x86/kprobes: Avoid kretprobe recursion bug

Avoid kretprobe recursion loop bg by setting a dummy
kprobes to current_kprobe per-CPU variable.

This bug has been introduced with the asm-coded trampoline
code, since previously it used another kprobe for hooking
the function return placeholder (which only has a nop) and
trampoline handler was called from that kprobe.

This revives the old lost kprobe again.

With this fix, we don't see deadlock anymore.

And you can see that all inner-called kretprobe are skipped.

  event_1                                  235               0
  event_2                                19375           19612

The 1st column is recorded count and the 2nd is missed count.
Above shows (event_1 rec) + (event_2 rec) ~= (event_2 missed)
(some difference are here because the counter is racy)
Reported-by: Andrea Righi <righi.andrea@gmail.com>
Tested-by: Andrea Righi <righi.andrea@gmail.com>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Fixes: c9becf58 ("[PATCH] kretprobe: kretprobe-booster")
Link: http://lkml.kernel.org/r/155094064889.6137.972160690963039.stgit@devboxSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/kprobes/core.c

@@ -749,11 +749,16 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
+static struct kprobe kretprobe_kprobe = {
+	.addr = (void *)kretprobe_trampoline,
+};
+
 /*
  * Called from kretprobe_trampoline
  */
 static __used void *trampoline_handler(struct pt_regs *regs)
 {
+	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
@@ -763,6 +768,17 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 	void *frame_pointer;
 	bool skipped = false;
 
+	preempt_disable();
+
+	/*
+	 * Set a dummy kprobe for avoiding kretprobe recursion.
+	 * Since kretprobe never run in kprobe handler, kprobe must not
+	 * be running at this point.
+	 */
+	kcb = get_kprobe_ctlblk();
+	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
@@ -838,10 +854,9 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
+			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -857,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);