From: Jens Remus <jremus@linux.ibm.com>
To: Josh Poimboeuf <jpoimboe@kernel.org>, x86@kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>,
Steven Rostedt <rostedt@goodmis.org>,
Ingo Molnar <mingo@kernel.org>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
linux-kernel@vger.kernel.org,
Indu Bhagat <indu.bhagat@oracle.com>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
linux-perf-users@vger.kernel.org, Mark Brown <broonie@kernel.org>,
linux-toolchains@vger.kernel.org, Jordan Rome <jordalgo@meta.com>,
Sam James <sam@gentoo.org>,
linux-trace-kernel@vger.kerne.org,
Andrii Nakryiko <andrii.nakryiko@gmail.com>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Florian Weimer <fweimer@redhat.com>,
Andy Lutomirski <luto@kernel.org>,
Heiko Carstens <hca@linux.ibm.com>,
Vasily Gorbik <gor@linux.ibm.com>
Subject: Re: [PATCH v3 07/19] unwind: Add user space unwinding API
Date: Fri, 6 Dec 2024 11:29:21 +0100 [thread overview]
Message-ID: <978a9ecd-47e9-442b-8daa-aee8f3d93dbb@linux.ibm.com> (raw)
In-Reply-To: <f89a9137e983902f22611e5379606062a64b2382.1730150953.git.jpoimboe@kernel.org>
On 28.10.2024 22:47, Josh Poimboeuf wrote:
> Introduce a user space unwinder API which provides a generic way to
> unwind user stacks.
...
> diff --git a/kernel/unwind/user.c b/kernel/unwind/user.c
...
> +int unwind_user_next(struct unwind_user_state *state)
> +{
> + struct unwind_user_frame _frame;
> + struct unwind_user_frame *frame = &_frame;
> + unsigned long prev_ip, cfa, fp, ra = 0;
> +
> + if (state->done)
> + return -EINVAL;
> +
> + prev_ip = state->ip;
> +
> + switch (state->type) {
> + case UNWIND_USER_TYPE_FP:
> + frame = &fp_frame;
> + break;
> + default:
> + BUG();
> + }
> +
> + cfa = (frame->use_fp ? state->fp : state->sp) + frame->cfa_off;
> +
> + if (frame->ra_off && get_user(ra, (unsigned long __user *)(cfa + frame->ra_off)))
> + goto the_end;
> +
> + if (ra == prev_ip)
> + goto the_end;
This seems too restrictive to me, as it effectively prevents
unwinding from recursive functions, e.g. Glibc internal merge sort
msort_with_tmp():
$ perf record -F 9999 --call-graph fp /usr/bin/objdump -wdWF /usr/bin/objdump
$ perf script
...
objdump 8314 236064.515562: 100010 task-clock:ppp:
100630a compare_symbols+0x2a (/usr/bin/objdump)
3ffb9e58e7c msort_with_tmp.part.0+0x15c (/usr/lib64/libc.so.6)
3ffb9e58d76 msort_with_tmp.part.0+0x56 (/usr/lib64/libc.so.6)
[unwinding unexpectedly stops]
Would it be an option to only stop unwinding if both the IP and SP do
not change?
if (sp == prev_sp && ra == prev_ra)
gote the_end;
> +
> + if (frame->fp_off && get_user(fp, (unsigned long __user *)(cfa + frame->fp_off)))
> + goto the_end;
> +
> + state->sp = cfa;
> + state->ip = ra;
> + if (frame->fp_off)
> + state->fp = fp;
> +
> + return 0;
> +
> +the_end:
> + state->done = true;
> + return -EINVAL;
> +}
...
Thanks and regards,
Jens
--
Jens Remus
Linux on Z Development (D3303) and z/VSE Support
+49-7031-16-1128 Office
jremus@de.ibm.com
IBM
IBM Deutschland Research & Development GmbH; Vorsitzender des Aufsichtsrats: Wolfgang Wendt; Geschäftsführung: David Faller; Sitz der Gesellschaft: Böblingen; Registergericht: Amtsgericht Stuttgart, HRB 243294
IBM Data Privacy Statement: https://www.ibm.com/privacy/
next prev parent reply other threads:[~2024-12-06 10:29 UTC|newest]
Thread overview: 119+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-28 21:47 [PATCH v3 00/19] unwind, perf: sframe user space unwinding Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 01/19] x86/vdso: Fix DWARF generation for getrandom() Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 02/19] x86/asm: Avoid emitting DWARF CFI for non-VDSO Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-30 17:19 ` Jens Remus
2024-10-30 17:51 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 03/19] x86/asm: Fix VDSO DWARF generation with kernel IBT enabled Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 04/19] x86/vdso: Use SYM_FUNC_{START,END} in __kernel_vsyscall() Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 05/19] x86/vdso: Use CFI macros in __vdso_sgx_enter_enclave() Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 06/19] x86/vdso: Enable sframe generation in VDSO Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-30 18:20 ` Jens Remus
2024-10-30 19:17 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 07/19] unwind: Add user space unwinding API Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-12-06 10:29 ` Jens Remus [this message]
2024-12-09 20:54 ` Josh Poimboeuf
2024-12-11 14:53 ` Jens Remus
2024-12-11 17:48 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 08/19] unwind/x86: Enable CONFIG_HAVE_UNWIND_USER_FP Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-29 13:13 ` Peter Zijlstra
2024-10-29 16:31 ` Josh Poimboeuf
2024-10-29 18:08 ` Peter Zijlstra
2024-10-28 21:47 ` [PATCH v3 09/19] unwind: Introduce sframe user space unwinding Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-29 13:27 ` Peter Zijlstra
2024-10-29 16:50 ` Josh Poimboeuf
2024-10-29 18:10 ` Peter Zijlstra
2024-10-29 23:32 ` Andrii Nakryiko
2024-10-30 5:53 ` Josh Poimboeuf
2024-10-31 20:57 ` Andrii Nakryiko
2024-10-31 21:00 ` Nick Desaulniers
2024-10-31 21:38 ` Indu Bhagat
2024-11-01 18:38 ` Andrii Nakryiko
2024-11-01 18:47 ` Steven Rostedt
2024-11-01 18:54 ` Andrii Nakryiko
2024-11-03 0:07 ` Indu Bhagat
2024-10-31 23:03 ` Josh Poimboeuf
2024-11-01 18:34 ` Andrii Nakryiko
2024-11-01 19:29 ` Josh Poimboeuf
2024-11-01 19:44 ` Andrii Nakryiko
2024-11-01 19:46 ` Andrii Nakryiko
2024-11-01 19:51 ` Josh Poimboeuf
2024-11-01 19:09 ` Segher Boessenkool
2024-11-01 19:33 ` Josh Poimboeuf
2024-11-01 19:35 ` Josh Poimboeuf
2024-11-01 19:48 ` Josh Poimboeuf
2024-11-01 21:35 ` Segher Boessenkool
2024-11-05 17:40 ` Steven Rostedt
2024-11-05 17:45 ` Steven Rostedt
2024-11-06 17:04 ` Jens Remus
2024-11-07 8:25 ` Weinan Liu
2024-11-07 16:59 ` Jens Remus
2024-11-13 20:50 ` Steven Rostedt
2024-11-13 21:15 ` Josh Poimboeuf
2024-11-13 22:13 ` Steven Rostedt
2024-11-13 22:21 ` Steven Rostedt
2024-11-13 22:25 ` Steven Rostedt
2024-11-14 9:57 ` Jens Remus
2024-11-13 15:56 ` Jens Remus
2024-11-13 20:50 ` Steven Rostedt
2024-11-13 21:13 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 10/19] unwind/x86: Enable CONFIG_HAVE_UNWIND_USER_SFRAME Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-29 13:14 ` Peter Zijlstra
2024-10-28 21:47 ` [PATCH v3 11/19] unwind: Add deferred user space unwinding API Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-29 13:48 ` Peter Zijlstra
2024-10-29 16:51 ` Josh Poimboeuf
2024-10-29 13:49 ` Peter Zijlstra
2024-10-29 17:05 ` Josh Poimboeuf
2024-10-29 18:11 ` Peter Zijlstra
2024-10-29 13:56 ` Peter Zijlstra
2024-10-29 17:17 ` Josh Poimboeuf
2024-10-29 17:47 ` Mathieu Desnoyers
2024-10-29 18:20 ` Peter Zijlstra
2024-10-30 6:17 ` Steven Rostedt
2024-10-30 14:03 ` Peter Zijlstra
2024-10-30 19:58 ` Steven Rostedt
2024-10-30 20:48 ` Josh Poimboeuf
2024-10-29 18:34 ` Josh Poimboeuf
2024-10-30 13:44 ` Mathieu Desnoyers
2024-10-30 17:47 ` Josh Poimboeuf
2024-10-30 17:55 ` Josh Poimboeuf
2024-10-30 18:25 ` Josh Poimboeuf
2024-10-29 23:32 ` Andrii Nakryiko
2024-10-30 6:10 ` Josh Poimboeuf
2024-10-31 21:22 ` Andrii Nakryiko
2024-10-31 23:13 ` Josh Poimboeuf
2024-10-31 23:28 ` Andrii Nakryiko
2024-11-01 17:41 ` Josh Poimboeuf
2024-11-01 18:05 ` Andrii Nakryiko
2024-10-28 21:47 ` [PATCH v3 12/19] perf: Remove get_perf_callchain() 'init_nr' argument Josh Poimboeuf
2024-10-28 21:47 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 13/19] perf: Remove get_perf_callchain() 'crosstask' argument Josh Poimboeuf
2024-10-28 21:48 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 14/19] perf: Simplify get_perf_callchain() user logic Josh Poimboeuf
2024-10-28 21:48 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 15/19] perf: Add deferred user callchains Josh Poimboeuf
2024-10-28 21:48 ` Josh Poimboeuf
2024-10-29 14:06 ` Peter Zijlstra
2024-11-06 9:45 ` Jens Remus
2024-10-28 21:47 ` [PATCH v3 16/19] perf tools: Minimal CALLCHAIN_DEFERRED support Josh Poimboeuf
2024-10-28 21:48 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 17/19] perf record: Enable defer_callchain for user callchains Josh Poimboeuf
2024-10-28 21:48 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 18/19] perf script: Display PERF_RECORD_CALLCHAIN_DEFERRED Josh Poimboeuf
2024-10-28 21:48 ` Josh Poimboeuf
2024-10-28 21:47 ` [PATCH v3 19/19] perf tools: Merge deferred user callchains Josh Poimboeuf
2024-10-28 21:48 ` Josh Poimboeuf
2024-10-28 21:54 ` [PATCH v3 00/19] unwind, perf: sframe user space unwinding Josh Poimboeuf
2024-10-28 23:55 ` Josh Poimboeuf
2024-10-29 14:08 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=978a9ecd-47e9-442b-8daa-aee8f3d93dbb@linux.ibm.com \
--to=jremus@linux.ibm.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=andrii.nakryiko@gmail.com \
--cc=broonie@kernel.org \
--cc=fweimer@redhat.com \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=indu.bhagat@oracle.com \
--cc=irogers@google.com \
--cc=jolsa@kernel.org \
--cc=jordalgo@meta.com \
--cc=jpoimboe@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=linux-toolchains@vger.kernel.org \
--cc=linux-trace-kernel@vger.kerne.org \
--cc=luto@kernel.org \
--cc=mark.rutland@arm.com \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=sam@gentoo.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.