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

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...

11 files changed, 605 insertions, 128 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 683d559a0ee..867bd1dd2dd 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -62,6 +62,8 @@
 #define FTRACE_HASH_DEFAULT_BITS 10
 #define FTRACE_HASH_MAX_BITS 12
 
+#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
+
 /* ftrace_enabled is a method to turn ftrace on or off */
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
@@ -89,12 +91,14 @@ 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_control_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;
+static struct ftrace_ops control_ops;
 
 static void
 ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
@@ -168,6 +172,32 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
 }
 #endif
 
+static void control_ops_disable_all(struct ftrace_ops *ops)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(ops->disabled, cpu) = 1;
+}
+
+static int control_ops_alloc(struct ftrace_ops *ops)
+{
+	int __percpu *disabled;
+
+	disabled = alloc_percpu(int);
+	if (!disabled)
+		return -ENOMEM;
+
+	ops->disabled = disabled;
+	control_ops_disable_all(ops);
+	return 0;
+}
+
+static void control_ops_free(struct ftrace_ops *ops)
+{
+	free_percpu(ops->disabled);
+}
+
 static void update_global_ops(void)
 {
 	ftrace_func_t func;
@@ -259,6 +289,26 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 	return 0;
 }
 
+static void add_ftrace_list_ops(struct ftrace_ops **list,
+				struct ftrace_ops *main_ops,
+				struct ftrace_ops *ops)
+{
+	int first = *list == &ftrace_list_end;
+	add_ftrace_ops(list, ops);
+	if (first)
+		add_ftrace_ops(&ftrace_ops_list, main_ops);
+}
+
+static int remove_ftrace_list_ops(struct ftrace_ops **list,
+				  struct ftrace_ops *main_ops,
+				  struct ftrace_ops *ops)
+{
+	int ret = remove_ftrace_ops(list, ops);
+	if (!ret && *list == &ftrace_list_end)
+		ret = remove_ftrace_ops(&ftrace_ops_list, main_ops);
+	return ret;
+}
+
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
 	if (ftrace_disabled)
@@ -270,15 +320,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return -EBUSY;
 
+	/* We don't support both control and global flags set. */
+	if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
+		return -EINVAL;
+
 	if (!core_kernel_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
 	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		int first = ftrace_global_list == &ftrace_list_end;
-		add_ftrace_ops(&ftrace_global_list, ops);
+		add_ftrace_list_ops(&ftrace_global_list, &global_ops, ops);
 		ops->flags |= FTRACE_OPS_FL_ENABLED;
-		if (first)
-			add_ftrace_ops(&ftrace_ops_list, &global_ops);
+	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+		if (control_ops_alloc(ops))
+			return -ENOMEM;
+		add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops);
 	} else
 		add_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -302,11 +357,23 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 		return -EINVAL;
 
 	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		ret = remove_ftrace_ops(&ftrace_global_list, ops);
-		if (!ret && ftrace_global_list == &ftrace_list_end)
-			ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops);
+		ret = remove_ftrace_list_ops(&ftrace_global_list,
+					     &global_ops, ops);
 		if (!ret)
 			ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+		ret = remove_ftrace_list_ops(&ftrace_control_list,
+					     &control_ops, ops);
+		if (!ret) {
+			/*
+			 * The ftrace_ops is now removed from the list,
+			 * so there'll be no new users. We must ensure
+			 * all current users are done before we free
+			 * the control data.
+			 */
+			synchronize_sched();
+			control_ops_free(ops);
+		}
 	} else
 		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -1119,6 +1186,12 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
 	call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
 }
 
+void ftrace_free_filter(struct ftrace_ops *ops)
+{
+	free_ftrace_hash(ops->filter_hash);
+	free_ftrace_hash(ops->notrace_hash);
+}
+
 static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
 {
 	struct ftrace_hash *hash;
@@ -1129,7 +1202,7 @@ static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
 		return NULL;
 
 	size = 1 << size_bits;
-	hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL);
+	hash->buckets = kcalloc(size, sizeof(*hash->buckets), GFP_KERNEL);
 
 	if (!hash->buckets) {
 		kfree(hash);
@@ -3146,8 +3219,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 	mutex_lock(&ftrace_regex_lock);
 	if (reset)
 		ftrace_filter_reset(hash);
-	if (buf)
-		ftrace_match_records(hash, buf, len);
+	if (buf && !ftrace_match_records(hash, buf, len)) {
+		ret = -EINVAL;
+		goto out_regex_unlock;
+	}
 
 	mutex_lock(&ftrace_lock);
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
@@ -3157,6 +3232,7 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 
 	mutex_unlock(&ftrace_lock);
 
+ out_regex_unlock:
 	mutex_unlock(&ftrace_regex_lock);
 
 	free_ftrace_hash(hash);
@@ -3173,10 +3249,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
  * Filters denote which functions should be enabled when tracing is enabled.
  * If @buf is NULL and reset is set, all functions will be enabled for tracing.
  */
-void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
+int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
 		       int len, int reset)
 {
-	ftrace_set_regex(ops, buf, len, reset, 1);
+	return ftrace_set_regex(ops, buf, len, reset, 1);
 }
 EXPORT_SYMBOL_GPL(ftrace_set_filter);
 
@@ -3191,10 +3267,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter);
  * is enabled. If @buf is NULL and reset is set, all functions will be enabled
  * for tracing.
  */
-void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
+int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
 			int len, int reset)
 {
-	ftrace_set_regex(ops, buf, len, reset, 0);
+	return ftrace_set_regex(ops, buf, len, reset, 0);
 }
 EXPORT_SYMBOL_GPL(ftrace_set_notrace);
 /**
@@ -3871,6 +3947,36 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 static void
+ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
+{
+	struct ftrace_ops *op;
+
+	if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
+		return;
+
+	/*
+	 * Some of the ops may be dynamically allocated,
+	 * they must be freed after a synchronize_sched().
+	 */
+	preempt_disable_notrace();
+	trace_recursion_set(TRACE_CONTROL_BIT);
+	op = rcu_dereference_raw(ftrace_control_list);
+	while (op != &ftrace_list_end) {
+		if (!ftrace_function_local_disabled(op) &&
+		    ftrace_ops_test(op, ip))
+			op->func(ip, parent_ip);
+
+		op = rcu_dereference_raw(op->next);
+	};
+	trace_recursion_clear(TRACE_CONTROL_BIT);
+	preempt_enable_notrace();
+}
+
+static struct ftrace_ops control_ops = {
+	.func = ftrace_ops_control_func,
+};
+
+static void
 ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 {
 	struct ftrace_ops *op;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a3f1bc5d2a0..10d5503f0d0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2764,12 +2764,12 @@ static const char readme_msg[] =
 	"tracing mini-HOWTO:\n\n"
 	"# mount -t debugfs nodev /sys/kernel/debug\n\n"
 	"# cat /sys/kernel/debug/tracing/available_tracers\n"
-	"wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
+	"wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n"
 	"# cat /sys/kernel/debug/tracing/current_tracer\n"
 	"nop\n"
-	"# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n"
+	"# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n"
 	"# cat /sys/kernel/debug/tracing/current_tracer\n"
-	"sched_switch\n"
+	"wakeup\n"
 	"# cat /sys/kernel/debug/tracing/trace_options\n"
 	"noprint-parent nosym-offset nosym-addr noverbose\n"
 	"# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b93ecbadad6..54faec790bc 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -56,17 +56,23 @@ enum trace_type {
 #define F_STRUCT(args...)		args
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)	\
-	struct struct_name {					\
-		struct trace_entry	ent;			\
-		tstruct						\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+	struct struct_name {						\
+		struct trace_entry	ent;				\
+		tstruct							\
 	}
 
 #undef TP_ARGS
 #define TP_ARGS(args...)	args
 
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
+#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
+
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print,	\
+			 filter, regfn) \
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 
 #include "trace_entries.h"
 
@@ -288,6 +294,8 @@ struct tracer {
 /* for function tracing recursion */
 #define TRACE_INTERNAL_BIT		(1<<11)
 #define TRACE_GLOBAL_BIT		(1<<12)
+#define TRACE_CONTROL_BIT		(1<<13)
+
 /*
  * Abuse of the trace_recursion.
  * As we need a way to maintain state if we are tracing the function
@@ -589,6 +597,8 @@ static inline int ftrace_trace_task(struct task_struct *task)
 static inline int ftrace_is_dead(void) { return 0; }
 #endif
 
+int ftrace_event_is_function(struct ftrace_event_call *call);
+
 /*
  * struct trace_parser - servers for reading the user input separated by spaces
  * @cont: set if the input is not complete - no final space char was found
@@ -766,9 +776,7 @@ struct filter_pred {
 	u64 			val;
 	struct regex		regex;
 	unsigned short		*ops;
-#ifdef CONFIG_FTRACE_STARTUP_TEST
 	struct ftrace_event_field *field;
-#endif
 	int 			offset;
 	int 			not;
 	int 			op;
@@ -818,12 +826,22 @@ extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, id, tstruct, print)		\
+#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
 	extern struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_##call;
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print)		\
-	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter)	\
+	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 #include "trace_entries.h"
 
+#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_FUNCTION_TRACER
+int perf_ftrace_event_register(struct ftrace_event_call *call,
+			       enum trace_reg type, void *data);
+#else
+#define perf_ftrace_event_register NULL
+#endif /* CONFIG_FUNCTION_TRACER */
+#endif /* CONFIG_PERF_EVENTS */
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 93365907f21..d91eb0541b3 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -55,7 +55,7 @@
 /*
  * Function trace entry - function address and parent function address:
  */
-FTRACE_ENTRY(function, ftrace_entry,
+FTRACE_ENTRY_REG(function, ftrace_entry,
 
 	TRACE_FN,
 
@@ -64,7 +64,11 @@ FTRACE_ENTRY(function, ftrace_entry,
 		__field(	unsigned long,	parent_ip	)
 	),
 
-	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip)
+	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip),
+
+	FILTER_TRACE_FN,
+
+	perf_ftrace_event_register
 );
 
 /* Function call entry */
@@ -78,7 +82,9 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
 		__field_desc(	int,		graph_ent,	depth		)
 	),
 
-	F_printk("--> %lx (%d)", __entry->func, __entry->depth)
+	F_printk("--> %lx (%d)", __entry->func, __entry->depth),
+
+	FILTER_OTHER
 );
 
 /* Function return entry */
@@ -98,7 +104,9 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
 	F_printk("<-- %lx (%d) (start: %llx  end: %llx) over: %d",
 		 __entry->func, __entry->depth,
 		 __entry->calltime, __entry->rettime,
-		 __entry->depth)
+		 __entry->depth),
+
+	FILTER_OTHER
 );
 
 /*
@@ -127,8 +135,9 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry,
 	F_printk("%u:%u:%u  ==> %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
-		 __entry->next_cpu
-		)
+		 __entry->next_cpu),
+
+	FILTER_OTHER
 );
 
 /*
@@ -146,8 +155,9 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
 	F_printk("%u:%u:%u  ==+ %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
-		 __entry->next_cpu
-		)
+		 __entry->next_cpu),
+
+	FILTER_OTHER
 );
 
 /*
@@ -169,7 +179,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
 		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
 		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
-		 __entry->caller[6], __entry->caller[7])
+		 __entry->caller[6], __entry->caller[7]),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(user_stack, userstack_entry,
@@ -185,7 +197,9 @@ FTRACE_ENTRY(user_stack, userstack_entry,
 		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
 		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
 		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
-		 __entry->caller[6], __entry->caller[7])
+		 __entry->caller[6], __entry->caller[7]),
+
+	FILTER_OTHER
 );
 
 /*
@@ -202,7 +216,9 @@ FTRACE_ENTRY(bprint, bprint_entry,
 	),
 
 	F_printk("%08lx fmt:%p",
-		 __entry->ip, __entry->fmt)
+		 __entry->ip, __entry->fmt),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(print, print_entry,
@@ -215,7 +231,9 @@ FTRACE_ENTRY(print, print_entry,
 	),
 
 	F_printk("%08lx %s",
-		 __entry->ip, __entry->buf)
+		 __entry->ip, __entry->buf),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
@@ -234,7 +252,9 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
 
 	F_printk("%lx %lx %lx %d %x %x",
 		 (unsigned long)__entry->phys, __entry->value, __entry->pc,
-		 __entry->map_id, __entry->opcode, __entry->width)
+		 __entry->map_id, __entry->opcode, __entry->width),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
@@ -252,7 +272,9 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
 
 	F_printk("%lx %lx %lx %d %x",
 		 (unsigned long)__entry->phys, __entry->virt, __entry->len,
-		 __entry->map_id, __entry->opcode)
+		 __entry->map_id, __entry->opcode),
+
+	FILTER_OTHER
 );
 
 
@@ -272,6 +294,8 @@ FTRACE_ENTRY(branch, trace_branch,
 
 	F_printk("%u:%s:%s (%u)",
 		 __entry->line,
-		 __entry->func, __entry->file, __entry->correct)
+		 __entry->func, __entry->file, __entry->correct),
+
+	FILTER_OTHER
 );
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 19a359d5e6d..fee3752ae8f 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -24,6 +24,11 @@ static int	total_ref_count;
 static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
+	/* The ftrace function trace is allowed only for root. */
+	if (ftrace_event_is_function(tp_event) &&
+	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/* No tracing, just counting, so no obvious leak */
 	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
 		return 0;
@@ -44,23 +49,17 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 	return 0;
 }
 
-static int perf_trace_event_init(struct ftrace_event_call *tp_event,
-				 struct perf_event *p_event)
+static int perf_trace_event_reg(struct ftrace_event_call *tp_event,
+				struct perf_event *p_event)
 {
 	struct hlist_head __percpu *list;
-	int ret;
+	int ret = -ENOMEM;
 	int cpu;
 
-	ret = perf_trace_event_perm(tp_event, p_event);
-	if (ret)
-		return ret;
-
 	p_event->tp_event = tp_event;
 	if (tp_event->perf_refcount++ > 0)
 		return 0;
 
-	ret = -ENOMEM;
-
 	list = alloc_percpu(struct hlist_head);
 	if (!list)
 		goto fail;
@@ -83,7 +82,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 		}
 	}
 
-	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
+	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL);
 	if (ret)
 		goto fail;
 
@@ -108,6 +107,69 @@ fail:
 	return ret;
 }
 
+static void perf_trace_event_unreg(struct perf_event *p_event)
+{
+	struct ftrace_event_call *tp_event = p_event->tp_event;
+	int i;
+
+	if (--tp_event->perf_refcount > 0)
+		goto out;
+
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
+
+	/*
+	 * Ensure our callback won't be called anymore. The buffers
+	 * will be freed after that.
+	 */
+	tracepoint_synchronize_unregister();
+
+	free_percpu(tp_event->perf_events);
+	tp_event->perf_events = NULL;
+
+	if (!--total_ref_count) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+			free_percpu(perf_trace_buf[i]);
+			perf_trace_buf[i] = NULL;
+		}
+	}
+out:
+	module_put(tp_event->mod);
+}
+
+static int perf_trace_event_open(struct perf_event *p_event)
+{
+	struct ftrace_event_call *tp_event = p_event->tp_event;
+	return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event);
+}
+
+static void perf_trace_event_close(struct perf_event *p_event)
+{
+	struct ftrace_event_call *tp_event = p_event->tp_event;
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event);
+}
+
+static int perf_trace_event_init(struct ftrace_event_call *tp_event,
+				 struct perf_event *p_event)
+{
+	int ret;
+
+	ret = perf_trace_event_perm(tp_event, p_event);
+	if (ret)
+		return ret;
+
+	ret = perf_trace_event_reg(tp_event, p_event);
+	if (ret)
+		return ret;
+
+	ret = perf_trace_event_open(p_event);
+	if (ret) {
+		perf_trace_event_unreg(p_event);
+		return ret;
+	}
+
+	return 0;
+}
+
 int perf_trace_init(struct perf_event *p_event)
 {
 	struct ftrace_event_call *tp_event;
@@ -130,6 +192,14 @@ int perf_trace_init(struct perf_event *p_event)
 	return ret;
 }
 
+void perf_trace_destroy(struct perf_event *p_event)
+{
+	mutex_lock(&event_mutex);
+	perf_trace_event_close(p_event);
+	perf_trace_event_unreg(p_event);
+	mutex_unlock(&event_mutex);
+}
+
 int perf_trace_add(struct perf_event *p_event, int flags)
 {
 	struct ftrace_event_call *tp_event = p_event->tp_event;
@@ -146,43 +216,14 @@ int perf_trace_add(struct perf_event *p_event, int flags)
 	list = this_cpu_ptr(pcpu_list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
-	return 0;
+	return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event);
 }
 
 void perf_trace_del(struct perf_event *p_event, int flags)
 {
-	hlist_del_rcu(&p_event->hlist_entry);
-}
-
-void perf_trace_destroy(struct perf_event *p_event)
-{
 	struct ftrace_event_call *tp_event = p_event->tp_event;
-	int i;
-
-	mutex_lock(&event_mutex);
-	if (--tp_event->perf_refcount > 0)
-		goto out;
-
-	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
-
-	/*
-	 * Ensure our callback won't be called anymore. The buffers
-	 * will be freed after that.
-	 */
-	tracepoint_synchronize_unregister();
-
-	free_percpu(tp_event->perf_events);
-	tp_event->perf_events = NULL;
-
-	if (!--total_ref_count) {
-		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
-			free_percpu(perf_trace_buf[i]);
-			perf_trace_buf[i] = NULL;
-		}
-	}
-out:
-	module_put(tp_event->mod);
-	mutex_unlock(&event_mutex);
+	hlist_del_rcu(&p_event->hlist_entry);
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
 }
 
 __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
@@ -214,3 +255,86 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	return raw_data;
 }
 EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void
+perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct ftrace_entry *entry;
+	struct hlist_head *head;
+	struct pt_regs regs;
+	int rctx;
+
+#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
+		    sizeof(u64)) - sizeof(u32))
+
+	BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);
+
+	perf_fetch_caller_regs(&regs);
+
+	entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
+	if (!entry)
+		return;
+
+	entry->ip = ip;
+	entry->parent_ip = parent_ip;
+
+	head = this_cpu_ptr(event_function.perf_events);
+	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
+			      1, &regs, head);
+
+#undef ENTRY_SIZE
+}
+
+static int perf_ftrace_function_register(struct perf_event *event)
+{
+	struct ftrace_ops *ops = &event->ftrace_ops;
+
+	ops->flags |= FTRACE_OPS_FL_CONTROL;
+	ops->func = perf_ftrace_function_call;
+	return register_ftrace_function(ops);
+}
+
+static int perf_ftrace_function_unregister(struct perf_event *event)
+{
+	struct ftrace_ops *ops = &event->ftrace_ops;
+	int ret = unregister_ftrace_function(ops);
+	ftrace_free_filter(ops);
+	return ret;
+}
+
+static void perf_ftrace_function_enable(struct perf_event *event)
+{
+	ftrace_function_local_enable(&event->ftrace_ops);
+}
+
+static void perf_ftrace_function_disable(struct perf_event *event)
+{
+	ftrace_function_local_disable(&event->ftrace_ops);
+}
+
+int perf_ftrace_event_register(struct ftrace_event_call *call,
+			       enum trace_reg type, void *data)
+{
+	switch (type) {
+	case TRACE_REG_REGISTER:
+	case TRACE_REG_UNREGISTER:
+		break;
+	case TRACE_REG_PERF_REGISTER:
+	case TRACE_REG_PERF_UNREGISTER:
+		return 0;
+	case TRACE_REG_PERF_OPEN:
+		return perf_ftrace_function_register(data);
+	case TRACE_REG_PERF_CLOSE:
+		return perf_ftrace_function_unregister(data);
+	case TRACE_REG_PERF_ADD:
+		perf_ftrace_function_enable(data);
+		return 0;
+	case TRACE_REG_PERF_DEL:
+		perf_ftrace_function_disable(data);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c212a7f934e..079a93ae8a9 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -147,7 +147,8 @@ int trace_event_raw_init(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
-int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
+int ftrace_event_reg(struct ftrace_event_call *call,
+		     enum trace_reg type, void *data)
 {
 	switch (type) {
 	case TRACE_REG_REGISTER:
@@ -170,6 +171,11 @@ int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
 					    call->class->perf_probe,
 					    call);
 		return 0;
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+		return 0;
 #endif
 	}
 	return 0;
@@ -209,7 +215,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 				tracing_stop_cmdline_record();
 				call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
 			}
-			call->class->reg(call, TRACE_REG_UNREGISTER);
+			call->class->reg(call, TRACE_REG_UNREGISTER, NULL);
 		}
 		break;
 	case 1:
@@ -218,7 +224,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 				tracing_start_cmdline_record();
 				call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
 			}
-			ret = call->class->reg(call, TRACE_REG_REGISTER);
+			ret = call->class->reg(call, TRACE_REG_REGISTER, NULL);
 			if (ret) {
 				tracing_stop_cmdline_record();
 				pr_info("event trace: Could not enable event "
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 24aee712745..431dba8b754 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -81,6 +81,7 @@ enum {
 	FILT_ERR_TOO_MANY_PREDS,
 	FILT_ERR_MISSING_FIELD,
 	FILT_ERR_INVALID_FILTER,
+	FILT_ERR_IP_FIELD_ONLY,
 };
 
 static char *err_text[] = {
@@ -96,6 +97,7 @@ static char *err_text[] = {
 	"Too many terms in predicate expression",
 	"Missing field name and/or value",
 	"Meaningless filter expression",
+	"Only 'ip' field is supported for function trace",
 };
 
 struct opstack_op {
@@ -685,7 +687,7 @@ find_event_field(struct ftrace_event_call *call, char *name)
 
 static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
 {
-	stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
+	stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL);
 	if (!stack->preds)
 		return -ENOMEM;
 	stack->index = n_preds;
@@ -826,8 +828,7 @@ static int __alloc_preds(struct event_filter *filter, int n_preds)
 	if (filter->preds)
 		__free_preds(filter);
 
-	filter->preds =
-		kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL);
+	filter->preds = kcalloc(n_preds, sizeof(*filter->preds), GFP_KERNEL);
 
 	if (!filter->preds)
 		return -ENOMEM;
@@ -900,6 +901,11 @@ int filter_assign_type(const char *type)
 	return FILTER_OTHER;
 }
 
+static bool is_function_field(struct ftrace_event_field *field)
+{
+	return field->filter_type == FILTER_TRACE_FN;
+}
+
 static bool is_string_field(struct ftrace_event_field *field)
 {
 	return field->filter_type == FILTER_DYN_STRING ||
@@ -987,6 +993,11 @@ static int init_pred(struct filter_parse_state *ps,
 			fn = filter_pred_strloc;
 		else
 			fn = filter_pred_pchar;
+	} else if (is_function_field(field)) {
+		if (strcmp(field->name, "ip")) {
+			parse_error(ps, FILT_ERR_IP_FIELD_ONLY, 0);
+			return -EINVAL;
+		}
 	} else {
 		if (field->is_signed)
 			ret = strict_strtoll(pred->regex.pattern, 0, &val);
@@ -1334,10 +1345,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps,
 
 	strcpy(pred.regex.pattern, operand2);
 	pred.regex.len = strlen(pred.regex.pattern);
-
-#ifdef CONFIG_FTRACE_STARTUP_TEST
 	pred.field = field;
-#endif
 	return init_pred(ps, field, &pred) ? NULL : &pred;
 }
 
@@ -1486,7 +1494,7 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
 	children = count_leafs(preds, &preds[root->left]);
 	children += count_leafs(preds, &preds[root->right]);
 
-	root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL);
+	root->ops = kcalloc(children, sizeof(*root->ops), GFP_KERNEL);
 	if (!root->ops)
 		return -ENOMEM;
 
@@ -1950,6 +1958,148 @@ void ftrace_profile_free_filter(struct perf_event *event)
 	__free_filter(filter);
 }
 
+struct function_filter_data {
+	struct ftrace_ops *ops;
+	int first_filter;
+	int first_notrace;
+};
+
+#ifdef CONFIG_FUNCTION_TRACER
+static char **
+ftrace_function_filter_re(char *