On Thu, Jul 06, 2023 at 08:48:13PM -0700, Andrii Nakryiko wrote:
> On Fri, Jun 30, 2023 at 1:35 AM Jiri Olsa <jolsa@xxxxxxxxxx> wrote:
> >
> > Adding elf_resolve_syms_offsets 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@xxxxxxxxxx>
> > ---
> > tools/lib/bpf/elf.c | 105 +++++++++++++++++++++++++++++++++++++
> > tools/lib/bpf/libbpf_elf.h | 2 +
> > 2 files changed, 107 insertions(+)
> >
> > diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
> > index fcce4bd2478f..7e2f3b2e1fb6 100644
> > --- a/tools/lib/bpf/elf.c
> > +++ b/tools/lib/bpf/elf.c
> > @@ -271,3 +271,108 @@ long elf_find_func_offset_from_file(const char *binary_path, const char *name)
> > elf_close(&elf_fd);
> > return ret;
> > }
> > +
> > +struct symbol {
> > + const char *name;
> > + int bind;
> > + int idx;
> > +};
> > +
> > +static int symbol_cmp(const void *_a, const void *_b)
> > +{
> > + const struct symbol *a = _a;
> > + const struct symbol *b = _b;
>
> please, let's not (over)use leading underscores, x/y, s1/s2, whatever
ok
>
> > +
> > + return strcmp(a->name, b->name);
> > +}
> > +
>
> probably worth leaving a comment that the caller should free offsets on success?
ook
>
> > +int elf_resolve_syms_offsets(const char *binary_path, int cnt,
> > + const char **syms, unsigned long **poffsets)
> > +{
> > + int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
> > + int err = 0, i, cnt_done = 0;
> > + unsigned long *offsets;
> > + struct symbol *symbols;
> > + struct elf_fd elf_fd;
> > +
> > + err = elf_open(binary_path, &elf_fd);
> > + if (err)
> > + return err;
> > +
> > + offsets = calloc(cnt, sizeof(*offsets));
> > + symbols = calloc(cnt, sizeof(*symbols));
> > +
> > + if (!offsets || !symbols) {
> > + err = -ENOMEM;
> > + goto out;
> > + }
> > +
> > + for (i = 0; i < cnt; i++) {
> > + symbols[i].name = syms[i];
> > + symbols[i].idx = i;
> > + }
> > +
> > + qsort(symbols, cnt, sizeof(*symbols), symbol_cmp);
> > +
> > + for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
> > + struct elf_sym_iter iter;
> > + struct elf_sym *sym;
> > +
> > + err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC);
> > + if (err) {
> > + if (err == -ENOENT)
> > + continue;
> > + goto out;
> > + }
>
> same nit, no need for nested ifs
ok
> > +
> > + while ((sym = elf_sym_iter_next(&iter))) {
> > + int bind = GELF_ST_BIND(sym->sym.st_info);
> > + struct symbol *found, tmp = {
> > + .name = sym->name,
> > + };
> > + unsigned long *offset;
> > +
> > + found = bsearch(&tmp, symbols, cnt, sizeof(*symbols), symbol_cmp);
> > + if (!found)
> > + continue;
> > +
> > + offset = &offsets[found->idx];
> > + if (*offset > 0) {
> > + /* same offset, no problem */
> > + if (*offset == elf_sym_offset(sym))
> > + continue;
> > + /* handle multiple matches */
> > + if (found->bind != STB_WEAK && bind != STB_WEAK) {
> > + /* Only accept one non-weak bind. */
> > + pr_warn("elf: ambiguous match foundr '%s', '%s' in '%s'\n",
>
> typo: found
>
> but also wouldn't sym->name and found->name be always the same? Maybe
> log sym->name, previous *offset and newly calculated
> elf_sym_offset(sym) instead?
ok
>
> > + sym->name, found->name, binary_path);
> > + err = -LIBBPF_ERRNO__FORMAT;
>
> I'd minimize using those custom libbpf-only errors, why not -ESRCH here?
ok
>
> > + goto out;
> > + } else if (bind == STB_WEAK) {
> > + /* already have a non-weak bind, and
> > + * this is a weak bind, so ignore.
> > + */
> > + continue;
> > + }
> > + } else {
> > + cnt_done++;
> > + }
> > + *offset = elf_sym_offset(sym);
>
> maybe remember elf_sym_offset() result in a variable? you are using it
> in two (and with my suggestion above it will be three) places already
ok
jirka
