Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core

7 files changed, 419 insertions, 152 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a0e246e2cee3..c3e4575e7829 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -88,6 +88,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly = {
 static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
@@ -146,9 +147,11 @@ void clear_ftrace_function(void)
 {
 	ftrace_trace_function = ftrace_stub;
 	__ftrace_trace_function = ftrace_stub;
+	__ftrace_trace_function_delay = ftrace_stub;
 	ftrace_pid_function = ftrace_stub;
 }
 
+#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 /*
  * For those archs that do not test ftrace_trace_stop in their
@@ -208,7 +211,12 @@ static void update_ftrace_function(void)
 #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	ftrace_trace_function = func;
 #else
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* do not update till all functions have been modified */
+	__ftrace_trace_function_delay = func;
+#else
 	__ftrace_trace_function = func;
+#endif
 	ftrace_trace_function = ftrace_test_stop_func;
 #endif
 }
@@ -1170,8 +1178,14 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 	return NULL;
 }
 
+static void
+ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash);
+static void
+ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash);
+
 static int
-ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
+ftrace_hash_move(struct ftrace_ops *ops, int enable,
+		 struct ftrace_hash **dst, struct ftrace_hash *src)
 {
 	struct ftrace_func_entry *entry;
 	struct hlist_node *tp, *tn;
@@ -1181,9 +1195,16 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	unsigned long key;
 	int size = src->count;
 	int bits = 0;
+	int ret;
 	int i;
 
 	/*
+	 * Remove the current set, update the hash and add
+	 * them back.
+	 */
+	ftrace_hash_rec_disable(ops, enable);
+
+	/*
 	 * If the new source is empty, just free dst and assign it
 	 * the empty_hash.
 	 */
@@ -1203,9 +1224,10 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	if (bits > FTRACE_HASH_MAX_BITS)
 		bits = FTRACE_HASH_MAX_BITS;
 
+	ret = -ENOMEM;
 	new_hash = alloc_ftrace_hash(bits);
 	if (!new_hash)
-		return -ENOMEM;
+		goto out;
 
 	size = 1 << src->size_bits;
 	for (i = 0; i < size; i++) {
@@ -1224,7 +1246,16 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	rcu_assign_pointer(*dst, new_hash);
 	free_ftrace_hash_rcu(old_hash);
 
-	return 0;
+	ret = 0;
+ out:
+	/*
+	 * Enable regardless of ret:
+	 *  On success, we enable the new hash.
+	 *  On failure, we re-enable the original hash.
+	 */
+	ftrace_hash_rec_enable(ops, enable);
+
+	return ret;
 }
 
 /*
@@ -1584,6 +1615,12 @@ static int __ftrace_modify_code(void *data)
 {
 	int *command = data;
 
+	/*
+	 * Do not call function tracer while we update the code.
+	 * We are in stop machine, no worrying about races.
+	 */
+	function_trace_stop++;
+
 	if (*command & FTRACE_ENABLE_CALLS)
 		ftrace_replace_code(1);
 	else if (*command & FTRACE_DISABLE_CALLS)
@@ -1597,6 +1634,18 @@ static int __ftrace_modify_code(void *data)
 	else if (*command & FTRACE_STOP_FUNC_RET)
 		ftrace_disable_ftrace_graph_caller();
 
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	/*
+	 * For archs that call ftrace_test_stop_func(), we must
+	 * wait till after we update all the function callers
+	 * before we update the callback. This keeps different
+	 * ops that record different functions from corrupting
+	 * each other.
+	 */
+	__ftrace_trace_function = __ftrace_trace_function_delay;
+#endif
+	function_trace_stop--;
+
 	return 0;
 }
 
@@ -2865,7 +2914,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 		ftrace_match_records(hash, buf, len);
 
 	mutex_lock(&ftrace_lock);
-	ret = ftrace_hash_move(orig_hash, hash);
+	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
+	if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED
+	    && ftrace_enabled)
+		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+
 	mutex_unlock(&ftrace_lock);
 
 	mutex_unlock(&ftrace_regex_lock);
@@ -3048,18 +3101,12 @@ ftrace_regex_release(struct inode *inode, struct file *file)
 			orig_hash = &iter->ops->notrace_hash;
 
 		mutex_lock(&ftrace_lock);
-		/*
-		 * Remove the current set, update the hash and add
-		 * them back.
-		 */
-		ftrace_hash_rec_disable(iter->ops, filter_hash);
-		ret = ftrace_hash_move(orig_hash, iter->hash);
-		if (!ret) {
-			ftrace_hash_rec_enable(iter->ops, filter_hash);
-			if (iter->ops->flags & FTRACE_OPS_FL_ENABLED
-			    && ftrace_enabled)
-				ftrace_run_update_code(FTRACE_ENABLE_CALLS);
-		}
+		ret = ftrace_hash_move(iter->ops, filter_hash,
+				       orig_hash, iter->hash);
+		if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED)
+		    && ftrace_enabled)
+			ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+
 		mutex_unlock(&ftrace_lock);
 	}
 	free_ftrace_hash(iter->hash);
@@ -3338,7 +3385,7 @@ static int ftrace_process_locs(struct module *mod,
 {
 	unsigned long *p;
 	unsigned long addr;
-	unsigned long flags;
+	unsigned long flags = 0; /* Shut up gcc */
 
 	mutex_lock(&ftrace_lock);
 	p = start;
@@ -3356,12 +3403,18 @@ static int ftrace_process_locs(struct module *mod,
 	}
 
 	/*
-	 * Disable interrupts to prevent interrupts from executing
-	 * code that is being modified.
+	 * We only need to disable interrupts on start up
+	 * because we are modifying code that an interrupt
+	 * may execute, and the modification is not atomic.
+	 * But for modules, nothing runs the code we modify
+	 * until we are finished with it, and there's no
+	 * reason to cause large interrupt latencies while we do it.
 	 */
-	local_irq_save(flags);
+	if (!mod)
+		local_irq_save(flags);
 	ftrace_update_code(mod);
-	local_irq_restore(flags);
+	if (!mod)
+		local_irq_restore(flags);
 	mutex_unlock(&ftrace_lock);
 
 	return 0;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d9c16123f6e2..e5df02c69b1d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1248,6 +1248,15 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 }
 
 #ifdef CONFIG_STACKTRACE
+
+#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
+struct ftrace_stack {
+	unsigned long		calls[FTRACE_STACK_MAX_ENTRIES];
+};
+
+static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+static DEFINE_PER_CPU(int, ftrace_stack_reserve);
+
 static void __ftrace_trace_stack(struct ring_buffer *buffer,
 				 unsigned long flags,
 				 int skip, int pc, struct pt_regs *regs)
@@ -1256,25 +1265,77 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 	struct stack_trace trace;
+	int use_stack;
+	int size = FTRACE_STACK_ENTRIES;
+
+	trace.nr_entries	= 0;
+	trace.skip		= skip;
+
+	/*
+	 * Since events can happen in NMIs there's no safe way to
+	 * use the per cpu ftrace_stacks. We reserve it and if an interrupt
+	 * or NMI comes in, it will just have to use the default
+	 * FTRACE_STACK_SIZE.
+	 */
+	preempt_disable_notrace();
+
+	use_stack = ++__get_cpu_var(ftrace_stack_reserve);
+	/*
+	 * We don't need any atomic variables, just a barrier.
+	 * If an interrupt comes in, we don't care, because it would
+	 * have exited and put the counter back to what we want.
+	 * We just need a barrier to keep gcc from moving things
+	 * around.
+	 */
+	barrier();
+	if (use_stack == 1) {
+		trace.entries		= &__get_cpu_var(ftrace_stack).calls[0];
+		trace.max_entries	= FTRACE_STACK_MAX_ENTRIES;
+
+		if (regs)
+			save_stack_trace_regs(regs, &trace);
+		else
+			save_stack_trace(&trace);
+
+		if (trace.nr_entries > size)
+			size = trace.nr_entries;
+	} else
+		/* From now on, use_stack is a boolean */
+		use_stack = 0;
+
+	size *= sizeof(unsigned long);
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
-					  sizeof(*entry), flags, pc);
+					  sizeof(*entry) + size, flags, pc);
 	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	memset(&entry->caller, 0, sizeof(entry->caller));
+		goto out;
+	entry = ring_buffer_event_data(event);
 
-	trace.nr_entries	= 0;
-	trace.max_entries	= FTRACE_STACK_ENTRIES;
-	trace.skip		= skip;
-	trace.entries		= entry->caller;
+	memset(&entry->caller, 0, size);
+
+	if (use_stack)
+		memcpy(&entry->caller, trace.entries,
+		       trace.nr_entries * sizeof(unsigned long));
+	else {
+		trace.max_entries	= FTRACE_STACK_ENTRIES;
+		trace.entries		= entry->caller;
+		if (regs)
+			save_stack_trace_regs(regs, &trace);
+		else
+			save_stack_trace(&trace);
+	}
+
+	entry->size = trace.nr_entries;
 
-	if (regs)
-		save_stack_trace_regs(regs, &trace);
-	else
-		save_stack_trace(&trace);
 	if (!filter_check_discard(call, entry, buffer, event))
 		ring_buffer_unlock_commit(buffer, event);
+
+ out:
+	/* Again, don't let gcc optimize things here */
+	barrier();
+	__get_cpu_var(ftrace_stack_reserve)--;
+	preempt_enable_notrace();
+
 }
 
 void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
@@ -1562,7 +1623,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 
 	ftrace_enable_cpu();
 
-	return event ? ring_buffer_event_data(event) : NULL;
+	if (event) {
+		iter->ent_size = ring_buffer_event_length(event);
+		return ring_buffer_event_data(event);
+	}
+	iter->ent_size = 0;
+	return NULL;
 }
 
 static struct trace_entry *
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 30a94c26dcb3..3f381d0b20a8 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -278,6 +278,29 @@ struct tracer {
 };
 
 
+/* Only current can touch trace_recursion */
+#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
+#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
+
+/* Ring buffer has the 10 LSB bits to count */
+#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+
+/* for function tracing recursion */
+#define TRACE_INTERNAL_BIT		(1<<11)
+#define TRACE_GLOBAL_BIT		(1<<12)
+/*
+ * Abuse of the trace_recursion.
+ * As we need a way to maintain state if we are tracing the function
+ * graph in irq because we want to trace a particular function that
+ * was called in irq context but we have irq tracing off. Since this
+ * can only be modified by current, we can reuse trace_recursion.
+ */
+#define TRACE_IRQ_BIT			(1<<13)
+
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
+
 #define TRACE_PIPE_ALL_CPU	-1
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
@@ -516,8 +539,18 @@ static inline int ftrace_graph_addr(unsigned long addr)
 		return 1;
 
 	for (i = 0; i < ftrace_graph_count; i++) {
-		if (addr == ftrace_graph_funcs[i])
+		if (addr == ftrace_graph_funcs[i]) {
+			/*
+			 * If no irqs are to be traced, but a set_graph_function
+			 * is set, and called by an interrupt handler, we still
+			 * want to trace it.
+			 */
+			if (in_irq())
+				trace_recursion_set(TRACE_IRQ_BIT);
+			else
+				trace_recursion_clear(TRACE_IRQ_BIT);
 			return 1;
+		}
 	}
 
 	return 0;
@@ -795,19 +828,4 @@ extern const char *__stop___trace_bprintk_fmt[];
 	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
-/* Only current can touch trace_recursion */
-#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
-#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
-
-/* Ring buffer has the 10 LSB bits to count */
-#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
-
-/* for function tracing recursion */
-#define TRACE_INTERNAL_BIT		(1<<11)
-#define TRACE_GLOBAL_BIT		(1<<12)
-
-#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
-#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
-#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
-
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e32744c84d94..93365907f219 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -161,7 +161,8 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 	TRACE_STACK,
 
 	F_STRUCT(
-		__array(	unsigned long,	caller, FTRACE_STACK_ENTRIES	)
+		__field(	int,		size	)
+		__dynamic_array(unsigned long,	caller	)
 	),
 
 	F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index e8d6bb55d719..a7d2a4c653d8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -227,7 +227,7 @@ int __trace_graph_entry(struct trace_array *tr,
 
 static inline int ftrace_graph_ignore_irqs(void)
 {
-	if (!ftrace_graph_skip_irqs)
+	if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
 		return 0;
 
 	return in_irq();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7db7b68c6c37..5fb3697bf0e5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -343,6 +343,14 @@ DEFINE_BASIC_FETCH_FUNCS(deref)
 DEFINE_FETCH_deref(string)
 DEFINE_FETCH_deref(string_size)
 
+static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
+{
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		update_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		update_symbol_cache(data->orig.data);
+}
+
 static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 {
 	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
@@ -377,6 +385,19 @@ DEFINE_BASIC_FETCH_FUNCS(bitfield)
 #define fetch_bitfield_string_size NULL
 
 static __kprobes void
+update_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+	/*
+	 * Don't check the bitfield itself, because this must be the
+	 * last fetch function.
+	 */
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		update_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		update_symbol_cache(data->orig.data);
+}
+
+static __kprobes void
 free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 {
 	/*
@@ -389,6 +410,7 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 		free_symbol_cache(data->orig.data);
 	kfree(data);
 }
+
 /* Default (unsigned long) fetch type */
 #define __DEFAULT_FETCH_TYPE(t) u##t
 #define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
@@ -536,6 +558,7 @@ struct probe_arg {
 /* Flags for trace_probe */
 #define TP_FLAG_TRACE	1
 #define TP_FLAG_PROFILE	2
+#define TP_FLAG_REGISTERED 4
 
 struct trace_probe {
 	struct list_head	list;
@@ -555,16 +578,49 @@ struct trace_probe {
 	(sizeof(struct probe_arg) * (n)))
 
 
-static __kprobes int probe_is_return(struct trace_probe *tp)
+static __kprobes int trace_probe_is_return(struct trace_probe *tp)
 {
 	return tp->rp.handler != NULL;
 }
 
-static __kprobes const char *probe_symbol(struct trace_probe *tp)
+static __kprobes const char *trace_probe_symbol(struct trace_probe *tp)
 {
 	return tp->symbol ? tp->symbol : "unknown";
 }
 
+static __kprobes unsigned long trace_probe_offset(struct trace_probe *tp)
+{
+	return tp->rp.kp.offset;
+}
+
+static __kprobes bool trace_probe_is_enabled(struct trace_probe *tp)
+{
+	return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+}
+
+static __kprobes bool trace_probe_is_registered(struct trace_probe *tp)
+{
+	return !!(tp->flags & TP_FLAG_REGISTERED);
+}
+
+static __kprobes bool trace_probe_has_gone(struct trace_probe *tp)
+{
+	return !!(kprobe_gone(&tp->rp.kp));
+}
+
+static __kprobes bool trace_probe_within_module(struct trace_probe *tp,
+						struct module *mod)
+{
+	int len = strlen(mod->name);
+	const char *name = trace_probe_symbol(tp);
+	return strncmp(mod->name, name, len) == 0 && name[len] == ':';
+}
+
+static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp)
+{
+	return !!strchr(trace_probe_symbol(tp), ':');
+}
+
 static int register_probe_event(struct trace_probe *tp);
 static void unregister_probe_event(struct trace_probe *tp);
 
@@ -646,6 +702,16 @@ error:
 	return ERR_PTR(ret);
 }
 
+static void update_probe_arg(struct probe_arg *arg)
+{
+	if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+		update_bitfield_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+		update_deref_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
+		update_symbol_cache(arg->fetch.data);
+}
+
 static void free_probe_arg(struct probe_arg *arg)
 {
 	if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
@@ -671,7 +737,7 @@ static void free_trace_probe(struct trace_probe *tp)
 	kfree(tp);
 }
 
-static struct trace_probe *find_probe_event(const char *event,
+static struct trace_probe *find_trace_probe(const char *event,
 					    const char *group)
 {
 	struct trace_probe *tp;
@@ -683,13 +749,96 @@ static struct trace_probe *find_probe_event(const char *event,
 	return NULL;
 }
 
+/* Enable trace_probe - @flag must be TP_FLAG_TRACE or TP_FLAG_PROFILE */
+static int enable_trace_probe(struct trace_probe *tp, int flag)
+{
+	int ret = 0;
+
+	tp->flags |= flag;
+	if (trace_probe_is_enabled(tp) && trace_probe_is_registered(tp) &&
+	    !trace_probe_has_gone(tp)) {
+		if (trace_probe_is_return(tp))
+			ret = enable_kretprobe(&tp->rp);
+		else
+			ret = enable_kprobe(&tp->rp.kp);
+	}
+
+	return ret;
+}
+
+/* Disable trace_probe - @flag must be TP_FLAG_TRACE or TP_FLAG_PROFILE */
+static void disable_trace_probe(struct trace_probe *tp, int flag)
+{
+	tp->flags &= ~flag;
+	if (!trace_probe_is_enabled(tp) && trace_probe_is_registered(tp)) {
+		if (trace_probe_is_return(tp))
+			disable_kretprobe(&tp->rp);
+		else
+			disable_kprobe(&tp->rp.kp);
+	}
+}
+
+/* Internal register function - just handle k*probes and flags */
+static int __register_trace_probe(struct trace_probe *tp)
+{
+	int i, ret;
+
+	if (trace_probe_is_registered(tp))
+		return -EINVAL;
+
+	for (i = 0; i < tp->nr_args; i++)
+		update_probe_arg(&tp->args[i]);
+
+	/* Set/clear disabled flag according to tp->flag */
+	if (trace_probe_is_enabled(tp))
+		tp->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
+	else
+		tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+
+	if (trace_probe_is_return(tp))
+		ret = register_kretprobe(&tp->rp);
+	else
+		ret = register_kprobe(&tp->rp.kp);
+
+	if (ret == 0)
+		tp->flags |= TP_FLAG_REGISTERED;
+	else {
+		pr_warning("Could not insert probe at %s+%lu: %d\n",
+			   trace_probe_symbol(tp), trace_probe_offset(tp), ret);
+		if (ret == -ENOENT && trace_probe_is_on_module(tp)) {
+			pr_warning("This probe might be able to register after"
+				   "target module is loaded. Continue.\n");
+			ret = 0;
+		} else if (ret == -EILSEQ) {
+			pr_warning("Probing address(0x%p) is not an "
+				   "instruction boundary.\n",
+				   tp->rp.kp.addr);
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+/* Internal unregister function - just handle k*probes and flags */
+static void __unregister_trace_probe(struct trace_probe *tp)
+{
+	if (trace_probe_is_registered(tp)) {
+		if (trace_probe_is_return(tp))
+			unregister_kretprobe(&tp->rp);
+		else
+			unregister_kprobe(&tp->rp.kp);
+		tp->flags &= ~TP_FLAG_REGISTERED;
+		/* Cleanup kprobe for reuse */
+		if (tp->rp.kp.symbol_name)
+			tp->rp.kp.addr = NULL;
+	}
+}
+
 /* Unregister a trace_probe and probe_event: call with locking probe_lock */
 static void unregister_trace_probe(struct trace_probe *tp)
 {
-	if (probe_is_return(tp))
-		unregister_kretprobe(&tp->rp);
-	else
-		unregister_kprobe(&tp->rp.kp);
+	__unregister_trace_probe(tp);
 	list_del(&tp->list);
 	unregister_probe_event(tp);
 }
@@ -702,41 +851,65 @@ static int register_trace_probe(struct trace_probe *tp)
 
 	mutex_lock(&probe_lock);
 
-	/* register as an event */
-	old_tp = find_probe_event(tp->call.name, tp->call.class->system);
+	/* Delete old (same name) event if exist */
+	old_tp = find_trace_probe(tp->call.name, tp->call.class->system);
 	if (old_tp) {
-		/* delete old event */
 		unregister_trace_probe(old_tp);
 		free_trace_probe(old_tp);
 	}
+
+	/* Register new event */
 	ret = register_probe_event(tp);
 	if (ret) {
 		pr_warning("Failed to register probe event(%d)\n", ret);
 		goto end;
 	}
 
-	tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
-	if (probe_is_return(tp))
-		ret = register_kretprobe(&tp->rp);
-	else
-		ret = register_kprobe(&tp->rp.kp);
-
-	if (ret) {
-		pr_warning("Could not insert probe(%d)\n", ret);
-		if (ret == -EILSEQ) {
-			pr_warning("Probing address(0x%p) is not an "
-				   "instruction boundary.\n",
-				   tp->rp.kp.addr);
-			ret = -EINVAL;
-		}
+	/* Register k*probe */
+	ret = __register_trace_probe(tp);
+	if (ret < 0)
 		unregister_probe_event(tp);
-	} else
+	else
 		list_add_tail(&tp->list, &probe_list);
+
 end:
 	mutex_unlock(&probe_lock);
 	return ret;
 }
 
+/* Module notifier call back, checking event on the module */
+static int trace_probe_module_callback(struct notifier_block *nb,
+				       unsigned long val, void *data)
+{
+	struct module *mod = data;
+	struct trace_probe *tp;
+	int ret;
+
+	if (val != MODULE_STATE_COMING)
+		return NOTIFY_DONE;
+
+	/* Update probes on coming module */
+	mutex_lock(&probe_lock);
+	list_for_each_entry(tp, &probe_list, list) {
+		if (trace_probe_within_module(tp, mod)) {
+			__unregister_trace_probe(tp);
+			ret = __register_trace_probe(tp);
+			if (ret)
+				pr_warning("Failed to re-register probe %s on"
+					   "%s: %d\n",
+					   tp->call.name, mod->name, ret);
+		}
+	}
+	mutex_unlock(&probe_lock);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block trace_probe_module_nb = {
+	.notifier_call = trace_probe_module_callback,
+	.priority = 1	/* Invoked after kprobe module callback */
+};
+
 /* Split symbol and offset. */
 static int split_symbol_offset(char *symbol, unsigned long *offset)
 {
@@ -962,8 +1135,8 @@ static int create_trace_probe(int argc, char **argv)
 {
 	/*
 	 * Argument syntax:
-	 *  - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
-	 *  - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
+	 *  - Add kprobe: p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
+	 *  - Add kretprobe: r[:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
 	 * Fetch args:
 	 *  $retval	: fetch return value
 	 *  $stack	: fetch stack address
@@ -1025,7 +1198,7 @@ static int create_trace_probe(int argc, char **argv)
 			return -EINVAL;
 		}
 		mutex_lock(&probe_lock);
-		tp = find_probe_event(event, group);
+		tp = find_trace_probe(event, group);
 		if (!tp) {
 			mutex_unlock(&probe_lock);
 			pr_info("Event %s/%s doesn't exist.\n", group, event);
@@ -1144,7 +1317,7 @@ error:
 	return ret;
 }
 
-static void cleanup_all_probes(void)
+static void release_all_trace_probes(void)
 {
 	struct trace_probe *tp;
 
@@ -1158,7 +1331,6 @@ static void cleanup_all_probes(void)
 	mutex_unlock(&probe_lock);
 }
 
-
 /* Probes listing interfaces */
 static void *probes_seq_start(struct seq_file *m, loff_t *pos)
 {
@@ -1181,15 +1353,16 @@ static int probes_seq_show(struct seq_file *m, void *v)
 	struct trace_probe *tp = v;
 	int i;
 
-	seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+	seq_printf(m, "%c", trace_probe_is_return(tp) ? 'r' : 'p');
 	seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
 
 	if (!tp->symbol)
 		seq_printf(m, " 0x%p", tp->rp.kp.addr);
 	else if (tp->rp.kp.offset)
-		seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset);
+		seq_printf(m, " %s+%u", trace_probe_symbol(tp),
+			   tp->rp.kp.offset);
 	else
-		seq_printf(m, " %s", probe_symbol(tp));
+		seq_printf(m, " %s", trace_probe_symbol(tp));
 
 	for (i = 0; i < tp->nr_args; i++)
 		seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
@@ -1209,7 +1382,7 @@ static int probes_open(struct inode *inode, struct file *file)
 {
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
-		cleanup_all_probes();
+		release_all_trace_probes();
 
 	return seq_open(file, &probes_seq_op);
 }
@@ -1513,30 +1686,6 @@ partial:
 	return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static int probe_event_enable(struct ftrace_event_call *call)
-{
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	tp->flags |= TP_FLAG_TRACE;
-	if (probe_is_return(tp))
-		return enable_kretprobe(&tp->rp);
-	else
-		return enable_kprobe(&tp->rp.kp);
-}
-
-static void probe_event_disable(struct ftrace_event_call *call)
-{
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	tp->flags &= ~TP_FLAG_TRACE;
-	if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
-		if (probe_is_return(tp))
-			disable_kretprobe(&tp->rp);
-		else
-			disable_kprobe(&tp->rp.kp);
-	}
-}
-
 #undef DEFINE_FIELD
 #define DEFINE_FIELD(type, item, name, is_signed)			\
 	do {								\
@@ -1598,7 +1747,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
 
 	const char *fmt, *arg;
 
-	if (!probe_is_return(tp)) {
+	if (!trace_probe_is_return(tp)) {
 		fmt = "(%lx)";
 		arg = "REC->" FIELD_STRING_IP;
 	} else {
@@ -1715,49 +1864,25 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	head = this_cpu_ptr(call->perf_events);
 	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
 }
-
-static int probe_perf_enable(struct ftrace_event_call *call)
-{
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	tp->flags |= TP_FLAG_PROFILE;
-
-	if (probe_is_return(tp))
-		return enable_kretprobe(&tp->rp);
-	else
-		return enable_kprobe(&tp->rp.kp);
-}
-
-static void probe_perf_disable(struct ftrace_event_call *call)
-{
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	tp->flags &= ~TP_FLAG_PROFILE;
-
-	if (!(tp->flags & TP_FLAG_TRACE)) {
-		if (probe_is_return(tp))
-			disable_kretprobe(&tp->rp);
-		else
-			disable_kprobe(&tp->rp.kp);
-	}
-}
 #endif	/* CONFIG_PERF_EVENTS */
 
 static __kprobes
 int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
 {
+	struct trace_probe *tp = (struct trace_probe *)event->data;
+
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return probe_event_enable(event);
+		return enable_trace_probe(tp, TP_FLAG_TRACE);
 	case TRACE_REG_UNREGISTER:
-		probe_event_disable(event);
+		disable_trace_probe(tp, TP_FLAG_TRACE);
 		return 0;
 
 #ifdef CONFIG_PERF_EVENTS
 	case TRACE_REG_PERF_REGISTER:
-		return probe_perf_enable(event);
+		return enable_trace_probe(tp, TP_FLAG_PROFILE);
 	case TRACE_REG_PERF_UNREGISTER:
-		probe_perf_disable(event);
+		disable_trace_probe(tp, TP_FLAG_PROFILE);
 		return 0;
 #endif
 	}
@@ -1807,7 +1932,7 @@ static int register_probe_event(struct trace_probe *tp)
 
 	/* Initialize ftrace_event_call */
 	INIT_LIST_HEAD(&call->class->fields);
-	if (probe_is_return(tp)) {
+	if (trace_probe_is_return(tp)) {
 		call->event.funcs = &kretprobe_funcs;
 		call->class->define_fields = kretprobe_event_define_fields;
 	} else {
@@ -1846,6 +1971,9 @@ static __init int init_kprobe_trace(void)
 	struct dentry *d_tracer;
 	struct dentry *entry;
 
+	if (register_module_notifier(&trace_probe_module_nb))
+		return -EINVAL;
+
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
 		return 0;
@@ -1899,12 +2027,12 @@ static __init int kprobe_trace_self_tests_init(void)
 		warn++;
 	} else {
 		/* Enable trace point */
-		tp = find_probe_event("testprobe", KPROBE_EVENT_SYSTEM);
+		tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
 		if (WARN_ON_ONCE(tp == NULL)) {
 			pr_warning("error on getting new probe.\n");
 			warn++;
 		} else
-			probe_event_enable(&tp->call);
+			enable_trace_probe(tp, TP_FLAG_TRACE);
 	}
 
 	ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
@@ -1914,12 +2042,12 @@ static __init int kprobe_trace_self_tests_init(void)
 		warn++;
 	} else {
 		/* Enable trace point */
-		tp = find_probe_event("testprobe2", KPROBE_EVENT_SYSTEM);
+		tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
 		if (WARN_ON_ONCE(tp == NULL)) {
 			pr_warning("error on getting new probe.\n");
 			warn++;
 		} else
-			probe_event_enable(&tp->call);
+			enable_trace_probe(tp, TP_FLAG_TRACE);
 	}
 
 	if (warn)
@@ -1940,7 +2068,7 @@ static __init int kprobe_trace_self_tests_init(void)
 	}
 
 end:
-	cleanup_all_probes();
+	release_all_trace_probes();
 	if (warn)
 		pr_cont("NG: Some tests are failed. Please check them.\n");
 	else
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index e37de492a9e1..51999309a6cf 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1107,19 +1107,20 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 {
 	struct stack_entry *field;
 	struct trace_seq *s = &iter->seq;
-	int i;
+	unsigned long *p;
+	unsigned long *end;
 
 	trace_assign_type(field, iter->ent);
+	end = (unsigned long *)((long)iter->ent + iter->ent_size);
 
 	if (!trace_seq_puts(s, "<stack trace>\n"))
 		goto partial;
-	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
-		if (!field->caller[i] || (field->caller[i] == ULONG_MAX))
-			break;
+
+	for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) {
 		if (!trace_seq_puts(s, " => "))
 			goto partial;
 
-		if (!seq_print_ip_sym(s, field->caller[i], flags))
+		if (!seq_print_ip_sym(s, *p, flags))
 			goto partial;
 		if (!trace_seq_puts(s, "\n"))
 			goto partial;