Merge tag 'trace-v5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Have recordmcount work with > 64K sections (to support LTO)

 - kprobe RCU fixes

 - Correct a kprobe critical section with missing mutex

 - Remove redundant arch_disarm_kprobe() call

 - Fix lockup when kretprobe triggers within kprobe_flush_task()

 - Fix memory leak in fetch_op_data operations

 - Fix sleep in atomic in ftrace trace array sample code

 - Free up memory on failure in sample trace array code

 - Fix incorrect reporting of function_graph fields in format file

 - Fix quote within quote parsing in bootconfig

 - Fix return value of bootconfig tool

 - Add testcases for bootconfig tool

 - Fix maybe uninitialized warning in ftrace pid file code

 - Remove unused variable in tracing_iter_reset()

 - Fix some typos

* tag 'trace-v5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  ftrace: Fix maybe-uninitialized compiler warning
  tools/bootconfig: Add testcase for show-command and quotes test
  tools/bootconfig: Fix to return 0 if succeeded to show the bootconfig
  tools/bootconfig: Fix to use correct quotes for value
  proc/bootconfig: Fix to use correct quotes for value
  tracing: Remove unused event variable in tracing_iter_reset
  tracing/probe: Fix memleak in fetch_op_data operations
  trace: Fix typo in allocate_ftrace_ops()'s comment
  tracing: Make ftrace packed events have align of 1
  sample-trace-array: Remove trace_array 'sample-instance'
  sample-trace-array: Fix sleeping function called from invalid context
  kretprobe: Prevent triggering kretprobe from within kprobe_flush_task
  kprobes: Remove redundant arch_disarm_kprobe() call
  kprobes: Fix to protect kick_kprobe_optimizer() by kprobe_mutex
  kprobes: Use non RCU traversal APIs on kprobe_tables if possible
  kprobes: Suppress the suspicious RCU warning on kprobes
  recordmcount: support >64k sections

8 files changed, 88 insertions, 27 deletions

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 50cd84f53df0..4a904cc56d68 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -46,6 +46,11 @@
 
 
 static int kprobes_initialized;
+/* kprobe_table can be accessed by
+ * - Normal hlist traversal and RCU add/del under kprobe_mutex is held.
+ * Or
+ * - RCU hlist traversal under disabling preempt (breakpoint handlers)
+ */
 static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
 static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 
@@ -326,7 +331,8 @@ struct kprobe *get_kprobe(void *addr)
 	struct kprobe *p;
 
 	head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)];
-	hlist_for_each_entry_rcu(p, head, hlist) {
+	hlist_for_each_entry_rcu(p, head, hlist,
+				 lockdep_is_held(&kprobe_mutex)) {
 		if (p->addr == addr)
 			return p;
 	}
@@ -586,11 +592,12 @@ static void kprobe_optimizer(struct work_struct *work)
 	mutex_unlock(&module_mutex);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
-	mutex_unlock(&kprobe_mutex);
 
 	/* Step 5: Kick optimizer again if needed */
 	if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
 		kick_kprobe_optimizer();
+
+	mutex_unlock(&kprobe_mutex);
 }
 
 /* Wait for completing optimization and unoptimization */
@@ -668,8 +675,6 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op)
 	lockdep_assert_cpus_held();
 	arch_unoptimize_kprobe(op);
 	op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
-	if (kprobe_disabled(&op->kp))
-		arch_disarm_kprobe(&op->kp);
 }
 
 /* Unoptimize a kprobe if p is optimized */
@@ -849,7 +854,7 @@ static void optimize_all_kprobes(void)
 	kprobes_allow_optimization = true;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry_rcu(p, head, hlist)
+		hlist_for_each_entry(p, head, hlist)
 			if (!kprobe_disabled(p))
 				optimize_kprobe(p);
 	}
@@ -876,7 +881,7 @@ static void unoptimize_all_kprobes(void)
 	kprobes_allow_optimization = false;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry_rcu(p, head, hlist) {
+		hlist_for_each_entry(p, head, hlist) {
 			if (!kprobe_disabled(p))
 				unoptimize_kprobe(p, false);
 		}
@@ -1236,6 +1241,26 @@ __releases(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
+struct kprobe kprobe_busy = {
+	.addr = (void *) get_kprobe,
+};
+
+void kprobe_busy_begin(void)
+{
+	struct kprobe_ctlblk *kcb;
+
+	preempt_disable();
+	__this_cpu_write(current_kprobe, &kprobe_busy);
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+}
+
+void kprobe_busy_end(void)
+{
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+}
+
 /*
  * This function is called from finish_task_switch when task tk becomes dead,
  * so that we can recycle any function-return probe instances associated
@@ -1253,6 +1278,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		/* Early boot.  kretprobe_table_locks not yet initialized. */
 		return;
 
+	kprobe_busy_begin();
+
 	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
@@ -1266,6 +1293,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		hlist_del(&ri->hlist);
 		kfree(ri);
 	}
+
+	kprobe_busy_end();
 }
 NOKPROBE_SYMBOL(kprobe_flush_task);
 
@@ -1499,12 +1528,14 @@ static struct kprobe *__get_valid_kprobe(struct kprobe *p)
 {
 	struct kprobe *ap, *list_p;
 
+	lockdep_assert_held(&kprobe_mutex);
+
 	ap = get_kprobe(p->addr);
 	if (unlikely(!ap))
 		return NULL;
 
 	if (p != ap) {
-		list_for_each_entry_rcu(list_p, &ap->list, list)
+		list_for_each_entry(list_p, &ap->list, list)
 			if (list_p == p)
 			/* kprobe p is a valid probe */
 				goto valid;
@@ -1669,7 +1700,9 @@ static int aggr_kprobe_disabled(struct kprobe *ap)
 {
 	struct kprobe *kp;
 
-	list_for_each_entry_rcu(kp, &ap->list, list)
+	lockdep_assert_held(&kprobe_mutex);
+
+	list_for_each_entry(kp, &ap->list, list)
 		if (!kprobe_disabled(kp))
 			/*
 			 * There is an active probe on the list.
@@ -1748,7 +1781,7 @@ static int __unregister_kprobe_top(struct kprobe *p)
 	else {
 		/* If disabling probe has special handlers, update aggrprobe */
 		if (p->post_handler && !kprobe_gone(p)) {
-			list_for_each_entry_rcu(list_p, &ap->list, list) {
+			list_for_each_entry(list_p, &ap->list, list) {
 				if ((list_p != p) && (list_p->post_handler))
 					goto noclean;
 			}
@@ -2062,13 +2095,15 @@ static void kill_kprobe(struct kprobe *p)
 {
 	struct kprobe *kp;
 
+	lockdep_assert_held(&kprobe_mutex);
+
 	p->flags |= KPROBE_FLAG_GONE;
 	if (kprobe_aggrprobe(p)) {
 		/*
 		 * If this is an aggr_kprobe, we have to list all the
 		 * chained probes and mark them GONE.
 		 */
-		list_for_each_entry_rcu(kp, &p->list, list)
+		list_for_each_entry(kp, &p->list, list)
 			kp->flags |= KPROBE_FLAG_GONE;
 		p->post_handler = NULL;
 		kill_optimized_kprobe(p);
@@ -2312,7 +2347,7 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	mutex_lock(&kprobe_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry_rcu(p, head, hlist)
+		hlist_for_each_entry(p, head, hlist)
 			if (within_module_init((unsigned long)p->addr, mod) ||
 			    (checkcore &&
 			     within_module_core((unsigned long)p->addr, mod))) {
@@ -2550,7 +2585,7 @@ static int arm_all_kprobes(void)
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		/* Arm all kprobes on a best-effort basis */
-		hlist_for_each_entry_rcu(p, head, hlist) {
+		hlist_for_each_entry(p, head, hlist) {
 			if (!kprobe_disabled(p)) {
 				err = arm_kprobe(p);
 				if (err)  {
@@ -2593,7 +2628,7 @@ static int disarm_all_kprobes(void)
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		/* Disarm all kprobes on a best-effort basis */
-		hlist_for_each_entry_rcu(p, head, hlist) {
+		hlist_for_each_entry(p, head, hlist) {
 			if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) {
 				err = disarm_kprobe(p, false);
 				if (err) {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c163c3531faf..1903b80db6eb 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2260,7 +2260,7 @@ ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,
 
 		if (hash_contains_ip(ip, op->func_hash))
 			return op;
-	} 
+	}
 
 	return NULL;
 }
@@ -3599,7 +3599,7 @@ static int t_show(struct seq_file *m, void *v)
 			if (direct)
 				seq_printf(m, "\n\tdirect-->%pS", (void *)direct);
 		}
-	}	
+	}
 
 	seq_putc(m, '\n');
 
@@ -7151,6 +7151,10 @@ static int pid_open(struct inode *inode, struct file *file, int type)
 	case TRACE_NO_PIDS:
 		seq_ops = &ftrace_no_pid_sops;
 		break;
+	default:
+		trace_array_put(tr);
+		WARN_ON_ONCE(1);
+		return -EINVAL;
 	}
 
 	ret = seq_open(file, seq_ops);
@@ -7229,6 +7233,10 @@ pid_write(struct file *filp, const char __user *ubuf,
 		other_pids = rcu_dereference_protected(tr->function_pids,
 					     lockdep_is_held(&ftrace_lock));
 		break;
+	default:
+		ret = -EINVAL;
+		WARN_ON_ONCE(1);
+		goto out;
 	}
 
 	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ec44b0e2a19c..bb62269724d5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3570,7 +3570,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 {
-	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter;
 	unsigned long entries = 0;
 	u64 ts;
@@ -3588,7 +3587,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 	 * that a reset never took place on a cpu. This is evident
 	 * by the timestamp being before the start of the buffer.
 	 */
-	while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
+	while (ring_buffer_iter_peek(buf_iter, &ts)) {
 		if (ts >= iter->array_buffer->time_start)
 			break;
 		entries++;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index def769df5bf1..13db4000af3f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -61,6 +61,9 @@ enum trace_type {
 #undef __field_desc
 #define __field_desc(type, container, item)
 
+#undef __field_packed
+#define __field_packed(type, container, item)
+
 #undef __array
 #define __array(type, item, size)	type	item[size];
 
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index a523da0dae0a..18c4a58aff79 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -78,8 +78,8 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
 
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
-		__field_desc(	unsigned long,	graph_ent,	func		)
-		__field_desc(	int,		graph_ent,	depth		)
+		__field_packed(	unsigned long,	graph_ent,	func		)
+		__field_packed(	int,		graph_ent,	depth		)
 	),
 
 	F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth)
@@ -92,11 +92,11 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ret,	ret	)
-		__field_desc(	unsigned long,	ret,		func	)
-		__field_desc(	unsigned long,	ret,		overrun	)
-		__field_desc(	unsigned long long, ret,	calltime)
-		__field_desc(	unsigned long long, ret,	rettime	)
-		__field_desc(	int,		ret,		depth	)
+		__field_packed(	unsigned long,	ret,		func	)
+		__field_packed(	unsigned long,	ret,		overrun	)
+		__field_packed(	unsigned long long, ret,	calltime)
+		__field_packed(	unsigned long long, ret,	rettime	)
+		__field_packed(	int,		ret,		depth	)
 	),
 
 	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d",
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 77ce5a3b6773..70d3d0a09053 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -45,6 +45,9 @@ static int ftrace_event_register(struct trace_event_call *call,
 #undef __field_desc
 #define __field_desc(type, container, item)		type item;
 
+#undef __field_packed
+#define __field_packed(type, container, item)		type item;
+
 #undef __array
 #define __array(type, item, size)			type item[size];
 
@@ -85,6 +88,13 @@ static void __always_unused ____ftrace_check_##name(void)		\
 	.size = sizeof(_type), .align = __alignof__(_type),		\
 	is_signed_type(_type), .filter_type = _filter_type },
 
+
+#undef __field_ext_packed
+#define __field_ext_packed(_type, _item, _filter_type) {	\
+	.type = #_type, .name = #_item,				\
+	.size = sizeof(_type), .align = 1,			\
+	is_signed_type(_type), .filter_type = _filter_type },
+
 #undef __field
 #define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER)
 
@@ -94,6 +104,9 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #undef __field_desc
 #define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER)
 
+#undef __field_packed
+#define __field_packed(_type, _container, _item) __field_ext_packed(_type, _item, FILTER_OTHER)
+
 #undef __array
 #define __array(_type, _item, _len) {					\
 	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
@@ -129,6 +142,9 @@ static struct trace_event_fields ftrace_event_fields_##name[] = {	\
 #undef __field_desc
 #define __field_desc(type, container, item)
 
+#undef __field_packed
+#define __field_packed(type, container, item)
+
 #undef __array
 #define __array(type, item, len)
 
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8a4c8d5c2c98..dd4dff71d89a 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -42,7 +42,7 @@ static int allocate_ftrace_ops(struct trace_array *tr)
 	if (!ops)
 		return -ENOMEM;
 
-	/* Currently only the non stack verision is supported */
+	/* Currently only the non stack version is supported */
 	ops->func = function_trace_call;
 	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID;
 
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index b8a928e925c7..d2867ccc6aca 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -639,8 +639,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			ret = -EINVAL;
 			goto fail;
 		}
-		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) ||
-		     parg->count) {
+		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM ||
+		     code->op == FETCH_OP_DATA) || parg->count) {
 			/*
 			 * IMM, DATA and COMM is pointing actual address, those
 			 * must be kept, and if parg->count != 0, this is an