Merge tag 'trace-v5.11-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Initialize tracing-graph-pause at task creation, not start of
   function tracing, to avoid corrupting the pause counter.

 - Set "pause-on-trace" for latency tracers as that option breaks their
   output (regression).

 - Fix the wrong error return for setting kretprobes on future modules
   (before they are loaded).

 - Fix re-registering the same kretprobe.

 - Add missing value check for added RCU variable reload.

* tag 'trace-v5.11-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  tracepoint: Fix race between tracing and removing tracepoint
  kretprobe: Avoid re-registration of the same kretprobe earlier
  tracing/kprobe: Fix to support kretprobe events on unloaded modules
  tracing: Use pause-on-trace with the latency tracers
  fgraph: Initialize tracing_graph_pause at task creation

include/linux/kprobes.h

@@ -266,7 +266,7 @@ extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
 extern int arch_populate_kprobe_blacklist(void);
 extern bool arch_kprobe_on_func_entry(unsigned long offset);
-extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
+extern int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
 
 extern bool within_kprobe_blacklist(unsigned long addr);
 extern int kprobe_add_ksym_blacklist(unsigned long entry);

include/linux/tracepoint.h

@@ -307,11 +307,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 									\
 		it_func_ptr =						\
 			rcu_dereference_raw((&__tracepoint_##_name)->funcs); \
-		do {							\
-			it_func = (it_func_ptr)->func;			\
-			__data = (it_func_ptr)->data;			\
-			((void(*)(void *, proto))(it_func))(__data, args); \
-		} while ((++it_func_ptr)->func);			\
+		if (it_func_ptr) {					\
+			do {						\
+				it_func = (it_func_ptr)->func;		\
+				__data = (it_func_ptr)->data;		\
+				((void(*)(void *, proto))(it_func))(__data, args); \
+			} while ((++it_func_ptr)->func);		\
+		}							\
 		return 0;						\
 	}								\
 	DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name);

init/init_task.c

@@ -198,7 +198,8 @@ struct task_struct init_task
 	.lockdep_recursion = 0,
 #endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	.ret_stack	= NULL,
+	.ret_stack		= NULL,
+	.tracing_graph_pause	= ATOMIC_INIT(0),
 #endif
 #if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPTION)
 	.trace_recursion = 0,

kernel/kprobes.c

@@ -1954,28 +1954,48 @@ bool __weak arch_kprobe_on_func_entry(unsigned long offset)
 	return !offset;
 }
 
-bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
+/**
+ * kprobe_on_func_entry() -- check whether given address is function entry
+ * @addr: Target address
+ * @sym:  Target symbol name
+ * @offset: The offset from the symbol or the address
+ *
+ * This checks whether the given @addr+@offset or @sym+@offset is on the
+ * function entry address or not.
+ * This returns 0 if it is the function entry, or -EINVAL if it is not.
+ * And also it returns -ENOENT if it fails the symbol or address lookup.
+ * Caller must pass @addr or @sym (either one must be NULL), or this
+ * returns -EINVAL.
+ */
+int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
 {
 	kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
 
 	if (IS_ERR(kp_addr))
-		return false;
+		return PTR_ERR(kp_addr);
 
-	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) ||
-						!arch_kprobe_on_func_entry(offset))
-		return false;
+	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset))
+		return -ENOENT;
 
-	return true;
+	if (!arch_kprobe_on_func_entry(offset))
+		return -EINVAL;
+
+	return 0;
 }
 
 int register_kretprobe(struct kretprobe *rp)
 {
-	int ret = 0;
+	int ret;
 	struct kretprobe_instance *inst;
 	int i;
 	void *addr;
 
-	if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset))
+	ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset);
+	if (ret)
+		return ret;
+
+	/* If only rp->kp.addr is specified, check reregistering kprobes */
+	if (rp->kp.addr && check_kprobe_rereg(&rp->kp))
 		return -EINVAL;
 
 	if (kretprobe_blacklist_size) {

kernel/trace/fgraph.c

@@ -394,7 +394,6 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 		}
 
 		if (t->ret_stack == NULL) {
-			atomic_set(&t->tracing_graph_pause, 0);
 			atomic_set(&t->trace_overrun, 0);
 			t->curr_ret_stack = -1;
 			t->curr_ret_depth = -1;
@@ -489,7 +488,6 @@ static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack);
 static void
 graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
 {
-	atomic_set(&t->tracing_graph_pause, 0);
 	atomic_set(&t->trace_overrun, 0);
 	t->ftrace_timestamp = 0;
 	/* make curr_ret_stack visible before we add the ret_stack */

kernel/trace/trace_irqsoff.c

@@ -562,6 +562,8 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
 	/* non overwrite screws up the latency tracers */
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
+	/* without pause, we will produce garbage if another latency occurs */
+	set_tracer_flag(tr, TRACE_ITER_PAUSE_ON_TRACE, 1);
 
 	tr->max_latency = 0;
 	irqsoff_trace = tr;
@@ -583,11 +585,13 @@ static void __irqsoff_tracer_reset(struct trace_array *tr)
 {
 	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
 	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+	int pause_flag = save_flags & TRACE_ITER_PAUSE_ON_TRACE;
 
 	stop_irqsoff_tracer(tr, is_graph(tr));
 
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
+	set_tracer_flag(tr, TRACE_ITER_PAUSE_ON_TRACE, pause_flag);
 	ftrace_reset_array_ops(tr);
 
 	irqsoff_busy = false;

kernel/trace/trace_kprobe.c

@@ -221,9 +221,9 @@ bool trace_kprobe_on_func_entry(struct trace_event_call *call)
 {
 	struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);
 
-	return tk ? kprobe_on_func_entry(tk->rp.kp.addr,
+	return tk ? (kprobe_on_func_entry(tk->rp.kp.addr,
 			tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name,
-			tk->rp.kp.addr ? 0 : tk->rp.kp.offset) : false;
+			tk->rp.kp.addr ? 0 : tk->rp.kp.offset) == 0) : false;
 }
 
 bool trace_kprobe_error_injectable(struct trace_event_call *call)
@@ -828,9 +828,11 @@ static int trace_kprobe_create(int argc, const char *argv[])
 		}
 		if (is_return)
 			flags |= TPARG_FL_RETURN;
-		if (kprobe_on_func_entry(NULL, symbol, offset))
+		ret = kprobe_on_func_entry(NULL, symbol, offset);
+		if (ret == 0)
 			flags |= TPARG_FL_FENTRY;
-		if (offset && is_return && !(flags & TPARG_FL_FENTRY)) {
+		/* Defer the ENOENT case until register kprobe */
+		if (ret == -EINVAL && is_return) {
 			trace_probe_log_err(0, BAD_RETPROBE);
 			goto parse_error;
 		}