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
  ...

1 files changed, 128 insertions, 38 deletions

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 27963e2bf4bf..7d854290bf81 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -41,6 +41,23 @@ static LIST_HEAD(ftrace_common_fields);
 static struct kmem_cache *field_cachep;
 static struct kmem_cache *file_cachep;
 
+#define SYSTEM_FL_FREE_NAME		(1 << 31)
+
+static inline int system_refcount(struct event_subsystem *system)
+{
+	return system->ref_count & ~SYSTEM_FL_FREE_NAME;
+}
+
+static int system_refcount_inc(struct event_subsystem *system)
+{
+	return (system->ref_count++) & ~SYSTEM_FL_FREE_NAME;
+}
+
+static int system_refcount_dec(struct event_subsystem *system)
+{
+	return (--system->ref_count) & ~SYSTEM_FL_FREE_NAME;
+}
+
 /* Double loops, do not use break, only goto's work */
 #define do_for_each_event_file(tr, file)			\
 	list_for_each_entry(tr, &ftrace_trace_arrays, list) {	\
@@ -97,7 +114,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
 
 	field = kmem_cache_alloc(field_cachep, GFP_TRACE);
 	if (!field)
-		goto err;
+		return -ENOMEM;
 
 	field->name = name;
 	field->type = type;
@@ -114,11 +131,6 @@ static int __trace_define_field(struct list_head *head, const char *type,
 	list_add(&field->link, head);
 
 	return 0;
-
-err:
-	kmem_cache_free(field_cachep, field);
-
-	return -ENOMEM;
 }
 
 int trace_define_field(struct ftrace_event_call *call, const char *type,
@@ -279,9 +291,11 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,
 			}
 			call->class->reg(call, TRACE_REG_UNREGISTER, file);
 		}
-		/* If in SOFT_MODE, just set the SOFT_DISABLE_BIT */
+		/* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */
 		if (file->flags & FTRACE_EVENT_FL_SOFT_MODE)
 			set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags);
+		else
+			clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags);
 		break;
 	case 1:
 		/*
@@ -349,8 +363,8 @@ static void __put_system(struct event_subsystem *system)
 {
 	struct event_filter *filter = system->filter;
 
-	WARN_ON_ONCE(system->ref_count == 0);
-	if (--system->ref_count)
+	WARN_ON_ONCE(system_refcount(system) == 0);
+	if (system_refcount_dec(system))
 		return;
 
 	list_del(&system->list);
@@ -359,13 +373,15 @@ static void __put_system(struct event_subsystem *system)
 		kfree(filter->filter_string);
 		kfree(filter);
 	}
+	if (system->ref_count & SYSTEM_FL_FREE_NAME)
+		kfree(system->name);
 	kfree(system);
 }
 
 static void __get_system(struct event_subsystem *system)
 {
-	WARN_ON_ONCE(system->ref_count == 0);
-	system->ref_count++;
+	WARN_ON_ONCE(system_refcount(system) == 0);
+	system_refcount_inc(system);
 }
 
 static void __get_system_dir(struct ftrace_subsystem_dir *dir)
@@ -379,7 +395,7 @@ static void __put_system_dir(struct ftrace_subsystem_dir *dir)
 {
 	WARN_ON_ONCE(dir->ref_count == 0);
 	/* If the subsystem is about to be freed, the dir must be too */
-	WARN_ON_ONCE(dir->subsystem->ref_count == 1 && dir->ref_count != 1);
+	WARN_ON_ONCE(system_refcount(dir->subsystem) == 1 && dir->ref_count != 1);
 
 	__put_system(dir->subsystem);
 	if (!--dir->ref_count)
@@ -394,16 +410,45 @@ static void put_system(struct ftrace_subsystem_dir *dir)
 }
 
 /*
+ * Open and update trace_array ref count.
+ * Must have the current trace_array passed to it.
+ */
+static int tracing_open_generic_file(struct inode *inode, struct file *filp)
+{
+	struct ftrace_event_file *file = inode->i_private;
+	struct trace_array *tr = file->tr;
+	int ret;
+
+	if (trace_array_get(tr) < 0)
+		return -ENODEV;
+
+	ret = tracing_open_generic(inode, filp);
+	if (ret < 0)
+		trace_array_put(tr);
+	return ret;
+}
+
+static int tracing_release_generic_file(struct inode *inode, struct file *filp)
+{
+	struct ftrace_event_file *file = inode->i_private;
+	struct trace_array *tr = file->tr;
+
+	trace_array_put(tr);
+
+	return 0;
+}
+
+/*
  * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
  */
-static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
-				  const char *sub, const char *event, int set)
+static int
+__ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match,
+			      const char *sub, const char *event, int set)
 {
 	struct ftrace_event_file *file;
 	struct ftrace_event_call *call;
 	int ret = -EINVAL;
 
-	mutex_lock(&event_mutex);
 	list_for_each_entry(file, &tr->events, list) {
 
 		call = file->event_call;
@@ -429,6 +474,17 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
 
 		ret = 0;
 	}
+
+	return ret;
+}
+
+static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
+				  const char *sub, const char *event, int set)
+{
+	int ret;
+
+	mutex_lock(&event_mutex);
+	ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set);
 	mutex_unlock(&event_mutex);
 
 	return ret;
@@ -624,17 +680,17 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
 {
 	struct ftrace_event_file *file = filp->private_data;
-	char *buf;
+	char buf[4] = "0";
 
-	if (file->flags & FTRACE_EVENT_FL_ENABLED) {
-		if (file->flags & FTRACE_EVENT_FL_SOFT_DISABLED)
-			buf = "0*\n";
-		else if (file->flags & FTRACE_EVENT_FL_SOFT_MODE)
-			buf = "1*\n";
-		else
-			buf = "1\n";
-	} else
-		buf = "0\n";
+	if (file->flags & FTRACE_EVENT_FL_ENABLED &&
+	    !(file->flags & FTRACE_EVENT_FL_SOFT_DISABLED))
+		strcpy(buf, "1");
+
+	if (file->flags & FTRACE_EVENT_FL_SOFT_DISABLED ||
+	    file->flags & FTRACE_EVENT_FL_SOFT_MODE)
+		strcat(buf, "*");
+
+	strcat(buf, "\n");
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, strlen(buf));
 }
@@ -992,6 +1048,7 @@ static int subsystem_open(struct inode *inode, struct file *filp)
 	int ret;
 
 	/* Make sure the system still exists */
+	mutex_lock(&trace_types_lock);
 	mutex_lock(&event_mutex);
 	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
 		list_for_each_entry(dir, &tr->systems, list) {
@@ -1007,6 +1064,7 @@ static int subsystem_open(struct inode *inode, struct file *filp)
 	}
  exit_loop:
 	mutex_unlock(&event_mutex);
+	mutex_unlock(&trace_types_lock);
 
 	if (!system)
 		return -ENODEV;
@@ -1014,9 +1072,17 @@ static int subsystem_open(struct inode *inode, struct file *filp)
 	/* Some versions of gcc think dir can be uninitialized here */
 	WARN_ON(!dir);
 
+	/* Still need to increment the ref count of the system */
+	if (trace_array_get(tr) < 0) {
+		put_system(dir);
+		return -ENODEV;
+	}
+
 	ret = tracing_open_generic(inode, filp);
-	if (ret < 0)
+	if (ret < 0) {
+		trace_array_put(tr);
 		put_system(dir);
+	}
 
 	return ret;
 }
@@ -1027,16 +1093,23 @@ static int system_tr_open(struct inode *inode, struct file *filp)
 	struct trace_array *tr = inode->i_private;
 	int ret;
 
+	if (trace_array_get(tr) < 0)
+		return -ENODEV;
+
 	/* Make a temporary dir that has no system but points to tr */
 	dir = kzalloc(sizeof(*dir), GFP_KERNEL);
-	if (!dir)
+	if (!dir) {
+		trace_array_put(tr);
 		return -ENOMEM;
+	}
 
 	dir->tr = tr;
 
 	ret = tracing_open_generic(inode, filp);
-	if (ret < 0)
+	if (ret < 0) {
+		trace_array_put(tr);
 		kfree(dir);
+	}
 
 	filp->private_data = dir;
 
@@ -1047,6 +1120,8 @@ static int subsystem_release(struct inode *inode, struct file *file)
 {
 	struct ftrace_subsystem_dir *dir = file->private_data;
 
+	trace_array_put(dir->tr);
+
 	/*
 	 * If dir->subsystem is NULL, then this is a temporary
 	 * descriptor that was made for a trace_array to enable
@@ -1174,9 +1249,10 @@ static const struct file_operations ftrace_set_event_fops = {
 };
 
 static const struct file_operations ftrace_enable_fops = {
-	.open = tracing_open_generic,
+	.open = tracing_open_generic_file,
 	.read = event_enable_read,
 	.write = event_enable_write,
+	.release = tracing_release_generic_file,
 	.llseek = default_llseek,
 };
 
@@ -1279,7 +1355,15 @@ create_new_subsystem(const char *name)
 		return NULL;
 
 	system->ref_count = 1;
-	system->name = name;
+
+	/* Only allocate if dynamic (kprobes and modules) */
+	if (!core_kernel_data((unsigned long)name)) {
+		system->ref_count |= SYSTEM_FL_FREE_NAME;
+		system->name = kstrdup(name, GFP_KERNEL);
+		if (!system->name)
+			goto out_free;
+	} else
+		system->name = name;
 
 	system->filter = NULL;
 
@@ -1292,6 +1376,8 @@ create_new_subsystem(const char *name)
 	return system;
 
  out_free:
+	if (system->ref_count & SYSTEM_FL_FREE_NAME)
+		kfree(system->name);
 	kfree(system);
 	return NULL;
 }
@@ -1591,6 +1677,7 @@ static void __add_event_to_tracers(struct ftrace_event_call *call,
 int trace_add_event_call(struct ftrace_event_call *call)
 {
 	int ret;
+	mutex_lock(&trace_types_lock);
 	mutex_lock(&event_mutex);
 
 	ret = __register_event(call, NULL);
@@ -1598,11 +1685,13 @@ int trace_add_event_call(struct ftrace_event_call *call)
 		__add_event_to_tracers(call, NULL);
 
 	mutex_unlock(&event_mutex);
+	mutex_unlock(&trace_types_lock);
 	return ret;
 }
 
 /*
- * Must be called under locking both of event_mutex and trace_event_sem.
+ * Must be called under locking of trace_types_lock, event_mutex and
+ * trace_event_sem.
  */
 static void __trace_remove_event_call(struct ftrace_event_call *call)
 {
@@ -1614,11 +1703,13 @@ static void __trace_remove_event_call(struct ftrace_event_call *call)
 /* Remove an event_call */
 void trace_remove_event_call(struct ftrace_event_call *call)
 {
+	mutex_lock(&trace_types_lock);
 	mutex_lock(&event_mutex);
 	down_write(&trace_event_sem);
 	__trace_remove_event_call(call);
 	up_write(&trace_event_sem);
 	mutex_unlock(&event_mutex);
+	mutex_unlock(&trace_types_lock);
 }
 
 #define for_each_event(event, start, end)			\
@@ -1762,6 +1853,7 @@ static int trace_module_notify(struct notifier_block *self,
 {
 	struct module *mod = data;
 
+	mutex_lock(&trace_types_lock);
 	mutex_lock(&event_mutex);
 	switch (val) {
 	case MODULE_STATE_COMING:
@@ -1772,6 +1864,7 @@ static int trace_module_notify(struct notifier_block *self,
 		break;
 	}
 	mutex_unlock(&event_mutex);
+	mutex_unlock(&trace_types_lock);
 
 	return 0;
 }
@@ -2011,10 +2104,7 @@ event_enable_func(struct ftrace_hash *hash,
 	int ret;
 
 	/* hash funcs only work with set_ftrace_filter */
-	if (!enabled)
-		return -EINVAL;
-
-	if (!param)
+	if (!enabled || !param)
 		return -EINVAL;
 
 	system = strsep(&param, ":");
@@ -2329,11 +2419,11 @@ early_event_add_tracer(struct dentry *parent, struct trace_array *tr)
 
 int event_trace_del_tracer(struct trace_array *tr)
 {
-	/* Disable any running events */
-	__ftrace_set_clr_event(tr, NULL, NULL, NULL, 0);
-
 	mutex_lock(&event_mutex);
 
+	/* Disable any running events */
+	__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
+
 	down_write(&trace_event_sem);
 	__trace_remove_event_dirs(tr);
 	debugfs_remove_recursive(tr->event_dir);