Re: [PATCH v2 1/2] perf: Fix user attribute access in kprobes

Re: [PATCH v2 1/2] perf: Fix user attribute access in kprobes

[Arnaldo Carvalho de Melo]

Em Tue, Jun 09, 2020 at 12:09:31PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Tue, Jun 09, 2020 at 10:10:18AM +0200, Sumanth Korikkar escreveu:
> > Issue:
> > perf probe -a 'do_sched_setscheduler  pid policy
> > param->sched_priority@user' did not work before.
> > 
> > Fix:
> > Make (perf probe -a 'do_sched_setscheduler  pid policy
> > param->sched_priority@user') output equivalent to ftrace
> > ('p:probe/do_sched_setscheduler _text+517384 pid=%r2:s32 policy=%r3:s32
> > sched_priority=+u0(%r4):s32' > kprobe_events)
> > 
> > Other:
> > 1. Right now, __match_glob() does not handle [u]<offset>. For now, use
> >   *u]<offset>.
> > 2. @user attribute was introduced in commit 1e032f7cfa14 ("perf-probe:
> >    Add user memory access attribute support")
> > 
> > Test:
> > 1. perf probe -a 'do_sched_setscheduler  pid policy
> >    param->sched_priority@user'
> > 
> > 2 ./perf script
> >    sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508)
> >    pid=261614 policy=2 sched_priority=1
> > 
> > 3. cat /sys/kernel/debug/tracing/trace
> >    <...>-309956 [006] .... 1616098.093957: 0: prio: 1
> 
> Thanks, I'm adding this:
> 
> Fixes: 1e032f7cfa14 ("perf-probe: Add user memory access attribute support")
> Cc: Masami Hiramatsu <mhiramat@kernel.org>
> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
> 
> So that the stable guys pick this up eventually,
> 
> That first hunk with the strcmp() return check could have gone into a
> separate patch, but I'll process it as-is for expediency,

I also added this:

ommitter testing:

Before:

  # perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user'
  param(type:sched_param) has no member sched_priority@user.
    Error: Failed to add events.
  # pahole sched_param
  struct sched_param {
        int                        sched_priority;       /*     0     4 */

        /* size: 4, cachelines: 1, members: 1 */
        /* last cacheline: 4 bytes */
  };
  #

After:

  # perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user'
  Added new event:
    probe:do_sched_setscheduler (on do_sched_setscheduler with pid policy sched_priority=param->sched_priority)

  You can now use it in all perf tools, such as:

        perf record -e probe:do_sched_setscheduler -aR sleep 1

  # cat /sys/kernel/debug/tracing/kprobe_events
  p:probe/do_sched_setscheduler _text+1113792 pid=%di:s32 policy=%si:s32 sched_priority=+u0(%dx):s32
  #

 
> - Arnaldo
>  
> > Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
> > Reviewed-by: Thomas Richter <tmricht@linux.ibm.com>
> > Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
> > ---
> >  tools/perf/util/probe-event.c | 7 +++++--
> >  tools/perf/util/probe-file.c  | 2 +-
> >  2 files changed, 6 insertions(+), 3 deletions(-)
> > 
> > diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
> > index a08f373d3305..df713a5d1e26 100644
> > --- a/tools/perf/util/probe-event.c
> > +++ b/tools/perf/util/probe-event.c
> > @@ -1575,7 +1575,7 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
> >  	}
> >  
> >  	tmp = strchr(str, '@');
> > -	if (tmp && tmp != str && strcmp(tmp + 1, "user")) { /* user attr */
> > +	if (tmp && tmp != str && !strcmp(tmp + 1, "user")) { /* user attr */
> >  		if (!user_access_is_supported()) {
> >  			semantic_error("ftrace does not support user access\n");
> >  			return -EINVAL;
> > @@ -1995,7 +1995,10 @@ static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
> >  		if (depth < 0)
> >  			return depth;
> >  	}
> > -	err = strbuf_addf(buf, "%+ld(", ref->offset);
> > +	if (ref->user_access)
> > +		err = strbuf_addf(buf, "%s%ld(", "+u", ref->offset);
> > +	else
> > +		err = strbuf_addf(buf, "%+ld(", ref->offset);
> >  	return (err < 0) ? err : depth;
> >  }
> >  
> > diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
> > index 8c852948513e..064b63a6a3f3 100644
> > --- a/tools/perf/util/probe-file.c
> > +++ b/tools/perf/util/probe-file.c
> > @@ -1044,7 +1044,7 @@ static struct {
> >  	DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
> >  	DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
> >  	DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"),
> > -	DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"),
> > +	DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*u]<offset>*"),
> >  	DEFINE_TYPE(FTRACE_README_MULTIPROBE_EVENT, "*Create/append/*"),
> >  	DEFINE_TYPE(FTRACE_README_IMMEDIATE_VALUE, "*\\imm-value,*"),
> >  };
> > -- 
> > 2.17.1
> > 
> 
> -- 
> 
> - Arnaldo

-- 

- Arnaldo

Re: [PATCH v2 2/2] perf: Fix bpf prologue generation

[Arnaldo Carvalho de Melo]

Em Tue, Jun 09, 2020 at 10:10:19AM +0200, Sumanth Korikkar escreveu:
> Issue:
> bpf_probe_read is no longer available for architecture which has
> overlapping address space. Hence bpf prologue generation fails
> 
> Fix:
> Use bpf_probe_read_kernel for kernel member access. For user
> attribute access in kprobes, use bpf_probe_read_user.
> 
> Other:
> @user attribute was introduced in commit 1e032f7cfa14 ("perf-probe:
>  Add user memory access attribute support")
> 
> Test:
> 1. ulimit -l 128 ; ./perf record -e tests/bpf_sched_setscheduler.c
> 2. cat tests/bpf_sched_setscheduler.c
> 
> static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
>         (void *) 6;
> static int (*bpf_probe_read_user)(void *dst, __u32 size,
>                                   const void *unsafe_ptr) = (void *) 112;
> static int (*bpf_probe_read_kernel)(void *dst, __u32 size,
>         const void *unsafe_ptr) = (void *) 113;
> 
> SEC("func=do_sched_setscheduler  pid policy param->sched_priority@user")
> int bpf_func__setscheduler(void *ctx, int err, pid_t pid, int policy,
>                            int param)
> {
>         char fmt[] = "prio: %ld";
>         bpf_trace_printk(fmt, sizeof(fmt), param);
>         return 1;
> }
> 
> char _license[] SEC("license") = "GPL";
> int _version SEC("version") = LINUX_VERSION_CODE;
> 
> 3. ./perf script
>    sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508)
>    pid=261614 policy=2 sched_priority=1
> 
> 4. cat /sys/kernel/debug/tracing/trace
>    <...>-309956 [006] .... 1616098.093957: 0: prio: 1

Thanks for providing a detailed set of steps to test your patch, that is
great!

I added this, an alterenative way to test it, combining all the aspects
in one 'perf trace' call:

Committer testing:

I had to add some missing headers in the bpf_sched_setscheduler.c test
proggie, then instead of using record+script I used 'perf trace' to
drive everything in one go:

  # cat bpf_sched_setscheduler.c
  #include <linux/types.h>
  #include <bpf.h>

  static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = (void *) 6;
  static int (*bpf_probe_read_user)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 112;
  static int (*bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 113;

  SEC("func=do_sched_setscheduler  pid policy param->sched_priority@user")
  int bpf_func__setscheduler(void *ctx, int err, pid_t pid, int policy, int param)
  {
          char fmt[] = "prio: %ld";
          bpf_trace_printk(fmt, sizeof(fmt), param);
          return 1;
  }

  char _license[] SEC("license") = "GPL";
  int _version SEC("version") = LINUX_VERSION_CODE;
  #
  #
  # perf trace -e bpf_sched_setscheduler.c chrt -f 42 sleep 1
     0.000 chrt/80125 perf_bpf_probe:func(__probe_ip: -1676607808, policy: 1, sched_priority: 42)
  #

And even with backtraces :-)

  # perf trace -e bpf_sched_setscheduler.c/max-stack=8/ chrt -f 42 sleep 1
       0.000 chrt/79805 perf_bpf_probe:func(__probe_ip: -1676607808, policy: 1, sched_priority: 42)
                                         do_sched_setscheduler ([kernel.kallsyms])
                                         __x64_sys_sched_setscheduler ([kernel.kallsyms])
                                         do_syscall_64 ([kernel.kallsyms])
                                         entry_SYSCALL_64 ([kernel.kallsyms])
                                         __GI___sched_setscheduler (/usr/lib64/libc-2.30.so)
  # 

- Arnaldo