Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Misc fixes:
   - various tooling fixes
   - kretprobe fixes
   - kprobes annotation fixes
   - kprobes error checking fix
   - fix the default events for AMD Family 17h CPUs
   - PEBS fix
   - AUX record fix
   - address filtering fix"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/kprobes: Avoid kretprobe recursion bug
  kprobes: Mark ftrace mcount handler functions nokprobe
  x86/kprobes: Verify stack frame on kretprobe
  perf/x86/amd: Add event map for AMD Family 17h
  perf bpf: Return NULL when RB tree lookup fails in perf_env__find_btf()
  perf tools: Fix map reference counting
  perf evlist: Fix side band thread draining
  perf tools: Check maps for bpf programs
  perf bpf: Return NULL when RB tree lookup fails in perf_env__find_bpf_prog_info()
  tools include uapi: Sync sound/asound.h copy
  perf top: Always sample time to satisfy needs of use of ordered queuing
  perf evsel: Use hweight64() instead of hweight_long(attr.sample_regs_user)
  tools lib traceevent: Fix missing equality check for strcmp
  perf stat: Disable DIR_FORMAT feature for 'perf stat record'
  perf scripts python: export-to-sqlite.py: Fix use of parent_id in calls_view
  perf header: Fix lock/unlock imbalances when processing BPF/BTF info
  perf/x86: Fix incorrect PEBS_REGS
  perf/ring_buffer: Fix AUX record suppression
  perf/core: Fix the address filtering fix
  kprobes: Fix error check when reusing optimized probes

1 files changed, 46 insertions, 2 deletions

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a034cb808e7e..fed46ddb1eef 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 	unsigned long *sara = stack_addr(regs);
 
 	ri->ret_addr = (kprobe_opcode_t *) *sara;
+	ri->fp = sara;
 
 	/* Replace the return addr with trampoline addr */
 	*sara = (unsigned long) &kretprobe_trampoline;
@@ -748,26 +749,48 @@ 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;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 	kprobe_opcode_t *correct_ret_addr = NULL;
+	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 */
 #ifdef CONFIG_X86_64
 	regs->cs = __KERNEL_CS;
+	/* On x86-64, we use pt_regs->sp for return address holder. */
+	frame_pointer = &regs->sp;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
 	regs->gs = 0;
+	/* On x86-32, we use pt_regs->flags for return address holder. */
+	frame_pointer = &regs->flags;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
@@ -789,8 +812,25 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		/*
+		 * Return probes must be pushed on this hash list correct
+		 * order (same as return order) so that it can be poped
+		 * correctly. However, if we find it is pushed it incorrect
+		 * order, this means we find a function which should not be
+		 * probed, because the wrong order entry is pushed on the
+		 * path of processing other kretprobe itself.
+		 */
+		if (ri->fp != frame_pointer) {
+			if (!skipped)
+				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+			skipped = true;
+			continue;
+		}
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
+		if (skipped)
+			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+				ri->rp->kp.addr);
 
 		if (orig_ret_address != trampoline_address)
 			/*
@@ -808,14 +848,15 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		if (ri->fp != frame_pointer)
+			continue;
 
 		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);
@@ -831,6 +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);