Re: [PATCHv2 bpf-next 08/24] libbpf: Add elf_find_multi_func_offset function

[Jiri Olsa <olsajiri@gmail.com>]

On Fri, Jun 23, 2023 at 01:39:54PM -0700, Andrii Nakryiko wrote:
> On Tue, Jun 20, 2023 at 1:37 AM Jiri Olsa <jolsa@kernel.org> wrote:
> >
> > Adding elf_find_multi_func_offset function that looks up
> > offsets for symbols specified in syms array argument.
> >
> > Offsets are returned in allocated array with the 'cnt' size,
> > that needs to be released by the caller.
> >
> > Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> > ---
> >  tools/lib/bpf/libbpf.c          | 112 ++++++++++++++++++++++++++++++++
> >  tools/lib/bpf/libbpf_internal.h |   2 +
> >  2 files changed, 114 insertions(+)
> >
> > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > index 30d9e3b69114..1c310b718961 100644
> > --- a/tools/lib/bpf/libbpf.c
> > +++ b/tools/lib/bpf/libbpf.c
> > @@ -11053,6 +11053,118 @@ static long elf_find_func_offset(Elf *elf, const char *binary_path, const char *
> >         return ret;
> >  }
> >
> > +struct elf_symbol_offset {
> > +       const char *name;
> > +       unsigned long offset;
> > +       int bind;
> > +       int idx;
> > +};
> > +
> > +static int cmp_func_offset(const void *_a, const void *_b)
> > +{
> > +       const struct elf_symbol_offset *a = _a;
> > +       const struct elf_symbol_offset *b = _b;
> > +
> > +       return strcmp(a->name, b->name);
> > +}
> > +
> > +static int
> > +__elf_find_multi_func_offset(Elf *elf, const char *binary_path, int cnt,
> > +                            const char **syms, unsigned long **poffsets)
> > +{
> > +       int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
> > +       struct elf_symbol_offset *func_offs;
> > +       int err = 0, i, idx, cnt_done = 0;
> > +       unsigned long *offsets = NULL;
> > +
> > +       func_offs = calloc(cnt, sizeof(*func_offs));
> > +       if (!func_offs)
> > +               return -ENOMEM;
> > +
> > +       for (i = 0; i < cnt; i++) {
> > +               func_offs[i].name = syms[i];
> > +               func_offs[i].idx = i;
> > +       }
> > +
> > +       qsort(func_offs, cnt, sizeof(*func_offs), cmp_func_offset);
> > +
> > +       for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
> > +               struct elf_symbol_iter iter;
> > +               struct elf_symbol *sym;
> > +
> > +               if (elf_symbol_iter_new(&iter, elf, binary_path, sh_types[i]))
> 
> a bit lax handling of initialization errors here, let's be a bit more
> strict here?

right, I'll have elf_symbol_iter_new return -ENOENT in case there's no
'sh_types[i]' section type (and we want to try next section type) and
fail otherwise

> 
> > +                       continue;
> > +
> > +               while ((sym = elf_symbol_iter_next(&iter))) {
> > +                       struct elf_symbol_offset *fo, tmp = {
> > +                               .name = sym->name,
> > +                       };
> > +
> > +                       fo = bsearch(&tmp, func_offs, cnt, sizeof(*func_offs),
> > +                                    cmp_func_offset);
> > +                       if (!fo)
> > +                               continue;
> > +
> > +                       if (fo->offset > 0) {
> > +                               /* same offset, no problem */
> > +                               if (fo->offset == sym->offset)
> > +                                       continue;
> > +                               /* handle multiple matches */
> > +                               if (fo->bind != STB_WEAK && sym->bind != STB_WEAK) {
> > +                                       /* Only accept one non-weak bind. */
> > +                                       pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
> > +                                               sym->name, fo->name, binary_path);
> > +                                       err = -LIBBPF_ERRNO__FORMAT;
> > +                                       goto out;
> > +                               } else if (sym->bind == STB_WEAK) {
> > +                                       /* already have a non-weak bind, and
> > +                                        * this is a weak bind, so ignore.
> > +                                        */
> > +                                       continue;
> > +                               }
> > +                       }
> > +                       if (!fo->offset)
> > +                               cnt_done++;
> > +                       fo->offset = sym->offset;
> > +                       fo->bind = sym->bind;
> > +               }
> > +       }
> > +
> > +       if (cnt != cnt_done) {
> > +               err = -ENOENT;
> > +               goto out;
> > +       }
> > +       offsets = calloc(cnt, sizeof(*offsets));
> 
> you can allocate it at the very beginning and fill it out based on
> fo->idx, there is no need to store offset in elf_symbol_offset

true, will fix

> 
> > +       if (!offsets) {
> > +               err = -ENOMEM;
> > +               goto out;
> > +       }
> > +       for (i = 0; i < cnt; i++) {
> > +               idx = func_offs[i].idx;
> > +               offsets[idx] = func_offs[i].offset;
> > +       }
> > +
> > +out:
> > +       *poffsets = offsets;
> > +       free(func_offs);
> > +       return err;
> > +}
> > +
> > +int elf_find_multi_func_offset(const char *binary_path, int cnt,
> > +                              const char **syms, unsigned long **poffsets)
> > +{
> > +       struct elf_fd elf_fd = {};
> 
> do you need to initialize this struct?

I recall getting gcc warn/error, which I can't see anymore ;-)
will remove

> 
> > +       long ret = -ENOENT;
> 
> same here, you always override ret, so no need to init it?

yes

> 
> > +
> > +       ret = open_elf(binary_path, &elf_fd);
> > +       if (ret)
> > +               return ret;
> > +
> > +       ret = __elf_find_multi_func_offset(elf_fd.elf, binary_path, cnt, syms, poffsets);
> 
> is there a point of having elf_find_multi_func_offset and
> __elf_find_multi_func_offset separately? can you please combine?

ok

thanks,
jirka