Re: [PATCH bpf-next 1/2] bpf: Add a bpf_kallsyms_lookup helper

[KP Singh]

On Fri, Nov 27, 2020 at 8:35 AM Yonghong Song <yhs@xxxxxx> wrote:
>
>
>
> On 11/26/20 8:57 AM, Florent Revest wrote:
> > This helper exposes the kallsyms_lookup function to eBPF tracing
> > programs. This can be used to retrieve the name of the symbol at an
> > address. For example, when hooking into nf_register_net_hook, one can
> > audit the name of the registered netfilter hook and potentially also
> > the name of the module in which the symbol is located.
> >
> > Signed-off-by: Florent Revest <revest@xxxxxxxxxx>
> > ---
> >   include/uapi/linux/bpf.h       | 16 +++++++++++++
> >   kernel/trace/bpf_trace.c       | 41 ++++++++++++++++++++++++++++++++++
> >   tools/include/uapi/linux/bpf.h | 16 +++++++++++++
> >   3 files changed, 73 insertions(+)
> >
> > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> > index c3458ec1f30a..670998635eac 100644
> > --- a/include/uapi/linux/bpf.h
> > +++ b/include/uapi/linux/bpf.h
> > @@ -3817,6 +3817,21 @@ union bpf_attr {
> >    *          The **hash_algo** is returned on success,
> >    *          **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if
> >    *          invalid arguments are passed.
> > + *
> > + * long bpf_kallsyms_lookup(u64 address, char *symbol, u32 symbol_size, char *module, u32 module_size)
> > + *   Description
> > + *           Uses kallsyms to write the name of the symbol at *address*
> > + *           into *symbol* of size *symbol_sz*. This is guaranteed to be
> > + *           zero terminated.
> > + *           If the symbol is in a module, up to *module_size* bytes of
> > + *           the module name is written in *module*. This is also
> > + *           guaranteed to be zero-terminated. Note: a module name
> > + *           is always shorter than 64 bytes.
> > + *   Return
> > + *           On success, the strictly positive length of the full symbol
> > + *           name, If this is greater than *symbol_size*, the written
> > + *           symbol is truncated.
> > + *           On error, a negative value.
> >    */
> >   #define __BPF_FUNC_MAPPER(FN)               \
> >       FN(unspec),                     \
> > @@ -3981,6 +3996,7 @@ union bpf_attr {
> >       FN(bprm_opts_set),              \
> >       FN(ktime_get_coarse_ns),        \
> >       FN(ima_inode_hash),             \
> > +     FN(kallsyms_lookup),    \
> >       /* */
> >
> >   /* integer value in 'imm' field of BPF_CALL instruction selects which helper
> > diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> > index d255bc9b2bfa..9d86e20c2b13 100644
> > --- a/kernel/trace/bpf_trace.c
> > +++ b/kernel/trace/bpf_trace.c
> > @@ -17,6 +17,7 @@
> >   #include <linux/error-injection.h>
> >   #include <linux/btf_ids.h>
> >   #include <linux/bpf_lsm.h>
> > +#include <linux/kallsyms.h>
> >
> >   #include <net/bpf_sk_storage.h>
> >
> > @@ -1260,6 +1261,44 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
> >       .arg5_type      = ARG_ANYTHING,
> >   };
> >
> > +BPF_CALL_5(bpf_kallsyms_lookup, u64, address, char *, symbol, u32, symbol_size,
> > +        char *, module, u32, module_size)
> > +{
> > +     char buffer[KSYM_SYMBOL_LEN];
> > +     unsigned long offset, size;
> > +     const char *name;
> > +     char *modname;
> > +     long ret;
> > +
> > +     name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
> > +     if (!name)
> > +             return -EINVAL;
> > +
> > +     ret = strlen(name) + 1;
> > +     if (symbol_size) {
> > +             strncpy(symbol, name, symbol_size);
> > +             symbol[symbol_size - 1] = '\0';
> > +     }
> > +
> > +     if (modname && module_size) {
> > +             strncpy(module, modname, module_size);
> > +             module[module_size - 1] = '\0';
>
> In this case, module name may be truncated and user did not get any
> indication from return value. In the helper description, it is mentioned
> that module name currently is most 64 bytes. But from UAPI perspective,
> it may be still good to return something to let user know the name
> is truncated.
>
> I do not know what is the best way to do this. One suggestion is
> to break it into two helpers, one for symbol name and another

I think it would be slightly preferable to have one helper though.
maybe something like bpf_get_symbol_info (better names anyone? :))
with flags to get the module name or the symbol name depending
on the flag?

> for module name. What is the use cases people want to get both
> symbol name and module name and is it common?

The use case would be to disambiguate symbols in the
kernel from the ones from a kernel module. Similar to what
/proc/kallsyms does:

T cpufreq_gov_powersave_init [cpufreq_powersave]

>
> > +     }
> > +
> > +     return ret;
> > +}
> > +
> > +const struct bpf_func_proto bpf_kallsyms_lookup_proto = {
> > +     .func           = bpf_kallsyms_lookup,
> > +     .gpl_only       = false,
> > +     .ret_type       = RET_INTEGER,
> > +     .arg1_type      = ARG_ANYTHING,
> > +     .arg2_type      = ARG_PTR_TO_MEM,
> ARG_PTR_TO_UNINIT_MEM?
>
> > +     .arg3_type      = ARG_CONST_SIZE,
> ARG_CONST_SIZE_OR_ZERO? This is especially true for current format
> which tries to return both symbol name and module name and
> user may just want to do one of them.
>
> > +     .arg4_type      = ARG_PTR_TO_MEM,
> ARG_PTR_TO_UNINIT_MEM?
>
> > +     .arg5_type      = ARG_CONST_SIZE,
> ARG_CONST_SIZE_OR_ZERO?
>
> > +};
> > +
> >   const struct bpf_func_proto *
> >   bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
> >   {
> > @@ -1356,6 +1395,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
> >               return &bpf_per_cpu_ptr_proto;
> >       case BPF_FUNC_bpf_this_cpu_ptr:
> >               return &bpf_this_cpu_ptr_proto;
> > +     case BPF_FUNC_kallsyms_lookup:
> > +             return &bpf_kallsyms_lookup_proto;
> >       default:
> >               return NULL;
> >       }
> [...]