Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1205484

RE: perf probe -L sys_select or sys_poll

Show all headers | View raw

Hi Arnaldo,

> From: Arnaldo Carvalho de Melo [mailto:acme@kernel.org]
> 
> Hi Masami,
> 
> 	Have you noticed that sys_select or sys_poll stops after the
> first few lines? Please let me know if you need more info than is below.

OK, I'll see what is going.

> 
>   [root@zoo ~]# perf probe -L sys_select
>   <SyS_select@/home/git/linux/fs/select.c:0>
>       0  SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
>                         fd_set __user *, exp, struct timeval __user *, tvp)
>          {
>                 struct timespec end_time, *to = NULL;
> 
>   [root@zoo ~]# perf probe -L sys_poll
>   <SyS_poll@/home/git/linux/fs/select.c:0>
>       0  SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
>                         int, timeout_msecs)
>          {
>                 struct timespec end_time, *to = NULL;
> 
>   [root@zoo ~]#
> 
> I haven't investigated it too much, if there is some trouble that makes
> 'perf probe -L' to stop like that maybe we should warn the user somehow?

It seems a bug of -L, since it works correctly with fs/select.c:957.

$ ./perf probe -L fs/select.c:957
</home/mhiramat/ksrc/linux-3/fs/select.c:957>
    957  SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds$
                        int, timeout_msecs)
         {
    960         struct timespec end_time, *to = NULL;
                int ret;

    963         if (timeout_msecs >= 0) {
    964                 to = &end_time;
    965                 poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SE$
    966                         NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC))$
                }

    969         ret = do_sys_poll(ufds, nfds, to);

    971         if (ret == -EINTR) {
                        struct restart_block *restart_block;

So, something goes wrong when processing syscall functions.

Thanks!



-- 
Masami HIRAMATSU
Linux Technology Research Center, System Productivity Research Dept.
Center for Technology Innovation - Systems Engineering
Hitachi, Ltd., Research & Development Group
E-mail: masami.hiramatsu.pt@hitachi.com
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

perf probe -L sys_select or sys_poll Arnaldo Carvalho de Melo <acme@kernel.org> - 2015-08-11 16:20 +0200
  RE: perf probe -L sys_select or sys_poll 平松雅巳 / HIRAMATU，MASAMI   <masami.hiramatsu.pt@hitachi.com> - 2015-08-12 01:00 +0200
  RE: perf probe -L sys_select or sys_poll 平松雅巳 / HIRAMATU，MASAMI   <masami.hiramatsu.pt@hitachi.com> - 2015-08-12 02:50 +0200
    [BUGFIX PATCH perf/core ] perf-probe: Fix to show lines of sys_  functions correctly Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> - 2015-08-12 03:30 +0200
      Re: [BUGFIX PATCH perf/core ] perf-probe: Fix to show lines of sys_  functions correctly Arnaldo Carvalho de Melo <acme@kernel.org> - 2015-08-12 15:30 +0200
        Re: [BUGFIX PATCH perf/core ] perf-probe: Fix to show lines of sys_  functions correctly Arnaldo Carvalho de Melo <acme@kernel.org> - 2015-08-12 15:50 +0200
          Re: [BUGFIX PATCH perf/core ] perf-probe: Fix to show lines of sys_  functions correctly 平松雅巳 / HIRAMATU，MASAMI   <masami.hiramatsu.pt@hitachi.com> - 2015-08-12 23:40 +0200
      [tip:perf/core] perf probe:   Fix to show lines of sys_ functions correctly tip-bot for Masami Hiramatsu <tipbot@zytor.com> - 2015-08-13 10:10 +0200

csiph-web