Merge tag 'trace-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "Most of the changes were largely clean ups, and some documentation.
  But there were a few features that were added:

  Uprobes now work with event triggers and multi buffers and have
  support under ftrace and perf.

  The big feature is that the function tracer can now be used within the
  multi buffer instances.  That is, you can now trace some functions in
  one buffer, others in another buffer, all functions in a third buffer
  and so on.  They are basically agnostic from each other.  This only
  works for the function tracer and not for the function graph trace,
  although you can have the function graph tracer running in the top
  level buffer (or any tracer for that matter) and have different
  function tracing going on in the sub buffers"

* tag 'trace-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (45 commits)
  tracing: Add BUG_ON when stack end location is over written
  tracepoint: Remove unused API functions
  Revert "tracing: Move event storage for array from macro to standalone function"
  ftrace: Constify ftrace_text_reserved
  tracepoints: API doc update to tracepoint_probe_register() return value
  tracepoints: API doc update to data argument
  ftrace: Fix compilation warning about control_ops_free
  ftrace/x86: BUG when ftrace recovery fails
  ftrace: Warn on error when modifying ftrace function
  ftrace: Remove freelist from struct dyn_ftrace
  ftrace: Do not pass data to ftrace_dyn_arch_init
  ftrace: Pass retval through return in ftrace_dyn_arch_init()
  ftrace: Inline the code from ftrace_dyn_table_alloc()
  ftrace: Cleanup of global variables ftrace_new_pgs and ftrace_update_cnt
  tracing: Evaluate len expression only once in __dynamic_array macro
  tracing: Correctly expand len expressions from __dynamic_array macro
  tracing/module: Replace include of tracepoint.h with jump_label.h in module.h
  tracing: Fix event header migrate.h to include tracepoint.h
  tracing: Fix event header writeback.h to include tracepoint.h
  tracing: Warn if a tracepoint is not set via debugfs
  ...

Documentation/trace/ftrace-design.txt

@@ -358,11 +358,8 @@ Every arch has an init callback function.  If you need to do something early on
 to initialize some state, this is the time to do that.  Otherwise, this simple
 function below should be sufficient for most people:
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	/* return value is done indirectly via data */
-	*(unsigned long *)data = 0;
-
 	return 0;
 }
 

arch/arm/kernel/ftrace.c

@@ -156,10 +156,8 @@ int ftrace_make_nop(struct module *mod,
 	return ret;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	*(unsigned long *)data = 0;
-
 	return 0;
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */

arch/blackfin/kernel/ftrace.c

@@ -65,11 +65,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(ip, call, sizeof(call));
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	/* return value is done indirectly via data */
-	*(unsigned long *)data = 0;
-
 	return 0;
 }
 

arch/ia64/kernel/ftrace.c

@@ -198,9 +198,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 }
 
 /* run from kstop_machine */
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	*(unsigned long *)data = 0;
-
 	return 0;
 }

arch/metag/kernel/ftrace.c

@@ -117,10 +117,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 }
 
 /* run from kstop_machine */
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	/* The return code is returned via data */
-	writel(0, data);
-
 	return 0;
 }

arch/microblaze/kernel/ftrace.c

@@ -171,11 +171,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ret;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	/* The return code is retured via data */
-	*(unsigned long *)data = 0;
-
 	return 0;
 }
 

arch/mips/kernel/ftrace.c

@@ -201,7 +201,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(FTRACE_CALL_IP, new);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	/* Encode the instructions when booting */
 	ftrace_dyn_arch_init_insns();
@@ -209,9 +209,6 @@ int __init ftrace_dyn_arch_init(void *data)
 	/* Remove "b ftrace_stub" to ensure ftrace_caller() is executed */
 	ftrace_modify_code(MCOUNT_ADDR, INSN_NOP);
 
-	/* The return code is retured via data */
-	*(unsigned long *)data = 0;
-
 	return 0;
 }
 #endif	/* CONFIG_DYNAMIC_FTRACE */

arch/powerpc/kernel/ftrace.c

@@ -532,13 +532,8 @@ void arch_ftrace_update_code(int command)
 		ftrace_disable_ftrace_graph_caller();
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	/* caller expects data to be zero */
-	unsigned long *p = data;
-
-	*p = 0;
-
 	return 0;
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */

arch/s390/kernel/ftrace.c

@@ -130,9 +130,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return 0;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	*(unsigned long *) data = 0;
 	return 0;
 }
 

arch/sh/kernel/ftrace.c

@@ -272,11 +272,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ftrace_modify_code(rec->ip, old, new);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	/* The return code is retured via data */
-	__raw_writel(0, (unsigned long)data);
-
 	return 0;
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */

arch/sparc/kernel/ftrace.c

@@ -82,12 +82,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(ip, old, new);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	unsigned long *p = data;
-
-	*p = 0;
-
 	return 0;
 }
 #endif

arch/tile/kernel/ftrace.c

@@ -167,10 +167,8 @@ int ftrace_make_nop(struct module *mod,
 	return ret;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	*(unsigned long *)data = 0;
-
 	return 0;
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */

arch/x86/kernel/ftrace.c

@@ -308,7 +308,10 @@ static int ftrace_write(unsigned long ip, const char *val, int size)
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa_symbol(ip));
 
-	return probe_kernel_write((void *)ip, val, size);
+	if (probe_kernel_write((void *)ip, val, size))
+		return -EPERM;
+
+	return 0;
 }
 
 static int add_break(unsigned long ip, const char *old)
@@ -323,10 +326,7 @@ static int add_break(unsigned long ip, const char *old)
 	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
 
-	if (ftrace_write(ip, &brk, 1))
-		return -EPERM;
-
-	return 0;
+	return ftrace_write(ip, &brk, 1);
 }
 
 static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -425,7 +425,7 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
 
 	/* If this does not have a breakpoint, we are done */
 	if (ins[0] != brk)
-		return -1;
+		return 0;
 
 	nop = ftrace_nop_replace();
 
@@ -455,7 +455,7 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
 	}
 
  update:
-	return probe_kernel_write((void *)ip, &nop[0], 1);
+	return ftrace_write(ip, nop, 1);
 }
 
 static int add_update_code(unsigned long ip, unsigned const char *new)
@@ -463,9 +463,7 @@ static int add_update_code(unsigned long ip, unsigned const char *new)
 	/* skip breakpoint */
 	ip++;
 	new++;
-	if (ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1))
-		return -EPERM;
-	return 0;
+	return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1);
 }
 
 static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -520,10 +518,7 @@ static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	new = ftrace_call_replace(ip, addr);
 
-	if (ftrace_write(ip, new, 1))
-		return -EPERM;
-
-	return 0;
+	return ftrace_write(ip, new, 1);
 }
 
 static int finish_update_nop(struct dyn_ftrace *rec)
@@ -533,9 +528,7 @@ static int finish_update_nop(struct dyn_ftrace *rec)
 
 	new = ftrace_nop_replace();
 
-	if (ftrace_write(ip, new, 1))
-		return -EPERM;
-	return 0;
+	return ftrace_write(ip, new, 1);
 }
 
 static int finish_update(struct dyn_ftrace *rec, int enable)
@@ -632,8 +625,14 @@ void ftrace_replace_code(int enable)
 	printk(KERN_WARNING "Failed on %s (%d):\n", report, count);
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
-		remove_breakpoint(rec);
+		/*
+		 * Breakpoints are handled only when this function is in
+		 * progress. The system could not work with them.
+		 */
+		if (remove_breakpoint(rec))
+			BUG();
 	}
+	run_sync();
 }
 
 static int
@@ -655,16 +654,19 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
 	run_sync();
 
 	ret = ftrace_write(ip, new_code, 1);
-	if (ret) {
-		ret = -EPERM;
-		goto out;
-	}
-	run_sync();
+	/*
+	 * The breakpoint is handled only when this function is in progress.
+	 * The system could not work if we could not remove it.
+	 */
+	BUG_ON(ret);
  out:
+	run_sync();
 	return ret;
 
  fail_update:
-	probe_kernel_write((void *)ip, &old_code[0], 1);
+	/* Also here the system could not work with the breakpoint */
+	if (ftrace_write(ip, old_code, 1))
+		BUG();
 	goto out;
 }
 
@@ -678,11 +680,8 @@ void arch_ftrace_update_code(int command)
 	atomic_dec(&modifying_ftrace_code);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	/* The return code is retured via data */
-	*(unsigned long *)data = 0;
-
 	return 0;
 }
 #endif

include/linux/ftrace.h

@@ -92,6 +92,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  * STUB   - The ftrace_ops is just a place holder.
  * INITIALIZED - The ftrace_ops has already been initialized (first use time
  *            register_ftrace_function() is called, it will initialized the ops)
+ * DELETED - The ops are being deleted, do not let them be registered again.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -103,13 +104,26 @@ enum {
 	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 6,
 	FTRACE_OPS_FL_STUB			= 1 << 7,
 	FTRACE_OPS_FL_INITIALIZED		= 1 << 8,
+	FTRACE_OPS_FL_DELETED			= 1 << 9,
 };
 
+/*
+ * Note, ftrace_ops can be referenced outside of RCU protection.
+ * (Although, for perf, the control ops prevent that). If ftrace_ops is
+ * allocated and not part of kernel core data, the unregistering of it will
+ * perform a scheduling on all CPUs to make sure that there are no more users.
+ * Depending on the load of the system that may take a bit of time.
+ *
+ * Any private data added must also take care not to be freed and if private
+ * data is added to a ftrace_ops that is in core code, the user of the
+ * ftrace_ops must perform a schedule_on_each_cpu() before freeing it.
+ */
 struct ftrace_ops {
 	ftrace_func_t			func;
 	struct ftrace_ops		*next;
 	unsigned long			flags;
 	int __percpu			*disabled;
+	void				*private;
 #ifdef CONFIG_DYNAMIC_FTRACE
 	struct ftrace_hash		*notrace_hash;
 	struct ftrace_hash		*filter_hash;
@@ -285,7 +299,7 @@ extern void
 unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
 extern void unregister_ftrace_function_probe_all(char *glob);
 
-extern int ftrace_text_reserved(void *start, void *end);
+extern int ftrace_text_reserved(const void *start, const void *end);
 
 extern int ftrace_nr_registered_ops(void);
 
@@ -316,12 +330,9 @@ enum {
 #define FTRACE_REF_MAX		((1UL << 29) - 1)
 
 struct dyn_ftrace {
-	union {
-		unsigned long		ip; /* address of mcount call-site */
-		struct dyn_ftrace	*freelist;
-	};
+	unsigned long		ip; /* address of mcount call-site */
 	unsigned long		flags;
-	struct dyn_arch_ftrace		arch;
+	struct dyn_arch_ftrace	arch;
 };
 
 int ftrace_force_update(void);
@@ -409,7 +420,7 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
 
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
-extern int ftrace_dyn_arch_init(void *data);
+extern int ftrace_dyn_arch_init(void);
 extern void ftrace_replace_code(int enable);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
@@ -541,7 +552,7 @@ static inline __init int unregister_ftrace_command(char *cmd_name)
 {
 	return -EINVAL;
 }
-static inline int ftrace_text_reserved(void *start, void *end)
+static inline int ftrace_text_reserved(const void *start, const void *end)
 {
 	return 0;
 }

include/linux/ftrace_event.h

@@ -163,6 +163,8 @@ void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
 
 void tracing_record_cmdline(struct task_struct *tsk);
 
+int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...);
+
 struct event_filter;
 
 enum trace_reg {
@@ -197,6 +199,32 @@ struct ftrace_event_class {
 extern int ftrace_event_reg(struct ftrace_event_call *event,
 			    enum trace_reg type, void *data);
 
+int ftrace_output_event(struct trace_iterator *iter, struct ftrace_event_call *event,
+			char *fmt, ...);
+
+int ftrace_event_define_field(struct ftrace_event_call *call,
+			      char *type, int len, char *item, int offset,
+			      int field_size, int sign, int filter);
+
+struct ftrace_event_buffer {
+	struct ring_buffer		*buffer;
+	struct ring_buffer_event	*event;
+	struct ftrace_event_file	*ftrace_file;
+	void				*entry;
+	unsigned long			flags;
+	int				pc;
+};
+
+void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer,
+				  struct ftrace_event_file *ftrace_file,
+				  unsigned long len);
+
+void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer);
+
+int ftrace_event_define_field(struct ftrace_event_call *call,
+			      char *type, int len, char *item, int offset,
+			      int field_size, int sign, int filter);
+
 enum {
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,

include/linux/module.h

@@ -15,7 +15,7 @@
 #include <linux/stringify.h>
 #include <linux/kobject.h>
 #include <linux/moduleparam.h>
-#include <linux/tracepoint.h>
+#include <linux/jump_label.h>
 #include <linux/export.h>
 
 #include <linux/percpu.h>

include/linux/tracepoint.h

@@ -48,12 +48,6 @@ extern int tracepoint_probe_register(const char *name, void *probe, void *data);
 extern int
 tracepoint_probe_unregister(const char *name, void *probe, void *data);
 
-extern int tracepoint_probe_register_noupdate(const char *name, void *probe,
-					      void *data);
-extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
-						void *data);
-extern void tracepoint_probe_update_all(void);
-
 #ifdef CONFIG_MODULES
 struct tp_module {
 	struct list_head list;
@@ -68,18 +62,6 @@ static inline bool trace_module_has_bad_taint(struct module *mod)
 }
 #endif /* CONFIG_MODULES */
 
-struct tracepoint_iter {
-#ifdef CONFIG_MODULES
-	struct tp_module *module;
-#endif /* CONFIG_MODULES */
-	struct tracepoint * const *tracepoint;
-};
-
-extern void tracepoint_iter_start(struct tracepoint_iter *iter);
-extern void tracepoint_iter_next(struct tracepoint_iter *iter);
-extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
-extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
-
 /*
  * tracepoint_synchronize_unregister must be called between the last tracepoint
  * probe unregistration and the end of module exit to make sure there is no

include/trace/events/migrate.h

@@ -4,6 +4,8 @@
 #if !defined(_TRACE_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_MIGRATE_H
 
+#include <linux/tracepoint.h>
+
 #define MIGRATE_MODE						\
 	{MIGRATE_ASYNC,		"MIGRATE_ASYNC"},		\
 	{MIGRATE_SYNC_LIGHT,	"MIGRATE_SYNC_LIGHT"},		\

include/trace/events/writeback.h

@@ -4,6 +4,7 @@
 #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_WRITEBACK_H
 
+#include <linux/tracepoint.h>
 #include <linux/backing-dev.h>
 #include <linux/writeback.h>
 

include/trace/ftrace.h

@@ -265,11 +265,9 @@ static notrace enum print_line_t					\
 ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 			 struct trace_event *event)			\
 {									\
-	struct trace_seq *s = &iter->seq;				\
 	struct ftrace_raw_##template *field;				\
 	struct trace_entry *entry;					\
 	struct trace_seq *p = &iter->tmp_seq;				\
-	int ret;							\
 									\
 	entry = iter->ent;						\
 									\
@@ -281,13 +279,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 	field = (typeof(field))entry;					\
 									\
 	trace_seq_init(p);						\
-	ret = trace_seq_printf(s, "%s: ", #call);			\
-	if (ret)							\
-		ret = trace_seq_printf(s, print);			\
-	if (!ret)							\
-		return TRACE_TYPE_PARTIAL_LINE;				\
-									\
-	return TRACE_TYPE_HANDLED;					\
+	return ftrace_output_call(iter, #call, print);			\
 }									\
 static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 	.trace			= ftrace_raw_output_##call,		\
@@ -370,10 +362,11 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 
 #undef __dynamic_array
 #define __dynamic_array(type, item, len)				\
+	__item_length = (len) * sizeof(type);				\
 	__data_offsets->item = __data_size +				\
 			       offsetof(typeof(*entry), __data);	\
-	__data_offsets->item |= (len * sizeof(type)) << 16;		\
-	__data_size += (len) * sizeof(type);
+	__data_offsets->item |= __item_length << 16;			\
+	__data_size += __item_length;
 
 #undef __string
 #define __string(item, src) __dynamic_array(char, item,			\
@@ -385,6 +378,7 @@ static inline notrace int ftrace_get_offsets_##call(			\
 	struct ftrace_data_offsets_##call *__data_offsets, proto)       \
 {									\
 	int __data_size = 0;						\
+	int __maybe_unused __item_length;				\
 	struct ftrace_raw_##call __maybe_unused *entry;			\
 									\
 	tstruct;							\
@@ -541,37 +535,27 @@ static notrace void							\
 ftrace_raw_event_##call(void *__data, proto)				\
 {									\
 	struct ftrace_event_file *ftrace_file = __data;			\
-	struct ftrace_event_call *event_call = ftrace_file->event_call;	\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
-	struct ring_buffer_event *event;				\
+	struct ftrace_event_buffer fbuffer;				\
 	struct ftrace_raw_##call *entry;				\
-	struct ring_buffer *buffer;					\
-	unsigned long irq_flags;					\
 	int __data_size;						\
-	int pc;								\
 									\
 	if (ftrace_trigger_soft_disabled(ftrace_file))			\
 		return;							\
 									\
-	local_save_flags(irq_flags);					\
-	pc = preempt_count();						\
-									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\
-	event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,	\
-				 event_call->event.type,		\
-				 sizeof(*entry) + __data_size,		\
-				 irq_flags, pc);			\
-	if (!event)							\
+	entry = ftrace_event_buffer_reserve(&fbuffer, ftrace_file,	\
+				 sizeof(*entry) + __data_size);		\
+									\
+	if (!entry)							\
 		return;							\
-	entry	= ring_buffer_event_data(event);			\
 									\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
-	event_trigger_unlock_commit(ftrace_file, buffer, event, entry, \
-				    irq_flags, pc);		       \
+	ftrace_event_buffer_commit(&fbuffer);				\
 }
 /*
  * The ftrace_test_probe is compiled out, it is only here as a build time check

kernel/trace/blktrace.c

@@ -1429,7 +1429,8 @@ static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
 	return print_one_line(iter, true);
 }
 
-static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set)
+static int
+blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 	/* don't output context-info for blk_classic output */
 	if (bit == TRACE_BLK_OPT_CLASSIC) {

kernel/trace/trace.h

@@ -210,6 +210,11 @@ struct trace_array {
 	struct list_head	events;
 	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
 	int			ref;
+#ifdef CONFIG_FUNCTION_TRACER
+	struct ftrace_ops	*ops;
+	/* function tracing enabled */
+	int			function_enabled;
+#endif
 };
 
 enum {
@@ -355,14 +360,16 @@ struct tracer {
 	void			(*print_header)(struct seq_file *m);
 	enum print_line_t	(*print_line)(struct trace_iterator *iter);
 	/* If you handled the flag setting, return 0 */
-	int			(*set_flag)(u32 old_flags, u32 bit, int set);
+	int			(*set_flag)(struct trace_array *tr,
+					    u32 old_flags, u32 bit, int set);
 	/* Return 0 if OK with change, else return non-zero */
-	int			(*flag_changed)(struct tracer *tracer,
+	int			(*flag_changed)(struct trace_array *tr,
 						u32 mask, int set);
 	struct tracer		*next;
 	struct tracer_flags	*flags;
+	int			enabled;
 	bool			print_max;
-	bool			enabled;
+	bool			allow_instances;
 #ifdef CONFIG_TRACER_MAX_TRACE
 	bool			use_max_tr;
 #endif
@@ -812,13 +819,36 @@ static inline int ftrace_trace_task(struct task_struct *task)
 	return test_tsk_trace_trace(task);
 }
 extern int ftrace_is_dead(void);
+int ftrace_create_function_files(struct trace_array *tr,
+				 struct dentry *parent);
+void ftrace_destroy_function_files(struct trace_array *tr);
 #else
 static inline int ftrace_trace_task(struct task_struct *task)
 {
 	return 1;
 }
 static inline int ftrace_is_dead(void) { return 0; }
-#endif
+static inline int
+ftrace_create_function_files(struct trace_array *tr,
+			     struct dentry *parent)
+{
+	return 0;
+}
+static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+void ftrace_create_filter_files(struct ftrace_ops *ops,
+				struct dentry *parent);
+void ftrace_destroy_filter_files(struct ftrace_ops *ops);
+#else
+/*
+ * The ops parameter passed in is usually undefined.
+ * This must be a macro.
+ */
+#define ftrace_create_filter_files(ops, parent) do { } while (0)
+#define ftrace_destroy_filter_files(ops) do { } while (0)
+#endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */
 
 int ftrace_event_is_function(struct ftrace_event_call *call);
 

kernel/trace/trace_events.c

@@ -188,6 +188,36 @@ int trace_event_raw_init(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
+void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer,
+				  struct ftrace_event_file *ftrace_file,
+				  unsigned long len)
+{
+	struct ftrace_event_call *event_call = ftrace_file->event_call;
+
+	local_save_flags(fbuffer->flags);
+	fbuffer->pc = preempt_count();
+	fbuffer->ftrace_file = ftrace_file;
+
+	fbuffer->event =
+		trace_event_buffer_lock_reserve(&fbuffer->buffer, ftrace_file,
+						event_call->event.type, len,
+						fbuffer->flags, fbuffer->pc);
+	if (!fbuffer->event)
+		return NULL;
+
+	fbuffer->entry = ring_buffer_event_data(fbuffer->event);
+	return fbuffer->entry;
+}
+EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve);
+
+void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer)
+{
+	event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer,
+				    fbuffer->event, fbuffer->entry,
+				    fbuffer->flags, fbuffer->pc);
+}
+EXPORT_SYMBOL_GPL(ftrace_event_buffer_commit);
+
 int ftrace_event_reg(struct ftrace_event_call *call,
 		     enum trace_reg type, void *data)
 {

kernel/trace/trace_functions.c

@@ -13,32 +13,106 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 
 #include "trace.h"
 
-/* function tracing enabled */
-static int			ftrace_function_enabled;
+static void tracing_start_function_trace(struct trace_array *tr);
+static void tracing_stop_function_trace(struct trace_array *tr);
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip,
+		    struct ftrace_ops *op, struct pt_regs *pt_regs);
+static void
+function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
+			  struct ftrace_ops *op, struct pt_regs *pt_regs);
+static struct ftrace_ops trace_ops;
+static struct ftrace_ops trace_stack_ops;
+static struct tracer_flags func_flags;
+
+/* Our option */
+enum {
+	TRACE_FUNC_OPT_STACK	= 0x1,
+};
+
+static int allocate_ftrace_ops(struct trace_array *tr)
+{
+	struct ftrace_ops *ops;
+
+	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+	if (!ops)
+		return -ENOMEM;
 
-static struct trace_array	*func_trace;
+	/* Currently only the non stack verision is supported */
+	ops->func = function_trace_call;
+	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE;
+
+	tr->ops = ops;
+	ops->private = tr;
+	return 0;
+}
+
+
+int ftrace_create_function_files(struct trace_array *tr,
+				 struct dentry *parent)
+{
+	int ret;
+
+	/* The top level array uses the "global_ops". */
+	if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL)) {
+		ret = allocate_ftrace_ops(tr);
+		if (ret)
+			return ret;
+	}
+
+	ftrace_create_filter_files(tr->ops, parent);
+
+	return 0;
+}
 
-static void tracing_start_function_trace(void);
-static void tracing_stop_function_trace(void);
+void ftrace_destroy_function_files(struct trace_array *tr)
+{
+	ftrace_destroy_filter_files(tr->ops);
+	kfree(tr->ops);
+	tr->ops = NULL;
+}
 
 static int function_trace_init(struct trace_array *tr)
 {
-	func_trace = tr;
+	struct ftrace_ops *ops;
+
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
+		/* There's only one global tr */
+		if (!trace_ops.private) {
+			trace_ops.private = tr;
+			trace_stack_ops.private = tr;
+		}
+
+		if (func_flags.val & TRACE_FUNC_OPT_STACK)
+			ops = &trace_stack_ops;
+		else
+			ops = &trace_ops;
+		tr->ops = ops;
+	} else if (!tr->ops) {
+		/*
+		 * Instance trace_arrays get their ops allocated
+		 * at instance creation. Unless it failed
+		 * the allocation.
+		 */
+		return -ENOMEM;
+	}
+
 	tr->trace_buffer.cpu = get_cpu();
 	put_cpu();
 
 	tracing_start_cmdline_record();
-	tracing_start_function_trace();
+	tracing_start_function_trace(tr);
 	return 0;
 }
 
 static void function_trace_reset(struct trace_array *tr)
 {
-	tracing_stop_function_trace();
+	tracing_stop_function_trace(tr);
 	tracing_stop_cmdline_record();
 }
 
@@ -47,25 +121,18 @@ static void function_trace_start(struct trace_array *tr)
 	tracing_reset_online_cpus(&tr->trace_buffer);
 }
 
-/* Our option */
-enum {
-	TRACE_FUNC_OPT_STACK	= 0x1,
-};
-
-static struct tracer_flags func_flags;
-
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
 		    struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
-	struct trace_array *tr = func_trace;
+	struct trace_array *tr = op->private;
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	int bit;
 	int cpu;
 	int pc;
 
-	if (unlikely(!ftrace_function_enabled))
+	if (unlikely(!tr->function_enabled))
 		return;
 
 	pc = preempt_count();
@@ -91,14 +158,14 @@ static void
 function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
-	struct trace_array *tr = func_trace;
+	struct trace_array *tr = op->private;
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	long disabled;
 	int cpu;
 	int pc;
 
-	if (unlikely(!ftrace_function_enabled))
+	if (unlikely(!tr->function_enabled))
 		return;
 
 	/*
@@ -128,7 +195,6 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	local_irq_restore(flags);
 }
 
-
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = function_trace_call,
@@ -153,29 +219,21 @@ static struct tracer_flags func_flags = {
 	.opts = func_opts
 };
 
-static void tracing_start_function_trace(void)
+static void tracing_start_function_trace(struct trace_array *tr)
 {
-	ftrace_function_enabled = 0;
-
-	if (func_flags.val & TRACE_FUNC_OPT_STACK)
-		register_ftrace_function(&trace_stack_ops);
-	else
-		register_ftrace_function(&trace_ops);
-
-	ftrace_function_enabled = 1;
+	tr->function_enabled = 0;
+	register_ftrace_function(tr->ops);
+	tr->function_enabled = 1;
 }
 
-static void tracing_stop_function_trace(void)
+static void tracing_stop_function_trace(struct trace_array *tr)
 {
-	ftrace_function_enabled = 0;
-
-	if (func_flags.val & TRACE_FUNC_OPT_STACK)
-		unregister_ftrace_function(&trace_stack_ops);
-	else
-		unregister_ftrace_function(&trace_ops);
+	tr->function_enabled = 0;
+	unregister_ftrace_function(tr->ops);
 }
 
-static int func_set_flag(u32 old_flags, u32 bit, int set)
+static int
+func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 	switch (bit) {
 	case TRACE_FUNC_OPT_STACK:
@@ -183,12 +241,14 @@ static int func_set_flag(u32 old_flags, u32 bit, int set)
 		if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
 			break;
 
+		unregister_ftrace_function(tr->ops);
+
 		if (set) {
-			unregister_ftrace_function(&trace_ops);
-			register_ftrace_function(&trace_stack_ops);
+			tr->ops = &trace_stack_ops;
+			register_ftrace_function(tr->ops);
 		} else {
-			unregister_ftrace_function(&trace_stack_ops);
-			register_ftrace_function(&trace_ops);
+			tr->ops = &trace_ops;
+			register_ftrace_function(tr->ops);
 		}
 
 		break;
@@ -208,6 +268,7 @@ static struct tracer function_trace __tracer_data =
 	.wait_pipe	= poll_wait_pipe,
 	.flags		= &func_flags,
 	.set_flag	= func_set_flag,
+	.allow_instances = true,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_function,
 #endif

kernel/trace/trace_functions_graph.c

@@ -1476,7 +1476,8 @@ void graph_trace_close(struct trace_iterator *iter)
 	}
 }
 
-static int func_graph_set_flag(u32 old_flags, u32 bit, int set)
+static int
+func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 	if (bit == TRACE_GRAPH_PRINT_IRQS)
 		ftrace_graph_skip_irqs = !set;

kernel/trace/trace_irqsoff.c

@@ -160,7 +160,8 @@ static struct ftrace_ops trace_ops __read_mostly =
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+static int
+irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 	int cpu;
 
@@ -266,7 +267,8 @@ __trace_function(struct trace_array *tr,
 #else
 #define __trace_function trace_function
 
-static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+static int
+irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 	return -EINVAL;
 }
@@ -570,8 +572,10 @@ static void irqsoff_function_set(int set)
 		unregister_irqsoff_function(is_graph());
 }
 
-static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set)
+static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set)
 {
+	struct tracer *tracer = tr->current_trace;
+
 	if (mask & TRACE_ITER_FUNCTION)
 		irqsoff_function_set(set);
 

kernel/trace/trace_kprobe.c

@@ -35,11 +35,6 @@ struct trace_kprobe {
 	struct trace_probe	tp;
 };
 
-struct event_file_link {
-	struct ftrace_event_file	*file;
-	struct list_head		list;
-};
-
 #define SIZEOF_TRACE_KPROBE(n)				\
 	(offsetof(struct trace_kprobe, tp.args) +	\
 	(sizeof(struct probe_arg) * (n)))
@@ -387,18 +382,6 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file)
 	return ret;
 }
 
-static struct event_file_link *
-find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
-{
-	struct event_file_link *link;
-
-	list_for_each_entry(link, &tp->files, list)
-		if (link->file == file)
-			return link;
-
-	return NULL;
-}
-
 /*
  * Disable trace_probe
  * if the file is NULL, disable "perf" handler, or disable "trace" handler.

kernel/trace/trace_nop.c

@@ -62,7 +62,7 @@ static void nop_trace_reset(struct trace_array *tr)
  * If you don't implement it, then the flag setting will be
  * automatically accepted.
  */
-static int nop_set_flag(u32 old_flags, u32 bit, int set)
+static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 	/*
 	 * Note that you don't need to update nop_flags.val yourself.
@@ -96,6 +96,7 @@ struct tracer nop_trace __read_mostly =
 	.selftest	= trace_selftest_startup_nop,
 #endif
 	.flags		= &nop_flags,
-	.set_flag	= nop_set_flag
+	.set_flag	= nop_set_flag,
+	.allow_instances = true,
 };
 

kernel/trace/trace_output.c

@@ -439,6 +439,37 @@ int ftrace_raw_output_prep(struct trace_iterator *iter,
 }
 EXPORT_SYMBOL(ftrace_raw_output_prep);
 
+static int ftrace_output_raw(struct trace_iterator *iter, char *name,
+			     char *fmt, va_list ap)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	ret = trace_seq_printf(s, "%s: ", name);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	ret = trace_seq_vprintf(s, fmt, ap);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = ftrace_output_raw(iter, name, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ftrace_output_call);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {

kernel/trace/trace_probe.h

@@ -288,6 +288,11 @@ struct trace_probe {
 	struct probe_arg		args[];
 };
 
+struct event_file_link {
+	struct ftrace_event_file	*file;
+	struct list_head		list;
+};
+
 static inline bool trace_probe_is_enabled(struct trace_probe *tp)
 {
 	return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
@@ -316,6 +321,18 @@ static inline int is_good_name(const char *name)
 	return 1;
 }
 
+static inline struct event_file_link *
+find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
+{
+	struct event_file_link *link;
+
+	list_for_each_entry(link, &tp->files, list)
+		if (link->file == file)
+			return link;
+
+	return NULL;
+}
+
 extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
 		   struct probe_arg *parg, bool is_return, bool is_kprobe);
 

kernel/trace/trace_sched_wakeup.c

@@ -179,8 +179,10 @@ static void wakeup_function_set(int set)
 		unregister_wakeup_function(is_graph());
 }
 
-static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set)
+static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set)
 {
+	struct tracer *tracer = tr->current_trace;
+
 	if (mask & TRACE_ITER_FUNCTION)
 		wakeup_function_set(set);
 
@@ -209,7 +211,8 @@ static void stop_func_tracer(int graph)
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+static int
+wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 
 	if (!(bit & TRACE_DISPLAY_GRAPH))
@@ -311,7 +314,8 @@ __trace_function(struct trace_array *tr,
 #else
 #define __trace_function trace_function
 
-static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+static int
+wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 	return -EINVAL;
 }

kernel/trace/trace_stack.c

@@ -13,6 +13,7 @@
 #include <linux/sysctl.h>
 #include <linux/init.h>
 #include <linux/fs.h>
+#include <linux/magic.h>
 
 #include <asm/setup.h>
 
@@ -144,6 +145,8 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
+	BUG_ON(current != &init_task &&
+		*(end_of_stack(current)) != STACK_END_MAGIC);
  out:
 	arch_spin_unlock(&max_stack_lock);
 	local_irq_restore(flags);