Merge tag 'trace-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "Lots of tweaks, small fixes, optimizations, and some helper functions
  to help out the rest of the kernel to ease their use of trace events.

  The big change for this release is the allowing of other tracers, such
  as the latency tracers, to be used in the trace instances and allow
  for function or function graph tracing to be in the top level
  simultaneously"

* tag 'trace-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (44 commits)
  tracing: Fix memory leak on instance deletion
  tracing: Fix leak of ring buffer data when new instances creation fails
  tracing/kprobes: Avoid self tests if tracing is disabled on boot up
  tracing: Return error if ftrace_trace_arrays list is empty
  tracing: Only calculate stats of tracepoint benchmarks for 2^32 times
  tracing: Convert stddev into u64 in tracepoint benchmark
  tracing: Introduce saved_cmdlines_size file
  tracing: Add __get_dynamic_array_len() macro for trace events
  tracing: Remove unused variable in trace_benchmark
  tracing: Eliminate double free on failure of allocation on boot up
  ftrace/x86: Call text_ip_addr() instead of the duplicated code
  tracing: Print max callstack on stacktrace bug
  tracing: Move locking of trace_cmdline_lock into start/stop seq calls
  tracing: Try again for saved cmdline if failed due to locking
  tracing: Have saved_cmdlines use the seq_read infrastructure
  tracing: Add tracepoint benchmark tracepoint
  tracing: Print nasty banner when trace_printk() is in use
  tracing: Add funcgraph_tail option to print function name after closing braces
  tracing: Eliminate duplicate TRACE_GRAPH_PRINT_xx defines
  tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks
  ...

17 files changed, 951 insertions, 460 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8639819f6cef..d4409356f40d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -535,6 +535,36 @@ config MMIOTRACE_TEST
 
 	  Say N, unless you absolutely know what you are doing.
 
+config TRACEPOINT_BENCHMARK
+        bool "Add tracepoint that benchmarks tracepoints"
+	help
+	 This option creates the tracepoint "benchmark:benchmark_event".
+	 When the tracepoint is enabled, it kicks off a kernel thread that
+	 goes into an infinite loop (calling cond_sched() to let other tasks
+	 run), and calls the tracepoint. Each iteration will record the time
+	 it took to write to the tracepoint and the next iteration that
+	 data will be passed to the tracepoint itself. That is, the tracepoint
+	 will report the time it took to do the previous tracepoint.
+	 The string written to the tracepoint is a static string of 128 bytes
+	 to keep the time the same. The initial string is simply a write of
+	 "START". The second string records the cold cache time of the first
+	 write which is not added to the rest of the calculations.
+
+	 As it is a tight loop, it benchmarks as hot cache. That's fine because
+	 we care most about hot paths that are probably in cache already.
+
+	 An example of the output:
+
+	      START
+	      first=3672 [COLD CACHED]
+	      last=632 first=3672 max=632 min=632 avg=316 std=446 std^2=199712
+	      last=278 first=3672 max=632 min=278 avg=303 std=316 std^2=100337
+	      last=277 first=3672 max=632 min=277 avg=296 std=258 std^2=67064
+	      last=273 first=3672 max=632 min=273 avg=292 std=224 std^2=50411
+	      last=273 first=3672 max=632 min=273 avg=288 std=200 std^2=40389
+	      last=281 first=3672 max=632 min=273 avg=287 std=183 std^2=33666
+
+
 config RING_BUFFER_BENCHMARK
 	tristate "Ring buffer benchmark stress tester"
 	depends on RING_BUFFER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 1378e84fbe39..2611613f14f1 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -17,6 +17,7 @@ ifdef CONFIG_TRACING_BRANCHES
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 endif
 
+CFLAGS_trace_benchmark.o := -I$(src)
 CFLAGS_trace_events_filter.o := -I$(src)
 
 obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o
@@ -62,4 +63,6 @@ endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
 obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
 
+obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
+
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4a54a25afa2f..5b372e3ed675 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -62,7 +62,7 @@
 #define FTRACE_HASH_DEFAULT_BITS 10
 #define FTRACE_HASH_MAX_BITS 12
 
-#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
+#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_CONTROL)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define INIT_REGEX_LOCK(opsname)	\
@@ -103,7 +103,6 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
@@ -171,23 +170,6 @@ int ftrace_nr_registered_ops(void)
 	return cnt;
 }
 
-static void
-ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
-			struct ftrace_ops *op, struct pt_regs *regs)
-{
-	int bit;
-
-	bit = trace_test_and_set_recursion(TRACE_GLOBAL_START, TRACE_GLOBAL_MAX);
-	if (bit < 0)
-		return;
-
-	do_for_each_ftrace_op(op, ftrace_global_list) {
-		op->func(ip, parent_ip, op, regs);
-	} while_for_each_ftrace_op(op);
-
-	trace_clear_recursion(bit);
-}
-
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			    struct ftrace_ops *op, struct pt_regs *regs)
 {
@@ -237,43 +219,6 @@ static int control_ops_alloc(struct ftrace_ops *ops)
 	return 0;
 }
 
-static void update_global_ops(void)
-{
-	ftrace_func_t func = ftrace_global_list_func;
-	void *private = NULL;
-
-	/* The list has its own recursion protection. */
-	global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
-
-	/*
-	 * If there's only one function registered, then call that
-	 * function directly. Otherwise, we need to iterate over the
-	 * registered callers.
-	 */
-	if (ftrace_global_list == &ftrace_list_end ||
-	    ftrace_global_list->next == &ftrace_list_end) {
-		func = ftrace_global_list->func;
-		private = ftrace_global_list->private;
-		/*
-		 * As we are calling the function directly.
-		 * If it does not have recursion protection,
-		 * the function_trace_op needs to be updated
-		 * accordingly.
-		 */
-		if (!(ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE))
-			global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE;
-	}
-
-	/* If we filter on pids, update to use the pid function */
-	if (!list_empty(&ftrace_pids)) {
-		set_ftrace_pid_function(func);
-		func = ftrace_pid_func;
-	}
-
-	global_ops.func = func;
-	global_ops.private = private;
-}
-
 static void ftrace_sync(struct work_struct *work)
 {
 	/*
@@ -301,8 +246,6 @@ static void update_ftrace_function(void)
 {
 	ftrace_func_t func;
 
-	update_global_ops();
-
 	/*
 	 * If we are at the end of the list and this ops is
 	 * recursion safe and not dynamic and the arch supports passing ops,
@@ -314,10 +257,7 @@ static void update_ftrace_function(void)
 	     (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) &&
 	     !FTRACE_FORCE_LIST_FUNC)) {
 		/* Set the ftrace_ops that the arch callback uses */
-		if (ftrace_ops_list == &global_ops)
-			set_function_trace_op = ftrace_global_list;
-		else
-			set_function_trace_op = ftrace_ops_list;
+		set_function_trace_op = ftrace_ops_list;
 		func = ftrace_ops_list->func;
 	} else {
 		/* Just use the default ftrace_ops */
@@ -373,6 +313,11 @@ static void update_ftrace_function(void)
 	ftrace_trace_function = func;
 }
 
+int using_ftrace_ops_list_func(void)
+{
+	return ftrace_trace_function == ftrace_ops_list_func;
+}
+
 static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 {
 	ops->next = *list;
@@ -434,16 +379,9 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if (ops->flags & FTRACE_OPS_FL_DELETED)
 		return -EINVAL;
 
-	if (FTRACE_WARN_ON(ops == &global_ops))
-		return -EINVAL;
-
 	if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return -EBUSY;
 
-	/* We don't support both control and global flags set. */
-	if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
-		return -EINVAL;
-
 #ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	/*
 	 * If the ftrace_ops specifies SAVE_REGS, then it only can be used
@@ -461,10 +399,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if (!core_kernel_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		add_ftrace_list_ops(&ftrace_global_list, &global_ops, ops);
-		ops->flags |= FTRACE_OPS_FL_ENABLED;
-	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+	if (ops->flags & FTRACE_OPS_FL_CONTROL) {
 		if (control_ops_alloc(ops))
 			return -ENOMEM;
 		add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops);
@@ -484,15 +419,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
 		return -EBUSY;
 
-	if (FTRACE_WARN_ON(ops == &global_ops))
-		return -EINVAL;
-
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		ret = remove_ftrace_list_ops(&ftrace_global_list,
-					     &global_ops, ops);
-		if (!ret)
-			ops->flags &= ~FTRACE_OPS_FL_ENABLED;
-	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+	if (ops->flags & FTRACE_OPS_FL_CONTROL) {
 		ret = remove_ftrace_list_ops(&ftrace_control_list,
 					     &control_ops, ops);
 	} else
@@ -895,7 +822,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
 
 	local_irq_save(flags);
 
-	stat = &__get_cpu_var(ftrace_profile_stats);
+	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
@@ -926,7 +853,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	stat = &__get_cpu_var(ftrace_profile_stats);
+	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
@@ -1178,7 +1105,7 @@ struct ftrace_page {
 static struct ftrace_page	*ftrace_pages_start;
 static struct ftrace_page	*ftrace_pages;
 
-static bool ftrace_hash_empty(struct ftrace_hash *hash)
+static bool __always_inline ftrace_hash_empty(struct ftrace_hash *hash)
 {
 	return !hash || !hash->count;
 }
@@ -1625,7 +1552,14 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip);
 
 			/*
+			 * If filter_hash is set, we want to match all functions
+			 * that are in the hash but not in the other hash.
 			 *
+			 * If filter_hash is not set, then we are decrementing.
+			 * That means we match anything that is in the hash
+			 * and also in the other_hash. That is, we need to turn
+			 * off functions in the other hash because they are disabled
+			 * by this hash.
 			 */
 			if (filter_hash && in_hash && !in_other_hash)
 				match = 1;
@@ -1767,19 +1701,15 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 		/*
 		 * If this record is being updated from a nop, then
 		 *   return UPDATE_MAKE_CALL.
-		 * Otherwise, if the EN flag is set, then return
-		 *   UPDATE_MODIFY_CALL_REGS to tell the caller to convert
-		 *   from the non-save regs, to a save regs function.
 		 * Otherwise,
 		 *   return UPDATE_MODIFY_CALL to tell the caller to convert
-		 *   from the save regs, to a non-save regs function.
+		 *   from the save regs, to a non-save regs function or
+		 *   vice versa.
 		 */
 		if (flag & FTRACE_FL_ENABLED)
 			return FTRACE_UPDATE_MAKE_CALL;
-		else if (rec->flags & FTRACE_FL_REGS_EN)
-			return FTRACE_UPDATE_MODIFY_CALL_REGS;
-		else
-			return FTRACE_UPDATE_MODIFY_CALL;
+
+		return FTRACE_UPDATE_MODIFY_CALL;
 	}
 
 	if (update) {
@@ -1821,6 +1751,42 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable)
 	return ftrace_check_record(rec, enable, 0);
 }
 
+/**
+ * ftrace_get_addr_new - Get the call address to set to
+ * @rec:  The ftrace record descriptor
+ *
+ * If the record has the FTRACE_FL_REGS set, that means that it
+ * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
+ * is not not set, then it wants to convert to the normal callback.
+ *
+ * Returns the address of the trampoline to set to
+ */
+unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec)
+{
+	if (rec->flags & FTRACE_FL_REGS)
+		return (unsigned long)FTRACE_REGS_ADDR;
+	else
+		return (unsigned long)FTRACE_ADDR;
+}
+
+/**
+ * ftrace_get_addr_curr - Get the call address that is already there
+ * @rec:  The ftrace record descriptor
+ *
+ * The FTRACE_FL_REGS_EN is set when the record already points to
+ * a function that saves all the regs. Basically the '_EN' version
+ * represents the current state of the function.
+ *
+ * Returns the address of the trampoline that is currently being called
+ */
+unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec)
+{
+	if (rec->flags & FTRACE_FL_REGS_EN)
+		return (unsigned long)FTRACE_REGS_ADDR;
+	else
+		return (unsigned long)FTRACE_ADDR;
+}
+
 static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
@@ -1828,12 +1794,12 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	unsigned long ftrace_addr;
 	int ret;
 
-	ret = ftrace_update_record(rec, enable);
+	ftrace_addr = ftrace_get_addr_new(rec);
 
-	if (rec->flags & FTRACE_FL_REGS)
-		ftrace_addr = (unsigned long)FTRACE_REGS_ADDR;
-	else
-		ftrace_addr = (unsigned long)FTRACE_ADDR;
+	/* This needs to be done before we call ftrace_update_record */
+	ftrace_old_addr = ftrace_get_addr_curr(rec);
+
+	ret = ftrace_update_record(rec, enable);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
@@ -1845,13 +1811,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	case FTRACE_UPDATE_MAKE_NOP:
 		return ftrace_make_nop(NULL, rec, ftrace_addr);
 
-	case FTRACE_UPDATE_MODIFY_CALL_REGS:
 	case FTRACE_UPDATE_MODIFY_CALL:
-		if (rec->flags & FTRACE_FL_REGS)
-			ftrace_old_addr = (unsigned long)FTRACE_ADDR;
-		else
-			ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR;
-
 		return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr);
 	}
 
@@ -2115,7 +2075,6 @@ static void ftrace_startup_enable(int command)
 
 static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
-	bool hash_enable = true;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -2128,18 +2087,9 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 	ftrace_start_up++;
 	command |= FTRACE_UPDATE_CALLS;
 
-	/* ops marked global share the filter hashes */
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		ops = &global_ops;
-		/* Don't update hash if global is already set */
-		if (global_start_up)
-			hash_enable = false;
-		global_start_up++;
-	}
-
 	ops->flags |= FTRACE_OPS_FL_ENABLED;
-	if (hash_enable)
-		ftrace_hash_rec_enable(ops, 1);
+
+	ftrace_hash_rec_enable(ops, 1);
 
 	ftrace_startup_enable(command);
 
@@ -2148,7 +2098,6 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 
 static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 {
-	bool hash_disable = true;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -2166,21 +2115,9 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 */
 	WARN_ON_ONCE(ftrace_start_up < 0);
 
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		ops = &global_ops;
-		global_start_up--;
-		WARN_ON_ONCE(global_start_up < 0);
-		/* Don't update hash if global still has users */
-		if (global_start_up) {
-			WARN_ON_ONCE(!ftrace_start_up);
-			hash_disable = false;
-		}
-	}
-
-	if (hash_disable)
-		ftrace_hash_rec_disable(ops, 1);
+	ftrace_hash_rec_disable(ops, 1);
 
-	if (ops != &global_ops || !global_start_up)
+	if (!global_start_up)
 		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
 
 	command |= FTRACE_UPDATE_CALLS;
@@ -3524,10 +3461,6 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	struct ftrace_hash *hash;
 	int ret;
 
-	/* All global ops uses the global ops filters */
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL)
-		ops = &global_ops;
-
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
@@ -3639,8 +3572,7 @@ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
 }
 EXPORT_SYMBOL_GPL(ftrace_set_notrace);
 /**
- * ftrace_set_filter - set a function to filter on in ftrace
- * @ops - the ops to set the filter with
+ * ftrace_set_global_filter - set a function to filter on with global tracers
  * @buf - the string that holds the function filter text.
  * @len - the length of the string.
  * @reset - non zero to reset all filters before applying this filter.
@@ -3655,8 +3587,7 @@ void ftrace_set_global_filter(unsigned char *buf, int len, int reset)
 EXPORT_SYMBOL_GPL(ftrace_set_global_filter);
 
 /**
- * ftrace_set_notrace - set a function to not trace in ftrace
- * @ops - the ops to set the notrace filter with
+ * ftrace_set_global_notrace - set a function to not trace with global tracers
  * @buf - the string that holds the function notrace text.
  * @len - the length of the string.
  * @reset - non zero to reset all filters before applying this filter.
@@ -4443,6 +4374,34 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+__init void ftrace_init_global_array_ops(struct trace_array *tr)
+{
+	tr->ops = &global_ops;
+	tr->ops->private = tr;
+}
+
+void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func)
+{
+	/* If we filter on pids, update to use the pid function */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
+		if (WARN_ON(tr->ops->func != ftrace_stub))
+			printk("ftrace ops had %pS for function\n",
+			       tr->ops->func);
+		/* Only the top level instance does pid tracing */
+		if (!list_empty(&ftrace_pids)) {
+			set_ftrace_pid_function(func);
+			func = ftrace_pid_func;
+		}
+	}
+	tr->ops->func = func;
+	tr->ops->private = tr;
+}
+
+void ftrace_reset_array_ops(struct trace_array *tr)
+{
+	tr->ops->func = ftrace_stub;
+}
+
 static void
 ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 			struct ftrace_ops *op, struct pt_regs *regs)
@@ -4501,9 +4460,16 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	 */
 	preempt_disable_notrace();
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		if (ftrace_ops_test(op, ip, regs))
+		if (ftrace_ops_test(op, ip, regs)) {
+			if (WARN_ON(!op->func)) {
+				function_trace_stop = 1;
+				printk("op=%p %pS\n", op, op);
+				goto out;
+			}
 			op->func(ip, parent_ip, op, regs);
+		}
 	} while_for_each_ftrace_op(op);
+out:
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
@@ -4908,7 +4874,6 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 static int ftrace_graph_active;
-static struct notifier_block ftrace_suspend_notifier;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
@@ -5054,13 +5019,6 @@ ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
 	return NOTIFY_DONE;
 }
 
-/* Just a place holder for function graph */
-static struct ftrace_ops fgraph_ops __read_mostly = {
-	.func		= ftrace_stub,
-	.flags		= FTRACE_OPS_FL_STUB | FTRACE_OPS_FL_GLOBAL |
-				FTRACE_OPS_FL_RECURSION_SAFE,
-};
-
 static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
 {
 	if (!ftrace_ops_test(&global_ops, trace->func, NULL))
@@ -5085,6 +5043,10 @@ static void update_function_graph_func(void)
 		ftrace_graph_entry = ftrace_graph_entry_test;
 }
 
+static struct notifier_block ftrace_suspend_notifier = {
+	.notifier_call = ftrace_suspend_notifier_call,
+};
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -5098,7 +5060,6 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 		goto out;
 	}
 
-	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
 	register_pm_notifier(&ftrace_suspend_notifier);
 
 	ftrace_graph_active++;
@@ -5120,7 +5081,10 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_graph_entry = ftrace_graph_entry_test;
 	update_function_graph_func();
 
-	ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
+	/* Function graph doesn't use the .func field of global_ops */
+	global_ops.flags |= FTRACE_OPS_FL_STUB;
+
+	ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
@@ -5138,7 +5102,8 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	__ftrace_graph_entry = ftrace_graph_entry_stub;
-	ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
+	ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
+	global_ops.flags &= ~FTRACE_OPS_FL_STUB;
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 737b0efa1a62..16f7038d1f4d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -275,7 +275,7 @@ int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
 }
 EXPORT_SYMBOL_GPL(call_filter_check_discard);
 
-cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
+static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
 	u64 ts;
 
@@ -599,7 +599,7 @@ static int alloc_snapshot(struct trace_array *tr)
 	return 0;
 }
 
-void free_snapshot(struct trace_array *tr)
+static void free_snapshot(struct trace_array *tr)
 {
 	/*
 	 * We don't free the ring buffer. instead, resize it because
@@ -963,27 +963,9 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
-/*
- * ftrace_max_lock is used to protect the swapping of buffers
- * when taking a max snapshot. The buffers themselves are
- * protected by per_cpu spinlocks. But the action of the swap
- * needs its own lock.
- *
- * This is defined as a arch_spinlock_t in order to help
- * with performance when lockdep debugging is enabled.
- *
- * It is also used in other places outside the update_max_tr
- * so it needs to be defined outside of the
- * CONFIG_TRACER_MAX_TRACE.
- */
-static arch_spinlock_t ftrace_max_lock =
-	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-
 unsigned long __read_mostly	tracing_thresh;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-unsigned long __read_mostly	tracing_max_latency;
-
 /*
  * Copy the new maximum trace into the separate maximum-trace
  * structure. (this way the maximum trace is permanently saved,
@@ -1000,7 +982,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	max_buf->cpu = cpu;
 	max_buf->time_start = data->preempt_timestamp;
 
-	max_data->saved_latency = tracing_max_latency;
+	max_data->saved_latency = tr->max_latency;
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
 
@@ -1048,14 +1030,14 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 	}
 
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 
 	buf = tr->trace_buffer.buffer;
 	tr->trace_buffer.buffer = tr->max_buffer.buffer;
 	tr->max_buffer.buffer = buf;
 
 	__update_max_tr(tr, tsk, cpu);
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 }
 
 /**
@@ -1081,7 +1063,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 	}
 
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 
 	ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu);
 
@@ -1099,11 +1081,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
 	__update_max_tr(tr, tsk, cpu);
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static void default_wait_pipe(struct trace_iterator *iter)
+static void wait_on_pipe(struct trace_iterator *iter)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
@@ -1220,8 +1202,6 @@ int register_tracer(struct tracer *type)
 	else
 		if (!type->flags->opts)
 			type->flags->opts = dummy_tracer_opt;
-	if (!type->wait_pipe)
-		type->wait_pipe = default_wait_pipe;
 
 	ret = run_tracer_selftest(type);
 	if (ret < 0)
@@ -1305,22 +1285,71 @@ void tracing_reset_all_online_cpus(void)
 	}
 }
 
-#define SAVED_CMDLINES 128
+#define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
-static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
-static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
-static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
-static int cmdline_idx;
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+struct saved_cmdlines_buffer {
+	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
+	unsigned *map_cmdline_to_pid;
+	unsigned cmdline_num;
+	int cmdline_idx;
+	char *saved_cmdlines;
+};
+static struct saved_cmdlines_buffer *savedcmd;
 
 /* temporary disable recording */
 static atomic_t trace_record_cmdline_disabled __read_mostly;
 
-static void trace_init_cmdlines(void)
+static inline char *get_saved_cmdlines(int idx)
 {
-	memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline));
-	memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid));
-	cmdline_idx = 0;
+	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
+}
+
+static inline void set_cmdline(int idx, const char *cmdline)
+{
+	memcpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
+}
+
+static int allocate_cmdlines_buffer(unsigned int val,
+				    struct saved_cmdlines_buffer *s)
+{
+	s->map_cmdline_to_pid = kmalloc(val * sizeof(*s->map_cmdline_to_pid),
+					GFP_KERNEL);
+	if (!s->map_cmdline_to_pid)
+		return -ENOMEM;
+
+	s->saved_cmdlines = kmalloc(val * TASK_COMM_LEN, GFP_KERNEL);
+	if (!s->saved_cmdlines) {
+		kfree(s->map_cmdline_to_pid);
+		return -ENOMEM;
+	}
+
+	s->cmdline_idx = 0;
+	s->cmdline_num = val;
+	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
+	       sizeof(s->map_pid_to_cmdline));
+	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
+	       val * sizeof(*s->map_cmdline_to_pid));
+
+	return 0;
+}
+
+static int trace_create_savedcmd(void)
+{
+	int ret;
+
+	savedcmd = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL);
+	if (!savedcmd)
+		return -ENOMEM;
+
+	ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
+	if (ret < 0) {
+		kfree(savedcmd);
+		savedcmd = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 int is_tracing_stopped(void)
@@ -1353,7 +1382,7 @@ void tracing_start(void)
 	}
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&global_trace.max_lock);
 
 	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
@@ -1365,7 +1394,7 @@ void tracing_start(void)
 		ring_buffer_record_enable(buffer);
 #endif
 
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&global_trace.max_lock);
 
 	ftrace_start();
  out:
@@ -1420,7 +1449,7 @@ void tracing_stop(void)
 		goto out;
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&global_trace.max_lock);
 
 	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
@@ -1432,7 +1461,7 @@ void tracing_stop(void)
 		ring_buffer_record_disable(buffer);
 #endif
 
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&global_trace.max_lock);
 
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
@@ -1461,12 +1490,12 @@ static void tracing_stop_tr(struct trace_array *tr)
 
 void trace_stop_cmdline_recording(void);
 
-static void trace_save_cmdline(struct task_struct *tsk)
+static int trace_save_cmdline(struct task_struct *tsk)
 {
 	unsigned pid, idx;
 
 	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
-		return;
+		return 0;
 
 	/*
 	 * It's not the end of the world if we don't get
@@ -1475,11 +1504,11 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	 * so if we miss here, then better luck next time.
 	 */
 	if (!arch_spin_trylock(&trace_cmdline_lock))
-		return;
+		return 0;
 
-	idx = map_pid_to_cmdline[tsk->pid];
+	idx = savedcmd->map_pid_to_cmdline[tsk->pid];
 	if (idx == NO_CMDLINE_MAP) {
-		idx = (cmdline_idx + 1) % SAVED_CMDLINES;
+		idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;
 
 		/*
 		 * Check whether the cmdline buffer at idx has a pid
@@ -1487,22 +1516,24 @@ static void trace_save_cmdline(struct task_struct *tsk)
 		 * need to clear the map_pid_to_cmdline. Otherwise we
 		 * would read the new comm for the old pid.
 		 */
-		pid = map_cmdline_to_pid[idx];
+		pid = savedcmd->map_cmdline_to_pid[idx];
 		if (pid != NO_CMDLINE_MAP)
-			map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
+			savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
 
-		map_cmdline_to_pid[idx] = tsk->pid;
-		map_pid_to_cmdline[tsk->pid] = idx;
+		savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
+		savedcmd->map_pid_to_cmdline[tsk->pid] = idx;
 
-		cmdline_idx = idx;
+		savedcmd->cmdline_idx = idx;
 	}
 
-	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
+	set_cmdline(idx, tsk->comm);
 
 	arch_spin_unlock(&trace_cmdline_lock);
+
+	return 1;
 }
 
-void trace_find_cmdline(int pid, char comm[])
+static void __trace_find_cmdline(int pid, char comm[])
 {
 	unsigned map;
 
@@ -1521,13 +1552,19 @@ void trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
-	preempt_disable();
-	arch_spin_lock(&trace_cmdline_lock);
-	map = map_pid_to_cmdline[pid];
+	map = savedcmd->map_pid_to_cmdline[pid];
 	if (map != NO_CMDLINE_MAP)
-		strcpy(comm, saved_cmdlines[map]);
+		strcpy(comm, get_saved_cmdlines(map));
 	else
 		strcpy(comm, "<...>");
+}<