Merge tag 'trace-3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "Not much changes for the 3.12 merge window.  The major tracing changes
  are still in flux, and will have to wait for 3.13.

  The changes for 3.12 are mostly clean ups and minor fixes.

  H Peter Anvin added a check to x86_32 static function tracing that
  helps a small segment of the kernel community.

  Oleg Nesterov had a few changes from 3.11, but were mostly clean ups
  and not worth pushing in the -rc time frame.

  Li Zefan had small clean up with annotating a raw_init with __init.

  I fixed a slight race in updating function callbacks, but the race is
  so small and the bug that happens when it occurs is so minor it's not
  even worth pushing to stable.

  The only real enhancement is from Alexander Z Lam that made the
  tracing_cpumask work for trace buffer instances, instead of them all
  sharing a global cpumask"

* tag 'trace-3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  ftrace/rcu: Do not trace debug_lockdep_rcu_enabled()
  x86-32, ftrace: Fix static ftrace when early microcode is enabled
  ftrace: Fix a slight race in modifying what function callback gets traced
  tracing: Make tracing_cpumask available for all instances
  tracing: Kill the !CONFIG_MODULES code in trace_events.c
  tracing: Don't pass file_operations array to event_create_dir()
  tracing: Kill trace_create_file_ops() and friends
  tracing/syscalls: Annotate raw_init function with __init

7 files changed, 68 insertions, 209 deletions

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 2cfbc3a3a2dd..f0dcb0ceb6a2 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1176,6 +1176,9 @@ ftrace_restore_flags:
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 ENTRY(mcount)
+	cmpl $__PAGE_OFFSET, %esp
+	jb ftrace_stub		/* Paging not enabled yet? */
+
 	cmpl $0, function_trace_stop
 	jne  ftrace_stub
 
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 33eb4620aa17..b02a339836b4 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -122,7 +122,7 @@ struct lockdep_map rcu_sched_lock_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 
-int debug_lockdep_rcu_enabled(void)
+int notrace debug_lockdep_rcu_enabled(void)
 {
 	return rcu_scheduler_active && debug_locks &&
 	       current->lockdep_recursion == 0;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a6d098c6df3f..03cf44ac54d3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1978,12 +1978,27 @@ int __weak ftrace_arch_code_modify_post_process(void)
 
 void ftrace_modify_all_code(int command)
 {
+	int update = command & FTRACE_UPDATE_TRACE_FUNC;
+
+	/*
+	 * If the ftrace_caller calls a ftrace_ops func directly,
+	 * we need to make sure that it only traces functions it
+	 * expects to trace. When doing the switch of functions,
+	 * we need to update to the ftrace_ops_list_func first
+	 * before the transition between old and new calls are set,
+	 * as the ftrace_ops_list_func will check the ops hashes
+	 * to make sure the ops are having the right functions
+	 * traced.
+	 */
+	if (update)
+		ftrace_update_ftrace_func(ftrace_ops_list_func);
+
 	if (command & FTRACE_UPDATE_CALLS)
 		ftrace_replace_code(1);
 	else if (command & FTRACE_DISABLE_CALLS)
 		ftrace_replace_code(0);
 
-	if (command & FTRACE_UPDATE_TRACE_FUNC)
+	if (update && ftrace_trace_function != ftrace_ops_list_func)
 		ftrace_update_ftrace_func(ftrace_trace_function);
 
 	if (command & FTRACE_START_FUNC_RET)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 496f94d57698..7974ba20557d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3166,11 +3166,6 @@ static const struct file_operations show_traces_fops = {
 };
 
 /*
- * Only trace on a CPU if the bitmask is set:
- */
-static cpumask_var_t tracing_cpumask;
-
-/*
  * The tracer itself will not take this lock, but still we want
  * to provide a consistent cpumask to user-space:
  */
@@ -3186,11 +3181,12 @@ static ssize_t
 tracing_cpumask_read(struct file *filp, char __user *ubuf,
 		     size_t count, loff_t *ppos)
 {
+	struct trace_array *tr = file_inode(filp)->i_private;
 	int len;
 
 	mutex_lock(&tracing_cpumask_update_lock);
 
-	len = cpumask_scnprintf(mask_str, count, tracing_cpumask);
+	len = cpumask_scnprintf(mask_str, count, tr->tracing_cpumask);
 	if (count - len < 2) {
 		count = -EINVAL;
 		goto out_err;
@@ -3208,7 +3204,7 @@ static ssize_t
 tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		      size_t count, loff_t *ppos)
 {
-	struct trace_array *tr = filp->private_data;
+	struct trace_array *tr = file_inode(filp)->i_private;
 	cpumask_var_t tracing_cpumask_new;
 	int err, cpu;
 
@@ -3228,12 +3224,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		 * Increase/decrease the disabled counter if we are
 		 * about to flip a bit in the cpumask:
 		 */
-		if (cpumask_test_cpu(cpu, tracing_cpumask) &&
+		if (cpumask_test_cpu(cpu, tr->tracing_cpumask) &&
 				!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled);
 			ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu);
 		}
-		if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
+		if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) &&
 				cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled);
 			ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu);
@@ -3242,7 +3238,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	arch_spin_unlock(&ftrace_max_lock);
 	local_irq_enable();
 
-	cpumask_copy(tracing_cpumask, tracing_cpumask_new);
+	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
 
 	mutex_unlock(&tracing_cpumask_update_lock);
 	free_cpumask_var(tracing_cpumask_new);
@@ -3256,9 +3252,10 @@ err_unlock:
 }
 
 static const struct file_operations tracing_cpumask_fops = {
-	.open		= tracing_open_generic,
+	.open		= tracing_open_generic_tr,
 	.read		= tracing_cpumask_read,
 	.write		= tracing_cpumask_write,
+	.release	= tracing_release_generic_tr,
 	.llseek		= generic_file_llseek,
 };
 
@@ -5938,6 +5935,11 @@ static int new_instance_create(const char *name)
 	if (!tr->name)
 		goto out_free_tr;
 
+	if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL))
+		goto out_free_tr;
+
+	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
+
 	raw_spin_lock_init(&tr->start_lock);
 
 	tr->current_trace = &nop_trace;
@@ -5969,6 +5971,7 @@ static int new_instance_create(const char *name)
  out_free_tr:
 	if (tr->trace_buffer.buffer)
 		ring_buffer_free(tr->trace_buffer.buffer);
+	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
 
@@ -6098,6 +6101,9 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 {
 	int cpu;
 
+	trace_create_file("tracing_cpumask", 0644, d_tracer,
+			  tr, &tracing_cpumask_fops);
+
 	trace_create_file("trace_options", 0644, d_tracer,
 			  tr, &tracing_iter_fops);
 
@@ -6147,9 +6153,6 @@ static __init int tracer_init_debugfs(void)
 
 	init_tracer_debugfs(&global_trace, d_tracer);
 
-	trace_create_file("tracing_cpumask", 0644, d_tracer,
-			&global_trace, &tracing_cpumask_fops);
-
 	trace_create_file("available_tracers", 0444, d_tracer,
 			&global_trace, &show_traces_fops);
 
@@ -6371,7 +6374,7 @@ __init static int tracer_alloc_buffers(void)
 	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
 		goto out;
 
-	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
+	if (!alloc_cpumask_var(&global_trace.tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
 
 	/* Only allocate trace_printk buffers if a trace_printk exists */
@@ -6386,7 +6389,7 @@ __init static int tracer_alloc_buffers(void)
 		ring_buf_size = 1;
 
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
-	cpumask_copy(tracing_cpumask, cpu_all_mask);
+	cpumask_copy(global_trace.tracing_cpumask, cpu_all_mask);
 
 	raw_spin_lock_init(&global_trace.start_lock);
 
@@ -6441,7 +6444,7 @@ out_free_cpumask:
 #ifdef CONFIG_TRACER_MAX_TRACE
 	free_percpu(global_trace.max_buffer.data);
 #endif
-	free_cpumask_var(tracing_cpumask);
+	free_cpumask_var(global_trace.tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);
 out:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index fe39acd4c1aa..10c86fb7a2b4 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -206,6 +206,7 @@ struct trace_array {
 	struct dentry		*event_dir;
 	struct list_head	systems;
 	struct list_head	events;
+	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
 	int			ref;
 };
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 29a7ebcfb426..368a4d50cc30 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1489,12 +1489,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 }
 
 static int
-event_create_dir(struct dentry *parent,
-		 struct ftrace_event_file *file,
-		 const struct file_operations *id,
-		 const struct file_operations *enable,
-		 const struct file_operations *filter,
-		 const struct file_operations *format)
+event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
 {
 	struct ftrace_event_call *call = file->event_call;
 	struct trace_array *tr = file->tr;
@@ -1522,12 +1517,13 @@ event_create_dir(struct dentry *parent,
 
 	if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
 		trace_create_file("enable", 0644, file->dir, file,
-				  enable);
+				  &ftrace_enable_fops);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (call->event.type && call->class->reg)
 		trace_create_file("id", 0444, file->dir,
-				  (void *)(long)call->event.type, id);
+				  (void *)(long)call->event.type,
+				  &ftrace_event_id_fops);
 #endif
 
 	/*
@@ -1544,10 +1540,10 @@ event_create_dir(struct dentry *parent,
 		}
 	}
 	trace_create_file("filter", 0644, file->dir, call,
-			  filter);
+			  &ftrace_event_filter_fops);
 
 	trace_create_file("format", 0444, file->dir, call,
-			  format);
+			  &ftrace_event_format_fops);
 
 	return 0;
 }
@@ -1648,12 +1644,7 @@ trace_create_new_event(struct ftrace_event_call *call,
 
 /* Add an event to a trace directory */
 static int
-__trace_add_new_event(struct ftrace_event_call *call,
-		      struct trace_array *tr,
-		      const struct file_operations *id,
-		      const struct file_operations *enable,
-		      const struct file_operations *filter,
-		      const struct file_operations *format)
+__trace_add_new_event(struct ftrace_event_call *call, struct trace_array *tr)
 {
 	struct ftrace_event_file *file;
 
@@ -1661,7 +1652,7 @@ __trace_add_new_event(struct ftrace_event_call *call,
 	if (!file)
 		return -ENOMEM;
 
-	return event_create_dir(tr->event_dir, file, id, enable, filter, format);
+	return event_create_dir(tr->event_dir, file);
 }
 
 /*
@@ -1683,8 +1674,7 @@ __trace_early_add_new_event(struct ftrace_event_call *call,
 }
 
 struct ftrace_module_file_ops;
-static void __add_event_to_tracers(struct ftrace_event_call *call,
-				   struct ftrace_module_file_ops *file_ops);
+static void __add_event_to_tracers(struct ftrace_event_call *call);
 
 /* Add an additional event_call dynamically */
 int trace_add_event_call(struct ftrace_event_call *call)
@@ -1695,7 +1685,7 @@ int trace_add_event_call(struct ftrace_event_call *call)
 
 	ret = __register_event(call, NULL);
 	if (ret >= 0)
-		__add_event_to_tracers(call, NULL);
+		__add_event_to_tracers(call);
 
 	mutex_unlock(&event_mutex);
 	mutex_unlock(&trace_types_lock);
@@ -1769,100 +1759,21 @@ int trace_remove_event_call(struct ftrace_event_call *call)
 
 #ifdef CONFIG_MODULES
 
-static LIST_HEAD(ftrace_module_file_list);
-
-/*
- * Modules must own their file_operations to keep up with
- * reference counting.
- */
-struct ftrace_module_file_ops {
-	struct list_head		list;
-	struct module			*mod;
-	struct file_operations		id;
-	struct file_operations		enable;
-	struct file_operations		format;
-	struct file_operations		filter;
-};
-
-static struct ftrace_module_file_ops *
-find_ftrace_file_ops(struct ftrace_module_file_ops *file_ops, struct module *mod)
-{
-	/*
-	 * As event_calls are added in groups by module,
-	 * when we find one file_ops, we don't need to search for
-	 * each call in that module, as the rest should be the
-	 * same. Only search for a new one if the last one did
-	 * not match.
-	 */
-	if (file_ops && mod == file_ops->mod)
-		return file_ops;
-
-	list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
-		if (file_ops->mod == mod)
-			return file_ops;
-	}
-	return NULL;
-}
-
-static struct ftrace_module_file_ops *
-trace_create_file_ops(struct module *mod)
-{
-	struct ftrace_module_file_ops *file_ops;
-
-	/*
-	 * This is a bit of a PITA. To allow for correct reference
-	 * counting, modules must "own" their file_operations.
-	 * To do this, we allocate the file operations that will be
-	 * used in the event directory.
-	 */
-
-	file_ops = kmalloc(sizeof(*file_ops), GFP_KERNEL);
-	if (!file_ops)
-		return NULL;
-
-	file_ops->mod = mod;
-
-	file_ops->id = ftrace_event_id_fops;
-	file_ops->id.owner = mod;
-
-	file_ops->enable = ftrace_enable_fops;
-	file_ops->enable.owner = mod;
-
-	file_ops->filter = ftrace_event_filter_fops;
-	file_ops->filter.owner = mod;
-
-	file_ops->format = ftrace_event_format_fops;
-	file_ops->format.owner = mod;
-
-	list_add(&file_ops->list, &ftrace_module_file_list);
-
-	return file_ops;
-}
-
 static void trace_module_add_events(struct module *mod)
 {
-	struct ftrace_module_file_ops *file_ops = NULL;
 	struct ftrace_event_call **call, **start, **end;
 
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
 
-	if (start == end)
-		return;
-
-	file_ops = trace_create_file_ops(mod);
-	if (!file_ops)
-		return;
-
 	for_each_event(call, start, end) {
 		__register_event(*call, mod);
-		__add_event_to_tracers(*call, file_ops);
+		__add_event_to_tracers(*call);
 	}
 }
 
 static void trace_module_remove_events(struct module *mod)
 {
-	struct ftrace_module_file_ops *file_ops;
 	struct ftrace_event_call *call, *p;
 	bool clear_trace = false;
 
@@ -1874,16 +1785,6 @@ static void trace_module_remove_events(struct module *mod)
 			__trace_remove_event_call(call);
 		}
 	}
-
-	/* Now free the file_operations */
-	list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
-		if (file_ops->mod == mod)
-			break;
-	}
-	if (&file_ops->list != &ftrace_module_file_list) {
-		list_del(&file_ops->list);
-		kfree(file_ops);
-	}
 	up_write(&trace_event_sem);
 
 	/*
@@ -1919,67 +1820,21 @@ static int trace_module_notify(struct notifier_block *self,
 	return 0;
 }
 
-static int
-__trace_add_new_mod_event(struct ftrace_event_call *call,
-			  struct trace_array *tr,
-			  struct ftrace_module_file_ops *file_ops)
-{
-	return __trace_add_new_event(call, tr,
-				     &file_ops->id, &file_ops->enable,
-				     &file_ops->filter, &file_ops->format);
-}
-
-#else
-static inline struct ftrace_module_file_ops *
-find_ftrace_file_ops(struct ftrace_module_file_ops *file_ops, struct module *mod)
-{
-	return NULL;
-}
-static inline int trace_module_notify(struct notifier_block *self,
-				      unsigned long val, void *data)
-{
-	return 0;
-}
-static inline int
-__trace_add_new_mod_event(struct ftrace_event_call *call,
-			  struct trace_array *tr,
-			  struct ftrace_module_file_ops *file_ops)
-{
-	return -ENODEV;
-}
+static struct notifier_block trace_module_nb = {
+	.notifier_call = trace_module_notify,
+	.priority = 0,
+};
 #endif /* CONFIG_MODULES */
 
 /* Create a new event directory structure for a trace directory. */
 static void
 __trace_add_event_dirs(struct trace_array *tr)
 {
-	struct ftrace_module_file_ops *file_ops = NULL;
 	struct ftrace_event_call *call;
 	int ret;
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		if (call->mod) {
-			/*
-			 * Directories for events by modules need to
-			 * keep module ref counts when opened (as we don't
-			 * want the module to disappear when reading one
-			 * of these files). The file_ops keep account of
-			 * the module ref count.
-			 */
-			file_ops = find_ftrace_file_ops(file_ops, call->mod);
-			if (!file_ops)
-				continue; /* Warn? */
-			ret = __trace_add_new_mod_event(call, tr, file_ops);
-			if (ret < 0)
-				pr_warning("Could not create directory for event %s\n",
-					   call->name);
-			continue;
-		}
-		ret = __trace_add_new_event(call, tr,
-					    &ftrace_event_id_fops,
-					    &ftrace_enable_fops,
-					    &ftrace_event_filter_fops,
-					    &ftrace_event_format_fops);
+		ret = __trace_add_new_event(call, tr);
 		if (ret < 0)
 			pr_warning("Could not create directory for event %s\n",
 				   call->name);
@@ -2287,11 +2142,7 @@ __trace_early_add_event_dirs(struct trace_array *tr)
 
 
 	list_for_each_entry(file, &tr->events, list) {
-		ret = event_create_dir(tr->event_dir, file,
-				       &ftrace_event_id_fops,
-				       &ftrace_enable_fops,
-				       &ftrace_event_filter_fops,
-				       &ftrace_event_format_fops);
+		ret = event_create_dir(tr->event_dir, file);
 		if (ret < 0)
 			pr_warning("Could not create directory for event %s\n",
 				   file->event_call->name);
@@ -2332,29 +2183,14 @@ __trace_remove_event_dirs(struct trace_array *tr)
 		remove_event_file_dir(file);
 }
 
-static void
-__add_event_to_tracers(struct ftrace_event_call *call,
-		       struct ftrace_module_file_ops *file_ops)
+static void __add_event_to_tracers(struct ftrace_event_call *call)
 {
 	struct trace_array *tr;
 
-	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
-		if (file_ops)
-			__trace_add_new_mod_event(call, tr, file_ops);
-		else
-			__trace_add_new_event(call, tr,
-					      &ftrace_event_id_fops,
-					      &ftrace_enable_fops,
-					      &ftrace_event_filter_fops,
-					      &ftrace_event_format_fops);
-	}
+	list_for_each_entry(tr, &ftrace_trace_arrays, list)
+		__trace_add_new_event(call, tr);
 }
 
-static struct notifier_block trace_module_nb = {
-	.notifier_call = trace_module_notify,
-	.priority = 0,
-};
-
 extern struct ftrace_event_call *__start_ftrace_events[];
 extern struct ftrace_event_call *__stop_ftrace_events[];
 
@@ -2559,10 +2395,11 @@ static __init int event_trace_init(void)
 	if (ret)
 		return ret;
 
+#ifdef CONFIG_MODULES
 	ret = register_module_notifier(&trace_module_nb);
 	if (ret)
 		pr_warning("Failed to register trace events module notifier\n");
-
+#endif
 	return 0;
 }
 early_initcall(event_trace_memsetup);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 8fd03657bc7d..559329d9bd2f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -200,8 +200,8 @@ extern char *__bad_type_size(void);
 		#type, #name, offsetof(typeof(trace), name),		\
 		sizeof(trace.name), is_signed_type(type)
 
-static
-int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
+static int __init
+__set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 {
 	int i;
 	int pos = 0;
@@ -228,7 +228,7 @@ int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 	return pos;
 }
 
-static int set_syscall_print_fmt(struct ftrace_event_call *call)
+static int __init set_syscall_print_fmt(struct ftrace_event_call *call)
 {
 	char *print_fmt;
 	int len;
@@ -253,7 +253,7 @@ static int set_syscall_print_fmt(struct ftrace_event_call *call)
 	return 0;
 }
 
-static void free_syscall_print_fmt(struct ftrace_event_call *call)
+static void __init free_syscall_print_fmt(struct ftrace_event_call *call)
 {
 	struct syscall_metadata *entry = call->data;
 
@@ -459,7 +459,7 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,
 	mutex_unlock(&syscall_trace_lock);
 }
 
-static int init_syscall_trace(struct ftrace_event_call *call)
+static int __init init_syscall_trace(struct ftrace_event_call *call)
 {
 	int id;
 	int num;