1 files changed, 267 insertions, 48 deletions

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4d3d381bfd95..cb0ce3fc36d3 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -9,6 +9,8 @@
 #include <linux/mmiotrace.h>
 #include <linux/ftrace.h>
 #include <trace/boot.h>
+#include <trace/kmemtrace.h>
+#include <trace/power.h>
 
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
@@ -16,9 +18,9 @@ enum trace_type {
 	TRACE_FN,
 	TRACE_CTX,
 	TRACE_WAKE,
-	TRACE_CONT,
 	TRACE_STACK,
 	TRACE_PRINT,
+	TRACE_BPRINT,
 	TRACE_SPECIAL,
 	TRACE_MMIO_RW,
 	TRACE_MMIO_MAP,
@@ -29,9 +31,14 @@ enum trace_type {
 	TRACE_GRAPH_ENT,
 	TRACE_USER_STACK,
 	TRACE_HW_BRANCHES,
+	TRACE_SYSCALL_ENTER,
+	TRACE_SYSCALL_EXIT,
+	TRACE_KMEM_ALLOC,
+	TRACE_KMEM_FREE,
 	TRACE_POWER,
+	TRACE_BLK,
 
-	__TRACE_LAST_TYPE
+	__TRACE_LAST_TYPE,
 };
 
 /*
@@ -42,7 +49,6 @@ enum trace_type {
  */
 struct trace_entry {
 	unsigned char		type;
-	unsigned char		cpu;
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
@@ -60,13 +66,13 @@ struct ftrace_entry {
 
 /* Function call entry */
 struct ftrace_graph_ent_entry {
-	struct trace_entry			ent;
+	struct trace_entry		ent;
 	struct ftrace_graph_ent		graph_ent;
 };
 
 /* Function return entry */
 struct ftrace_graph_ret_entry {
-	struct trace_entry			ent;
+	struct trace_entry		ent;
 	struct ftrace_graph_ret		ret;
 };
 extern struct tracer boot_tracer;
@@ -112,12 +118,18 @@ struct userstack_entry {
 };
 
 /*
- * ftrace_printk entry:
+ * trace_printk entry:
  */
+struct bprint_entry {
+	struct trace_entry	ent;
+	unsigned long		ip;
+	const char		*fmt;
+	u32			buf[];
+};
+
 struct print_entry {
 	struct trace_entry	ent;
 	unsigned long		ip;
-	int			depth;
 	char			buf[];
 };
 
@@ -170,15 +182,45 @@ struct trace_power {
 	struct power_trace	state_data;
 };
 
+struct kmemtrace_alloc_entry {
+	struct trace_entry	ent;
+	enum kmemtrace_type_id type_id;
+	unsigned long call_site;
+	const void *ptr;
+	size_t bytes_req;
+	size_t bytes_alloc;
+	gfp_t gfp_flags;
+	int node;
+};
+
+struct kmemtrace_free_entry {
+	struct trace_entry	ent;
+	enum kmemtrace_type_id type_id;
+	unsigned long call_site;
+	const void *ptr;
+};
+
+struct syscall_trace_enter {
+	struct trace_entry	ent;
+	int			nr;
+	unsigned long		args[];
+};
+
+struct syscall_trace_exit {
+	struct trace_entry	ent;
+	int			nr;
+	unsigned long		ret;
+};
+
+
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
  *  IRQS_OFF		- interrupts were disabled
- *  IRQS_NOSUPPORT 	- arch does not support irqs_disabled_flags
+ *  IRQS_NOSUPPORT	- arch does not support irqs_disabled_flags
  *  NEED_RESCED		- reschedule is requested
  *  HARDIRQ		- inside an interrupt handler
  *  SOFTIRQ		- inside a softirq handler
- *  CONT		- multiple entries hold the trace item
  */
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
@@ -186,7 +228,6 @@ enum trace_flag_type {
 	TRACE_FLAG_NEED_RESCHED		= 0x04,
 	TRACE_FLAG_HARDIRQ		= 0x08,
 	TRACE_FLAG_SOFTIRQ		= 0x10,
-	TRACE_FLAG_CONT			= 0x20,
 };
 
 #define TRACE_BUF_SIZE		1024
@@ -198,6 +239,7 @@ enum trace_flag_type {
  */
 struct trace_array_cpu {
 	atomic_t		disabled;
+	void			*buffer_page;	/* ring buffer spare */
 
 	/* these fields get copied into max-trace: */
 	unsigned long		trace_idx;
@@ -262,10 +304,10 @@ extern void __ftrace_bad_type(void);
 	do {								\
 		IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN);	\
 		IF_ASSIGN(var, ent, struct ctx_switch_entry, 0);	\
-		IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
 		IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK);	\
 		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
+		IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT);	\
 		IF_ASSIGN(var, ent, struct special_entry, 0);		\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
 			  TRACE_MMIO_RW);				\
@@ -279,7 +321,15 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
 		IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
- 		IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
+		IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
+		IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,	\
+			  TRACE_KMEM_ALLOC);	\
+		IF_ASSIGN(var, ent, struct kmemtrace_free_entry,	\
+			  TRACE_KMEM_FREE);	\
+		IF_ASSIGN(var, ent, struct syscall_trace_enter,		\
+			  TRACE_SYSCALL_ENTER);				\
+		IF_ASSIGN(var, ent, struct syscall_trace_exit,		\
+			  TRACE_SYSCALL_EXIT);				\
 		__ftrace_bad_type();					\
 	} while (0)
 
@@ -287,7 +337,8 @@ extern void __ftrace_bad_type(void);
 enum print_line_t {
 	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
 	TRACE_TYPE_HANDLED	= 1,
-	TRACE_TYPE_UNHANDLED	= 2	/* Relay to other output functions */
+	TRACE_TYPE_UNHANDLED	= 2,	/* Relay to other output functions */
+	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
 };
 
 
@@ -297,8 +348,8 @@ enum print_line_t {
  * flags value in struct tracer_flags.
  */
 struct tracer_opt {
-	const char 	*name; /* Will appear on the trace_options file */
-	u32 		bit; /* Mask assigned in val field in tracer_flags */
+	const char	*name; /* Will appear on the trace_options file */
+	u32		bit; /* Mask assigned in val field in tracer_flags */
 };
 
 /*
@@ -307,28 +358,51 @@ struct tracer_opt {
  */
 struct tracer_flags {
 	u32			val;
-	struct tracer_opt 	*opts;
+	struct tracer_opt	*opts;
 };
 
 /* Makes more easy to define a tracer opt */
 #define TRACER_OPT(s, b)	.name = #s, .bit = b
 
-/*
- * A specific tracer, represented by methods that operate on a trace array:
+
+/**
+ * struct tracer - a specific tracer and its callbacks to interact with debugfs
+ * @name: the name chosen to select it on the available_tracers file
+ * @init: called when one switches to this tracer (echo name > current_tracer)
+ * @reset: called when one switches to another tracer
+ * @start: called when tracing is unpaused (echo 1 > tracing_enabled)
+ * @stop: called when tracing is paused (echo 0 > tracing_enabled)
+ * @open: called when the trace file is opened
+ * @pipe_open: called when the trace_pipe file is opened
+ * @wait_pipe: override how the user waits for traces on trace_pipe
+ * @close: called when the trace file is released
+ * @read: override the default read callback on trace_pipe
+ * @splice_read: override the default splice_read callback on trace_pipe
+ * @selftest: selftest to run on boot (see trace_selftest.c)
+ * @print_headers: override the first lines that describe your columns
+ * @print_line: callback that prints a trace
+ * @set_flag: signals one of your private flags changed (trace_options file)
+ * @flags: your private flags
  */
 struct tracer {
 	const char		*name;
-	/* Your tracer should raise a warning if init fails */
 	int			(*init)(struct trace_array *tr);
 	void			(*reset)(struct trace_array *tr);
 	void			(*start)(struct trace_array *tr);
 	void			(*stop)(struct trace_array *tr);
 	void			(*open)(struct trace_iterator *iter);
 	void			(*pipe_open)(struct trace_iterator *iter);
+	void			(*wait_pipe)(struct trace_iterator *iter);
 	void			(*close)(struct trace_iterator *iter);
 	ssize_t			(*read)(struct trace_iterator *iter,
 					struct file *filp, char __user *ubuf,
 					size_t cnt, loff_t *ppos);
+	ssize_t			(*splice_read)(struct trace_iterator *iter,
+					       struct file *filp,
+					       loff_t *ppos,
+					       struct pipe_inode_info *pipe,
+					       size_t len,
+					       unsigned int flags);
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 	int			(*selftest)(struct tracer *trace,
 					    struct trace_array *tr);
@@ -339,7 +413,8 @@ struct tracer {
 	int			(*set_flag)(u32 old_flags, u32 bit, int set);
 	struct tracer		*next;
 	int			print_max;
-	struct tracer_flags 	*flags;
+	struct tracer_flags	*flags;
+	struct tracer_stat	*stats;
 };
 
 struct trace_seq {
@@ -348,6 +423,16 @@ struct trace_seq {
 	unsigned int		readpos;
 };
 
+static inline void
+trace_seq_init(struct trace_seq *s)
+{
+	s->len = 0;
+	s->readpos = 0;
+}
+
+
+#define TRACE_PIPE_ALL_CPU	-1
+
 /*
  * Trace iterator - used by printout routines who present trace
  * results to users and which routines might sleep, etc:
@@ -356,6 +441,8 @@ struct trace_iterator {
 	struct trace_array	*tr;
 	struct tracer		*trace;
 	void			*private;
+	int			cpu_file;
+	struct mutex		mutex;
 	struct ring_buffer_iter	*buffer_iter[NR_CPUS];
 
 	/* The below is zeroed out in pipe_read */
@@ -371,6 +458,7 @@ struct trace_iterator {
 	cpumask_var_t		started;
 };
 
+int tracer_init(struct tracer *t, struct trace_array *tr);
 int tracing_is_enabled(void);
 void trace_wake_up(void);
 void tracing_reset(struct trace_array *tr, int cpu);
@@ -379,26 +467,50 @@ int tracing_open_generic(struct inode *inode, struct file *filp);
 struct dentry *tracing_init_dentry(void);
 void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
+struct ring_buffer_event;
+
+struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
+						    unsigned char type,
+						    unsigned long len,
+						    unsigned long flags,
+						    int pc);
+void trace_buffer_unlock_commit(struct trace_array *tr,
+				struct ring_buffer_event *event,
+				unsigned long flags, int pc);
+
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
+				  unsigned long flags, int pc);
+void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
+
+struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
+					  int *ent_cpu, u64 *ent_ts);
+
 void tracing_generic_entry_update(struct trace_entry *entry,
 				  unsigned long flags,
 				  int pc);
 
+void default_wait_pipe(struct trace_iterator *iter);
+void poll_wait_pipe(struct trace_iterator *iter);
+
 void ftrace(struct trace_array *tr,
 			    struct trace_array_cpu *data,
 			    unsigned long ip,
 			    unsigned long parent_ip,
 			    unsigned long flags, int pc);
 void tracing_sched_switch_trace(struct trace_array *tr,
-				struct trace_array_cpu *data,
 				struct task_struct *prev,
 				struct task_struct *next,
 				unsigned long flags, int pc);
 void tracing_record_cmdline(struct task_struct *tsk);
 
 void tracing_sched_wakeup_trace(struct trace_array *tr,
-				struct trace_array_cpu *data,
 				struct task_struct *wakee,
 				struct task_struct *cur,
 				unsigned long flags, int pc);
@@ -408,14 +520,12 @@ void trace_special(struct trace_array *tr,
 		   unsigned long arg2,
 		   unsigned long arg3, int pc);
 void trace_function(struct trace_array *tr,
-		    struct trace_array_cpu *data,
 		    unsigned long ip,
 		    unsigned long parent_ip,
 		    unsigned long flags, int pc);
 
 void trace_graph_return(struct ftrace_graph_ret *trace);
 int trace_graph_entry(struct ftrace_graph_ent *trace);
-void trace_hw_branch(struct trace_array *tr, u64 from, u64 to);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
@@ -434,15 +544,11 @@ void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
 
-extern cycle_t ftrace_now(int cpu);
+void __trace_stack(struct trace_array *tr,
+		   unsigned long flags,
+		   int skip, int pc);
 
-#ifdef CONFIG_FUNCTION_TRACER
-void tracing_start_function_trace(void);
-void tracing_stop_function_trace(void);
-#else
-# define tracing_start_function_trace()		do { } while (0)
-# define tracing_stop_function_trace()		do { } while (0)
-#endif
+extern cycle_t ftrace_now(int cpu);
 
 #ifdef CONFIG_CONTEXT_SWITCH_TRACER
 typedef void
@@ -456,10 +562,10 @@ struct tracer_switch_ops {
 	void				*private;
 	struct tracer_switch_ops	*next;
 };
-
-char *trace_find_cmdline(int pid);
 #endif /* CONFIG_CONTEXT_SWITCH_TRACER */
 
+extern void trace_find_cmdline(int pid, char comm[]);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern unsigned long ftrace_update_tot_cnt;
 #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
@@ -469,6 +575,8 @@ extern int DYN_FTRACE_TEST_NAME(void);
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,
 					   struct trace_array *tr);
+extern int trace_selftest_startup_function_graph(struct tracer *trace,
+						 struct trace_array *tr);
 extern int trace_selftest_startup_irqsoff(struct tracer *trace,
 					  struct trace_array *tr);
 extern int trace_selftest_startup_preemptoff(struct tracer *trace,
@@ -488,18 +596,11 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
-extern void trace_seq_print_cont(struct trace_seq *s,
-				 struct trace_iterator *iter);
-
-extern int
-seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
-		unsigned long sym_flags);
-extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
-				 size_t cnt);
 extern long ns2usecs(cycle_t nsec);
 extern int
-trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args);
+trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
+extern int
+trace_vprintk(unsigned long ip, const char *fmt, va_list args);
 
 extern unsigned long trace_flags;
 
@@ -580,7 +681,11 @@ enum trace_iterator_flags {
 	TRACE_ITER_ANNOTATE		= 0x2000,
 	TRACE_ITER_USERSTACKTRACE       = 0x4000,
 	TRACE_ITER_SYM_USEROBJ          = 0x8000,
-	TRACE_ITER_PRINTK_MSGONLY	= 0x10000
+	TRACE_ITER_PRINTK_MSGONLY	= 0x10000,
+	TRACE_ITER_CONTEXT_INFO		= 0x20000, /* Print pid/cpu/time */
+	TRACE_ITER_LATENCY_FMT		= 0x40000,
+	TRACE_ITER_GLOBAL_CLK		= 0x80000,
+	TRACE_ITER_SLEEP_TIME		= 0x100000,
 };
 
 /*
@@ -601,12 +706,12 @@ extern struct tracer nop_trace;
  * preempt_enable (after a disable), a schedule might take place
  * causing an infinite recursion.
  *
- * To prevent this, we read the need_recshed flag before
+ * To prevent this, we read the need_resched flag before
  * disabling preemption. When we want to enable preemption we
  * check the flag, if it is set, then we call preempt_enable_no_resched.
  * Otherwise, we call preempt_enable.
  *
- * The rational for doing the above is that if need resched is set
+ * The rational for doing the above is that if need_resched is set
  * and we have yet to reschedule, we are either in an atomic location
  * (where we do not need to check for scheduling) or we are inside
  * the scheduler and do not want to resched.
@@ -627,7 +732,7 @@ static inline int ftrace_preempt_disable(void)
  *
  * This is a scheduler safe way to enable preemption and not miss
  * any preemption checks. The disabled saved the state of preemption.
- * If resched is set, then we were either inside an atomic or
+ * If resched is set, then we are either inside an atomic or
  * are inside the scheduler (we would have already scheduled
  * otherwise). In this case, we do not want to call normal
  * preempt_enable, but preempt_enable_no_resched instead.
@@ -664,4 +769,118 @@ static inline void trace_branch_disable(void)
 }
 #endif /* CONFIG_BRANCH_TRACER */
 
+/* set ring buffers to default size if not already done so */
+int tracing_update_buffers(void);
+
+/* trace event type bit fields, not numeric */
+enum {
+	TRACE_EVENT_TYPE_PRINTF		= 1,
+	TRACE_EVENT_TYPE_RAW		= 2,
+};
+
+struct ftrace_event_field {
+	struct list_head	link;
+	char			*name;
+	char			*type;
+	int			offset;
+	int			size;
+};
+
+struct ftrace_event_call {
+	char			*name;
+	char			*system;
+	struct dentry		*dir;
+	int			enabled;
+	int			(*regfunc)(void);
+	void			(*unregfunc)(void);
+	int			id;
+	int			(*raw_init)(void);
+	int			(*show_format)(struct trace_seq *s);
+	int			(*define_fields)(void);
+	struct list_head	fields;
+	struct filter_pred	**preds;
+
+#ifdef CONFIG_EVENT_PROFILE
+	atomic_t	profile_count;
+	int		(*profile_enable)(struct ftrace_event_call *);
+	void		(*profile_disable)(struct ftrace_event_call *);
+#endif
+};
+
+struct event_subsystem {
+	struct list_head	list;
+	const char		*name;
+	struct dentry		*entry;
+	struct filter_pred	**preds;
+};
+
+#define events_for_each(event)						\
+	for (event = __start_ftrace_events;				\
+	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
+	     event++)
+
+#define MAX_FILTER_PRED 8
+
+struct filter_pred;
+
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
+
+struct filter_pred {
+	filter_pred_fn_t fn;
+	u64 val;
+	char *str_val;
+	int str_len;
+	char *field_name;
+	int offset;
+	int not;
+	int or;
+	int compound;
+	int clear;
+};
+
+int trace_define_field(struct ftrace_event_call *call, char *type,
+		       char *name, int offset, int size);
+extern void filter_free_pred(struct filter_pred *pred);
+extern void filter_print_preds(struct filter_pred **preds,
+			       struct trace_seq *s);
+extern int filter_parse(char **pbuf, struct filter_pred *pred);
+extern int filter_add_pred(struct ftrace_event_call *call,
+			   struct filter_pred *pred);
+extern void filter_free_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern void filter_free_subsystem_preds(struct event_subsystem *system);
+extern int filter_add_subsystem_pred(struct event_subsystem *system,
+				     struct filter_pred *pred);
+
+void event_trace_printk(unsigned long ip, const char *fmt, ...);
+extern struct ftrace_event_call __start_ftrace_events[];
+extern struct ftrace_event_call __stop_ftrace_events[];
+
+#define for_each_event(event)						\
+	for (event = __start_ftrace_events;				\
+	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
+	     event++)
+
+extern const char *__start___trace_bprintk_fmt[];
+extern const char *__stop___trace_bprintk_fmt[];
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement optimizing out.
+ */
+#define event_trace_printk(ip, fmt, args...)				\
+do {									\
+	__trace_printk_check_format(fmt, ##args);			\
+	tracing_record_cmdline(current);				\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
+	} else								\
+		__trace_printk(ip, fmt, ##args);			\
+} while (0)
+
 #endif /* _LINUX_KERNEL_TRACE_H */