On Tue, Oct 11, 2022 at 12:16:22AM -0700, Song Liu wrote:
> On Sun, Oct 9, 2022 at 3:00 PM Jiri Olsa <jolsa@xxxxxxxxxx> wrote:
> >
> > Currently we allow to create kprobe multi link on function from kernel
> > module, but we don't take the module reference to ensure it's not
> > unloaded while we are tracing it.
> >
> > The multi kprobe link is based on fprobe/ftrace layer which takes
> > different approach and releases ftrace hooks when module is unloaded
> > even if there's tracer registered on top of it.
> >
> > Adding code that gathers all the related modules for the link and takes
> > their references before it's attached. All kernel module references are
> > released after link is unregistered.
> >
> > Note that we do it the same way already for trampoline probes
> > (but for single address).
> >
> > Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
>
> [...]
>
> > + }
> > +
> > + if (realloc) {
> > + args->mods_alloc += 100;
>
> 100 seems arbitrary and too big to me.
[jolsa@krava linux-qemu]$ lsmod | wc -l
192
I'll check if we can get actuall modules count and base the
allocation on that
jirka
>
> Other than this, LGTM
>
> Acked-by: Song Liu <song@xxxxxxxxxx>
>
> > + mods = krealloc_array(args->mods, args->mods_alloc, sizeof(*mods), GFP_KERNEL);
> > + if (!mods)
> > + return -ENOMEM;
> > + args->mods = mods;
> > + }
> > +
> > + if (!try_module_get(mod))
> > + return -EINVAL;
> > +
> > + args->mods[args->mods_cnt] = mod;
> > + args->mods_cnt++;
> > + return 0;
> > +}
>
> On Sun, Oct 9, 2022 at 3:00 PM Jiri Olsa <jolsa@xxxxxxxxxx> wrote:
> >
> > Currently we allow to create kprobe multi link on function from kernel
> > module, but we don't take the module reference to ensure it's not
> > unloaded while we are tracing it.
> >
> > The multi kprobe link is based on fprobe/ftrace layer which takes
> > different approach and releases ftrace hooks when module is unloaded
> > even if there's tracer registered on top of it.
> >
> > Adding code that gathers all the related modules for the link and takes
> > their references before it's attached. All kernel module references are
> > released after link is unregistered.
> >
> > Note that we do it the same way already for trampoline probes
> > (but for single address).
> >
> > Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
> > ---
> > kernel/trace/bpf_trace.c | 100 +++++++++++++++++++++++++++++++++++++++
> > 1 file changed, 100 insertions(+)
> >
> > diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> > index 9be1a2b6b53b..f3d7565fee79 100644
> > --- a/kernel/trace/bpf_trace.c
> > +++ b/kernel/trace/bpf_trace.c
> > @@ -2447,6 +2447,8 @@ struct bpf_kprobe_multi_link {
> > unsigned long *addrs;
> > u64 *cookies;
> > u32 cnt;
> > + struct module **mods;
> > + u32 mods_cnt;
> > };
> >
> > struct bpf_kprobe_multi_run_ctx {
> > @@ -2502,6 +2504,14 @@ static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32
> > return err;
> > }
> >
> > +static void kprobe_multi_put_modules(struct module **mods, u32 cnt)
> > +{
> > + u32 i;
> > +
> > + for (i = 0; i < cnt; i++)
> > + module_put(mods[i]);
> > +}
> > +
> > static void free_user_syms(struct user_syms *us)
> > {
> > kvfree(us->syms);
> > @@ -2514,6 +2524,7 @@ static void bpf_kprobe_multi_link_release(struct bpf_link *link)
> >
> > kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
> > unregister_fprobe(&kmulti_link->fp);
> > + kprobe_multi_put_modules(kmulti_link->mods, kmulti_link->mods_cnt);
> > }
> >
> > static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
> > @@ -2523,6 +2534,7 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
> > kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
> > kvfree(kmulti_link->addrs);
> > kvfree(kmulti_link->cookies);
> > + kfree(kmulti_link->mods);
> > kfree(kmulti_link);
> > }
> >
> > @@ -2658,6 +2670,80 @@ static void symbols_swap_r(void *a, void *b, int size, const void *priv)
> > }
> > }
> >
> > +struct module_addr_args {
> > + unsigned long *addrs;
> > + u32 addrs_cnt;
> > + struct module **mods;
> > + int mods_cnt;
> > + int mods_alloc;
> > +};
> > +
> > +static int module_callback(void *data, const char *name,
> > + struct module *mod, unsigned long addr)
> > +{
> > + struct module_addr_args *args = data;
> > + bool realloc = !args->mods;
> > + struct module **mods;
> > +
> > + /* We iterate all modules symbols and for each we:
> > + * - search for it in provided addresses array
> > + * - if found we check if we already have the module pointer stored
> > + * (we iterate modules sequentially, so we can check just the last
> > + * module pointer)
> > + * - take module reference and store it
> > + */
> > + if (!bsearch(&addr, args->addrs, args->addrs_cnt, sizeof(unsigned long),
> > + bpf_kprobe_multi_addrs_cmp))
> > + return 0;
> > +
> > + if (args->mods) {
> > + struct module *prev = NULL;
> > +
> > + if (args->mods_cnt > 1)
> > + prev = args->mods[args->mods_cnt - 1];
> > + if (prev == mod)
> > + return 0;
> > + if (args->mods_cnt == args->mods_alloc)
> > + realloc = true;
> > + }
> > +
> > + if (realloc) {
> > + args->mods_alloc += 100;
> > + mods = krealloc_array(args->mods, args->mods_alloc, sizeof(*mods), GFP_KERNEL);
> > + if (!mods)
> > + return -ENOMEM;
> > + args->mods = mods;
> > + }
> > +
> > + if (!try_module_get(mod))
> > + return -EINVAL;
> > +
> > + args->mods[args->mods_cnt] = mod;
> > + args->mods_cnt++;
> > + return 0;
> > +}
> > +
> > +static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u32 addrs_cnt)
> > +{
> > + struct module_addr_args args = {
> > + .addrs = addrs,
> > + .addrs_cnt = addrs_cnt,
> > + };
> > + int err;
> > +
> > + /* We return either err < 0 in case of error, ... */
> > + err = module_kallsyms_on_each_symbol(module_callback, &args);
> > + if (err) {
> > + kprobe_multi_put_modules(args.mods, args.mods_cnt);
> > + kfree(args.mods);
> > + return err;
> > + }
> > +
> > + /* or number of modules found if everything is ok. */
> > + *mods = args.mods;
> > + return args.mods_cnt;
> > +}
> > +
> > int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
> > {
> > struct bpf_kprobe_multi_link *link = NULL;
> > @@ -2768,7 +2854,21 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
> > bpf_kprobe_multi_cookie_cmp,
> > bpf_kprobe_multi_cookie_swap,
> > link);
> > + } else {
> > + /*
> > + * We need to sort addrs array even if there are no cookies
> > + * provided, to allow bsearch in get_modules_for_addrs.
> > + */
> > + sort(addrs, cnt, sizeof(*addrs),
> > + bpf_kprobe_multi_addrs_cmp, NULL);
> > + }
> > +
> > + err = get_modules_for_addrs(&link->mods, addrs, cnt);
> > + if (err < 0) {
> > + bpf_link_cleanup(&link_primer);
> > + return err;
> > }
> > + link->mods_cnt = err;
> >
> > err = register_fprobe_ips(&link->fp, addrs, cnt);
> > if (err) {
> > --
> > 2.37.3
> >
