Hi Jessica, On Wed, 4 Oct 2017 21:14:13 +0200 Jessica Yu <jeyu@xxxxxxxxxx> wrote: > Improve error handling when arming ftrace-based kprobes. Specifically, if > we fail to arm a ftrace-based kprobe, register_kprobe()/enable_kprobe() > should report an error instead of success. Previously, this has lead to > confusing situations where register_kprobe() would return 0 indicating > success, but the kprobe would not be functional if ftrace registration > during the kprobe arming process had failed. We should therefore take any > errors returned by ftrace into account and propagate this error so that we > do not register/enable kprobes that cannot be armed. This can happen if, > for example, register_ftrace_function() finds an IPMODIFY conflict (since > kprobe_ftrace_ops has this flag set) and returns an error. Such a conflict > is possible since livepatches also set the IPMODIFY flag for their ftrace_ops. > > arm_all_kprobes() keeps its current behavior and attempts to arm all > kprobes. It returns the last encountered error and gives a warning if > not all kprobes could be armed. > > This patch is based on Petr Mladek's original patchset (patches 2 and 3) > back in 2015, which improved kprobes error handling, found here: > > https://lkml.org/lkml/2015/2/26/452 > > However, further work on this had been paused since then and the patches > were not upstreamed. Ok, I have some comment. See below. > > Based-on-patches-by: Petr Mladek <pmladek@xxxxxxxx> > Signed-off-by: Jessica Yu <jeyu@xxxxxxxxxx> > --- > kernel/kprobes.c | 87 +++++++++++++++++++++++++++++++++++++++----------------- > 1 file changed, 61 insertions(+), 26 deletions(-) > > diff --git a/kernel/kprobes.c b/kernel/kprobes.c > index 2d28377a0e32..6e889be0d93c 100644 > --- a/kernel/kprobes.c > +++ b/kernel/kprobes.c > @@ -979,18 +979,27 @@ static int prepare_kprobe(struct kprobe *p) > } > > /* Caller must lock kprobe_mutex */ > -static void arm_kprobe_ftrace(struct kprobe *p) > +static int arm_kprobe_ftrace(struct kprobe *p) > { > - int ret; > + int ret = 0; > > ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, > (unsigned long)p->addr, 0, 0); > - WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); > - kprobe_ftrace_enabled++; > - if (kprobe_ftrace_enabled == 1) { > + if (WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret)) > + return ret; > + > + if (kprobe_ftrace_enabled == 0) { > ret = register_ftrace_function(&kprobe_ftrace_ops); > - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); > + if (WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret)) > + goto err_ftrace; > } > + > + kprobe_ftrace_enabled++; > + return ret; > + > +err_ftrace: > + ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); > + return ret; > } > > /* Caller must lock kprobe_mutex */ > @@ -1009,22 +1018,23 @@ static void disarm_kprobe_ftrace(struct kprobe *p) > } > #else /* !CONFIG_KPROBES_ON_FTRACE */ > #define prepare_kprobe(p) arch_prepare_kprobe(p) > -#define arm_kprobe_ftrace(p) do {} while (0) > +#define arm_kprobe_ftrace(p) (0) > #define disarm_kprobe_ftrace(p) do {} while (0) > #endif > > /* Arm a kprobe with text_mutex */ > -static void arm_kprobe(struct kprobe *kp) > +static int arm_kprobe(struct kprobe *kp) > { > - if (unlikely(kprobe_ftrace(kp))) { > - arm_kprobe_ftrace(kp); > - return; > - } > + if (unlikely(kprobe_ftrace(kp))) > + return arm_kprobe_ftrace(kp); > + > cpus_read_lock(); > mutex_lock(&text_mutex); > __arm_kprobe(kp); > mutex_unlock(&text_mutex); > cpus_read_unlock(); > + > + return 0; > } > > /* Disarm a kprobe with text_mutex */ > @@ -1363,9 +1373,14 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) > > if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { > ap->flags &= ~KPROBE_FLAG_DISABLED; > - if (!kprobes_all_disarmed) > + if (!kprobes_all_disarmed) { > /* Arm the breakpoint again. */ > - arm_kprobe(ap); > + ret = arm_kprobe(ap); > + if (ret) { > + ap->flags |= KPROBE_FLAG_DISABLED; > + list_del_rcu(&p->list); Nice catch :) this list_del_rcu() is important to keep error case behavior sane. > + } > + } > } > return ret; > } > @@ -1570,13 +1585,16 @@ int register_kprobe(struct kprobe *p) > if (ret) > goto out; > > + if (!kprobes_all_disarmed && !kprobe_disabled(p)) { > + ret = arm_kprobe(p); > + if (ret) > + goto out; > + } > + No, this is no good. It is a small chance to hit kprobe on other CPUs before adding it to kprobe_table hashlist. In that case, we will see a stray breakpoint instruction. > INIT_HLIST_NODE(&p->hlist); > hlist_add_head_rcu(&p->hlist, > &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); > > - if (!kprobes_all_disarmed && !kprobe_disabled(p)) > - arm_kprobe(p); > - So, you'll have to rollback by hlist_del_rcu() here. Hmm, by the way, in this case, you also have to add a synchronize_rcu() in the end of error path, so that user can release kprobe right after error return of register_kprobe... (I think that's OK because it is not a hot path) Thank you, -- Masami Hiramatsu <mhiramat@xxxxxxxxxx> -- To unsubscribe from this list: send the line "unsubscribe live-patching" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
