Date: Tue, 9 Mar 2021 19:17:31 -0800 From: Mark Millard <marklmi@yahoo.com> To: freebsd-arm <freebsd-arm@freebsd.org>, freebsd-current <freebsd-current@freebsd.org> Subject: FYI: main (bad9fa56620e based): some unexpected SIGSEGV's are tied to interrupted system calls while using poudriere-devel to build armv7 ports on aarch64 Message-ID: <B376F90B-57E8-42C4-93EB-EDABC962C380@yahoo.com> References: <B376F90B-57E8-42C4-93EB-EDABC962C380.ref@yahoo.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Using the quickest to so-far-reliably-fail type of example from
another thread I used truss to see what happens, here filtered
down to two processes that appear to be involved and only
near the failure. (The overall truss output is huge from the
prior activity in the poudriere bulk relatated activity). Also,
this initiated watching from aarch64 but the failing code is
armv7.
83630 100199: #340(0x1,0xffffd18c,0xffffd17c) =3D 0 (0x0)
83630 100199: #416(0x14,0xffffd1b4,0xffffd19c) =3D 0 (0x0)
83630 100199: #7(0xffffffff,0xffffd178,0x1,0x0) =3D 0 (0x0)
83731 100161: #240(0xffffd5f0,0xffffd5f0) =3D 0 (0x0)
83731 100161: #1(0x0) =20
83731 100161: process exit, rval =3D 0
83630 100199: SIGNAL 20 (SIGCHLD) code=3DCLD_EXITED pid=3D83731 uid=3D0 =
status=3D0
83630 100199: #341(0xffffd17c) ERR#4 'Interrupted =
system call'
83630 100199: SIGNAL 11 (SIGSEGV) code=3DSEGV_MAPERR trapno=3D36 =
addr=3D0xffffffe1
83630 100199: process killed, signal =3D 11 (core dumped)
As a reminder of the lldb backtrace of the sh.core
and the like:
(lldb) bt
* thread #1, name =3D 'sh', stop reason =3D signal SIGSEGV
* frame #0: 0xffffe190
frame #1: 0x00031aa8 sh`waitcmdloop(job=3D0x00064230) at =
jobs.c:608:11
frame #2: 0x00031a24 sh`waitcmd(argc=3D<unavailable>, =
argv=3D<unavailable>) at jobs.c:554:13
frame #3: 0x00028f54 sh`evalcommand(cmd=3D0x400ad0e4, =
flags=3D<unavailable>, backcmd=3D0x00000000) at eval.c:1107:16
frame #4: 0x00027800 sh`evaltree(n=3D0x400ad0e4, =
flags=3D<unavailable>) at eval.c:289:4
frame #5: 0x000344d0 sh`cmdloop(top=3D1) at main.c:221:4
frame #6: 0x000342f4 sh`main(argc=3D<unavailable>, =
argv=3D<unavailable>) at main.c:168:3
frame #7: 0x0002480c sh`__start(argc=3D8, argv=3D<unavailable>, =
env=3D<unavailable>, ps_strings=3D<unavailable>, obj=3D0x400b4004, =
cleanup=3D0x40081aa0) at crt1_c.c:92:7
(lldb) up
frame #1: 0x00031aa8 sh`waitcmdloop(job=3D0x00064230) at jobs.c:608:11
605 break;
606 }
607 }
-> 608 } while (dowait(DOWAIT_BLOCK | DOWAIT_SIG, (struct job =
*)NULL) !=3D -1);
609 =09
610 sig =3D pendingsig_waitcmd;
611 pendingsig_waitcmd =3D 0;
(lldb) disass
sh`waitcmdloop:
0x31a54 <+0>: push {r4, r5, r6, r7, r8, r9, r10, r11, lr}
0x31a58 <+4>: add r11, sp, #28
0x31a5c <+8>: sub sp, sp, #4
0x31a60 <+12>: movw r6, #0x3ea0
0x31a64 <+16>: movw r7, #0x3e9c
0x31a68 <+20>: movw r9, #0x4040
0x31a6c <+24>: movw r8, #0x3ea4
0x31a70 <+28>: mov r4, r0
0x31a74 <+32>: movt r6, #0x6
0x31a78 <+36>: movt r7, #0x6
0x31a7c <+40>: movt r9, #0x6
0x31a80 <+44>: mov r10, #0
0x31a84 <+48>: movt r8, #0x6
0x31a88 <+52>: cmp r4, #0
0x31a8c <+56>: beq 0x31ab4 ; <+96> at =
jobs.c:590:37
0x31a90 <+60>: ldrb r0, [r4, #0x18]
0x31a94 <+64>: cmp r0, #2
0x31a98 <+68>: beq 0x31b84 ; <+304> [inlined] =
getjobstatus at jobs.c:575
0x31a9c <+72>: mov r0, #3
0x31aa0 <+76>: mov r1, #0
0x31aa4 <+80>: bl 0x32bcc ; dowait at =
jobs.c:1142
-> 0x31aa8 <+84>: cmn r0, #1
For reference a local context around the
SIGSEGV looks like (all lines in the range
selected):
. . .
83833 102738: fcntl(2,F_DUPFD_CLOEXEC,0xa) =3D 10 (0xa)
83833 102738: openat(AT_FDCWD,"/dev/null",O_WRONLY|O_CREAT|O_TRUNC,0666) =
=3D 3 (0x3)
83833 102738: dup2(3,2) =3D 2 (0x2)
83833 102738: close(3) =3D 0 (0x0)
83833 102738: unlink("./.data.json.SYR1bCaL") =3D 0 (0x0)
83833 102738: dup2(10,2) =3D 2 (0x2)
83833 102738: close(10) =3D 0 (0x0)
83833 102738: exit(0x0) =20
83833 102738: process exit, rval =3D 0
77872 100638: wait4(-1,{ EXITED,val=3D0 },0x0,0x0) =3D 83833 (0x14779)
77872 100638: fcntl(0,F_DUPFD_CLOEXEC,0xa) =3D 10 (0xa)
77872 100638: =
openat(AT_FDCWD,"/var/run/poudriere/lock-poudriere-shared-json_top.pid",O_=
RDONLY,00) =3D 3 (0x3)
77872 100638: dup2(3,0) =3D 0 (0x0)
77872 100638: close(3) =3D 0 (0x0)
77872 100638: fcntl(2,F_DUPFD_CLOEXEC,0xa) =3D 11 (0xb)
77872 100638: openat(AT_FDCWD,"/dev/null",O_WRONLY|O_CREAT|O_TRUNC,0666) =
=3D 3 (0x3)
77872 100638: dup2(3,2) =3D 2 (0x2)
77872 100638: close(3) =3D 0 (0x0)
77872 100638: lseek(0,0x0,SEEK_CUR) =3D 0 (0x0)
77872 100638: read(0,"77563",1024) =3D 5 (0x5)
77872 100638: read(0,0xffffffffb9e8,1024) =3D 0 (0x0)
77872 100638: dup2(10,0) =3D 0 (0x0)
77872 100638: close(10) =3D 0 (0x0)
77872 100638: dup2(11,2) =3D 2 (0x2)
77872 100638: close(11) =3D 0 (0x0)
77872 100638: fcntl(2,F_DUPFD_CLOEXEC,0xa) =3D 10 (0xa)
77872 100638: openat(AT_FDCWD,"/dev/null",O_WRONLY|O_CREAT|O_TRUNC,0666) =
=3D 3 (0x3)
77872 100638: dup2(3,2) =3D 2 (0x2)
77872 100638: close(3) =3D 0 (0x0)
77872 100638: rmdir("/var/run/poudriere/lock-poudriere-shared-json_top") =
=3D 0 (0x0)
77872 100638: dup2(10,2) =3D 2 (0x2)
77872 100638: close(10) =3D 0 (0x0)
77872 100638: sigprocmask(SIG_SETMASK,{ },0x0) =3D 0 (0x0)
77872 100638: fcntl(2,F_DUPFD_CLOEXEC,0xa) =3D 10 (0xa)
77872 100638: openat(AT_FDCWD,"/dev/null",O_WRONLY|O_CREAT|O_TRUNC,0666) =
=3D 3 (0x3)
77872 100638: dup2(3,2) =3D 2 (0x2)
77872 100638: close(3) =3D 0 (0x0)
77872 100638: sigaction(SIGINFO,{ 0x239c30 SA_RESTART ss_t },{ SIG_DFL =
0x0 ss_t }) =3D 0 (0x0)
83731 100161: #240(0xffffd5f0,0xffffd5f0) =3D 0 (0x0)
-- UNKNOWN FreeBSD32 SYSCALL 1 --
83731 100161: #1(0x0) =20
83731 100161: process exit, rval =3D 0
83630 100199: SIGNAL 20 (SIGCHLD) code=3DCLD_EXITED pid=3D83731 uid=3D0 =
status=3D0
83630 100199: #341(0xffffd17c) ERR#4 'Interrupted =
system call'
83630 100199: SIGNAL 11 (SIGSEGV) code=3DSEGV_MAPERR trapno=3D36 =
addr=3D0xffffffe1
83630 100199: process killed, signal =3D 11 (core dumped)
83316 100123: #7(0xffffffff,0xffffca58,0x0,0x0) =3D 83630 (0x146ae)
-- UNKNOWN FreeBSD32 SYSCALL 477 --
83316 100123: =
#477(0x0,0x7000,0x3,0xc001002,0xffffffff,0x40401428,0x0,0x0) =3D =
1077833728 (0x403e7000)
-- UNKNOWN FreeBSD32 SYSCALL 552 --
83316 100123: #552(0xffffff9c,0xffffc504,0xffffc908,0x0) ERR#2 'No such =
file or directory'
-- UNKNOWN FreeBSD32 SYSCALL 552 --
83316 100123: #552(0xffffff9c,0xffffc504,0xffffc908,0x0) ERR#2 'No such =
file or directory'
-- UNKNOWN FreeBSD32 SYSCALL 552 --
83316 100123: #552(0xffffff9c,0xffffc504,0xffffc908,0x0) ERR#2 'No such =
file or directory'
-- UNKNOWN FreeBSD32 SYSCALL 552 --
83316 100123: #552(0xffffff9c,0xffffc504,0xffffc908,0x0) ERR#2 'No such =
file or directory'
-- UNKNOWN FreeBSD32 SYSCALL 477 --
83316 100123: =
#477(0x0,0x1000,0x3,0xc001002,0xffffffff,0x40401428,0x0,0x0) =3D =
1077862400 (0x403ee000)
-- UNKNOWN FreeBSD32 SYSCALL 4 --
83316 100123: #4(0x2,0x403ee000,0x21) =3D 33 (0x21)
-- UNKNOWN FreeBSD32 SYSCALL 477 --
83316 100123: =
#477(0x0,0x1000,0x3,0xc001002,0xffffffff,0x40401428,0x0,0x0) =3D =
1077866496 (0x403ef000)
-- UNKNOWN FreeBSD32 SYSCALL 477 --
83316 100123: =
#477(0x0,0x1000,0x3,0xc001002,0xffffffff,0x40401428,0x0,0x0) =3D =
1077870592 (0x403f0000)
-- UNKNOWN FreeBSD32 SYSCALL 477 --
83316 100123: =
#477(0x0,0x1000,0x3,0xc001002,0xffffffff,0x40401428,0x0,0x0) =3D =
1077874688 (0x403f1000)
-- UNKNOWN FreeBSD32 SYSCALL 4 --
83316 100123: #4(0x1,0x403ef000,0x2e) =3D 46 (0x2e)
-- UNKNOWN FreeBSD32 SYSCALL 542 --
83316 100123: #542(0xffffcd54,0x0) =3D 0 (0x0)
-- UNKNOWN FreeBSD32 SYSCALL 2 --
83842 100199: <new process>
83316 100123: #2() =3D 83842 (0x14782)
-- UNKNOWN FreeBSD32 SYSCALL 6 --
-- UNKNOWN FreeBSD32 SYSCALL 6 --
83316 100123: #6(0x7) =3D 0 (0x0)
83842 100199: #6(0x5) =3D 0 (0x0)
. . .
=3D=3D=3D
Mark Millard
marklmi at yahoo.com
( dsl-only.net went
away in early 2018-Mar)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?B376F90B-57E8-42C4-93EB-EDABC962C380>