Merge tag 'trace-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing changes from Steven Rostedt:
 "The majority of the changes here are cleanups for the large changes
  that were added to 3.10, which includes several bug fixes that have
  been marked for stable.

  As for new features, there were a few, but nothing to write to LWN
  about.  These include:

  New function trigger called "dump" and "cpudump" that will cause
  ftrace to dump its buffer to the console when the function is called.
  The difference between "dump" and "cpudump" is that "dump" will dump
  the entire contents of the ftrace buffer, where as "cpudump" will only
  dump the contents of the ftrace buffer for the CPU that called the
  function.

  Another small enhancement is a new sysctl switch called
  "traceoff_on_warning" which, when enabled, will disable tracing if any
  WARN_ON() is triggered.  This is useful if you want to debug what
  caused a warning and do not want to risk losing your trace data by the
  ring buffer overwriting the data before you can disable it.  There's
  also a kernel command line option that will make this enabled at boot
  up called the same thing"

* tag 'trace-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (34 commits)
  tracing: Make tracing_open_generic_{tr,tc}() static
  tracing: Remove ftrace() function
  tracing: Remove TRACE_EVENT_TYPE enum definition
  tracing: Make tracer_tracing_{off,on,is_on}() static
  tracing: Fix irqs-off tag display in syscall tracing
  uprobes: Fix return value in error handling path
  tracing: Fix race between deleting buffer and setting events
  tracing: Add trace_array_get/put() to event handling
  tracing: Get trace_array ref counts when accessing trace files
  tracing: Add trace_array_get/put() to handle instance refs better
  tracing: Protect ftrace_trace_arrays list in trace_events.c
  tracing: Make trace_marker use the correct per-instance buffer
  ftrace: Do not run selftest if command line parameter is set
  tracing/kprobes: Don't pass addr=ip to perf_trace_buf_submit()
  tracing: Use flag buffer_disabled for irqsoff tracer
  tracing/kprobes: Turn trace_probe->files into list_head
  tracing: Fix disabling of soft disable
  tracing: Add missing syscall_metadata comment
  tracing: Simplify code for showing of soft disabled flag
  tracing/kprobes: Kill probe_enable_lock
  ...

Documentation/kernel-parameters.txt

@@ -3081,6 +3081,19 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			See also Documentation/trace/ftrace.txt "trace options"
 			section.
 
+	traceoff_on_warning
+			[FTRACE] enable this option to disable tracing when a
+			warning is hit. This turns off "tracing_on". Tracing can
+			be enabled again by echoing '1' into the "tracing_on"
+			file located in /sys/kernel/debug/tracing/
+
+			This option is useful, as it disables the trace before
+			the WARNING dump is called, which prevents the trace to
+			be filled with content caused by the warning output.
+
+			This option can also be set at run time via the sysctl
+			option:  kernel/traceoff_on_warning
+
 	transparent_hugepage=
 			[KNL]
 			Format: [always|madvise|never]

Documentation/trace/events.txt

@@ -183,13 +183,22 @@ The relational-operators depend on the type of the field being tested:
 
 The operators available for numeric fields are:
 
-==, !=, <, <=, >, >=
+==, !=, <, <=, >, >=, &
 
 And for string fields they are:
 
-==, !=
+==, !=, ~
 
-Currently, only exact string matches are supported.
+The glob (~) only accepts a wild card character (*) at the start and or
+end of the string. For example:
+
+  prev_comm ~ "*sh"
+  prev_comm ~ "sh*"
+  prev_comm ~ "*sh*"
+
+But does not allow for it to be within the string:
+
+  prev_comm ~ "ba*sh"   <-- is invalid
 
 5.2 Setting filters
 -------------------

Documentation/trace/ftrace.txt

@@ -2430,6 +2430,19 @@ The following commands are supported:
    echo '!schedule:disable_event:sched:sched_switch' > \
    	 set_ftrace_filter
 
+- dump
+  When the function is hit, it will dump the contents of the ftrace
+  ring buffer to the console. This is useful if you need to debug
+  something, and want to dump the trace when a certain function
+  is hit. Perhaps its a function that is called before a tripple
+  fault happens and does not allow you to get a regular dump.
+
+- cpudump
+  When the function is hit, it will dump the contents of the ftrace
+  ring buffer for the current CPU to the console. Unlike the "dump"
+  command, it only prints out the contents of the ring buffer for the
+  CPU that executed the function that triggered the dump.
+
 trace_pipe
 ----------
 

include/linux/ftrace.h

@@ -566,10 +566,6 @@ static inline ssize_t ftrace_filter_write(struct file *file, const char __user *
 			    size_t cnt, loff_t *ppos) { return -ENODEV; }
 static inline ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
 			     size_t cnt, loff_t *ppos) { return -ENODEV; }
-static inline loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence)
-{
-	return -ENODEV;
-}
 static inline int
 ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; }
 #endif /* CONFIG_DYNAMIC_FTRACE */
@@ -828,10 +824,15 @@ enum ftrace_dump_mode;
 
 extern enum ftrace_dump_mode ftrace_dump_on_oops;
 
+extern void disable_trace_on_warning(void);
+extern int __disable_trace_on_warning;
+
 #ifdef CONFIG_PREEMPT
 #define INIT_TRACE_RECURSION		.trace_recursion = 0,
 #endif
 
+#else /* CONFIG_TRACING */
+static inline void  disable_trace_on_warning(void) { }
 #endif /* CONFIG_TRACING */
 
 #ifndef INIT_TRACE_RECURSION

include/trace/syscall.h

@@ -16,6 +16,7 @@
  * @nb_args: number of parameters it takes
  * @types: list of types as strings
  * @args: list of args as strings (args[i] matches types[i])
+ * @enter_fields: list of fields for syscall_enter trace event
  * @enter_event: associated syscall_enter trace event
  * @exit_event: associated syscall_exit trace event
  */

kernel/panic.c

@@ -15,6 +15,7 @@
 #include <linux/notifier.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/ftrace.h>
 #include <linux/reboot.h>
 #include <linux/delay.h>
 #include <linux/kexec.h>
@@ -399,6 +400,8 @@ struct slowpath_args {
 static void warn_slowpath_common(const char *file, int line, void *caller,
 				 unsigned taint, struct slowpath_args *args)
 {
+	disable_trace_on_warning();
+
 	pr_warn("------------[ cut here ]------------\n");
 	pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS()\n",
 		raw_smp_processor_id(), current->pid, file, line, caller);

kernel/sysctl.c

@@ -599,6 +599,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "traceoff_on_warning",
+		.data		= &__disable_trace_on_warning,
+		.maxlen		= sizeof(__disable_trace_on_warning),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #endif
 #ifdef CONFIG_MODULES
 	{

kernel/trace/ftrace.c

@@ -413,6 +413,17 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	return 0;
 }
 
+static void ftrace_sync(struct work_struct *work)
+{
+	/*
+	 * This function is just a stub to implement a hard force
+	 * of synchronize_sched(). This requires synchronizing
+	 * tasks even in userspace and idle.
+	 *
+	 * Yes, function tracing is rude.
+	 */
+}
+
 static int __unregister_ftrace_function(struct ftrace_ops *ops)
 {
 	int ret;
@@ -440,8 +451,12 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 			 * so there'll be no new users. We must ensure
 			 * all current users are done before we free
 			 * the control data.
+			 * Note synchronize_sched() is not enough, as we
+			 * use preempt_disable() to do RCU, but the function
+			 * tracer can be called where RCU is not active
+			 * (before user_exit()).
 			 */
-			synchronize_sched();
+			schedule_on_each_cpu(ftrace_sync);
 			control_ops_free(ops);
 		}
 	} else
@@ -456,9 +471,13 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	/*
 	 * Dynamic ops may be freed, we must make sure that all
 	 * callers are done before leaving this function.
+	 *
+	 * Again, normal synchronize_sched() is not good enough.
+	 * We need to do a hard force of sched synchronization.
 	 */
 	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
-		synchronize_sched();
+		schedule_on_each_cpu(ftrace_sync);
+
 
 	return 0;
 }
@@ -622,12 +641,18 @@ static int function_stat_show(struct seq_file *m, void *v)
 	if (rec->counter <= 1)
 		stddev = 0;
 	else {
-		stddev = rec->time_squared - rec->counter * avg * avg;
+		/*
+		 * Apply Welford's method:
+		 * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
+		 */
+		stddev = rec->counter * rec->time_squared -
+			 rec->time * rec->time;
+
 		/*
 		 * Divide only 1000 for ns^2 -> us^2 conversion.
 		 * trace_print_graph_duration will divide 1000 again.
 		 */
-		do_div(stddev, (rec->counter - 1) * 1000);
+		do_div(stddev, rec->counter * (rec->counter - 1) * 1000);
 	}
 
 	trace_seq_init(&s);
@@ -3512,8 +3537,12 @@ EXPORT_SYMBOL_GPL(ftrace_set_global_notrace);
 static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
 static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
 
+/* Used by function selftest to not test if filter is set */
+bool ftrace_filter_param __initdata;
+
 static int __init set_ftrace_notrace(char *str)
 {
+	ftrace_filter_param = true;
 	strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
 	return 1;
 }
@@ -3521,6 +3550,7 @@ __setup("ftrace_notrace=", set_ftrace_notrace);
 
 static int __init set_ftrace_filter(char *str)
 {
+	ftrace_filter_param = true;
 	strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
 	return 1;
 }

kernel/trace/trace.h

@@ -224,6 +224,11 @@ enum {
 
 extern struct list_head ftrace_trace_arrays;
 
+extern struct mutex trace_types_lock;
+
+extern int trace_array_get(struct trace_array *tr);
+extern void trace_array_put(struct trace_array *tr);
+
 /*
  * The global tracer (top) should be the first trace array added,
  * but we check the flag anyway.
@@ -554,11 +559,6 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu);
 
 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 task_struct *prev,
 				struct task_struct *next,
@@ -774,6 +774,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 extern struct list_head ftrace_pids;
 
 #ifdef CONFIG_FUNCTION_TRACER
+extern bool ftrace_filter_param __initdata;
 static inline int ftrace_trace_task(struct task_struct *task)
 {
 	if (list_empty(&ftrace_pids))
@@ -899,12 +900,6 @@ static inline void trace_branch_disable(void)
 /* 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;
 	const char		*name;

kernel/trace/trace_events_filter.c

@@ -44,6 +44,7 @@ enum filter_op_ids
 	OP_LE,
 	OP_GT,
 	OP_GE,
+	OP_BAND,
 	OP_NONE,
 	OP_OPEN_PAREN,
 };
@@ -54,6 +55,7 @@ struct filter_op {
 	int precedence;
 };
 
+/* Order must be the same as enum filter_op_ids above */
 static struct filter_op filter_ops[] = {
 	{ OP_OR,	"||",		1 },
 	{ OP_AND,	"&&",		2 },
@@ -64,6 +66,7 @@ static struct filter_op filter_ops[] = {
 	{ OP_LE,	"<=",		5 },
 	{ OP_GT,	">",		5 },
 	{ OP_GE,	">=",		5 },
+	{ OP_BAND,	"&",		6 },
 	{ OP_NONE,	"OP_NONE",	0 },
 	{ OP_OPEN_PAREN, "(",		0 },
 };
@@ -156,6 +159,9 @@ static int filter_pred_##type(struct filter_pred *pred, void *event)	\
 	case OP_GE:							\
 		match = (*addr >= val);					\
 		break;							\
+	case OP_BAND:							\
+		match = (*addr & val);					\
+		break;							\
 	default:							\
 		break;							\
 	}								\

kernel/trace/trace_functions.c

@@ -290,6 +290,21 @@ ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, void **data)
 		trace_dump_stack(STACK_SKIP);
 }
 
+static void
+ftrace_dump_probe(unsigned long ip, unsigned long parent_ip, void **data)
+{
+	if (update_count(data))
+		ftrace_dump(DUMP_ALL);
+}
+
+/* Only dump the current CPU buffer. */
+static void
+ftrace_cpudump_probe(unsigned long ip, unsigned long parent_ip, void **data)
+{
+	if (update_count(data))
+		ftrace_dump(DUMP_ORIG);
+}
+
 static int
 ftrace_probe_print(const char *name, struct seq_file *m,
 		   unsigned long ip, void *data)
@@ -327,6 +342,20 @@ ftrace_stacktrace_print(struct seq_file *m, unsigned long ip,
 	return ftrace_probe_print("stacktrace", m, ip, data);
 }
 
+static int
+ftrace_dump_print(struct seq_file *m, unsigned long ip,
+			struct ftrace_probe_ops *ops, void *data)
+{
+	return ftrace_probe_print("dump", m, ip, data);
+}
+
+static int
+ftrace_cpudump_print(struct seq_file *m, unsigned long ip,
+			struct ftrace_probe_ops *ops, void *data)
+{
+	return ftrace_probe_print("cpudump", m, ip, data);
+}
+
 static struct ftrace_probe_ops traceon_count_probe_ops = {
 	.func			= ftrace_traceon_count,
 	.print			= ftrace_traceon_print,
@@ -342,6 +371,16 @@ static struct ftrace_probe_ops stacktrace_count_probe_ops = {
 	.print			= ftrace_stacktrace_print,
 };
 
+static struct ftrace_probe_ops dump_probe_ops = {
+	.func			= ftrace_dump_probe,
+	.print			= ftrace_dump_print,
+};
+
+static struct ftrace_probe_ops cpudump_probe_ops = {
+	.func			= ftrace_cpudump_probe,
+	.print			= ftrace_cpudump_print,
+};
+
 static struct ftrace_probe_ops traceon_probe_ops = {
 	.func			= ftrace_traceon,
 	.print			= ftrace_traceon_print,
@@ -425,6 +464,32 @@ ftrace_stacktrace_callback(struct ftrace_hash *hash,
 					   param, enable);
 }
 
+static int
+ftrace_dump_callback(struct ftrace_hash *hash,
+			   char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+
+	ops = &dump_probe_ops;
+
+	/* Only dump once. */
+	return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+					   "1", enable);
+}
+
+static int
+ftrace_cpudump_callback(struct ftrace_hash *hash,
+			   char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+
+	ops = &cpudump_probe_ops;
+
+	/* Only dump once. */
+	return ftrace_trace_probe_callback(ops, hash, glob, cmd,
+					   "1", enable);
+}
+
 static struct ftrace_func_command ftrace_traceon_cmd = {
 	.name			= "traceon",
 	.func			= ftrace_trace_onoff_callback,
@@ -440,6 +505,16 @@ static struct ftrace_func_command ftrace_stacktrace_cmd = {
 	.func			= ftrace_stacktrace_callback,
 };
 
+static struct ftrace_func_command ftrace_dump_cmd = {
+	.name			= "dump",
+	.func			= ftrace_dump_callback,
+};
+
+static struct ftrace_func_command ftrace_cpudump_cmd = {
+	.name			= "cpudump",
+	.func			= ftrace_cpudump_callback,
+};
+
 static int __init init_func_cmd_traceon(void)
 {
 	int ret;
@@ -450,13 +525,31 @@ static int __init init_func_cmd_traceon(void)
 
 	ret = register_ftrace_command(&ftrace_traceon_cmd);
 	if (ret)
-		unregister_ftrace_command(&ftrace_traceoff_cmd);
+		goto out_free_traceoff;
 
 	ret = register_ftrace_command(&ftrace_stacktrace_cmd);
-	if (ret) {
-		unregister_ftrace_command(&ftrace_traceoff_cmd);
+	if (ret)
+		goto out_free_traceon;
+
+	ret = register_ftrace_command(&ftrace_dump_cmd);
+	if (ret)
+		goto out_free_stacktrace;
+
+	ret = register_ftrace_command(&ftrace_cpudump_cmd);
+	if (ret)
+		goto out_free_dump;
+
+	return 0;
+
+ out_free_dump:
+	unregister_ftrace_command(&ftrace_dump_cmd);
+ out_free_stacktrace:
+	unregister_ftrace_command(&ftrace_stacktrace_cmd);
+ out_free_traceon:
 	unregister_ftrace_command(&ftrace_traceon_cmd);
-	}
+ out_free_traceoff:
+	unregister_ftrace_command(&ftrace_traceoff_cmd);
+
 	return ret;
 }
 #else

kernel/trace/trace_irqsoff.c

@@ -373,7 +373,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 	struct trace_array_cpu *data;
 	unsigned long flags;
 
-	if (likely(!tracer_enabled))
+	if (!tracer_enabled || !tracing_is_enabled())
 		return;
 
 	cpu = raw_smp_processor_id();
@@ -416,7 +416,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
 	else
 		return;
 
-	if (!tracer_enabled)
+	if (!tracer_enabled || !tracing_is_enabled())
 		return;
 
 	data = per_cpu_ptr(tr->trace_buffer.data, cpu);

kernel/trace/trace_kprobe.c

@@ -35,12 +35,17 @@ struct trace_probe {
 	const char		*symbol;	/* symbol name */
 	struct ftrace_event_class	class;
 	struct ftrace_event_call	call;
-	struct ftrace_event_file * __rcu *files;
+	struct list_head	files;
 	ssize_t			size;		/* trace entry size */
 	unsigned int		nr_args;
 	struct probe_arg	args[];
 };
 
+struct event_file_link {
+	struct ftrace_event_file	*file;
+	struct list_head		list;
+};
+
 #define SIZEOF_TRACE_PROBE(n)			\
 	(offsetof(struct trace_probe, args) +	\
 	(sizeof(struct probe_arg) * (n)))
@@ -150,6 +155,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 		goto error;
 
 	INIT_LIST_HEAD(&tp->list);
+	INIT_LIST_HEAD(&tp->files);
 	return tp;
 error:
 	kfree(tp->call.name);
@@ -183,25 +189,6 @@ static struct trace_probe *find_trace_probe(const char *event,
 	return NULL;
 }
 
-static int trace_probe_nr_files(struct trace_probe *tp)
-{
-	struct ftrace_event_file **file;
-	int ret = 0;
-
-	/*
-	 * Since all tp->files updater is protected by probe_enable_lock,
-	 * we don't need to lock an rcu_read_lock.
-	 */
-	file = rcu_dereference_raw(tp->files);
-	if (file)
-		while (*(file++))
-			ret++;
-
-	return ret;
-}
-
-static DEFINE_MUTEX(probe_enable_lock);
-
 /*
  * Enable trace_probe
  * if the file is NULL, enable "perf" handler, or enable "trace" handler.
@@ -211,67 +198,42 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 {
 	int ret = 0;
 
-	mutex_lock(&probe_enable_lock);
-
 	if (file) {
-		struct ftrace_event_file **new, **old;
-		int n = trace_probe_nr_files(tp);
-
-		old = rcu_dereference_raw(tp->files);
-		/* 1 is for new one and 1 is for stopper */
-		new = kzalloc((n + 2) * sizeof(struct ftrace_event_file *),
-			      GFP_KERNEL);
-		if (!new) {
+		struct event_file_link *link;
+
+		link = kmalloc(sizeof(*link), GFP_KERNEL);
+		if (!link) {
 			ret = -ENOMEM;
-			goto out_unlock;
+			goto out;
 		}
-		memcpy(new, old, n * sizeof(struct ftrace_event_file *));
-		new[n] = file;
-		/* The last one keeps a NULL */
 
-		rcu_assign_pointer(tp->files, new);
-		tp->flags |= TP_FLAG_TRACE;
+		link->file = file;
+		list_add_tail_rcu(&link->list, &tp->files);
 
-		if (old) {
-			/* Make sure the probe is done with old files */
-			synchronize_sched();
-			kfree(old);
-		}
+		tp->flags |= TP_FLAG_TRACE;
 	} else
 		tp->flags |= TP_FLAG_PROFILE;
 
-	if (trace_probe_is_enabled(tp) && trace_probe_is_registered(tp) &&
-	    !trace_probe_has_gone(tp)) {
+	if (trace_probe_is_registered(tp) && !trace_probe_has_gone(tp)) {
 		if (trace_probe_is_return(tp))
 			ret = enable_kretprobe(&tp->rp);
 		else
 			ret = enable_kprobe(&tp->rp.kp);
 	}
-
- out_unlock:
-	mutex_unlock(&probe_enable_lock);
-
+ out:
 	return ret;
 }
 
-static int
-trace_probe_file_index(struct trace_probe *tp, struct ftrace_event_file *file)
+static struct event_file_link *
+find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
 {
-	struct ftrace_event_file **files;
-	int i;
+	struct event_file_link *link;
 
-	/*
-	 * Since all tp->files updater is protected by probe_enable_lock,
-	 * we don't need to lock an rcu_read_lock.
-	 */
-	files = rcu_dereference_raw(tp->files);
-	if (files) {
-		for (i = 0; files[i]; i++)
-			if (files[i] == file)
-				return i;
-	}
+	list_for_each_entry(link, &tp->files, list)
+		if (link->file == file)
+			return link;
 
-	return -1;
+	return NULL;
 }
 
 /*
@@ -283,41 +245,24 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 {
 	int ret = 0;
 
-	mutex_lock(&probe_enable_lock);
-
 	if (file) {
-		struct ftrace_event_file **new, **old;
-		int n = trace_probe_nr_files(tp);
-		int i, j;
+		struct event_file_link *link;
 
-		old = rcu_dereference_raw(tp->files);
-		if (n == 0 || trace_probe_file_index(tp, file) < 0) {
+		link = find_event_file_link(tp, file);
+		if (!link) {
 			ret = -EINVAL;
-			goto out_unlock;
+			goto out;
 		}
 
-		if (n == 1) {	/* Remove the last file */
-			tp->flags &= ~TP_FLAG_TRACE;
-			new = NULL;
-		} else {
-			new = kzalloc(n * sizeof(struct ftrace_event_file *),
-				      GFP_KERNEL);
-			if (!new) {
-				ret = -ENOMEM;
-				goto out_unlock;
-			}
-
-			/* This copy & check loop copies the NULL stopper too */
-			for (i = 0, j = 0; j < n && i < n + 1; i++)
-				if (old[i] != file)
-					new[j++] = old[i];
-		}
+		list_del_rcu(&link->list);
+		/* synchronize with kprobe_trace_func/kretprobe_trace_func */
+		synchronize_sched();
+		kfree(link);
 
-		rcu_assign_pointer(tp->files, new);
+		if (!list_empty(&tp->files))
+			goto out;
 
-		/* Make sure the probe is done with old files */
-		synchronize_sched();
-		kfree(old);
+		tp->flags &= ~TP_FLAG_TRACE;
 	} else
 		tp->flags &= ~TP_FLAG_PROFILE;
 
@@ -327,10 +272,7 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 		else
 			disable_kprobe(&tp->rp.kp);
 	}
-
- out_unlock:
-	mutex_unlock(&probe_enable_lock);
-
+ out:
 	return ret;
 }
 
@@ -885,20 +827,10 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
 static __kprobes void
 kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs)
 {
-	/*
-	 * Note: preempt is already disabled around the kprobe handler.
-	 * However, we still need an smp_read_barrier_depends() corresponding
-	 * to smp_wmb() in rcu_assign_pointer() to access the pointer.
-	 */
-	struct ftrace_event_file **file = rcu_dereference_raw(tp->files);
-
-	if (unlikely(!file))
-		return;
+	struct event_file_link *link;
 
-	while (*file) {
-		__kprobe_trace_func(tp, regs, *file);
-		file++;
-	}
+	list_for_each_entry_rcu(link, &tp->files, list)
+		__kprobe_trace_func(tp, regs, link->file);
 }
 
 /* Kretprobe handler */
@@ -945,20 +877,10 @@ static __kprobes void
 kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 		     struct pt_regs *regs)
 {
-	/*
-	 * Note: preempt is already disabled around the kprobe handler.
-	 * However, we still need an smp_read_barrier_depends() corresponding
-	 * to smp_wmb() in rcu_assign_pointer() to access the pointer.
-	 */
-	struct ftrace_event_file **file = rcu_dereference_raw(tp->files);
-
-	if (unlikely(!file))
-		return;
+	struct event_file_link *link;
 
-	while (*file) {
-		__kretprobe_trace_func(tp, ri, regs, *file);
-		file++;
-	}
+	list_for_each_entry_rcu(link, &tp->files, list)
+		__kretprobe_trace_func(tp, ri, regs, link->file);
 }
 
 /* Event entry printers */
@@ -1157,6 +1079,10 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
 	int size, __size, dsize;
 	int rctx;
 
+	head = this_cpu_ptr(call->perf_events);
+	if (hlist_empty(head))
+		return;
+
 	dsize = __get_data_size(tp, regs);
 	__size = sizeof(*entry) + tp->size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
@@ -1172,10 +1098,7 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
 	entry->ip = (unsigned long)tp->rp.kp.addr;
 	memset(&entry[1], 0, dsize);
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
-
-	head = this_cpu_ptr(call->perf_events);
-	perf_trace_buf_submit(entry, size, rctx,
-					entry->ip, 1, regs, head, NULL);
+	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
 }
 
 /* Kretprobe profile handler */
@@ -1189,6 +1112,10 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 	int size, __size, dsize;
 	int rctx;
 
+	head = this_cpu_ptr(call->perf_events);
+	if (hlist_empty(head))
+		return;
+
 	dsize = __get_data_size(tp, regs);
 	__size = sizeof(*entry) + tp->size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
@@ -1204,13 +1131,16 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 	entry->func = (unsigned long)tp->rp.kp.addr;
 	entry->ret_ip = (unsigned long)ri->ret_addr;
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
-
-	head = this_cpu_ptr(call->perf_events);
-	perf_trace_buf_submit(entry, size, rctx,
-					entry->ret_ip, 1, regs, head, NULL);
+	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
 }
 #endif	/* CONFIG_PERF_EVENTS */
 
+/*
+ * called by perf_trace_init() or __ftrace_set_clr_event() under event_mutex.
+ *
+ * kprobe_trace_self_tests_init() does enable_trace_probe/disable_trace_probe
+ * lockless, but we can't race with this __init function.
+ */
 static __kprobes
 int kprobe_register(struct ftrace_event_call *event,
 		    enum trace_reg type, void *data)
@@ -1376,6 +1306,10 @@ find_trace_probe_file(struct trace_probe *tp, struct trace_array *tr)
 	return NULL;
 }
 
+/*
+ * Nobody but us can call enable_trace_probe/disable_trace_probe at this
+ * stage, we can do this lockless.
+ */
 static __init int kprobe_trace_self_tests_init(void)
 {
 	int ret, warn = 0;

kernel/trace/trace_selftest.c

@@ -640,13 +640,20 @@ trace_selftest_function_regs(void)
  * Enable ftrace, sleep 1/10 second, and then read the trace
  * buffer to see if all is in order.
  */
-int
+__init int
 trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 {
 	int save_ftrace_enabled = ftrace_enabled;
 	unsigned long count;
 	int ret;
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	if (ftrace_filter_param) {
+		printk(KERN_CONT " ... kernel command line filter set: force PASS ... ");
+		return 0;
+	}
+#endif
+
 	/* make sure msleep has been recorded */
 	msleep(1);
 
@@ -727,13 +734,20 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
  * Pretty much the same than for the function tracer from which the selftest
  * has been borrowed.
  */
-int
+__init int
 trace_selftest_startup_function_graph(struct tracer *trace,
 					struct trace_array *tr)
 {
 	int ret;
 	unsigned long count;
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	if (ftrace_filter_param) {
+		printk(KERN_CONT " ... kernel command line filter set: force PASS ... ");
+		return 0;
+	}
+#endif
+
 	/*
 	 * Simulate the init() callback but we attach a watchdog callback
 	 * to detect and recover from possible hangs

kernel/trace/trace_syscalls.c

@@ -306,6 +306,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	unsigned long irq_flags;
+	int pc;
 	int syscall_nr;
 	int size;
 
@@ -321,9 +323,12 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
 	buffer = tr->trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer,
-			sys_data->enter_event->event.type, size, 0, 0);
+			sys_data->enter_event->event.type, size, irq_flags, pc);
 	if (!event)
 		return;
 
@@ -333,7 +338,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	if (!filter_current_check_discard(buffer, sys_data->enter_event,
 					  entry, event))
-		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+		trace_current_buffer_unlock_commit(buffer, event,
+						   irq_flags, pc);
 }
 
 static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -343,6 +349,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	unsigned long irq_flags;
+	int pc;
 	int syscall_nr;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
@@ -355,9 +363,13 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
 	buffer = tr->trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer,
-			sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
+			sys_data->exit_event->event.type, sizeof(*entry),
+			irq_flags, pc);
 	if (!event)
 		return;
 
@@ -367,7 +379,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 
 	if (!filter_current_check_discard(buffer, sys_data->exit_event,
 					  entry, event))
-		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+		trace_current_buffer_unlock_commit(buffer, event,
+						   irq_flags, pc);
 }
 
 static int reg_event_syscall_enter(struct ftrace_event_file *file,

kernel/trace/trace_uprobe.c

@@ -283,8 +283,10 @@ static int create_trace_uprobe(int argc, char **argv)
 		return -EINVAL;
 	}
 	arg = strchr(argv[1], ':');
-	if (!arg)
+	if (!arg) {
+		ret = -EINVAL;
 		goto fail_address_parse;
+	}
 
 	*arg++ = '\0';
 	filename = argv[1];