Merge tag 'trace-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "New features for this release:

   - Pretty much a full rewrite of the processing of function plugins.
     i.e. echo do_IRQ:stacktrace > set_ftrace_filter

   - The rewrite was needed to add plugins to be unique to tracing
     instances. i.e. mkdir instance/foo; cd instances/foo; echo
     do_IRQ:stacktrace > set_ftrace_filter The old way was written very
     hacky. This removes a lot of those hacks.

   - New "function-fork" tracing option. When set, pids in the
     set_ftrace_pid will have their children added when the processes
     with their pids listed in the set_ftrace_pid file forks.

   - Exposure of "maxactive" for kretprobe in kprobe_events

   - Allow for builtin init functions to be traced by the function
     tracer (via the kernel command line). Module init function tracing
     will come in the next release.

   - Added more selftests, and have selftests also test in an instance"

* tag 'trace-v4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (60 commits)
  ring-buffer: Return reader page back into existing ring buffer
  selftests: ftrace: Allow some event trigger tests to run in an instance
  selftests: ftrace: Have some basic tests run in a tracing instance too
  selftests: ftrace: Have event tests also run in an tracing instance
  selftests: ftrace: Make func_event_triggers and func_traceonoff_triggers tests do instances
  selftests: ftrace: Allow some tests to be run in a tracing instance
  tracing/ftrace: Allow for instances to trigger their own stacktrace probes
  tracing/ftrace: Allow for the traceonoff probe be unique to instances
  tracing/ftrace: Enable snapshot function trigger to work with instances
  tracing/ftrace: Allow instances to have their own function probes
  tracing/ftrace: Add a better way to pass data via the probe functions
  ftrace: Dynamically create the probe ftrace_ops for the trace_array
  tracing: Pass the trace_array into ftrace_probe_ops functions
  tracing: Have the trace_array hold the list of registered func probes
  ftrace: If the hash for a probe fails to update then free what was initialized
  ftrace: Have the function probes call their own function
  ftrace: Have each function probe use its own ftrace_ops
  ftrace: Have unregister_ftrace_function_probe_func() return a value
  ftrace: Add helper function ftrace_hash_move_and_update_ops()
  ftrace: Remove data field from ftrace_func_probe structure
  ...

Documentation/trace/kprobetrace.txt

@@ -24,7 +24,7 @@ current_tracer. Instead of that, add probe points via
 Synopsis of kprobe_events
 -------------------------
   p[:[GRP/]EVENT] [MOD:]SYM[+offs]|MEMADDR [FETCHARGS]	: Set a probe
-  r[:[GRP/]EVENT] [MOD:]SYM[+0] [FETCHARGS]		: Set a return probe
+  r[MAXACTIVE][:[GRP/]EVENT] [MOD:]SYM[+0] [FETCHARGS]	: Set a return probe
   -:[GRP/]EVENT						: Clear a probe
 
  GRP		: Group name. If omitted, use "kprobes" for it.
@@ -33,6 +33,9 @@ Synopsis of kprobe_events
  MOD		: Module name which has given SYM.
  SYM[+offs]	: Symbol+offset where the probe is inserted.
  MEMADDR	: Address where the probe is inserted.
+ MAXACTIVE	: Maximum number of instances of the specified function that
+		  can be probed simultaneously, or 0 for the default value
+		  as defined in Documentation/kprobes.txt section 1.3.1.
 
  FETCHARGS	: Arguments. Each probe can have up to 128 args.
   %REG		: Fetch register REG

arch/x86/kernel/ftrace.c

@@ -533,7 +533,13 @@ static void do_sync_core(void *data)
 
 static void run_sync(void)
 {
-	int enable_irqs = irqs_disabled();
+	int enable_irqs;
+
+	/* No need to sync if there's only one CPU */
+	if (num_online_cpus() == 1)
+		return;
+
+	enable_irqs = irqs_disabled();
 
 	/* We may be called with interrupts disabled (on bootup). */
 	if (enable_irqs)

include/linux/ftrace.h

@@ -42,8 +42,10 @@
 /* Main tracing buffer and events set up */
 #ifdef CONFIG_TRACING
 void trace_init(void);
+void early_trace_init(void);
 #else
 static inline void trace_init(void) { }
+static inline void early_trace_init(void) { }
 #endif
 
 struct module;
@@ -144,6 +146,10 @@ struct ftrace_ops_hash {
 	struct ftrace_hash		*filter_hash;
 	struct mutex			regex_lock;
 };
+
+void ftrace_free_init_mem(void);
+#else
+static inline void ftrace_free_init_mem(void) { }
 #endif
 
 /*
@@ -260,6 +266,7 @@ static inline int ftrace_nr_registered_ops(void)
 }
 static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
+static inline void ftrace_free_init_mem(void) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_STACK_TRACER
@@ -279,15 +286,45 @@ int
 stack_trace_sysctl(struct ctl_table *table, int write,
 		   void __user *buffer, size_t *lenp,
 		   loff_t *ppos);
-#endif
 
-struct ftrace_func_command {
-	struct list_head	list;
-	char			*name;
-	int			(*func)(struct ftrace_hash *hash,
-					char *func, char *cmd,
-					char *params, int enable);
-};
+/* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
+DECLARE_PER_CPU(int, disable_stack_tracer);
+
+/**
+ * stack_tracer_disable - temporarily disable the stack tracer
+ *
+ * There's a few locations (namely in RCU) where stack tracing
+ * cannot be executed. This function is used to disable stack
+ * tracing during those critical sections.
+ *
+ * This function must be called with preemption or interrupts
+ * disabled and stack_tracer_enable() must be called shortly after
+ * while preemption or interrupts are still disabled.
+ */
+static inline void stack_tracer_disable(void)
+{
+	/* Preemption or interupts must be disabled */
+	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
+		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
+	this_cpu_inc(disable_stack_tracer);
+}
+
+/**
+ * stack_tracer_enable - re-enable the stack tracer
+ *
+ * After stack_tracer_disable() is called, stack_tracer_enable()
+ * must be called shortly afterward.
+ */
+static inline void stack_tracer_enable(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_DEBUG))
+		WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
+	this_cpu_dec(disable_stack_tracer);
+}
+#else
+static inline void stack_tracer_disable(void) { }
+static inline void stack_tracer_enable(void) { }
+#endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -315,30 +352,6 @@ void ftrace_bug(int err, struct dyn_ftrace *rec);
 
 struct seq_file;
 
-struct ftrace_probe_ops {
-	void			(*func)(unsigned long ip,
-					unsigned long parent_ip,
-					void **data);
-	int			(*init)(struct ftrace_probe_ops *ops,
-					unsigned long ip, void **data);
-	void			(*free)(struct ftrace_probe_ops *ops,
-					unsigned long ip, void **data);
-	int			(*print)(struct seq_file *m,
-					 unsigned long ip,
-					 struct ftrace_probe_ops *ops,
-					 void *data);
-};
-
-extern int
-register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
-			      void *data);
-extern void
-unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
-				void *data);
-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(const void *start, const void *end);
 
 extern int ftrace_nr_registered_ops(void);
@@ -400,9 +413,6 @@ void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
 void ftrace_free_filter(struct ftrace_ops *ops);
 void ftrace_ops_set_global_filter(struct ftrace_ops *ops);
 
-int register_ftrace_command(struct ftrace_func_command *cmd);
-int unregister_ftrace_command(struct ftrace_func_command *cmd);
-
 enum {
 	FTRACE_UPDATE_CALLS		= (1 << 0),
 	FTRACE_DISABLE_CALLS		= (1 << 1),
@@ -433,8 +443,8 @@ enum {
 	FTRACE_ITER_FILTER	= (1 << 0),
 	FTRACE_ITER_NOTRACE	= (1 << 1),
 	FTRACE_ITER_PRINTALL	= (1 << 2),
-	FTRACE_ITER_DO_HASH	= (1 << 3),
-	FTRACE_ITER_HASH	= (1 << 4),
+	FTRACE_ITER_DO_PROBES	= (1 << 3),
+	FTRACE_ITER_PROBE	= (1 << 4),
 	FTRACE_ITER_ENABLED	= (1 << 5),
 };
 
@@ -618,14 +628,6 @@ static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_module_init(struct module *mod) { }
 static inline void ftrace_module_enable(struct module *mod) { }
 static inline void ftrace_release_mod(struct module *mod) { }
-static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
-{
-	return -EINVAL;
-}
-static inline __init int unregister_ftrace_command(char *cmd_name)
-{
-	return -EINVAL;
-}
 static inline int ftrace_text_reserved(const void *start, const void *end)
 {
 	return 0;

include/linux/init.h

@@ -39,7 +39,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold notrace __latent_entropy
+#define __init		__section(.init.text) __cold __inittrace __latent_entropy
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)
@@ -68,8 +68,10 @@
 
 #ifdef MODULE
 #define __exitused
+#define __inittrace notrace
 #else
 #define __exitused  __used
+#define __inittrace
 #endif
 
 #define __exit          __section(.exit.text) __exitused __cold notrace

include/linux/rcupdate.h

@@ -97,6 +97,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long secs,
 			       unsigned long c_old,
 			       unsigned long c);
+bool rcu_irq_enter_disabled(void);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 					  int *flags,
@@ -113,6 +114,10 @@ static inline void rcutorture_record_test_transition(void)
 static inline void rcutorture_record_progress(unsigned long vernum)
 {
 }
+static inline bool rcu_irq_enter_disabled(void)
+{
+	return false;
+}
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,

include/linux/ring_buffer.h

@@ -185,7 +185,7 @@ size_t ring_buffer_page_len(void *page);
 
 
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu);
-void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
+void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data);
 int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
 			  size_t len, int cpu, int full);
 

include/linux/trace_events.h

@@ -138,16 +138,7 @@ enum print_line_t {
 	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
 };
 
-/*
- * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq
- * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function
- * simplifies those functions and keeps them in sync.
- */
-static inline enum print_line_t trace_handle_return(struct trace_seq *s)
-{
-	return trace_seq_has_overflowed(s) ?
-		TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED;
-}
+enum print_line_t trace_handle_return(struct trace_seq *s);
 
 void tracing_generic_entry_update(struct trace_entry *entry,
 				  unsigned long flags,

include/linux/tracepoint.h

@@ -128,7 +128,7 @@ extern void syscall_unregfunc(void);
  * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
  * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
  */
-#define __DO_TRACE(tp, proto, args, cond, prercu, postrcu)		\
+#define __DO_TRACE(tp, proto, args, cond, rcucheck)			\
 	do {								\
 		struct tracepoint_func *it_func_ptr;			\
 		void *it_func;						\
@@ -136,7 +136,11 @@ extern void syscall_unregfunc(void);
 									\
 		if (!(cond))						\
 			return;						\
-		prercu;							\
+		if (rcucheck) {						\
+			if (WARN_ON_ONCE(rcu_irq_enter_disabled()))	\
+				return;					\
+			rcu_irq_enter_irqson();				\
+		}							\
 		rcu_read_lock_sched_notrace();				\
 		it_func_ptr = rcu_dereference_sched((tp)->funcs);	\
 		if (it_func_ptr) {					\
@@ -147,20 +151,19 @@ extern void syscall_unregfunc(void);
 			} while ((++it_func_ptr)->func);		\
 		}							\
 		rcu_read_unlock_sched_notrace();			\
-		postrcu;						\
+		if (rcucheck)						\
+			rcu_irq_exit_irqson();				\
 	} while (0)
 
 #ifndef MODULE
-#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)	\
+#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) \
 	static inline void trace_##name##_rcuidle(proto)		\
 	{								\
 		if (static_key_false(&__tracepoint_##name.key))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
-				TP_CONDITION(cond),			\
-				rcu_irq_enter_irqson(),			\
-				rcu_irq_exit_irqson());			\
+				TP_CONDITION(cond), 1);			\
 	}
 #else
 #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)
@@ -186,7 +189,7 @@ extern void syscall_unregfunc(void);
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
-				TP_CONDITION(cond),,);			\
+				TP_CONDITION(cond), 0);			\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			rcu_read_lock_sched_notrace();			\
 			rcu_dereference_sched(__tracepoint_##name.funcs);\

init/main.c

@@ -545,6 +545,11 @@ asmlinkage __visible void __init start_kernel(void)
 	trap_init();
 	mm_init();
 
+	ftrace_init();
+
+	/* trace_printk can be enabled here */
+	early_trace_init();
+
 	/*
 	 * Set up the scheduler prior starting any interrupts (such as the
 	 * timer interrupt). Full topology setup happens at smp_init()
@@ -570,7 +575,7 @@ asmlinkage __visible void __init start_kernel(void)
 
 	rcu_init();
 
-	/* trace_printk() and trace points may be used after this */
+	/* Trace events are available after this */
 	trace_init();
 
 	context_tracking_init();
@@ -670,8 +675,6 @@ asmlinkage __visible void __init start_kernel(void)
 		efi_free_boot_services();
 	}
 
-	ftrace_init();
-
 	/* Do the rest non-__init'ed, we're now alive */
 	rest_init();
 }
@@ -959,6 +962,7 @@ static int __ref kernel_init(void *unused)
 	kernel_init_freeable();
 	/* need to finish all async __init code before freeing the memory */
 	async_synchronize_full();
+	ftrace_free_init_mem();
 	free_initmem();
 	mark_readonly();
 	system_state = SYSTEM_RUNNING;

kernel/rcu/tree.c

@@ -57,6 +57,7 @@
 #include <linux/random.h>
 #include <linux/trace_events.h>
 #include <linux/suspend.h>
+#include <linux/ftrace.h>
 
 #include "tree.h"
 #include "rcu.h"
@@ -283,6 +284,20 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 };
 
+/*
+ * There's a few places, currently just in the tracing infrastructure,
+ * that uses rcu_irq_enter() to make sure RCU is watching. But there's
+ * a small location where that will not even work. In those cases
+ * rcu_irq_enter_disabled() needs to be checked to make sure rcu_irq_enter()
+ * can be called.
+ */
+static DEFINE_PER_CPU(bool, disable_rcu_irq_enter);
+
+bool rcu_irq_enter_disabled(void)
+{
+	return this_cpu_read(disable_rcu_irq_enter);
+}
+
 /*
  * Record entry into an extended quiescent state.  This is only to be
  * called when not already in an extended quiescent state.
@@ -771,25 +786,24 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
- * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
+ * rcu_eqs_enter_common - current CPU is entering an extended quiescent state
  *
- * If the new value of the ->dynticks_nesting counter now is zero,
- * we really have entered idle, and must do the appropriate accounting.
- * The caller must have disabled interrupts.
+ * Enter idle, doing appropriate accounting.  The caller must have
+ * disabled interrupts.
  */
-static void rcu_eqs_enter_common(long long oldval, bool user)
+static void rcu_eqs_enter_common(bool user)
 {
 	struct rcu_state *rsp;
 	struct rcu_data *rdp;
-	RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
-	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
+	trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0);
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
-		trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
+		trace_rcu_dyntick(TPS("Error on entry: not idle task"), rdtp->dynticks_nesting, 0);
 		rcu_ftrace_dump(DUMP_ORIG);
 		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
 			  current->pid, current->comm,
@@ -800,7 +814,10 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 		do_nocb_deferred_wakeup(rdp);
 	}
 	rcu_prepare_for_idle();
-	rcu_dynticks_eqs_enter();
+	__this_cpu_inc(disable_rcu_irq_enter);
+	rdtp->dynticks_nesting = 0; /* Breaks tracing momentarily. */
+	rcu_dynticks_eqs_enter(); /* After this, tracing works again. */
+	__this_cpu_dec(disable_rcu_irq_enter);
 	rcu_dynticks_task_enter();
 
 	/*
@@ -821,19 +838,15 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
  */
 static void rcu_eqs_enter(bool user)
 {
-	long long oldval;
 	struct rcu_dynticks *rdtp;
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
-	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     (oldval & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
-		rdtp->dynticks_nesting = 0;
-		rcu_eqs_enter_common(oldval, user);
-	} else {
+		     (rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
+	if ((rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+		rcu_eqs_enter_common(user);
+	else
 		rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
-	}
 }
 
 /**
@@ -892,19 +905,18 @@ void rcu_user_enter(void)
  */
 void rcu_irq_exit(void)
 {
-	long long oldval;
 	struct rcu_dynticks *rdtp;
 
 	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
-	oldval = rdtp->dynticks_nesting;
-	rdtp->dynticks_nesting--;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     rdtp->dynticks_nesting < 0);
-	if (rdtp->dynticks_nesting)
-		trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
-	else
-		rcu_eqs_enter_common(oldval, true);
+		     rdtp->dynticks_nesting < 1);
+	if (rdtp->dynticks_nesting <= 1) {
+		rcu_eqs_enter_common(true);
+	} else {
+		trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1);
+		rdtp->dynticks_nesting--;
+	}
 	rcu_sysidle_enter(1);
 }
 

kernel/trace/Kconfig

@@ -134,7 +134,8 @@ config FUNCTION_TRACER
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
-        select GLOB
+	select GLOB
+	select TASKS_RCU if PREEMPT
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation

kernel/trace/ring_buffer.c

@@ -438,6 +438,7 @@ struct ring_buffer_per_cpu {
 	raw_spinlock_t			reader_lock;	/* serialize readers */
 	arch_spinlock_t			lock;
 	struct lock_class_key		lock_key;
+	struct buffer_data_page		*free_page;
 	unsigned long			nr_pages;
 	unsigned int			current_context;
 	struct list_head		*pages;
@@ -4389,9 +4390,25 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  */
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 {
-	struct buffer_data_page *bpage;
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	struct buffer_data_page *bpage = NULL;
+	unsigned long flags;
 	struct page *page;
 
+	local_irq_save(flags);
+	arch_spin_lock(&cpu_buffer->lock);
+
+	if (cpu_buffer->free_page) {
+		bpage = cpu_buffer->free_page;
+		cpu_buffer->free_page = NULL;
+	}
+
+	arch_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
+
+	if (bpage)
+		goto out;
+
 	page = alloc_pages_node(cpu_to_node(cpu),
 				GFP_KERNEL | __GFP_NORETRY, 0);
 	if (!page)
@@ -4399,6 +4416,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 
 	bpage = page_address(page);
 
+ out:
 	rb_init_page(bpage);
 
 	return bpage;
@@ -4408,13 +4426,29 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
 /**
  * ring_buffer_free_read_page - free an allocated read page
  * @buffer: the buffer the page was allocate for
+ * @cpu: the cpu buffer the page came from
  * @data: the page to free
  *
  * Free a page allocated from ring_buffer_alloc_read_page.
  */
-void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
+void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
 {
-	free_page((unsigned long)data);
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	struct buffer_data_page *bpage = data;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	arch_spin_lock(&cpu_buffer->lock);
+
+	if (!cpu_buffer->free_page) {
+		cpu_buffer->free_page = bpage;
+		bpage = NULL;
+	}
+
+	arch_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
+
+	free_page((unsigned long)bpage);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
 

kernel/trace/ring_buffer_benchmark.c

@@ -171,7 +171,7 @@ static enum event_status read_page(int cpu)
 			}
 		}
 	}
-	ring_buffer_free_read_page(buffer, bpage);
+	ring_buffer_free_read_page(buffer, cpu, bpage);
 
 	if (ret < 0)
 		return EVENT_DROPPED;

kernel/trace/trace.h

@@ -262,6 +262,9 @@ struct trace_array {
 #ifdef CONFIG_FUNCTION_TRACER
 	struct ftrace_ops	*ops;
 	struct trace_pid_list	__rcu *function_pids;
+#ifdef CONFIG_DYNAMIC_FTRACE
+	struct list_head	func_probes;
+#endif
 	/* function tracing enabled */
 	int			function_enabled;
 #endif
@@ -579,6 +582,8 @@ void tracing_reset_all_online_cpus(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 bool tracing_is_disabled(void);
 int tracer_tracing_is_on(struct trace_array *tr);
+void tracer_tracing_on(struct trace_array *tr);
+void tracer_tracing_off(struct trace_array *tr);
 struct dentry *trace_create_file(const char *name,
 				 umode_t mode,
 				 struct dentry *parent,
@@ -696,6 +701,9 @@ extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern unsigned long ftrace_update_tot_cnt;
+void ftrace_init_trace_array(struct trace_array *tr);
+#else
+static inline void ftrace_init_trace_array(struct trace_array *tr) { }
 #endif
 #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
 extern int DYN_FTRACE_TEST_NAME(void);
@@ -880,6 +888,14 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 extern struct list_head ftrace_pids;
 
 #ifdef CONFIG_FUNCTION_TRACER
+struct ftrace_func_command {
+	struct list_head	list;
+	char			*name;
+	int			(*func)(struct trace_array *tr,
+					struct ftrace_hash *hash,
+					char *func, char *cmd,
+					char *params, int enable);
+};
 extern bool ftrace_filter_param __initdata;
 static inline int ftrace_trace_task(struct trace_array *tr)
 {
@@ -897,6 +913,8 @@ void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
 void ftrace_init_tracefs_toplevel(struct trace_array *tr,
 				  struct dentry *d_tracer);
 void ftrace_clear_pids(struct trace_array *tr);
+int init_function_trace(void);
+void ftrace_pid_follow_fork(struct trace_array *tr, bool enable);
 #else
 static inline int ftrace_trace_task(struct trace_array *tr)
 {
@@ -916,15 +934,70 @@ static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
 static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
 static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
 static inline void ftrace_clear_pids(struct trace_array *tr) { }
+static inline int init_function_trace(void) { return 0; }
+static inline void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) { }
 /* ftace_func_t type is not defined, use macro instead of static inline */
 #define ftrace_init_array_ops(tr, func) do { } while (0)
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+
+struct ftrace_probe_ops {
+	void			(*func)(unsigned long ip,
+					unsigned long parent_ip,
+					struct trace_array *tr,
+					struct ftrace_probe_ops *ops,
+					void *data);
+	int			(*init)(struct ftrace_probe_ops *ops,
+					struct trace_array *tr,
+					unsigned long ip, void *init_data,
+					void **data);
+	void			(*free)(struct ftrace_probe_ops *ops,
+					struct trace_array *tr,
+					unsigned long ip, void *data);
+	int			(*print)(struct seq_file *m,
+					 unsigned long ip,
+					 struct ftrace_probe_ops *ops,
+					 void *data);
+};
+
+struct ftrace_func_mapper;
+typedef int (*ftrace_mapper_func)(void *data);
+
+struct ftrace_func_mapper *allocate_ftrace_func_mapper(void);
+void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper,
+					   unsigned long ip);
+int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
+			       unsigned long ip, void *data);
+void *ftrace_func_mapper_remove_ip(struct ftrace_func_mapper *mapper,
+				   unsigned long ip);
+void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper,
+			     ftrace_mapper_func free_func);
+
+extern int
+register_ftrace_function_probe(char *glob, struct trace_array *tr,
+			       struct ftrace_probe_ops *ops, void *data);
+extern int
+unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
+				      struct ftrace_probe_ops *ops);
+
+int register_ftrace_command(struct ftrace_func_command *cmd);
+int unregister_ftrace_command(struct ftrace_func_command *cmd);
+
 void ftrace_create_filter_files(struct ftrace_ops *ops,
 				struct dentry *parent);
 void ftrace_destroy_filter_files(struct ftrace_ops *ops);
 #else
+struct ftrace_func_command;
+
+static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
+{
+	return -EINVAL;
+}
+static inline __init int unregister_ftrace_command(char *cmd_name)
+{
+	return -EINVAL;
+}
 /*
  * The ops parameter passed in is usually undefined.
  * This must be a macro.
@@ -989,11 +1062,13 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 
 #ifdef CONFIG_FUNCTION_TRACER
 # define FUNCTION_FLAGS						\
-		C(FUNCTION,		"function-trace"),
+		C(FUNCTION,		"function-trace"),	\
+		C(FUNC_FORK,		"function-fork"),
 # define FUNCTION_DEFAULT_FLAGS		TRACE_ITER_FUNCTION
 #else
 # define FUNCTION_FLAGS
 # define FUNCTION_DEFAULT_FLAGS		0UL
+# define TRACE_ITER_FUNC_FORK		0UL
 #endif
 
 #ifdef CONFIG_STACKTRACE

kernel/trace/trace_benchmark.c

@@ -153,10 +153,18 @@ static int benchmark_event_kthread(void *arg)
 		trace_do_benchmark();
 
 		/*
-		 * We don't go to sleep, but let others
-		 * run as well.
+		 * We don't go to sleep, but let others run as well.
+		 * This is bascially a "yield()" to let any task that
+		 * wants to run, schedule in, but if the CPU is idle,
+		 * we'll keep burning cycles.
+		 *
+		 * Note the _rcu_qs() version of cond_resched() will
+		 * notify synchronize_rcu_tasks() that this thread has
+		 * passed a quiescent state for rcu_tasks. Otherwise
+		 * this thread will never voluntarily schedule which would
+		 * block synchronize_rcu_tasks() indefinitely.
 		 */
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 
 	return 0;

kernel/trace/trace_events.c

@@ -2460,15 +2460,8 @@ struct event_probe_data {
 	bool				enable;
 };
 
-static void
-event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
+static void update_event_probe(struct event_probe_data *data)
 {
-	struct event_probe_data **pdata = (struct event_probe_data **)_data;
-	struct event_probe_data *data = *pdata;
-
-	if (!data)
-		return;
-
 	if (data->enable)
 		clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &data->file->flags);
 	else
@@ -2476,77 +2469,141 @@ event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
 }
 
 static void
-event_enable_count_probe(unsigned long ip, unsigned long parent_ip, void **_data)
+event_enable_probe(unsigned long ip, unsigned long parent_ip,
+		   struct trace_array *tr, struct ftrace_probe_ops *ops,
+		   void *data)
 {
-	struct event_probe_data **pdata = (struct event_probe_data **)_data;
-	struct event_probe_data *data = *pdata;
+	struct ftrace_func_mapper *mapper = data;
+	struct event_probe_data *edata;
+	void **pdata;
 
-	if (!data)
+	pdata = ftrace_func_mapper_find_ip(mapper, ip);
+	if (!pdata || !*pdata)
+		return;
+
+	edata = *pdata;
+	update_event_probe(edata);
+}
+
+static void
+event_enable_count_probe(unsigned long ip, unsigned long parent_ip,
+			 struct trace_array *tr, struct ftrace_probe_ops *ops,
+			 void *data)
+{
+	struct ftrace_func_mapper *mapper = data;
+	struct event_probe_data *edata;
+	void **pdata;
+
+	pdata = ftrace_func_mapper_find_ip(mapper, ip);
+	if (!pdata || !*pdata)
 		return;
 
-	if (!data->count)
+	edata = *pdata;
+
+	if (!edata->count)
 		return;
 
 	/* Skip if the event is in a state we want to switch to */
-	if (data->enable == !(data->file->flags & EVENT_FILE_FL_SOFT_DISABLED))
+	if (edata->enable == !(edata->file->flags & EVENT_FILE_FL_SOFT_DISABLED))
 		return;
 
-	if (data->count != -1)
-		(data->count)--;
+	if (edata->count != -1)
+		(edata->count)--;
 
-	event_enable_probe(ip, parent_ip, _data);
+	update_event_probe(edata);
 }
 
 static int
 event_enable_print(struct seq_file *m, unsigned long ip,
-		      struct ftrace_probe_ops *ops, void *_data)
+		   struct ftrace_probe_ops *ops, void *data)
 {
-	struct event_probe_data *data = _data;
+	struct ftrace_func_mapper *mapper = data;
+	struct event_probe_data *edata;
+	void **pdata;
+
+	pdata = ftrace_func_mapper_find_ip(mapper, ip);
+
+	if (WARN_ON_ONCE(!pdata || !*pdata))
+		return 0;
+
+	edata = *pdata;
 
 	seq_printf(m, "%ps:", (void *)ip);
 
 	seq_printf(m, "%s:%s:%s",
-		   data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
-		   data->file->event_call->class->system,
-		   trace_event_name(data->file->event_call));
+		   edata->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
+		   edata->file->event_call->class->system,
+		   trace_event_name(edata->file->event_call));
 
-	if (data->count == -1)
+	if (edata->count == -1)
 		seq_puts(m, ":unlimited\n");
 	else
-		seq_printf(m, ":count=%ld\n", data->count);
+		seq_printf(m, ":count=%ld\n", edata->count);
 
 	return 0;
 }
 
 static int
-event_enable_init(struct ftrace_probe_ops *ops, unsigned long ip,
-		  void **_data)
+event_enable_init(struct ftrace_probe_ops *ops, struct trace_array *tr,
+		  unsigned long ip, void *init_data, void **data)
 {
-	struct event_probe_data **pdata = (struct event_probe_data **)_data;
-	struct event_probe_data *data = *pdata;
+	struct ftrace_func_mapper *mapper = *data;
+	struct event_probe_data *edata = init_data;
+	int ret;
+
+	if (!mapper) {
+		mapper = allocate_ftrace_func_mapper();
+		if (!mapper)
+			return -ENODEV;
+		*data = mapper;
+	}
+
+	ret = ftrace_func_mapper_add_ip(mapper, ip, edata);
+	if (ret < 0)
+		return ret;
+
+	edata->ref++;
 
-	data->ref++;
+	return 0;
+}
+
+static int free_probe_data(void *data)
+{
+	struct event_probe_data *edata = data;
+
+	edata->ref--;
+	if (!edata->ref) {
+		/* Remove the SOFT_MODE flag */
+		__ftrace_event_enable_disable(edata->file, 0, 1);
+		module_put(edata->file->event_call->mod);
+		kfree(edata);
+	}
 	return 0;
 }
 
 static void
-event_enable_free(struct ftrace_probe_ops *ops, unsigned long ip,
-		  void **_data)
+event_enable_free(struct ftrace_probe_ops *ops, struct trace_array *tr,
+		  unsigned long ip, void *data)
 {
-	struct event_probe_data **pdata = (struct event_probe_data **)_data;
-	struct event_probe_data *data = *pdata;
+	struct ftrace_func_mapper *mapper = data;
+	struct event_probe_data *edata;
 
-	if (WARN_ON_ONCE(data->ref <= 0))
+	if (!ip) {
+		if (!mapper)
+			return;
+		free_ftrace_func_mapper(mapper, free_probe_data);
 		return;
-
-	data->ref--;
-	if (!data->ref) {
-		/* Remove the SOFT_MODE flag */
-		__ftrace_event_enable_disable(data->file, 0, 1);
-		module_put(data->file->event_call->mod);
-		kfree(data);
 	}
-	*pdata = NULL;
+
+	edata = ftrace_func_mapper_remove_ip(mapper, ip);
+
+	if (WARN_ON_ONCE(!edata))
+		return;
+
+	if (WARN_ON_ONCE(edata->ref <= 0))
+		return;
+
+	free_probe_data(edata);
 }
 
 static struct ftrace_probe_ops event_enable_probe_ops = {
@@ -2578,10 +2635,9 @@ static struct ftrace_probe_ops event_disable_count_probe_ops = {
 };
 
 static int
-event_enable_func(struct ftrace_hash *hash,
+event_enable_func(struct trace_array *tr, struct ftrace_hash *hash,
 		  char *glob, char *cmd, char *param, int enabled)
 {
-	struct trace_array *tr = top_trace_array();
 	struct trace_event_file *file;
 	struct ftrace_probe_ops *ops;
 	struct event_probe_data *data;
@@ -2619,12 +2675,12 @@ event_enable_func(struct ftrace_hash *hash,
 		ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops;
 
 	if (glob[0] == '!') {
-		unregister_ftrace_function_probe_func(glob+1, ops);
-		ret = 0;
+		ret = unregister_ftrace_function_probe_func(glob+1, tr, ops);
 		goto out;
 	}
 
 	ret = -ENOMEM;
+
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		goto out;
@@ -2661,7 +2717,8 @@ event_enable_func(struct ftrace_hash *hash,
 	ret = __ftrace_event_enable_disable(file, 1, 1);
 	if (ret < 0)
 		goto out_put;
-	ret = register_ftrace_function_probe(glob, ops, data);
+
+	ret = register_ftrace_function_probe(glob, tr, ops, data);
 	/*
 	 * The above returns on success the # of functions enabled,
 	 * but if it didn't find any functions it returns zero.

kernel/trace/trace_kprobe.c

@@ -25,6 +25,7 @@
 #include "trace_probe.h"
 
 #define KPROBE_EVENT_SYSTEM "kprobes"
+#define KRETPROBE_MAXACTIVE_MAX 4096
 
 /**
  * Kprobe event core functions
@@ -282,6 +283,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
 					     void *addr,
 					     const char *symbol,
 					     unsigned long offs,
+					     int maxactive,
 					     int nargs, bool is_return)
 {
 	struct trace_kprobe *tk;
@@ -309,6 +311,8 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
 	else
 		tk->rp.kp.pre_handler = kprobe_dispatcher;
 
+	tk->rp.maxactive = maxactive;
+
 	if (!event || !is_good_name(event)) {
 		ret = -EINVAL;
 		goto error;
@@ -598,8 +602,10 @@ static int create_trace_kprobe(int argc, char **argv)
 {
 	/*
 	 * Argument syntax:
-	 *  - Add kprobe: p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
-	 *  - Add kretprobe: r[:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
+	 *  - Add kprobe:
+	 *      p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
+	 *  - Add kretprobe:
+	 *      r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
 	 * Fetch args:
 	 *  $retval	: fetch return value
 	 *  $stack	: fetch stack address
@@ -619,6 +625,7 @@ static int create_trace_kprobe(int argc, char **argv)
 	int i, ret = 0;
 	bool is_return = false, is_delete = false;
 	char *symbol = NULL, *event = NULL, *group = NULL;
+	int maxactive = 0;
 	char *arg;
 	unsigned long offset = 0;
 	void *addr = NULL;
@@ -637,8 +644,28 @@ static int create_trace_kprobe(int argc, char **argv)
 		return -EINVAL;
 	}
 
-	if (argv[0][1] == ':') {
-		event = &argv[0][2];
+	event = strchr(&argv[0][1], ':');
+	if (event) {
+		event[0] = '\0';
+		event++;
+	}
+	if (is_return && isdigit(argv[0][1])) {
+		ret = kstrtouint(&argv[0][1], 0, &maxactive);
+		if (ret) {
+			pr_info("Failed to parse maxactive.\n");
+			return ret;
+		}
+		/* kretprobes instances are iterated over via a list. The
+		 * maximum should stay reasonable.
+		 */
+		if (maxactive > KRETPROBE_MAXACTIVE_MAX) {
+			pr_info("Maxactive is too big (%d > %d).\n",
+				maxactive, KRETPROBE_MAXACTIVE_MAX);
+			return -E2BIG;
+		}
+	}
+
+	if (event) {
 		if (strchr(event, '/')) {
 			group = event;
 			event = strchr(group, '/') + 1;
@@ -715,8 +742,8 @@ static int create_trace_kprobe(int argc, char **argv)
 				 is_return ? 'r' : 'p', addr);
 		event = buf;
 	}
-	tk = alloc_trace_kprobe(group, event, addr, symbol, offset, argc,
-			       is_return);
+	tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive,
+			       argc, is_return);
 	if (IS_ERR(tk)) {
 		pr_info("Failed to allocate trace_probe.(%d)\n",
 			(int)PTR_ERR(tk));

kernel/trace/trace_stack.c

@@ -35,7 +35,7 @@ unsigned long stack_trace_max_size;
 arch_spinlock_t stack_trace_max_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
-static DEFINE_PER_CPU(int, trace_active);
+DEFINE_PER_CPU(int, disable_stack_tracer);
 static DEFINE_MUTEX(stack_sysctl_mutex);
 
 int stack_tracer_enabled;
@@ -96,6 +96,14 @@ check_stack(unsigned long ip, unsigned long *stack)
 	if (in_nmi())
 		return;
 
+	/*
+	 * There's a slight chance that we are tracing inside the
+	 * RCU infrastructure, and rcu_irq_enter() will not work
+	 * as expected.
+	 */
+	if (unlikely(rcu_irq_enter_disabled()))
+		return;
+
 	local_irq_save(flags);
 	arch_spin_lock(&stack_trace_max_lock);
 
@@ -207,13 +215,12 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 		 struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	unsigned long stack;
-	int cpu;
 
 	preempt_disable_notrace();
 
-	cpu = raw_smp_processor_id();
 	/* no atomic needed, we only modify this variable by this cpu */
-	if (per_cpu(trace_active, cpu)++ != 0)
+	__this_cpu_inc(disable_stack_tracer);
+	if (__this_cpu_read(disable_stack_tracer) != 1)
 		goto out;
 
 	ip += MCOUNT_INSN_SIZE;
@@ -221,7 +228,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	check_stack(ip, &stack);
 
  out:
-	per_cpu(trace_active, cpu)--;
+	__this_cpu_dec(disable_stack_tracer);
 	/* prevent recursion in schedule */
 	preempt_enable_notrace();
 }
@@ -253,7 +260,6 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 	long *ptr = filp->private_data;
 	unsigned long val, flags;
 	int ret;
-	int cpu;
 
 	ret = kstrtoul_from_user(ubuf, count, 10, &val);
 	if (ret)
@@ -264,16 +270,15 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 	/*
 	 * In case we trace inside arch_spin_lock() or after (NMI),
 	 * we will cause circular lock, so we also need to increase
-	 * the percpu trace_active here.
+	 * the percpu disable_stack_tracer here.
 	 */
-	cpu = smp_processor_id();
-	per_cpu(trace_active, cpu)++;
+	__this_cpu_inc(disable_stack_tracer);
 
 	arch_spin_lock(&stack_trace_max_lock);
 	*ptr = val;
 	arch_spin_unlock(&stack_trace_max_lock);
 
-	per_cpu(trace_active, cpu)--;
+	__this_cpu_dec(disable_stack_tracer);
 	local_irq_restore(flags);
 
 	return count;
@@ -307,12 +312,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	int cpu;
-
 	local_irq_disable();
 
-	cpu = smp_processor_id();
-	per_cpu(trace_active, cpu)++;
+	__this_cpu_inc(disable_stack_tracer);
 
 	arch_spin_lock(&stack_trace_max_lock);
 
@@ -324,12 +326,9 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 
 static void t_stop(struct seq_file *m, void *p)
 {
-	int cpu;
-
 	arch_spin_unlock(&stack_trace_max_lock);
 
-	cpu = smp_processor_id();
-	per_cpu(trace_active, cpu)--;
+	__this_cpu_dec(disable_stack_tracer);
 
 	local_irq_enable();
 }

mm/page_alloc.c

@@ -65,6 +65,7 @@
 #include <linux/page_owner.h>
 #include <linux/kthread.h>
 #include <linux/memcontrol.h>
+#include <linux/ftrace.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>

scripts/recordmcount.c

@@ -412,6 +412,7 @@ static int
 is_mcounted_section_name(char const *const txtname)
 {
 	return strcmp(".text",           txtname) == 0 ||
+		strcmp(".init.text",     txtname) == 0 ||
 		strcmp(".ref.text",      txtname) == 0 ||
 		strcmp(".sched.text",    txtname) == 0 ||
 		strcmp(".spinlock.text", txtname) == 0 ||

scripts/recordmcount.pl

@@ -130,6 +130,7 @@ if ($inputfile =~ m,kernel/trace/ftrace\.o$,) {
 # Acceptable sections to record.
 my %text_sections = (
      ".text" => 1,
+     ".init.text" => 1,
      ".ref.text" => 1,
      ".sched.text" => 1,
      ".spinlock.text" => 1,

tools/testing/selftests/ftrace/ftracetest

@@ -16,6 +16,7 @@ echo "		-k|--keep  Keep passed test logs"
 echo "		-v|--verbose Increase verbosity of test messages"
 echo "		-vv        Alias of -v -v (Show all results in stdout)"
 echo "		-d|--debug Debug mode (trace all shell commands)"
+echo "		-l|--logdir <dir> Save logs on the <dir>"
 exit $1
 }
 
@@ -64,6 +65,10 @@ parse_opts() { # opts
       DEBUG=1
       shift 1
     ;;
+    --logdir|-l)
+      LOG_DIR=$2
+      shift 2
+    ;;
     *.tc)
       if [ -f "$1" ]; then
         OPT_TEST_CASES="$OPT_TEST_CASES `abspath $1`"
@@ -145,11 +150,16 @@ XFAILED_CASES=
 UNDEFINED_CASES=
 TOTAL_RESULT=0
 
+INSTANCE=
 CASENO=0
 testcase() { # testfile
   CASENO=$((CASENO+1))
   desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:`
-  prlog -n "[$CASENO]$desc"
+  prlog -n "[$CASENO]$INSTANCE$desc"
+}
+
+test_on_instance() { # testfile
+  grep -q "^#[ \t]*flags:.*instance" $1
 }
 
 eval_result() { # sigval
@@ -266,6 +276,17 @@ for t in $TEST_CASES; do
   run_test $t
 done
 
+# Test on instance loop
+INSTANCE=" (instance) "
+for t in $TEST_CASES; do
+  test_on_instance $t || continue
+  SAVED_TRACING_DIR=$TRACING_DIR
+  export TRACING_DIR=`mktemp -d $TRACING_DIR/instances/ftracetest.XXXXXX`
+  run_test $t
+  rmdir $TRACING_DIR
+  TRACING_DIR=$SAVED_TRACING_DIR
+done
+
 prlog ""
 prlog "# of passed: " `echo $PASSED_CASES | wc -w`
 prlog "# of failed: " `echo $FAILED_CASES | wc -w`

tools/testing/selftests/ftrace/test.d/00basic/basic2.tc

 #!/bin/sh
 # description: Basic test for tracers
+# flags: instance
 test -f available_tracers
 for t in `cat available_tracers`; do
   echo $t > current_tracer

tools/testing/selftests/ftrace/test.d/00basic/basic3.tc

 #!/bin/sh
 # description: Basic trace clock test
+# flags: instance
 test -f trace_clock
 for c in `cat trace_clock | tr  -d \[\]`; do
   echo $c > trace_clock

tools/testing/selftests/ftrace/test.d/event/event-enable.tc

 #!/bin/sh
 # description: event tracing - enable/disable with event level files
+# flags: instance
 
 do_reset() {
     echo > set_event

tools/testing/selftests/ftrace/test.d/event/event-pid.tc

 #!/bin/sh
 # description: event tracing - restricts events based on pid
+# flags: instance
 
 do_reset() {
     echo > set_event

tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc

 #!/bin/sh
 # description: event tracing - enable/disable with subsystem level files
+# flags: instance
 
 do_reset() {
     echo > set_event

tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc

+#!/bin/sh
+# description: ftrace - test for function event triggers
+# flags: instance
+#
+# Ftrace allows to add triggers to functions, such as enabling or disabling
+# tracing, enabling or disabling trace events, or recording a stack trace
+# within the ring buffer.
+#
+# This test is designed to test event triggers
+#
+
+# The triggers are set within the set_ftrace_filter file
+if [ ! -f set_ftrace_filter ]; then
+    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
+    exit_unsupported
+fi
+
+do_reset() {
+    reset_ftrace_filter
+    reset_tracer
+    disable_events
+    clear_trace
+    enable_tracing
+}
+
+fail() { # mesg
+    do_reset
+    echo $1
+    exit $FAIL
+}
+
+SLEEP_TIME=".1"
+
+do_reset
+
+echo "Testing function probes with events:"
+
+EVENT="sched:sched_switch"
+EVENT_ENABLE="events/sched/sched_switch/enable"
+
+cnt_trace() {
+    grep -v '^#' trace | wc -l
+}
+
+test_event_enabled() {
+    val=$1
+
+    e=`cat $EVENT_ENABLE`
+    if [ "$e" != $val ]; then
+	echo "Expected $val but found $e"
+	exit -1
+    fi
+}
+
+run_enable_disable() {
+    enable=$1			# enable
+    Enable=$2			# Enable
+    check_disable=$3		# 0
+    check_enable_star=$4	# 1*
+    check_disable_star=$5	# 0*
+
+    cnt=`cnt_trace`
+    if [ $cnt -ne 0 ]; then
+	fail "Found junk in trace file"
+    fi
+
+    echo "$Enable event all the time"
+
+    echo $check_disable > $EVENT_ENABLE
+    sleep $SLEEP_TIME
+
+    test_event_enabled $check_disable
+
+    echo "schedule:${enable}_event:$EVENT" > set_ftrace_filter
+
+    echo " make sure it works 5 times"
+
+    for i in `seq 5`; do
+	sleep $SLEEP_TIME
+	echo "  test $i"
+	test_event_enabled $check_enable_star
+
+	echo $check_disable > $EVENT_ENABLE
+    done
+    sleep $SLEEP_TIME
+    echo " make sure it's still works"
+    test_event_enabled $check_enable_star
+
+    reset_ftrace_filter
+
+    echo " make sure it only works 3 times"
+
+    echo $check_disable > $EVENT_ENABLE
+    sleep $SLEEP_TIME
+
+    echo "schedule:${enable}_event:$EVENT:3" > set_ftrace_filter
+
+    for i in `seq 3`; do
+	sleep $SLEEP_TIME
+	echo "  test $i"
+	test_event_enabled $check_enable_star
+
+	echo $check_disable > $EVENT_ENABLE
+    done
+
+    sleep $SLEEP_TIME
+    echo " make sure it stop working"
+    test_event_enabled $check_disable_star
+
+    do_reset
+}
+
+run_enable_disable enable Enable 0 "1*" "0*"
+run_enable_disable disable Disable 1 "0*" "1*"

tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc

+#!/bin/sh
+# description: ftrace - test reading of set_ftrace_filter
+#
+# The set_ftrace_filter file of ftrace is used to list functions as well as
+# triggers (probes) attached to functions. The code to read this file is not
+# straight forward and has had various bugs in the past. This test is designed
+# to add functions and triggers to that file in various ways and read that
+# file in various ways (cat vs dd).
+#
+
+# The triggers are set within the set_ftrace_filter file
+if [ ! -f set_ftrace_filter ]; then
+    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
+    exit_unsupported
+fi
+
+do_reset() {
+    reset_tracer
+    reset_ftrace_filter
+    disable_events
+    clear_trace
+    enable_tracing
+}
+
+fail() { # mesg
+    do_reset
+    echo $1
+    exit $FAIL
+}
+
+do_reset
+
+FILTER=set_ftrace_filter
+FUNC1="schedule"
+FUNC2="do_IRQ"
+
+ALL_FUNCS="#### all functions enabled ####"
+
+test_func() {
+    if ! echo "$1" | grep -q "^$2\$"; then
+	return 0
+    fi
+    echo "$1" | grep -v "^$2\$"
+    return 1
+}
+
+check_set_ftrace_filter() {
+    cat=`cat $FILTER`
+    dd1=`dd if=$FILTER bs=1 | grep -v -e 'records in' -e 'records out' -e 'bytes copied'`
+    dd100=`dd if=$FILTER bs=100 | grep -v -e 'records in' -e 'records out' -e 'bytes copied'`
+
+    echo "Testing '$@'"
+
+    while [ $# -gt 0 ]; do
+	echo "test $1"
+	if cat=`test_func "$cat" "$1"`; then
+	    return 0
+	fi
+	if dd1=`test_func "$dd1" "$1"`; then
+	    return 0
+	fi
+	if dd100=`test_func "$dd100" "$1"`; then
+	    return 0
+	fi
+	shift
+    done
+
+    if [ -n "$cat" ]; then
+	return 0
+    fi
+    if [ -n "$dd1" ]; then
+	return 0
+    fi
+    if [ -n "$dd100" ]; then
+	return 0
+    fi
+    return 1;
+}
+
+if check_set_ftrace_filter "$ALL_FUNCS"; then
+    fail "Expected only $ALL_FUNCS"
+fi
+
+echo "$FUNC1:traceoff" > set_ftrace_filter
+if check_set_ftrace_filter "$ALL_FUNCS" "$FUNC1:traceoff:unlimited"; then
+    fail "Expected $ALL_FUNCS and $FUNC1:traceoff:unlimited"
+fi
+
+echo "$FUNC1" > set_ftrace_filter
+if check_set_ftrace_filter "$FUNC1" "$FUNC1:traceoff:unlimited"; then
+    fail "Expected $FUNC1 and $FUNC1:traceoff:unlimited"
+fi
+
+echo "$FUNC2" >> set_ftrace_filter
+if check_set_ftrace_filter "$FUNC1" "$FUNC2" "$FUNC1:traceoff:unlimited"; then
+    fail "Expected $FUNC1 $FUNC2 and $FUNC1:traceoff:unlimited"
+fi
+
+echo "$FUNC2:traceoff" >> set_ftrace_filter
+if check_set_ftrace_filter "$FUNC1" "$FUNC2" "$FUNC1:traceoff:unlimited" "$FUNC2:traceoff:unlimited"; then
+    fail "Expected $FUNC1 $FUNC2 $FUNC1:traceoff:unlimited and $FUNC2:traceoff:unlimited"
+fi
+
+echo "$FUNC1" > set_ftrace_filter
+if check_set_ftrace_filter "$FUNC1" "$FUNC1:traceoff:unlimited" "$FUNC2:traceoff:unlimited"; then
+    fail "Expected $FUNC1 $FUNC1:traceoff:unlimited and $FUNC2:traceoff:unlimited"
+fi
+
+echo > set_ftrace_filter
+if check_set_ftrace_filter "$ALL_FUNCS" "$FUNC1:traceoff:unlimited" "$FUNC2:traceoff:unlimited"; then
+    fail "Expected $ALL_FUNCS $FUNC1:traceoff:unlimited and $FUNC2:traceoff:unlimited"
+fi
+
+reset_ftrace_filter
+
+if check_set_ftrace_filter "$ALL_FUNCS"; then
+    fail "Expected $ALL_FUNCS"
+fi
+
+echo "$FUNC1" > set_ftrace_filter
+if check_set_ftrace_filter "$FUNC1" ; then
+    fail "Expected $FUNC1"
+fi
+
+echo "$FUNC2" >> set_ftrace_filter
+if check_set_ftrace_filter "$FUNC1" "$FUNC2" ; then
+    fail "Expected $FUNC1 and $FUNC2"
+fi
+
+do_reset
+
+exit 0

tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc

+#!/bin/sh
+# description: ftrace - test for function traceon/off triggers
+# flags: instance
+#
+# Ftrace allows to add triggers to functions, such as enabling or disabling
+# tracing, enabling or disabling trace events, or recording a stack trace
+# within the ring buffer.
+#
+# This test is designed to test enabling and disabling tracing triggers
+#
+
+# The triggers are set within the set_ftrace_filter file
+if [ ! -f set_ftrace_filter ]; then
+    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
+    exit_unsupported
+fi
+
+do_reset() {
+    reset_ftrace_filter
+    reset_tracer
+    disable_events
+    clear_trace
+    enable_tracing
+}
+
+fail() { # mesg
+    do_reset
+    echo $1
+    exit $FAIL
+}
+
+SLEEP_TIME=".1"
+
+do_reset
+
+echo "Testing function probes with enabling disabling tracing:"
+
+cnt_trace() {
+    grep -v '^#' trace | wc -l
+}
+
+echo '** DISABLE TRACING'
+disable_tracing
+clear_trace
+
+cnt=`cnt_trace`
+if [ $cnt -ne 0 ]; then
+    fail "Found junk in trace"
+fi
+
+
+echo '** ENABLE EVENTS'
+
+echo 1 > events/enable
+
+echo '** ENABLE TRACING'
+enable_tracing
+
+cnt=`cnt_trace`
+if [ $cnt -eq 0 ]; then
+   fail "Nothing found in trace"
+fi
+
+# powerpc uses .schedule
+func="schedule"
+x=`grep '^\.schedule$' available_filter_functions | wc -l`
+if [ "$x" -eq 1 ]; then
+   func=".schedule"
+fi
+
+echo '** SET TRACEOFF'
+
+echo "$func:traceoff" > set_ftrace_filter
+
+cnt=`grep schedule set_ftrace_filter | wc -l`
+if [ $cnt -ne 1 ]; then
+   fail "Did not find traceoff trigger"
+fi
+
+cnt=`cnt_trace`
+sleep $SLEEP_TIME
+cnt2=`cnt_trace`
+
+if [ $cnt -ne $cnt2 ]; then
+   fail "Tracing is not stopped"
+fi
+
+on=`cat tracing_on`
+if [ $on != "0" ]; then
+    fail "Tracing is not off"
+fi
+
+line1=`cat trace | tail -1`
+sleep $SLEEP_TIME
+line2=`cat trace | tail -1`
+
+if [ "$line1" != "$line2" ]; then
+    fail "Tracing file is still changing"
+fi
+
+clear_trace
+
+cnt=`cnt_trace`
+if [ $cnt -ne 0 ]; then
+    fail "Tracing is still happeing"
+fi
+
+echo "!$func:traceoff" >> set_ftrace_filter
+
+cnt=`grep schedule set_ftrace_filter | wc -l`
+if [ $cnt -ne 0 ]; then
+    fail "traceoff trigger still exists"
+fi
+
+on=`cat tracing_on`
+if [ $on != "0" ]; then
+    fail "Tracing is started again"
+fi
+
+echo "$func:traceon" > set_ftrace_filter
+
+cnt=`grep schedule set_ftrace_filter | wc -l`
+if [ $cnt -ne 1 ]; then
+    fail "traceon trigger not found"
+fi
+
+cnt=`cnt_trace`
+if [ $cnt -eq 0 ]; then
+   fail "Tracing did not start"
+fi
+
+on=`cat tracing_on`
+if [ $on != "1" ]; then
+    fail "Tracing was not enabled"
+fi
+
+
+echo "!$func:traceon" >> set_ftrace_filter
+
+cnt=`grep schedule set_ftrace_filter | wc -l`
+if [ $cnt -ne 0 ]; then
+   fail "traceon trigger still exists"
+fi
+
+check_sleep() {
+    val=$1
+    sleep $SLEEP_TIME
+    cat set_ftrace_filter
+    on=`cat tracing_on`
+    if [ $on != "$val" ]; then
+	fail "Expected tracing_on to be $val, but it was $on"
+    fi
+}
+
+
+echo "$func:traceoff:3" > set_ftrace_filter
+check_sleep "0"
+echo 1 > tracing_on
+check_sleep "0"
+echo 1 > tracing_on
+check_sleep "0"
+echo 1 > tracing_on
+check_sleep "1"
+echo "!$func:traceoff:0" > set_ftrace_filter
+
+if grep -e traceon -e traceoff set_ftrace_filter; then
+    fail "Tracing on and off triggers still exist"
+fi
+
+disable_events
+
+exit 0

tools/testing/selftests/ftrace/test.d/functions

@@ -30,6 +30,27 @@ reset_events_filter() { # reset all current setting filters
     done
 }
 
+reset_ftrace_filter() { # reset all triggers in set_ftrace_filter
+    echo > set_ftrace_filter
+    grep -v '^#' set_ftrace_filter | while read t; do
+	tr=`echo $t | cut -d: -f2`
+	if [ "$tr" == "" ]; then
+	    continue
+	fi
+	if [ $tr == "enable_event" -o $tr == "disable_event" ]; then
+	    tr=`echo $t | cut -d: -f1-4`
+	    limit=`echo $t | cut -d: -f5`
+	else
+	    tr=`echo $t | cut -d: -f1-2`
+	    limit=`echo $t | cut -d: -f3`
+	fi
+	if [ "$limit" != "unlimited" ]; then
+	    tr="$tr:$limit"
+	fi
+	echo "!$tr" > set_ftrace_filter
+    done
+}
+
 disable_events() {
     echo 0 > events/enable
 }

tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc

+#!/bin/sh
+# description: Kretprobe dynamic event with maxactive
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo > kprobe_events
+
+# Test if we successfully reject unknown messages
+if echo 'a:myprobeaccept inet_csk_accept' > kprobe_events; then false; else true; fi
+
+# Test if we successfully reject too big maxactive
+if echo 'r1000000:myprobeaccept inet_csk_accept' > kprobe_events; then false; else true; fi
+
+# Test if we successfully reject unparsable numbers for maxactive
+if echo 'r10fuzz:myprobeaccept inet_csk_accept' > kprobe_events; then false; else true; fi
+
+# Test for kretprobe with event name without maxactive
+echo 'r:myprobeaccept inet_csk_accept' > kprobe_events
+grep myprobeaccept kprobe_events
+test -d events/kprobes/myprobeaccept
+echo '-:myprobeaccept' >> kprobe_events
+
+# Test for kretprobe with event name with a small maxactive
+echo 'r10:myprobeaccept inet_csk_accept' > kprobe_events
+grep myprobeaccept kprobe_events
+test -d events/kprobes/myprobeaccept
+echo '-:myprobeaccept' >> kprobe_events
+
+# Test for kretprobe without event name without maxactive
+echo 'r inet_csk_accept' > kprobe_events
+grep inet_csk_accept kprobe_events
+echo > kprobe_events
+
+# Test for kretprobe without event name with a small maxactive
+echo 'r10 inet_csk_accept' > kprobe_events
+grep inet_csk_accept kprobe_events
+echo > kprobe_events
+
+clear_trace

tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc

 #!/bin/sh
 # description: event trigger - test event enable/disable trigger
+# flags: instance
 
 do_reset() {
     reset_trigger

tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc

 #!/bin/sh
 # description: event trigger - test trigger filter
+# flags: instance
 
 do_reset() {
     reset_trigger

tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc

 #!/bin/sh
 # description: event trigger - test histogram modifiers
+# flags: instance
 
 do_reset() {
     reset_trigger

tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc

 #!/bin/sh
 # description: event trigger - test histogram trigger
+# flags: instance
 
 do_reset() {
     reset_trigger

tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc

 #!/bin/sh
 # description: event trigger - test multiple histogram triggers
+# flags: instance
 
 do_reset() {
     reset_trigger