Re: [PATCH v1 2/2] perf srcline: Make sentinel reading for binutils addr2line more robust

[Ian Rogers]

On Mon, Jun 12, 2023 at 12:11 PM Arnaldo Carvalho de Melo
<acme@xxxxxxxxxx> wrote:
>
> Em Fri, Jun 09, 2023 at 04:54:19PM -0700, Ian Rogers escreveu:
> > The addr2line process is sent an address then multiple function,
> > filename:line "records" are read. To detect the end of output a ',' is
> > sent and for llvm-addr2line a ',' is then read back showing the end of
> > addrline's output. For binutils addr2line the ',' translates to
> > address 0 and we expect the bogus filename marker "??:0" (see
> > filename_split) to be sent from addr2line. For some kernels address 0
> > may have a mapping and so a seemingly valid inline output is given and
> > breaking the sentinel discovery:
> >
> > ```
> > $ addr2line -e vmlinux -f -i
> > ,
> > __per_cpu_start
> > ./arch/x86/kernel/cpu/common.c:1850
> > ```
> >
> > To avoid this problem enable the address dumping for addr2line (the -a
> > option). If an address of 0x0000000000000000 is read then this is the
> > sentinel value working around the problem above. The filename_split
> > still needs to check for "??:0" as bogus non-zero addresses also need
> > handling.
> >
> > Reported-by: Changbin Du <changbin.du@xxxxxxxxxx>
>
> Changbin,
>
>         Did this fix the problem you reported? If so can I have your
> Tested-by?

There are ongoing issues that Changbin has found, the thread is here:
https://lore.kernel.org/linux-perf-users/CAP-5=fWdvMVOiZDhqiz1R9hucz+6+ho_L3jBixqP3YLcJD7Lew@xxxxxxxxxxxxxx/

Thanks,
Ian

> Thanks,
>
> - Arnaldo
>
> > Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
> > ---
> >  tools/perf/util/srcline.c | 61 ++++++++++++++++++++++++++++++++++-----
> >  1 file changed, 53 insertions(+), 8 deletions(-)
> >
> > diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
> > index fc85cdd6c8f9..c99a001453b4 100644
> > --- a/tools/perf/util/srcline.c
> > +++ b/tools/perf/util/srcline.c
> > @@ -406,7 +406,7 @@ static struct child_process *addr2line_subprocess_init(const char *addr2line_pat
> >       const char *argv[] = {
> >               addr2line_path ?: "addr2line",
> >               "-e", binary_path,
> > -             "-i", "-f", NULL
> > +             "-a", "-i", "-f", NULL
> >       };
> >       struct child_process *a2l = zalloc(sizeof(*a2l));
> >       int start_command_status = 0;
> > @@ -461,10 +461,10 @@ static enum a2l_style addr2line_configure(struct child_process *a2l, const char
> >                       style = LLVM;
> >                       cached = true;
> >                       lines = 1;
> > -             } else if (ch == '?') {
> > +             } else if (ch == '0') {
> >                       style = GNU_BINUTILS;
> >                       cached = true;
> > -                     lines = 2;
> > +                     lines = 3;
> >               } else {
> >                       if (!symbol_conf.disable_add2line_warn) {
> >                               char *output;
> > @@ -516,20 +516,64 @@ static int read_addr2line_record(struct io *io,
> >       if (line_nr != NULL)
> >               *line_nr = 0;
> >
> > +     /*
> > +      * Read the first line. Without an error this will be either an address
> > +      * like 0x1234 or for llvm-addr2line the sentinal ',' character.
> > +      */
> >       if (io__getline(io, &line, &line_len) < 0 || !line_len)
> >               goto error;
> >
> > -     if (style == LLVM && line_len == 2 && line[0] == ',') {
> > -             zfree(&line);
> > -             return 0;
> > +     if (style == LLVM) {
> > +             if (line_len == 2 && line[0] == ',') {
> > +                     zfree(&line);
> > +                     return 0;
> > +             }
> > +     } else {
> > +             int zero_count = 0, non_zero_count = 0;
> > +
> > +             /* The address should always start 0x. */
> > +             if (line_len < 2 || line[0] != '0' || line[1] != 'x')
> > +                     goto error;
> > +
> > +             for (size_t i = 2; i < line_len; i++) {
> > +                     if (line[i] == '0')
> > +                             zero_count++;
> > +                     else
> > +                             non_zero_count++;
> > +             }
> > +             if (!non_zero_count) {
> > +                     int ch;
> > +
> > +                     if (!zero_count) {
> > +                             /* Line was erroneous just '0x'. */
> > +                             goto error;
> > +                     }
> > +                     /*
> > +                      * Line was 0x0..0, the sentinel for binutils. Remove
> > +                      * the function and filename lines.
> > +                      */
> > +                     zfree(&line);
> > +                     do {
> > +                             ch = io__get_char(io);
> > +                     } while (ch > 0 && ch != '\n');
> > +                     do {
> > +                             ch = io__get_char(io);
> > +                     } while (ch > 0 && ch != '\n');
> > +                     return 0;
> > +             }
> >       }
> >
> > +     /* Read the second function name line. */
> > +     if (io__getline(io, &line, &line_len) < 0 || !line_len)
> > +             goto error;
> > +
> >       if (function != NULL)
> >               *function = strdup(strim(line));
> >
> >       zfree(&line);
> >       line_len = 0;
> >
> > +     /* Read the third filename and line number line. */
> >       if (io__getline(io, &line, &line_len) < 0 || !line_len)
> >               goto error;
> >
> > @@ -633,8 +677,9 @@ static int addr2line(const char *dso_name, u64 addr,
> >               goto out;
> >       case 0:
> >               /*
> > -              * The first record was invalid, so return failure, but first read another
> > -              * record, since we asked a junk question and have to clear the answer out.
> > +              * The first record was invalid, so return failure, but first
> > +              * read another record, since we sent a sentinel ',' for the
> > +              * sake of detected the last inlined function.
> >                */
> >               switch (read_addr2line_record(&io, a2l_style, NULL, NULL, NULL)) {
> >               case -1:
> > --
> > 2.41.0.162.gfafddb0af9-goog
> >
>
> --
>
> - Arnaldo