 1762 |
between syscall-enter-stop and syscall-exit-stop; |
| 1763 |
it happens |
| 1764 |
.I after |
| 1765 |
syscall-exit-stop.). |
| 1766 |
If the tracee is continued using any other method (including |
| 1767 |
.BR PTRACE_SYSEMU ), |
| 1768 |
no syscall-exit-stop occurs. |
| 1769 |
Note that all mentions |
| 1770 |
.B PTRACE_SYSEMU |
| 1771 |
apply equally to |
| 1772 |
.BR PTRACE_SYSEMU_SINGLESTEP . |
| 1773 |
.P |
| 1774 |
However, even if the tracee was continued using |
| 1775 |
.BR PTRACE_SYSCALL , |
| 1776 |
it is not guaranteed that the next stop will be a syscall-exit-stop. |
| 1777 |
Other possibilities are that the tracee may stop in a |
| 1778 |
.B PTRACE_EVENT |
| 1779 |
stop (including seccomp stops), exit (if it entered |
| 1780 |
.BR _exit (2) |
| 1781 |
or |
| 1782 |
.BR exit_group (2)), |
| 1783 |
be killed by |
| 1784 |
.BR SIGKILL , |
| 1785 |
or die silently (if it is a thread group leader, the |
| 1786 |
.BR execve (2) |
| 1787 |
happened in another thread, |
| 1788 |
and that thread is not traced by the same tracer; |
| 1789 |
this situation is discussed later). |
| 1790 |
.P |
| 1791 |
Syscall-enter-stop and syscall-exit-stop are observed by the tracer as |
| 1792 |
.BR waitpid (2) |
| 1793 |
returning with |
| 1794 |
.I WIFSTOPPED(status) |
| 1795 |
true, and |
| 1796 |
.I WSTOPSIG(status) |
| 1797 |
giving |
| 1798 |
.BR SIGTRAP . |
| 1799 |
If the |
| 1800 |
.B PTRACE_O_TRACESYSGOOD |
| 1801 |
option was set by the tracer, then |
| 1802 |
.I WSTOPSIG(status) |
| 1803 |
will give the value |
| 1804 |
.IR "(SIGTRAP\ |\ 0x80)" . |
| 1805 |
.P |
| 1806 |
Syscall-stops can be distinguished from signal-delivery-stop with |
| 1807 |
.B SIGTRAP |
| 1808 |
by querying |
| 1809 |
.B PTRACE_GETSIGINFO |
| 1810 |
for the following cases: |
| 1811 |
.TP |
| 1812 |
.IR si_code " <= 0" |
| 1813 |
.B SIGTRAP |
| 1814 |
was delivered as a result of a user-space action, |
| 1815 |
for example, a system call |
| 1816 |
.RB ( tgkill (2), |
| 1817 |
.BR kill (2), |
| 1818 |
.BR sigqueue (3), |
| 1819 |
etc.), |
| 1820 |
expiration of a POSIX timer, |
| 1821 |
change of state on a POSIX message queue, |
| 1822 |
or completion of an asynchronous I/O operation. |
| 1823 |
.TP |
| 1824 |
.IR si_code " == SI_KERNEL (0x80)" |
| 1825 |
.B SIGTRAP |
| 1826 |
was sent by the kernel. |
| 1827 |
.TP |
| 1828 |
.IR si_code " == SIGTRAP or " si_code " == (SIGTRAP|0x80)" |
| 1829 |
This is a syscall-stop. |
| 1830 |
.P |
| 1831 |
However, syscall-stops happen very often (twice per system call), |
| 1832 |
and performing |
| 1833 |
.B PTRACE_GETSIGINFO |
| 1834 |
for every syscall-stop may be somewhat expensive. |
| 1835 |
.P |
| 1836 |
Some architectures allow the cases to be distinguished |
| 1837 |
by examining registers. |
| 1838 |
For example, on x86, |
| 1839 |
.I rax |
| 1840 |
== |
| 1841 |
.RB \- ENOSYS |
| 1842 |
in syscall-enter-stop. |
| 1843 |
Since |
| 1844 |
.B SIGTRAP |
| 1845 |
(like any other signal) always happens |
| 1846 |
.I after |
| 1847 |
syscall-exit-stop, |
| 1848 |
and at this point |
| 1849 |
.I rax |
| 1850 |
almost never contains |
| 1851 |
.RB \- ENOSYS , |
| 1852 |
the |
| 1853 |
.B SIGTRAP |
| 1854 |
looks like "syscall-stop which is not syscall-enter-stop"; |
| 1855 |
in other words, it looks like a |
| 1856 |
"stray syscall-exit-stop" and can be detected this way. |
| 1857 |
But such detection is fragile and is best avoided. |
| 1858 |
.P |
| 1859 |
Using the |
| 1860 |
.B PTRACE_O_TRACESYSGOOD |
| 1861 |
option is the recommended method to distinguish syscall-stops |
| 1862 |
from other kinds of ptrace-stops, |
| 1863 |
since it is reliable and does not incur a performance penalty. |
| 1864 |
.P |
| 1865 |
Syscall-enter-stop and syscall-exit-stop are |
| 1866 |
indistinguishable from each other by the tracer. |
| 1867 |
The tracer needs to keep track of the sequence of |
| 1868 |
ptrace-stops in order to not misinterpret syscall-enter-stop as |
| 1869 |
syscall-exit-stop or vice versa. |
| 1870 |
In general, a syscall-enter-stop is |
| 1871 |
always followed by syscall-exit-stop, |
| 1872 |
.B PTRACE_EVENT |
| 1873 |
stop, or the tracee's death; |
| 1874 |
no other kinds of ptrace-stop can occur in between. |
| 1875 |
However, note that seccomp stops (see below) can cause syscall-exit-stops, |
| 1876 |
without preceding syscall-entry-stops. |
| 1877 |
If seccomp is in use, care needs |
| 1878 |
to be taken not to misinterpret such stops as syscall-entry-stops. |
| 1879 |
.P |
| 1880 |
If after syscall-enter-stop, |
| 1881 |
the tracer uses a restarting command other than |
| 1882 |
.BR PTRACE_SYSCALL , |
| 1883 |
syscall-exit-stop is not generated. |
| 1884 |
.P |
| 1885 |
.B PTRACE_GETSIGINFO |
| 1886 |
on syscall-stops returns |
| 1887 |
.B SIGTRAP |
| 1888 |
in |
| 1889 |
.IR si_signo , |
| 1890 |
with |
| 1891 |
.I si_code |
| 1892 |
set to |
| 1893 |
.B SIGTRAP |
| 1894 |
or |
| 1895 |
.IR (SIGTRAP|0x80) . |
| 1896 |
.\" |
| 1897 |
.SS PTRACE_EVENT_SECCOMP stops (Linux 3.5 to Linux 4.7) |
| 1898 |
The behavior of |
| 1899 |
.B PTRACE_EVENT_SECCOMP |
| 1900 |
stops and their interaction with other kinds |
| 1901 |
of ptrace stops has changed between kernel versions. |
| 1902 |
This documents the behavior |
| 1903 |
from their introduction until Linux 4.7 (inclusive). |
| 1904 |
The behavior in later kernel versions is documented in the next section. |
| 1905 |
.P |
| 1906 |
A |
| 1907 |
.B PTRACE_EVENT_SECCOMP |
| 1908 |
stop occurs whenever a |
| 1909 |
.B SECCOMP_RET_TRACE |
| 1910 |
rule is triggered. |
| 1911 |
This is independent of which methods was used to restart the system call. |
| 1912 |
Notably, seccomp still runs even if the tracee was restarted using |
| 1913 |
.B PTRACE_SYSEMU |
| 1914 |
and this system call is unconditionally skipped. |
| 1915 |
.P |
| 1916 |
Restarts from this stop will behave as if the stop had occurred right |
| 1917 |
before the system call in question. |
| 1918 |
In particular, both |
| 1919 |
.B PTRACE_SYSCALL |
| 1920 |
and |
| 1921 |
.B PTRACE_SYSEMU |
| 1922 |
will normally cause a subsequent syscall-entry-stop. |
| 1923 |
However, if after the |
| 1924 |
.B PTRACE_EVENT_SECCOMP |
| 1925 |
the system call number is negative, |
| 1926 |
both the syscall-entry-stop and the system call itself will be skipped. |
| 1927 |
This means that if the system call number is negative after a |
| 1928 |
.B PTRACE_EVENT_SECCOMP |
| 1929 |
and the tracee is restarted using |
| 1930 |
.BR PTRACE_SYSCALL , |
| 1931 |
the next observed stop will be a syscall-exit-stop, |
| 1932 |
rather than the syscall-entry-stop that might have been expected. |
| 1933 |
.\" |
| 1934 |
.SS PTRACE_EVENT_SECCOMP stops (since Linux 4.8) |
| 1935 |
Starting with Linux 4.8, |
| 1936 |
.\" commit 93e35efb8de45393cf61ed07f7b407629bf698ea |
| 1937 |
the |
| 1938 |
.B PTRACE_EVENT_SECCOMP |
| 1939 |
stop was reordered to occur between syscall-entry-stop and |
| 1940 |
syscall-exit-stop. |
| 1941 |
Note that seccomp no longer runs (and no |
| 1942 |
.B PTRACE_EVENT_SECCOMP |
| 1943 |
will be reported) if the system call is skipped due to |
| 1944 |
.BR PTRACE_SYSEMU . |
| 1945 |
.P |
| 1946 |
Functionally, a |
| 1947 |
.B PTRACE_EVENT_SECCOMP |
| 1948 |
stop functions comparably |
| 1949 |
to a syscall-entry-stop (i.e., continuations using |
| 1950 |
.B PTRACE_SYSCALL |
| 1951 |
will cause syscall-exit-stops, |
| 1952 |
the system call number may be changed and any other modified registers |
| 1953 |
are visible to the to-be-executed system call as well). |
| 1954 |
Note that there may be, |
| 1955 |
but need not have been a preceding syscall-entry-stop. |
| 1956 |
.P |
| 1957 |
After a |
| 1958 |
.B PTRACE_EVENT_SECCOMP |
| 1959 |
stop, seccomp will be rerun, with a |
| 1960 |
.B SECCOMP_RET_TRACE |
| 1961 |
rule now functioning the same as a |
| 1962 |
.BR SECCOMP_RET_ALLOW . |
| 1963 |
Specifically, this means that if registers are not modified during the |
| 1964 |
.B PTRACE_EVENT_SECCOMP |
| 1965 |
stop, the system call will then be allowed. |
| 1966 |
.\" |
| 1967 |
.SS PTRACE_SINGLESTEP stops |
| 1968 |
[Details of these kinds of stops are yet to be documented.] |
| 1969 |
.\" |
| 1970 |
.\" FIXME . |
| 1971 |
.\" document stops occurring with PTRACE_SINGLESTEP |
| 1972 |
.\" |
| 1973 |
.SS Informational and restarting ptrace commands |
| 1974 |
Most ptrace commands (all except |
| 1975 |
.BR PTRACE_ATTACH , |
| 1976 |
.BR PTRACE_SEIZE , |
| 1977 |
.BR PTRACE_TRACEME , |
| 1978 |
.BR PTRACE_INTERRUPT , |
| 1979 |
and |
| 1980 |
.BR PTRACE_KILL ) |
| 1981 |
require the tracee to be in a ptrace-stop, otherwise they fail with |
| 1982 |
.BR ESRCH . |
| 1983 |
.P |
| 1984 |
When the tracee is in ptrace-stop, |
| 1985 |
the tracer can read and write data to |
| 1986 |
the tracee using informational commands. |
| 1987 |
These commands leave the tracee in ptrace-stopped state: |
| 1988 |
.P |
| 1989 |
.in +4n |
| 1990 |
.EX |
| 1991 |
ptrace(PTRACE_PEEKTEXT/PEEKDATA/PEEKUSER, pid, addr, 0); |
| 1992 |
ptrace(PTRACE_POKETEXT/POKEDATA/POKEUSER, pid, addr, long_val); |
| 1993 |
ptrace(PTRACE_GETREGS/GETFPREGS, pid, 0, &struct); |
| 1994 |
ptrace(PTRACE_SETREGS/SETFPREGS, pid, 0, &struct); |
| 1995 |
ptrace(PTRACE_GETREGSET, pid, NT_foo, &iov); |
| 1996 |
ptrace(PTRACE_SETREGSET, pid, NT_foo, &iov); |
| 1997 |
ptrace(PTRACE_GETSIGINFO, pid, 0, &siginfo); |
| 1998 |
ptrace(PTRACE_SETSIGINFO, pid, 0, &siginfo); |
| 1999 |
ptrace(PTRACE_GETEVENTMSG, pid, 0, &long_var); |
| 2000 |
ptrace(PTRACE_SETOPTIONS, pid, 0, PTRACE_O_flags); |
| 2001 |
.EE |
| 2002 |
.in |
| 2003 |
.P |
| 2004 |
Note that some errors are not reported. |
| 2005 |
For example, setting signal information |
| 2006 |
.RI ( siginfo ) |
| 2007 |
may have no effect in some ptrace-stops, yet the call may succeed |
| 2008 |
(return 0 and not set |
| 2009 |
.IR errno ); |
| 2010 |
querying |
| 2011 |
.B PTRACE_GETEVENTMSG |
| 2012 |
may succeed and return some random value if current ptrace-stop |
| 2013 |
is not documented as returning a meaningful event message. |
| 2014 |
.P |
| 2015 |
The call |
| 2016 |
.P |
| 2017 |
.in +4n |
| 2018 |
.EX |
| 2019 |
ptrace(PTRACE_SETOPTIONS, pid, 0, PTRACE_O_flags); |
| 2020 |
.EE |
| 2021 |
.in |
| 2022 |
.P |
| 2023 |
affects one tracee. |
| 2024 |
The tracee's current flags are replaced. |
| 2025 |
Flags are inherited by new tracees created and "auto-attached" via active |
| 2026 |
.BR PTRACE_O_TRACEFORK , |
| 2027 |
.BR PTRACE_O_TRACEVFORK , |
| 2028 |
or |
| 2029 |
.B PTRACE_O_TRACECLONE |
| 2030 |
options. |
| 2031 |
.P |
| 2032 |
Another group of commands makes the ptrace-stopped tracee run. |
| 2033 |
They have the form: |
| 2034 |
.P |
| 2035 |
.in +4n |
| 2036 |
.EX |
| 2037 |
ptrace(cmd, pid, 0, sig); |
| 2038 |
.EE |
| 2039 |
.in |
| 2040 |
.P |
| 2041 |
where |
| 2042 |
.I cmd |
| 2043 |
is |
| 2044 |
.BR PTRACE_CONT , |
| 2045 |
.BR PTRACE_LISTEN , |
| 2046 |
.BR PTRACE_DETACH , |
| 2047 |
.BR PTRACE_SYSCALL , |
| 2048 |
.BR PTRACE_SINGLESTEP , |
| 2049 |
.BR PTRACE_SYSEMU , |
| 2050 |
or |
| 2051 |
.BR PTRACE_SYSEMU_SINGLESTEP . |
| 2052 |
If the tracee is in signal-delivery-stop, |
| 2053 |
.I sig |
| 2054 |
is the signal to be injected (if it is nonzero). |
| 2055 |
Otherwise, |
| 2056 |
.I sig |
| 2057 |
may be ignored. |
| 2058 |
(When restarting a tracee from a ptrace-stop other than signal-delivery-stop, |
| 2059 |
recommended practice is to always pass 0 in |
| 2060 |
.IR sig .) |
| 2061 |
.SS Attaching and detaching |
| 2062 |
A thread can be attached to the tracer using the call |
| 2063 |
.P |
| 2064 |
.in +4n |
| 2065 |
.EX |
| 2066 |
ptrace(PTRACE_ATTACH, pid, 0, 0); |
| 2067 |
.EE |
| 2068 |
.in |
| 2069 |
.P |
| 2070 |
or |
| 2071 |
.P |
| 2072 |
.in +4n |
| 2073 |
.EX |
| 2074 |
ptrace(PTRACE_SEIZE, pid, 0, PTRACE_O_flags); |
| 2075 |
.EE |
| 2076 |
.in |
| 2077 |
.P |
| 2078 |
.B PTRACE_ATTACH |
| 2079 |
sends |
| 2080 |
.B SIGSTOP |
| 2081 |
to this thread. |
| 2082 |
If the tracer wants this |
| 2083 |
.B SIGSTOP |
| 2084 |
to have no effect, it needs to suppress it. |
| 2085 |
Note that if other signals are concurrently sent to |
| 2086 |
this thread during attach, |
| 2087 |
the tracer may see the tracee enter signal-delivery-stop |
| 2088 |
with other signal(s) first! |
| 2089 |
The usual practice is to reinject these signals until |
| 2090 |
.B SIGSTOP |
| 2091 |
is seen, then suppress |
| 2092 |
.B SIGSTOP |
| 2093 |
injection. |
| 2094 |
The design bug here is that a ptrace attach and a concurrently delivered |
| 2095 |
.B SIGSTOP |
| 2096 |
may race and the concurrent |
| 2097 |
.B SIGSTOP |
| 2098 |
may be lost. |
| 2099 |
.\" |
| 2100 |
.\" FIXME Describe how to attach to a thread which is already group-stopped. |
| 2101 |
.P |
| 2102 |
Since attaching sends |
| 2103 |
.B SIGSTOP |
| 2104 |
and the tracer usually suppresses it, this may cause a stray |
| 2105 |
.B EINTR |
| 2106 |
return from the currently executing system call in the tracee, |
| 2107 |
as described in the "Signal injection and suppression" section. |
| 2108 |
.P |
| 2109 |
Since Linux 3.4, |
| 2110 |
.B PTRACE_SEIZE |
| 2111 |
can be used instead of |
| 2112 |
.BR PTRACE_ATTACH . |
| 2113 |
.B PTRACE_SEIZE |
| 2114 |
does not stop the attached process. |
| 2115 |
If you need to stop |
| 2116 |
it after attach (or at any other time) without sending it any signals, |
| 2117 |
use |
| 2118 |
.B PTRACE_INTERRUPT |
| 2119 |
command. |
| 2120 |
.P |
| 2121 |
The operation |
| 2122 |
.P |
| 2123 |
.in +4n |
| 2124 |
.EX |
| 2125 |
ptrace(PTRACE_TRACEME, 0, 0, 0); |
| 2126 |
.EE |
| 2127 |
.in |
| 2128 |
.P |
| 2129 |
turns the calling thread into a tracee. |
| 2130 |
The thread continues to run (doesn't enter ptrace-stop). |
| 2131 |
A common practice is to follow the |
| 2132 |
.B PTRACE_TRACEME |
| 2133 |
with |
| 2134 |
.P |
| 2135 |
.in +4n |
| 2136 |
.EX |
| 2137 |
raise(SIGSTOP); |
| 2138 |
.EE |
| 2139 |
.in |
| 2140 |
.P |
| 2141 |
and allow the parent (which is our tracer now) to observe our |
| 2142 |
signal-delivery-stop. |
| 2143 |
.P |
| 2144 |
If the |
| 2145 |
.BR PTRACE_O_TRACEFORK , |
| 2146 |
.BR PTRACE_O_TRACEVFORK , |
| 2147 |
or |
| 2148 |
.B PTRACE_O_TRACECLONE |
| 2149 |
options are in effect, then children created by, respectively, |
| 2150 |
.BR vfork (2) |
| 2151 |
or |
| 2152 |
.BR clone (2) |
| 2153 |
with the |
| 2154 |
.B CLONE_VFORK |
| 2155 |
flag, |
| 2156 |
.BR fork (2) |
| 2157 |
or |
| 2158 |
.BR clone (2) |
| 2159 |
with the exit signal set to |
| 2160 |
.BR SIGCHLD , |
| 2161 |
and other kinds of |
| 2162 |
.BR clone (2), |
| 2163 |
are automatically attached to the same tracer which traced their parent. |
| 2164 |
.B SIGSTOP |
| 2165 |
is delivered to the children, causing them to enter |
| 2166 |
signal-delivery-stop after they exit the system call which created them. |
| 2167 |
.P |
| 2168 |
Detaching of the tracee is performed by: |
| 2169 |
.P |
| 2170 |
.in +4n |
| 2171 |
.EX |
| 2172 |
ptrace(PTRACE_DETACH, pid, 0, sig); |
| 2173 |
.EE |
| 2174 |
.in |
| 2175 |
.P |
| 2176 |
.B PTRACE_DETACH |
| 2177 |
is a restarting operation; |
| 2178 |
therefore it requires the tracee to be in ptrace-stop. |
| 2179 |
If the tracee is in signal-delivery-stop, a signal can be injected. |
| 2180 |
Otherwise, the |
| 2181 |
.I sig |
| 2182 |
parameter may be silently ignored. |
| 2183 |
.P |
| 2184 |
If the tracee is running when the tracer wants to detach it, |
| 2185 |
the usual solution is to send |
| 2186 |
.B SIGSTOP |
| 2187 |
(using |
| 2188 |
.BR tgkill (2), |
| 2189 |
to make sure it goes to the correct thread), |
| 2190 |
wait for the tracee to stop in signal-delivery-stop for |
| 2191 |
.B SIGSTOP |
| 2192 |
and then detach it (suppressing |
| 2193 |
.B SIGSTOP |
| 2194 |
injection). |
| 2195 |
A design bug is that this can race with concurrent |
| 2196 |
.BR SIGSTOP s. |
| 2197 |
Another complication is that the tracee may enter other ptrace-stops |
| 2198 |
and needs to be restarted and waited for again, until |
| 2199 |
.B SIGSTOP |
| 2200 |
is seen. |
| 2201 |
Yet another complication is to be sure that |
| 2202 |
the tracee is not already ptrace-stopped, |
| 2203 |
because no signal delivery happens while it is\[em]not even |
| 2204 |
.BR SIGSTOP . |
| 2205 |
.\" FIXME Describe how to detach from a group-stopped tracee so that it |
| 2206 |
.\" doesn't run, but continues to wait for SIGCONT. |
| 2207 |
.P |
| 2208 |
If the tracer dies, all tracees are automatically detached and restarted, |
| 2209 |
unless they were in group-stop. |
| 2210 |
Handling of restart from group-stop is currently buggy, |
| 2211 |
but the "as planned" behavior is to leave tracee stopped and waiting for |
| 2212 |
.BR SIGCONT . |
| 2213 |
If the tracee is restarted from signal-delivery-stop, |
| 2214 |
the pending signal is injected. |
| 2215 |
.SS execve(2) under ptrace |
| 2216 |
.\" clone(2) CLONE_THREAD says: |
| 2217 |
.\" If any of the threads in a thread group performs an execve(2), |
| 2218 |
.\" then all threads other than the thread group leader are terminated, |
| 2219 |
.\" and the new program is executed in the thread group leader. |
| 2220 |
.\" |
| 2221 |
When one thread in a multithreaded process calls |
| 2222 |
.BR execve (2), |
| 2223 |
the kernel destroys all other threads in the process, |
| 2224 |
.\" In Linux 3.1 sources, see fs/exec.c::de_thread() |
| 2225 |
and resets the thread ID of the execing thread to the |
| 2226 |
thread group ID (process ID). |
| 2227 |
(Or, to put things another way, when a multithreaded process does an |
| 2228 |
.BR execve (2), |
| 2229 |
at completion of the call, it appears as though the |
| 2230 |
.BR execve (2) |
| 2231 |
occurred in the thread group leader, regardless of which thread did the |
| 2232 |
.BR execve (2).) |
| 2233 |
This resetting of the thread ID looks very confusing to tracers: |
| 2234 |
.IP \[bu] 3 |
| 2235 |
All other threads stop in |
| 2236 |
.B PTRACE_EVENT_EXIT |
| 2237 |
stop, if the |
| 2238 |
.B PTRACE_O_TRACEEXIT |
| 2239 |
option was turned on. |
| 2240 |
Then all other threads except the thread group leader report |
| 2241 |
death as if they exited via |
| 2242 |
.BR _exit (2) |
| 2243 |
with exit code 0. |
| 2244 |
.IP \[bu] |
| 2245 |
The execing tracee changes its thread ID while it is in the |
| 2246 |
.BR execve (2). |
| 2247 |
(Remember, under ptrace, the "pid" returned from |
| 2248 |
.BR waitpid (2), |
| 2249 |
or fed into ptrace calls, is the tracee's thread ID.) |
| 2250 |
That is, the tracee's thread ID is reset to be the same as its process ID, |
| 2251 |
which is the same as the thread group leader's thread ID. |
| 2252 |
.IP \[bu] |
| 2253 |
Then a |
| 2254 |
.B PTRACE_EVENT_EXEC |
| 2255 |
stop happens, if the |
| 2256 |
.B PTRACE_O_TRACEEXEC |
| 2257 |
option was turned on. |
| 2258 |
.IP \[bu] |
| 2259 |
If the thread group leader has reported its |
| 2260 |
.B PTRACE_EVENT_EXIT |
| 2261 |
stop by this time, |
| 2262 |
it appears to the tracer that |
| 2263 |
the dead thread leader "reappears from nowhere". |
| 2264 |
(Note: the thread group leader does not report death via |
| 2265 |
.I WIFEXITED(status) |
| 2266 |
until there is at least one other live thread. |
| 2267 |
This eliminates the possibility that the tracer will see |
| 2268 |
it dying and then reappearing.) |
| 2269 |
If the thread group leader was still alive, |
| 2270 |
for the tracer this may look as if thread group leader |
| 2271 |
returns from a different system call than it entered, |
| 2272 |
or even "returned from a system call even though |
| 2273 |
it was not in any system call". |
| 2274 |
If the thread group leader was not traced |
| 2275 |
(or was traced by a different tracer), then during |
| 2276 |
.BR execve (2) |
| 2277 |
it will appear as if it has become a tracee of |
| 2278 |
the tracer of the execing tracee. |
| 2279 |
.P |
| 2280 |
All of the above effects are the artifacts of |
| 2281 |
the thread ID change in the tracee. |
| 2282 |
.P |
| 2283 |
The |
| 2284 |
.B PTRACE_O_TRACEEXEC |
| 2285 |
option is the recommended tool for dealing with this situation. |
| 2286 |
First, it enables |
| 2287 |
.B PTRACE_EVENT_EXEC |
| 2288 |
stop, |
| 2289 |
which occurs before |
| 2290 |
.BR execve (2) |
| 2291 |
returns. |
| 2292 |
In this stop, the tracer can use |
| 2293 |
.B PTRACE_GETEVENTMSG |
| 2294 |
to retrieve the tracee's former thread ID. |
| 2295 |
(This feature was introduced in Linux 3.0.) |
| 2296 |
Second, the |
| 2297 |
.B PTRACE_O_TRACEEXEC |
| 2298 |
option disables legacy |
| 2299 |
.B SIGTRAP |
| 2300 |
generation on |
| 2301 |
.BR execve (2). |
| 2302 |
.P |
| 2303 |
When the tracer receives |
| 2304 |
.B PTRACE_EVENT_EXEC |
| 2305 |
stop notification, |
| 2306 |
it is guaranteed that except this tracee and the thread group leader, |
| 2307 |
no other threads from the process are alive. |
| 2308 |
.P |
| 2309 |
On receiving the |
| 2310 |
.B PTRACE_EVENT_EXEC |
| 2311 |
stop notification, |
| 2312 |
the tracer should clean up all its internal |
| 2313 |
data structures describing the threads of this process, |
| 2314 |
and retain only one data structure\[em]one which |
| 2315 |
describes the single still running tracee, with |
| 2316 |
.P |
| 2317 |
.in +4n |
| 2318 |
.EX |
| 2319 |
thread ID == thread group ID == process ID. |
| 2320 |
.EE |
| 2321 |
.in |
| 2322 |
.P |
| 2323 |
Example: two threads call |
| 2324 |
.BR execve (2) |
| 2325 |
at the same time: |
| 2326 |
.P |
| 2327 |
.nf |
| 2328 |
*** we get syscall-enter-stop in thread 1: ** |
| 2329 |
PID1 execve("/bin/foo", "foo" <unfinished ...> |
| 2330 |
*** we issue PTRACE_SYSCALL for thread 1 ** |
| 2331 |
*** we get syscall-enter-stop in thread 2: ** |
| 2332 |
PID2 execve("/bin/bar", "bar" <unfinished ...> |
| 2333 |
*** we issue PTRACE_SYSCALL for thread 2 ** |
| 2334 |
*** we get PTRACE_EVENT_EXEC for PID0, we issue PTRACE_SYSCALL ** |
| 2335 |
*** we get syscall-exit-stop for PID0: ** |
| 2336 |
PID0 <...\& execve resumed> ) = 0 |
| 2337 |
.fi |
| 2338 |
.P |
| 2339 |
If the |
| 2340 |
.B PTRACE_O_TRACEEXEC |
| 2341 |
option is |
| 2342 |
.I not |
| 2343 |
in effect for the execing tracee, |
| 2344 |
and if the tracee was |
| 2345 |
.BR PTRACE_ATTACH ed |
| 2346 |
rather that |
| 2347 |
.BR PTRACE_SEIZE d, |
| 2348 |
the kernel delivers an extra |
| 2349 |
.B SIGTRAP |
| 2350 |
to the tracee after |
| 2351 |
.BR execve (2) |
| 2352 |
returns. |
| 2353 |
This is an ordinary signal (similar to one which can be |
| 2354 |
generated by |
| 2355 |
.IR "kill \-TRAP" ), |
| 2356 |
not a special kind of ptrace-stop. |
| 2357 |
Employing |
| 2358 |
.B PTRACE_GETSIGINFO |
| 2359 |
for this signal returns |
| 2360 |
.I si_code |
| 2361 |
set to 0 |
| 2362 |
.RI ( SI_USER ). |
| 2363 |
This signal may be blocked by signal mask, |
| 2364 |
and thus may be delivered (much) later. |
| 2365 |
.P |
| 2366 |
Usually, the tracer (for example, |
| 2367 |
.BR strace (1)) |
| 2368 |
would not want to show this extra post-execve |
| 2369 |
.B SIGTRAP |
| 2370 |
signal to the user, and would suppress its delivery to the tracee (if |
| 2371 |
.B SIGTRAP |
| 2372 |
is set to |
| 2373 |
.BR SIG_DFL , |
| 2374 |
it is a killing signal). |
| 2375 |
However, determining |
| 2376 |
.I which |
| 2377 |
.B SIGTRAP |
| 2378 |
to suppress is not easy. |
| 2379 |
Setting the |
| 2380 |
.B PTRACE_O_TRACEEXEC |
| 2381 |
option or using |
| 2382 |
.B PTRACE_SEIZE |
| 2383 |
and thus suppressing this extra |
| 2384 |
.B SIGTRAP |
| 2385 |
is the recommended approach. |
| 2386 |
.SS Real parent |
| 2387 |
The ptrace API (ab)uses the standard UNIX parent/child signaling over |
| 2388 |
.BR waitpid (2). |
| 2389 |
This used to cause the real parent of the process to stop receiving |
| 2390 |
several kinds of |
| 2391 |
.BR waitpid (2) |
| 2392 |
notifications when the child process is traced by some other process. |
| 2393 |
.P |
| 2394 |
Many of these bugs have been fixed, but as of Linux 2.6.38 several still |
| 2395 |
exist; |
| 2396 |
see BUGS below. |
| 2397 |
.P |
| 2398 |
As of Linux 2.6.38, the following is believed to work correctly: |
| 2399 |
.IP \[bu] 3 |
| 2400 |
exit/death by signal is reported first to the tracer, then, |
| 2401 |
when the tracer consumes the |
| 2402 |
.BR waitpid (2) |
| 2403 |
result, to the real parent (to the real parent only when the |
| 2404 |
whole multithreaded process exits). |
| 2405 |
If the tracer and the real parent are the same process, |
| 2406 |
the report is sent only once. |
| 2407 |
.SH RETURN VALUE |
| 2408 |
On success, the |
| 2409 |
.B PTRACE_PEEK* |
| 2410 |
operations return the requested data (but see NOTES), |
| 2411 |
the |
| 2412 |
.B PTRACE_SECCOMP_GET_FILTER |
| 2413 |
operation returns the number of instructions in the BPF program, |
| 2414 |
the |
| 2415 |
.B PTRACE_GET_SYSCALL_INFO |
| 2416 |
operation returns the number of bytes available to be written by the kernel, |
| 2417 |
and other operations return zero. |
| 2418 |
.P |
| 2419 |
On error, all operations return \-1, and |
| 2420 |
.I errno |
| 2421 |
is set to indicate the error. |
| 2422 |
Since the value returned by a successful |
| 2423 |
.B PTRACE_PEEK* |
| 2424 |
operation may be \-1, the caller must clear |
| 2425 |
.I errno |
| 2426 |
before the call, and then check it afterward |
| 2427 |
to determine whether or not an error occurred. |
| 2428 |
.SH ERRORS |
| 2429 |
.TP |
| 2430 |
.B EBUSY |
| 2431 |
(i386 only) There was an error with allocating or freeing a debug register. |
| 2432 |
.TP |
| 2433 |
.B EFAULT |
| 2434 |
There was an attempt to read from or write to an invalid area in |
| 2435 |
the tracer's or the tracee's memory, |
| 2436 |
probably because the area wasn't mapped or accessible. |
| 2437 |
Unfortunately, under Linux, different variations of this fault |
| 2438 |
will return |
| 2439 |
.B EIO |
| 2440 |
or |
| 2441 |
.B EFAULT |
| 2442 |
more or less arbitrarily. |
| 2443 |
.TP |
| 2444 |
.B EINVAL |
| 2445 |
An attempt was made to set an invalid option. |
| 2446 |
.TP |
| 2447 |
.B EIO |
| 2448 |
.I op |
| 2449 |
is invalid, or an attempt was made to read from or |
| 2450 |
write to an invalid area in the tracer's or the tracee's memory, |
| 2451 |
or there was a word-alignment violation, |
| 2452 |
or an invalid signal was specified during a restart operation. |
| 2453 |
.TP |
| 2454 |
.B EPERM |
| 2455 |
The specified process cannot be traced. |
| 2456 |
This could be because the |
| 2457 |
tracer has insufficient privileges (the required capability is |
| 2458 |
.BR CAP_SYS_PTRACE ); |
| 2459 |
unprivileged processes cannot trace processes that they |
| 2460 |
cannot send signals to or those running |
| 2461 |
set-user-ID/set-group-ID programs, for obvious reasons. |
| 2462 |
Alternatively, the process may already be being traced, |
| 2463 |
or (before Linux 2.6.26) be |
| 2464 |
.BR init (1) |
| 2465 |
(PID 1). |
| 2466 |
.TP |
| 2467 |
.B ESRCH |
| 2468 |
The specified process does not exist, or is not currently being traced |
| 2469 |
by the caller, or is not stopped |
| 2470 |
(for operations that require a stopped tracee). |
| 2471 |
.SH STANDARDS |
| 2472 |
None. |
| 2473 |
.SH HISTORY |
| 2474 |
SVr4, 4.3BSD. |
| 2475 |
.P |
| 2476 |
Before Linux 2.6.26, |
| 2477 |
.\" See commit 00cd5c37afd5f431ac186dd131705048c0a11fdb |
| 2478 |
.BR init (1), |
| 2479 |
the process with PID 1, may not be traced. |
| 2480 |
.SH NOTES |
| 2481 |
Although arguments to |
| 2482 |
.BR ptrace () |
| 2483 |
are interpreted according to the prototype given, |
| 2484 |
glibc currently declares |
| 2485 |
.BR ptrace () |
| 2486 |
as a variadic function with only the |
| 2487 |
.I op |
| 2488 |
argument fixed. |
| 2489 |
It is recommended to always supply four arguments, |
| 2490 |
even if the requested operation does not use them, |
| 2491 |
setting unused/ignored arguments to |
| 2492 |
.I 0L |
| 2493 |
or |
| 2494 |
.IR "(void\ *)\ 0". |
| 2495 |
.P |
| 2496 |
A tracees parent continues to be the tracer even if that tracer calls |
| 2497 |
.BR execve (2). |
| 2498 |
.P |
| 2499 |
The layout of the contents of memory and the USER area are |
| 2500 |
quite operating-system- and architecture-specific. |
| 2501 |
The offset supplied, and the data returned, |
| 2502 |
might not entirely match with the definition of |
| 2503 |
.IR "struct user" . |
| 2504 |
.\" See http://lkml.org/lkml/2008/5/8/375 |
| 2505 |
.P |
| 2506 |
The size of a "word" is determined by the operating-system variant |
| 2507 |
(e.g., for 32-bit Linux it is 32 bits). |
| 2508 |
.P |
| 2509 |
This page documents the way the |
| 2510 |
.BR ptrace () |
| 2511 |
call works currently in Linux. |
| 2512 |
Its behavior differs significantly on other flavors of UNIX. |
| 2513 |
In any case, use of |
| 2514 |
.BR ptrace () |
| 2515 |
is highly specific to the operating system and architecture. |
| 2516 |
.\" |
| 2517 |
.\""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" |
| 2518 |
.\" |
| 2519 |
.SS Ptrace access mode checking |
| 2520 |
Various parts of the kernel-user-space API (not just |
| 2521 |
.BR ptrace () |
| 2522 |
operations), require so-called "ptrace access mode" checks, |
| 2523 |
whose outcome determines whether an operation is permitted |
| 2524 |
(or, in a few cases, causes a "read" operation to return sanitized data). |
| 2525 |
These checks are performed in cases where one process can |
| 2526 |
inspect sensitive information about, |
| 2527 |
or in some cases modify the state of, another process. |
| 2528 |
The checks are based on factors such as the credentials and capabilities |
| 2529 |
of the two processes, |
| 2530 |
whether or not the "target" process is dumpable, |
| 2531 |
and the results of checks performed by any enabled Linux Security Module |
| 2532 |
(LSM)\[em]for example, SELinux, Yama, or Smack\[em]and by the commoncap LSM |
| 2533 |
(which is always invoked). |
| 2534 |
.P |
| 2535 |
Prior to Linux 2.6.27, all access checks were of a single type. |
| 2536 |
Since Linux 2.6.27, |
| 2537 |
.\" commit 006ebb40d3d65338bd74abb03b945f8d60e362bd |
| 2538 |
two access mode levels are distinguished: |
| 2539 |
.TP |
| 2540 |
.B PTRACE_MODE_READ |
| 2541 |
For "read" operations or other operations that are less dangerous, |
| 2542 |
such as: |
| 2543 |
.BR get_robust_list (2); |
| 2544 |
.BR kcmp (2); |
| 2545 |
reading |
| 2546 |
.IR /proc/ pid /auxv , |
| 2547 |
.IR /proc/ pid /environ , |
| 2548 |
or |
| 2549 |
.IR /proc/ pid /stat ; |
| 2550 |
or |
| 2551 |
.BR readlink (2) |
| 2552 |
of a |
| 2553 |
.IR /proc/ pid /ns/* |
| 2554 |
file. |
| 2555 |
.TP |
| 2556 |
.B PTRACE_MODE_ATTACH |
| 2557 |
For "write" operations, or other operations that are more dangerous, |
| 2558 |
such as: ptrace attaching |
| 2559 |
.RB ( PTRACE_ATTACH ) |
| 2560 |
to another process |
| 2561 |
or calling |
| 2562 |
.BR process_vm_writev (2). |
| 2563 |
.RB ( PTRACE_MODE_ATTACH |
| 2564 |
was effectively the default before Linux 2.6.27.) |
| 2565 |
.\" |
| 2566 |
.\" Regarding the above description of the distinction between |
| 2567 |
.\" PTRACE_MODE_READ and PTRACE_MODE_ATTACH, Stephen Smalley notes: |
| 2568 |
.\" |
| 2569 |
.\" That was the intent when the distinction was introduced, but it doesn't |
| 2570 |
.\" appear to have been properly maintained, e.g., there is now a common |
| 2571 |
.\" helper lock_trace() that is used for |
| 2572 |
.\" /proc/pid/{stack,syscall,personality} but checks PTRACE_MODE_ATTACH, and |
| 2573 |
.\" PTRACE_MODE_ATTACH is also used in timerslack_ns_write/show(). Likely |
| 2574 |
.\" should review and make them consistent. There was also some debate |
| 2575 |
.\" about proper handling of /proc/pid/fd. Arguably that one might belong |
| 2576 |
.\" back in the _ATTACH camp. |
| 2577 |
.\" |
| 2578 |
.P |
| 2579 |
Since Linux 4.5, |
| 2580 |
.\" commit caaee6234d05a58c5b4d05e7bf766131b810a657 |
| 2581 |
the above access mode checks are combined (ORed) with |
| 2582 |
one of the following modifiers: |
| 2583 |
.TP |
| 2584 |
.B PTRACE_MODE_FSCREDS |
| 2585 |
Use the caller's filesystem UID and GID (see |
| 2586 |
.BR credentials (7)) |
| 2587 |
or effective capabilities for LSM checks. |
| 2588 |
.TP |
| 2589 |
.B PTRACE_MODE_REALCREDS |
| 2590 |
Use the caller's real UID and GID or permitted capabilities for LSM checks. |
| 2591 |
This was effectively the default before Linux 4.5. |
| 2592 |
.P |
| 2593 |
Because combining one of the credential modifiers with one of |
| 2594 |
the aforementioned access modes is typical, |
| 2595 |
some macros are defined in the kernel sources for the combinations: |
| 2596 |
.TP |
| 2597 |
.B PTRACE_MODE_READ_FSCREDS |
| 2598 |
Defined as |
| 2599 |
.BR "PTRACE_MODE_READ | PTRACE_MODE_FSCREDS" . |
| 2600 |
.TP |
| 2601 |
.B PTRACE_MODE_READ_REALCREDS |
| 2602 |
Defined as |
| 2603 |
.BR "PTRACE_MODE_READ | PTRACE_MODE_REALCREDS" . |
| 2604 |
.TP |
| 2605 |
.B PTRACE_MODE_ATTACH_FSCREDS |
| 2606 |
Defined as |
| 2607 |
.BR "PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS" . |
| 2608 |
.TP |
| 2609 |
.B PTRACE_MODE_ATTACH_REALCREDS |
| 2610 |
Defined as |
| 2611 |
.BR "PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS" . |
| 2612 |
.P |
| 2613 |
One further modifier can be ORed with the access mode: |
| 2614 |
.TP |
| 2615 |
.BR PTRACE_MODE_NOAUDIT " (since Linux 3.3)" |
| 2616 |
.\" commit 69f594a38967f4540ce7a29b3fd214e68a8330bd |
| 2617 |
.\" Just for /proc/pid/stat |
| 2618 |
Don't audit this access mode check. |
| 2619 |
This modifier is employed for ptrace access mode checks |
| 2620 |
(such as checks when reading |
| 2621 |
.IR /proc/ pid /stat ) |
| 2622 |
that merely cause the output to be filtered or sanitized, |
| 2623 |
rather than causing an error to be returned to the caller. |
| 2624 |
In these cases, accessing the file is not a security violation and |
| 2625 |
there is no reason to generate a security audit record. |
| 2626 |
This modifier suppresses the generation of |
| 2627 |
such an audit record for the particular access check. |
| 2628 |
.P |
| 2629 |
Note that all of the |
| 2630 |
.B PTRACE_MODE_* |
| 2631 |
constants described in this subsection are kernel-internal, |
| 2632 |
and not visible to user space. |
| 2633 |
The constant names are mentioned here in order to label the various kinds of |
| 2634 |
ptrace access mode checks that are performed for various system calls |
| 2635 |
and accesses to various pseudofiles (e.g., under |
| 2636 |
.IR /proc ). |
| 2637 |
These names are used in other manual pages to provide a simple |
| 2638 |
shorthand for labeling the different kernel checks. |
| 2639 |
.P |
| 2640 |
The algorithm employed for ptrace access mode checking determines whether |
| 2641 |
the calling process is allowed to perform the corresponding action |
| 2642 |
on the target process. |
| 2643 |
(In the case of opening |
| 2644 |
.IR /proc/ pid |
| 2645 |
files, the "calling process" is the one opening the file, |
| 2646 |
and the process with the corresponding PID is the "target process".) |
| 2647 |
The algorithm is as follows: |
| 2648 |
.IP (1) 5 |
| 2649 |
If the calling thread and the target thread are in the same |
| 2650 |
thread group, access is always allowed. |
| 2651 |
.IP (2) |
| 2652 |
If the access mode specifies |
| 2653 |
.BR PTRACE_MODE_FSCREDS , |
| 2654 |
then, for the check in the next step, |
| 2655 |
employ the caller's filesystem UID and GID. |
| 2656 |
(As noted in |
| 2657 |
.BR credentials (7), |
| 2658 |
the filesystem UID and GID almost always have the same values |
| 2659 |
as the corresponding effective IDs.) |
| 2660 |
.IP |
| 2661 |
Otherwise, the access mode specifies |
| 2662 |
.BR PTRACE_MODE_REALCREDS , |
| 2663 |
so use the caller's real UID and GID for the checks in the next step. |
| 2664 |
(Most APIs that check the caller's UID and GID use the effective IDs. |
| 2665 |
For historical reasons, the |
| 2666 |
.B PTRACE_MODE_REALCREDS |
| 2667 |
check uses the real IDs instead.) |
| 2668 |
.IP (3) |
| 2669 |
Deny access if |
| 2670 |
.I neither |
| 2671 |
of the following is true: |
| 2672 |
.RS |
| 2673 |
.IP \[bu] 3 |
| 2674 |
The real, effective, and saved-set user IDs of the target |
| 2675 |
match the caller's user ID, |
| 2676 |
.I and |
| 2677 |
the real, effective, and saved-set group IDs of the target |
| 2678 |
match the caller's group ID. |
| 2679 |
.IP \[bu] |
| 2680 |
The caller has the |
| 2681 |
.B CAP_SYS_PTRACE |
| 2682 |
capability in the user namespace of the target. |
| 2683 |
.RE |
| 2684 |
.IP (4) |
| 2685 |
Deny access if the target process "dumpable" attribute has a value other than 1 |
| 2686 |
.RB ( SUID_DUMP_USER ; |
| 2687 |
see the discussion of |
| 2688 |
.B PR_SET_DUMPABLE |
| 2689 |
in |
| 2690 |
.BR prctl (2)), |
| 2691 |
and the caller does not have the |
| 2692 |
.B CAP_SYS_PTRACE |
| 2693 |
capability in the user namespace of the target process. |
| 2694 |
.IP (5) |
| 2695 |
The kernel LSM |
| 2696 |
.IR security_ptrace_access_check () |
| 2697 |
interface is invoked to see if ptrace access is permitted. |
| 2698 |
The results depend on the LSM(s). |
| 2699 |
The implementation of this interface in the commoncap LSM performs |
| 2700 |
the following steps: |
| 2701 |
.\" (in cap_ptrace_access_check()): |
| 2702 |
.RS |
| 2703 |
.IP (5.1) 7 |
| 2704 |
If the access mode includes |
| 2705 |
.BR PTRACE_MODE_FSCREDS , |
| 2706 |
then use the caller's |
| 2707 |
.I effective |
| 2708 |
capability set |
| 2709 |
in the following check; |
| 2710 |
otherwise (the access mode specifies |
| 2711 |
.BR PTRACE_MODE_REALCREDS , |
| 2712 |
so) use the caller's |
| 2713 |
.I permitted |
| 2714 |
capability set. |
| 2715 |
.IP (5.2) |
| 2716 |
Deny access if |
| 2717 |
.I neither |
| 2718 |
of the following is true: |
| 2719 |
.RS |
| 2720 |
.IP \[bu] 3 |
| 2721 |
The caller and the target process are in the same user namespace, |
| 2722 |
and the caller's capabilities are a superset of the target process's |
| 2723 |
.I permitted |
| 2724 |
capabilities. |
| 2725 |
.IP \[bu] |
| 2726 |
The caller has the |
| 2727 |
.B CAP_SYS_PTRACE |
| 2728 |
capability in the target process's user namespace. |
| 2729 |
.RE |
| 2730 |
.IP |
| 2731 |
Note that the commoncap LSM does not distinguish between |
| 2732 |
.B PTRACE_MODE_READ |
| 2733 |
and |
| 2734 |
.BR PTRACE_MODE_ATTACH . |
| 2735 |
.RE |
| 2736 |
.IP (6) |
| 2737 |
If access has not been denied by any of the preceding steps, |
| 2738 |
then access is allowed. |
| 2739 |
.\" |
| 2740 |
.\""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" |
| 2741 |
.\" |
| 2742 |
.SS /proc/sys/kernel/yama/ptrace_scope |
| 2743 |
On systems with the Yama Linux Security Module (LSM) installed |
| 2744 |
(i.e., the kernel was configured with |
| 2745 |
.BR CONFIG_SECURITY_YAMA ), |
| 2746 |
the |
| 2747 |
.I /proc/sys/kernel/yama/ptrace_scope |
| 2748 |
file (available since Linux 3.4) |
| 2749 |
.\" commit 2d514487faf188938a4ee4fb3464eeecfbdcf8eb |
| 2750 |
can be used to restrict the ability to trace a process with |
| 2751 |
.BR ptrace () |
| 2752 |
(and thus also the ability to use tools such as |
| 2753 |
.BR strace (1) |
| 2754 |
and |
| 2755 |
.BR gdb (1)). |
| 2756 |
The goal of such restrictions is to prevent attack escalation whereby |
| 2757 |
a compromised process can ptrace-attach to other sensitive processes |
| 2758 |
(e.g., a GPG agent or an SSH session) owned by the user in order |
| 2759 |
to gain additional credentials that may exist in memory |
| 2760 |
and thus expand the scope of the attack. |
| 2761 |
.P |
| 2762 |
More precisely, the Yama LSM limits two types of operations: |
| 2763 |
.IP \[bu] 3 |
| 2764 |
Any operation that performs a ptrace access mode |
| 2765 |
.B PTRACE_MODE_ATTACH |
| 2766 |
check\[em]for example, |
| 2767 |
.BR ptrace () |
| 2768 |
.BR PTRACE_ATTACH . |
| 2769 |
(See the "Ptrace access mode checking" discussion above.) |
| 2770 |
.IP \[bu] |
| 2771 |
.BR ptrace () |
| 2772 |
.BR PTRACE_TRACEME . |
| 2773 |
.P |
| 2774 |
A process that has the |
| 2775 |
.B CAP_SYS_PTRACE |
| 2776 |
capability can update the |
| 2777 |
.I /proc/sys/kernel/yama/ptrace_scope |
| 2778 |
file with one of the following values: |
| 2779 |
.TP |
| 2780 |
0 ("classic ptrace permissions") |
| 2781 |
No additional restrictions on operations that perform |
| 2782 |
.B PTRACE_MODE_ATTACH |
| 2783 |
checks (beyond those imposed by the commoncap and other LSMs). |
| 2784 |
.IP |
| 2785 |
The use of |
| 2786 |
.B PTRACE_TRACEME |
| 2787 |
is unchanged. |
| 2788 |
.TP |
| 2789 |
1 ("restricted ptrace") [default value] |
| 2790 |
When performing an operation that requires a |
| 2791 |
.B PTRACE_MODE_ATTACH |
| 2792 |
check, the calling process must either have the |
| 2793 |
.B CAP_SYS_PTRACE |
| 2794 |
capability in the user namespace of the target process or |
| 2795 |
it must have a predefined relationship with the target process. |
| 2796 |
By default, |
| 2797 |
the predefined relationship is that the target process |
| 2798 |
must be a descendant of the caller. |
| 2799 |
.IP |
| 2800 |
A target process can employ the |
| 2801 |
.BR prctl (2) |
| 2802 |
.B PR_SET_PTRACER |
| 2803 |
operation to declare an additional PID that is allowed to perform |
| 2804 |
.B PTRACE_MODE_ATTACH |
| 2805 |
operations on the target. |
| 2806 |
See the kernel source file |
| 2807 |
.I Documentation/admin\-guide/LSM/Yama.rst |
| 2808 |
for further details. |
| 2809 |
.IP |
| 2810 |
The use of |
| 2811 |
.B PTRACE_TRACEME |
| 2812 |
is unchanged. |
| 2813 |
.TP |
| 2814 |
2 ("admin-only attach") |
| 2815 |
Only processes with the |
| 2816 |
.B CAP_SYS_PTRACE |
| 2817 |
capability in the user namespace of the target process may perform |
| 2818 |
.B PTRACE_MODE_ATTACH |
| 2819 |
operations or trace children that employ |
| 2820 |
.BR PTRACE_TRACEME . |
| 2821 |
.TP |
| 2822 |
3 ("no attach") |
| 2823 |
No process may perform |
| 2824 |
.B PTRACE_MODE_ATTACH |
| 2825 |
operations or trace children that employ |
| 2826 |
.BR PTRACE_TRACEME . |
| 2827 |
.IP |
| 2828 |
Once this value has been written to the file, it cannot be changed. |
| 2829 |
.P |
| 2830 |
With respect to values 1 and 2, |
| 2831 |
note that creating a new user namespace effectively removes the |
| 2832 |
protection offered by Yama. |
| 2833 |
This is because a process in the parent user namespace whose effective |
| 2834 |
UID matches the UID of the creator of a child namespace |
| 2835 |
has all capabilities (including |
| 2836 |
.BR CAP_SYS_PTRACE ) |
| 2837 |
when performing operations within the child user namespace |
| 2838 |
(and further-removed descendants of that namespace). |
| 2839 |
Consequently, when a process tries to use user namespaces to sandbox itself, |
| 2840 |
it inadvertently weakens the protections offered by the Yama LSM. |
| 2841 |
.\" |
| 2842 |
.\""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" |
| 2843 |
.\" |
| 2844 |
.SS C library/kernel differences |
| 2845 |
At the system call level, the |
| 2846 |
.BR PTRACE_PEEKTEXT , |
| 2847 |
.BR PTRACE_PEEKDATA , |
| 2848 |
and |
| 2849 |
.B PTRACE_PEEKUSER |
| 2850 |
operations have a different API: they store the result |
| 2851 |
at the address specified by the |
| 2852 |
.I data |
| 2853 |
parameter, and the return value is the error flag. |
| 2854 |
The glibc wrapper function provides the API given in DESCRIPTION above, |
| 2855 |
with the result being returned via the function return value. |
| 2856 |
.SH BUGS |
| 2857 |
On hosts with Linux 2.6 kernel headers, |
| 2858 |
.B PTRACE_SETOPTIONS |
| 2859 |
is declared with a different value than the one for Linux 2.4. |
| 2860 |
This leads to applications compiled with Linux 2.6 kernel |
| 2861 |
headers failing when run on Linux 2.4. |
| 2862 |
This can be worked around by redefining |
| 2863 |
.B PTRACE_SETOPTIONS |
| 2864 |
to |
| 2865 |
.BR PTRACE_OLDSETOPTIONS , |
| 2866 |
if that is defined. |
| 2867 |
.P |
| 2868 |
Group-stop notifications are sent to the tracer, but not to real parent. |
| 2869 |
Last confirmed on 2.6.38.6. |
| 2870 |
.P |
| 2871 |
If a thread group leader is traced and exits by calling |
| 2872 |
.BR _exit (2), |
| 2873 |
.\" Note from Denys Vlasenko: |
| 2874 |
.\" Here "exits" means any kind of death - _exit, exit_group, |
| 2875 |
.\" signal death. Signal death and exit_group cases are trivial, |
| 2876 |
.\" though: since signal death and exit_group kill all other threads |
| 2877 |
.\" too, "until all other threads exit" thing happens rather soon |
| 2878 |
.\" in these cases. Therefore, only _exit presents observably |
| 2879 |
.\" puzzling behavior to ptrace users: thread leader _exit's, |
| 2880 |
.\" but WIFEXITED isn't reported! We are trying to explain here |
| 2881 |
.\" why it is so. |
| 2882 |
a |
| 2883 |
.B PTRACE_EVENT_EXIT |
| 2884 |
stop will happen for it (if requested), but the subsequent |
| 2885 |
.B WIFEXITED |
| 2886 |
notification will not be delivered until all other threads exit. |
| 2887 |
As explained above, if one of other threads calls |
| 2888 |
.BR execve (2), |
| 2889 |
the death of the thread group leader will |
| 2890 |
.I never |
| 2891 |
be reported. |
| 2892 |
If the execed thread is not traced by this tracer, |
| 2893 |
the tracer will never know that |
| 2894 |
.BR execve (2) |
| 2895 |
happened. |
| 2896 |
One possible workaround is to |
| 2897 |
.B PTRACE_DETACH |
| 2898 |
the thread group leader instead of restarting it in this case. |
| 2899 |
Last confirmed on 2.6.38.6. |
| 2900 |
.\" FIXME . need to test/verify this scenario |
| 2901 |
.P |
| 2902 |
A |
| 2903 |
.B SIGKILL |
| 2904 |
signal may still cause a |
| 2905 |
.B PTRACE_EVENT_EXIT |
| 2906 |
stop before actual signal death. |
| 2907 |
This may be changed in the future; |
| 2908 |
.B SIGKILL |
| 2909 |
is meant to always immediately kill tasks even under ptrace. |
| 2910 |
Last confirmed on Linux 3.13. |
| 2911 |
.P |
| 2912 |
Some system calls return with |
| 2913 |
.B EINTR |
| 2914 |
if a signal was sent to a tracee, but delivery was suppressed by the tracer. |
| 2915 |
(This is very typical operation: it is usually |
| 2916 |
done by debuggers on every attach, in order to not introduce |
| 2917 |
a bogus |
| 2918 |
.BR SIGSTOP ). |
| 2919 |
As of Linux 3.2.9, the following system calls are affected |
| 2920 |
(this list is likely incomplete): |
| 2921 |
.BR epoll_wait (2), |
| 2922 |
and |
| 2923 |
.BR read (2) |
| 2924 |
from an |
| 2925 |
.BR inotify (7) |
| 2926 |
file descriptor. |
| 2927 |
The usual symptom of this bug is that when you attach to |
| 2928 |
a quiescent process with the command |
| 2929 |
.P |
| 2930 |
.in +4n |
| 2931 |
.EX |
| 2932 |
strace \-p <process\-ID> |
| 2933 |
.EE |
| 2934 |
.in |
| 2935 |
.P |
| 2936 |
then, instead of the usual |
| 2937 |
and expected one-line output such as |
| 2938 |
.P |
| 2939 |
.in +4n |
| 2940 |
.EX |
| 2941 |
restart_syscall(<...\& resuming interrupted call ...>_ |
| 2942 |
.EE |
| 2943 |
.in |
| 2944 |
.P |
| 2945 |
or |
| 2946 |
.P |
| 2947 |
.in +4n |
| 2948 |
.EX |
| 2949 |
select(6, [5], NULL, [5], NULL_ |
| 2950 |
.EE |
| 2951 |
.in |
| 2952 |
.P |
| 2953 |
('_' denotes the cursor position), you observe more than one line. |
| 2954 |
For example: |
| 2955 |
.P |
| 2956 |
.in +4n |
| 2957 |
.EX |
| 2958 |
clock_gettime(CLOCK_MONOTONIC, {15370, 690928118}) = 0 |
| 2959 |
epoll_wait(4,_ |
| 2960 |
.EE |
| 2961 |
.in |
| 2962 |
.P |
| 2963 |
What is not visible here is that the process was blocked in |
| 2964 |
.BR epoll_wait (2) |
| 2965 |
before |
| 2966 |
.BR strace (1) |
| 2967 |
has attached to it. |
| 2968 |
Attaching caused |
| 2969 |
.BR epoll_wait (2) |
| 2970 |
to return to user space with the error |
| 2971 |
.BR EINTR . |
| 2972 |
In this particular case, the program reacted to |
| 2973 |
.B EINTR |
| 2974 |
by checking the current time, and then executing |
| 2975 |
.BR epoll_wait (2) |
| 2976 |
again. |
| 2977 |
(Programs which do not expect such "stray" |
| 2978 |
.B EINTR |
| 2979 |
errors may behave in an unintended way upon an |
| 2980 |
.BR strace (1) |
| 2981 |
attach.) |
| 2982 |
.P |
| 2983 |
Contrary to the normal rules, the glibc wrapper for |
| 2984 |
.BR ptrace () |
| 2985 |
can set |
| 2986 |
.I errno |
| 2987 |
to zero. |
| 2988 |
.SH SEE ALSO |
| 2989 |
.BR gdb (1), |
| 2990 |
.BR ltrace (1), |
| 2991 |
.BR strace (1), |
| 2992 |
.BR clone (2), |
| 2993 |
.BR execve (2), |
| 2994 |
.BR fork (2), |
| 2995 |
.BR gettid (2), |
| 2996 |
.BR prctl (2), |
| 2997 |
.BR seccomp (2), |
| 2998 |
.BR sigaction (2), |
| 2999 |
.BR tgkill (2), |
| 3000 |
.BR vfork (2), |
| 3001 |
.BR waitpid (2), |
| 3002 |
.BR exec (3), |
| 3003 |
.BR capabilities (7), |
| 3004 |
.BR signal (7) |