Merge tag 'trace-v4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "This release has a few updates:

   - STM can hook into the function tracer
   - Function filtering now supports more advance glob matching
   - Ftrace selftests updates and added tests
   - Softirq tag in traces now show only softirqs
   - ARM nop added to non traced locations at compile time
   - New trace_marker_raw file that allows for binary input
   - Optimizations to the ring buffer
   - Removal of kmap in trace_marker
   - Wakeup and irqsoff tracers now adhere to the set_graph_notrace file
   - Other various fixes and clean ups"

* tag 'trace-v4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (42 commits)
  selftests: ftrace: Shift down default message verbosity
  kprobes/trace: Fix kprobe selftest for newer gcc
  tracing/kprobes: Add a helper method to return number of probe hits
  tracing/rb: Init the CPU mask on allocation
  tracing: Use SOFTIRQ_OFFSET for softirq dectection for more accurate results
  tracing/fgraph: Have wakeup and irqsoff tracers ignore graph functions too
  fgraph: Handle a case where a tracer ignores set_graph_notrace
  tracing: Replace kmap with copy_from_user() in trace_marker writing
  ftrace/x86_32: Set ftrace_stub to weak to prevent gcc from using short jumps to it
  tracing: Allow benchmark to be enabled at early_initcall()
  tracing: Have system enable return error if one of the events fail
  tracing: Do not start benchmark on boot up
  tracing: Have the reg function allow to fail
  ring-buffer: Force rb_end_commit() and rb_set_commit_to_write() inline
  ring-buffer: Froce rb_update_write_stamp() to be inlined
  ring-buffer: Force inline of hotpath helper functions
  tracing: Make __buffer_unlock_commit() always_inline
  tracing: Make tracepoint_printk a static_key
  ring-buffer: Always inline rb_event_data()
  ring-buffer: Make rb_reserve_next_event() always inlined
  ...

19 files changed, 685 insertions, 253 deletions

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 1475d2545b7e..1a292ebcbbb6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -627,7 +627,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &tracepoint_printk,
 		.maxlen		= sizeof(tracepoint_printk),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= tracepoint_printk_sysctl,
 	},
 #endif
 #ifdef CONFIG_KEXEC_CORE
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2a96b063d659..d5038005eb5d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -70,6 +70,7 @@ config FTRACE_NMI_ENTER
 
 config EVENT_TRACING
 	select CONTEXT_SWITCH_TRACER
+        select GLOB
 	bool
 
 config CONTEXT_SWITCH_TRACER
@@ -133,6 +134,7 @@ config FUNCTION_TRACER
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
+        select GLOB
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 33dd57f53f88..1f0f547c54da 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3511,6 +3511,10 @@ static int ftrace_match(char *str, struct ftrace_glob *g)
 		    memcmp(str + slen - g->len, g->search, g->len) == 0)
 			matched = 1;
 		break;
+	case MATCH_GLOB:
+		if (glob_match(g->search, str))
+			matched = 1;
+		break;
 	}
 
 	return matched;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 89a2611a1635..a85739efcc30 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -245,7 +245,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 EXPORT_SYMBOL_GPL(ring_buffer_event_length);
 
 /* inline for ring buffer fast paths */
-static void *
+static __always_inline void *
 rb_event_data(struct ring_buffer_event *event)
 {
 	if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
@@ -1798,48 +1798,48 @@ void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
 
-static inline void *
+static __always_inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
 	return bpage->data + index;
 }
 
-static inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
+static __always_inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
 {
 	return bpage->page->data + index;
 }
 
-static inline struct ring_buffer_event *
+static __always_inline struct ring_buffer_event *
 rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	return __rb_page_index(cpu_buffer->reader_page,
 			       cpu_buffer->reader_page->read);
 }
 
-static inline struct ring_buffer_event *
+static __always_inline struct ring_buffer_event *
 rb_iter_head_event(struct ring_buffer_iter *iter)
 {
 	return __rb_page_index(iter->head_page, iter->head);
 }
 
-static inline unsigned rb_page_commit(struct buffer_page *bpage)
+static __always_inline unsigned rb_page_commit(struct buffer_page *bpage)
 {
 	return local_read(&bpage->page->commit);
 }
 
 /* Size is determined by what has been committed */
-static inline unsigned rb_page_size(struct buffer_page *bpage)
+static __always_inline unsigned rb_page_size(struct buffer_page *bpage)
 {
 	return rb_page_commit(bpage);
 }
 
-static inline unsigned
+static __always_inline unsigned
 rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	return rb_page_commit(cpu_buffer->commit_page);
 }
 
-static inline unsigned
+static __always_inline unsigned
 rb_event_index(struct ring_buffer_event *event)
 {
 	unsigned long addr = (unsigned long)event;
@@ -2355,7 +2355,7 @@ static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
 	local_inc(&cpu_buffer->commits);
 }
 
-static void
+static __always_inline void
 rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	unsigned long max_count;
@@ -2410,7 +2410,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 		goto again;
 }
 
-static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
+static __always_inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	unsigned long commits;
 
@@ -2455,7 +2455,7 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
 		event->time_delta = 1;
 }
 
-static inline bool
+static __always_inline bool
 rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		   struct ring_buffer_event *event)
 {
@@ -2469,7 +2469,7 @@ rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		rb_commit_index(cpu_buffer) == index;
 }
 
-static void
+static __always_inline void
 rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 		      struct ring_buffer_event *event)
 {
@@ -2702,7 +2702,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 }
 
-static struct ring_buffer_event *
+static __always_inline struct ring_buffer_event *
 rb_reserve_next_event(struct ring_buffer *buffer,
 		      struct ring_buffer_per_cpu *cpu_buffer,
 		      unsigned long length)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 54d5270a5042..66f829c47bec 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -40,6 +40,7 @@
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/fs.h>
+#include <linux/trace.h>
 #include <linux/sched/rt.h>
 
 #include "trace.h"
@@ -68,6 +69,7 @@ bool __read_mostly tracing_selftest_disabled;
 /* Pipe tracepoints to printk */
 struct trace_iterator *tracepoint_print_iter;
 int tracepoint_printk;
+static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key);
 
 /* For tracers that don't implement custom flags */
 static struct tracer_opt dummy_tracer_opt[] = {
@@ -738,6 +740,31 @@ static inline void ftrace_trace_stack(struct trace_array *tr,
 
 #endif
 
+static __always_inline void
+trace_event_setup(struct ring_buffer_event *event,
+		  int type, unsigned long flags, int pc)
+{
+	struct trace_entry *ent = ring_buffer_event_data(event);
+
+	tracing_generic_entry_update(ent, flags, pc);
+	ent->type = type;
+}
+
+static __always_inline struct ring_buffer_event *
+__trace_buffer_lock_reserve(struct ring_buffer *buffer,
+			  int type,
+			  unsigned long len,
+			  unsigned long flags, int pc)
+{
+	struct ring_buffer_event *event;
+
+	event = ring_buffer_lock_reserve(buffer, len);
+	if (event != NULL)
+		trace_event_setup(event, type, flags, pc);
+
+	return event;
+}
+
 static void tracer_tracing_on(struct trace_array *tr)
 {
 	if (tr->trace_buffer.buffer)
@@ -767,6 +794,22 @@ void tracing_on(void)
 }
 EXPORT_SYMBOL_GPL(tracing_on);
 
+
+static __always_inline void
+__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
+{
+	__this_cpu_write(trace_cmdline_save, true);
+
+	/* If this is the temp buffer, we need to commit fully */
+	if (this_cpu_read(trace_buffered_event) == event) {
+		/* Length is in event->array[0] */
+		ring_buffer_write(buffer, event->array[0], &event->array[1]);
+		/* Release the temp buffer */
+		this_cpu_dec(trace_buffered_event_cnt);
+	} else
+		ring_buffer_unlock_commit(buffer, event);
+}
+
 /**
  * __trace_puts - write a constant string into the trace buffer.
  * @ip:	   The address of the caller
@@ -794,8 +837,8 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
-	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
-					  irq_flags, pc);
+	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
+					    irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -842,8 +885,8 @@ int __trace_bputs(unsigned long ip, const char *str)
 
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
-	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
-					  irq_flags, pc);
+	event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
+					    irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -1907,35 +1950,19 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 #endif
 		((pc & NMI_MASK    ) ? TRACE_FLAG_NMI     : 0) |
 		((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
-		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
+		((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) |
 		(tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
 		(test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
 }
 EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
-static __always_inline void
-trace_event_setup(struct ring_buffer_event *event,
-		  int type, unsigned long flags, int pc)
-{
-	struct trace_entry *ent = ring_buffer_event_data(event);
-
-	tracing_generic_entry_update(ent, flags, pc);
-	ent->type = type;
-}
-
 struct ring_buffer_event *
 trace_buffer_lock_reserve(struct ring_buffer *buffer,
 			  int type,
 			  unsigned long len,
 			  unsigned long flags, int pc)
 {
-	struct ring_buffer_event *event;
-
-	event = ring_buffer_lock_reserve(buffer, len);
-	if (event != NULL)
-		trace_event_setup(event, type, flags, pc);
-
-	return event;
+	return __trace_buffer_lock_reserve(buffer, type, len, flags, pc);
 }
 
 DEFINE_PER_CPU(struct ring_buffer_event *, trace_buffered_event);
@@ -2049,21 +2076,6 @@ void trace_buffered_event_disable(void)
 	preempt_enable();
 }
 
-void
-__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
-{
-	__this_cpu_write(trace_cmdline_save, true);
-
-	/* If this is the temp buffer, we need to commit fully */
-	if (this_cpu_read(trace_buffered_event) == event) {
-		/* Length is in event->array[0] */
-		ring_buffer_write(buffer, event->array[0], &event->array[1]);
-		/* Release the temp buffer */
-		this_cpu_dec(trace_buffered_event_cnt);
-	} else
-		ring_buffer_unlock_commit(buffer, event);
-}
-
 static struct ring_buffer *temp_buffer;
 
 struct ring_buffer_event *
@@ -2090,8 +2102,8 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 		this_cpu_dec(trace_buffered_event_cnt);
 	}
 
-	entry = trace_buffer_lock_reserve(*current_rb,
-					 type, len, flags, pc);
+	entry = __trace_buffer_lock_reserve(*current_rb,
+					    type, len, flags, pc);
 	/*
 	 * If tracing is off, but we have triggers enabled
 	 * we still need to look at the event data. Use the temp_buffer
@@ -2100,13 +2112,88 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 	 */
 	if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) {
 		*current_rb = temp_buffer;
-		entry = trace_buffer_lock_reserve(*current_rb,
-						  type, len, flags, pc);
+		entry = __trace_buffer_lock_reserve(*current_rb,
+						    type, len, flags, pc);
 	}
 	return entry;
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
+static DEFINE_SPINLOCK(tracepoint_iter_lock);
+static DEFINE_MUTEX(tracepoint_printk_mutex);
+
+static void output_printk(struct trace_event_buffer *fbuffer)
+{
+	struct trace_event_call *event_call;
+	struct trace_event *event;
+	unsigned long flags;
+	struct trace_iterator *iter = tracepoint_print_iter;
+
+	/* We should never get here if iter is NULL */
+	if (WARN_ON_ONCE(!iter))
+		return;
+
+	event_call = fbuffer->trace_file->event_call;
+	if (!event_call || !event_call->event.funcs ||
+	    !event_call->event.funcs->trace)
+		return;
+
+	event = &fbuffer->trace_file->event_call->event;
+
+	spin_lock_irqsave(&tracepoint_iter_lock, flags);
+	trace_seq_init(&iter->seq);
+	iter->ent = fbuffer->entry;
+	event_call->event.funcs->trace(iter, 0, event);
+	trace_seq_putc(&iter->seq, 0);
+	printk("%s", iter->seq.buffer);
+
+	spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
+}
+
+int tracepoint_printk_sysctl(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int save_tracepoint_printk;
+	int ret;
+
+	mutex_lock(&tracepoint_printk_mutex);
+	save_tracepoint_printk = tracepoint_printk;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	/*
+	 * This will force exiting early, as tracepoint_printk
+	 * is always zero when tracepoint_printk_iter is not allocated
+	 */
+	if (!tracepoint_print_iter)
+		tracepoint_printk = 0;
+
+	if (save_tracepoint_printk == tracepoint_printk)
+		goto out;
+
+	if (tracepoint_printk)
+		static_key_enable(&tracepoint_printk_key.key);
+	else
+		static_key_disable(&tracepoint_printk_key.key);
+
+ out:
+	mutex_unlock(&tracepoint_printk_mutex);
+
+	return ret;
+}
+
+void trace_event_buffer_commit(struct trace_event_buffer *fbuffer)
+{
+	if (static_key_false(&tracepoint_printk_key.key))
+		output_printk(fbuffer);
+
+	event_trigger_unlock_commit(fbuffer->trace_file, fbuffer->buffer,
+				    fbuffer->event, fbuffer->entry,
+				    fbuffer->flags, fbuffer->pc);
+}
+EXPORT_SYMBOL_GPL(trace_event_buffer_commit);
+
 void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 				     struct ring_buffer *buffer,
 				     struct ring_buffer_event *event,
@@ -2129,6 +2216,139 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 	ftrace_trace_userstack(buffer, flags, pc);
 }
 
+/*
+ * Similar to trace_buffer_unlock_commit_regs() but do not dump stack.
+ */
+void
+trace_buffer_unlock_commit_nostack(struct ring_buffer *buffer,
+				   struct ring_buffer_event *event)
+{
+	__buffer_unlock_commit(buffer, event);
+}
+
+static void
+trace_process_export(struct trace_export *export,
+	       struct ring_buffer_event *event)
+{
+	struct trace_entry *entry;
+	unsigned int size = 0;
+
+	entry = ring_buffer_event_data(event);
+	size = ring_buffer_event_length(event);
+	export->write(entry, size);
+}
+
+static DEFINE_MUTEX(ftrace_export_lock);
+
+static struct trace_export __rcu *ftrace_exports_list __read_mostly;
+
+static DEFINE_STATIC_KEY_FALSE(ftrace_exports_enabled);
+
+static inline void ftrace_exports_enable(void)
+{
+	static_branch_enable(&ftrace_exports_enabled);
+}
+
+static inline void ftrace_exports_disable(void)
+{
+	static_branch_disable(&ftrace_exports_enabled);
+}
+
+void ftrace_exports(struct ring_buffer_event *event)
+{
+	struct trace_export *export;
+
+	preempt_disable_notrace();
+
+	export = rcu_dereference_raw_notrace(ftrace_exports_list);
+	while (export) {
+		trace_process_export(export, event);
+		export = rcu_dereference_raw_notrace(export->next);
+	}
+
+	preempt_enable_notrace();
+}
+
+static inline void
+add_trace_export(struct trace_export **list, struct trace_export *export)
+{
+	rcu_assign_pointer(export->next, *list);
+	/*
+	 * We are entering export into the list but another
+	 * CPU might be walking that list. We need to make sure
+	 * the export->next pointer is valid before another CPU sees
+	 * the export pointer included into the list.
+	 */
+	rcu_assign_pointer(*list, export);
+}
+
+static inline int
+rm_trace_export(struct trace_export **list, struct trace_export *export)
+{
+	struct trace_export **p;
+
+	for (p = list; *p != NULL; p = &(*p)->next)
+		if (*p == export)
+			break;
+
+	if (*p != export)
+		return -1;
+
+	rcu_assign_pointer(*p, (*p)->next);
+
+	return 0;
+}
+
+static inline void
+add_ftrace_export(struct trace_export **list, struct trace_export *export)
+{
+	if (*list == NULL)
+		ftrace_exports_enable();
+
+	add_trace_export(list, export);
+}
+
+static inline int
+rm_ftrace_export(struct trace_export **list, struct trace_export *export)
+{
+	int ret;
+
+	ret = rm_trace_export(list, export);
+	if (*list == NULL)
+		ftrace_exports_disable();
+
+	return ret;
+}
+
+int register_ftrace_export(struct trace_export *export)
+{
+	if (WARN_ON_ONCE(!export->write))
+		return -1;
+
+	mutex_lock(&ftrace_export_lock);
+
+	add_ftrace_export(&ftrace_exports_list, export);
+
+	mutex_unlock(&ftrace_export_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_ftrace_export);
+
+int unregister_ftrace_export(struct trace_export *export)
+{
+	int ret;
+
+	mutex_lock(&ftrace_export_lock);
+
+	ret = rm_ftrace_export(&ftrace_exports_list, export);
+
+	mutex_unlock(&ftrace_export_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(unregister_ftrace_export);
+
 void
 trace_function(struct trace_array *tr,
 	       unsigned long ip, unsigned long parent_ip, unsigned long flags,
@@ -2139,16 +2359,19 @@ trace_function(struct trace_array *tr,
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
-	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
-					  flags, pc);
+	event = __trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
+					    flags, pc);
 	if (!event)
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event)) {
+		if (static_branch_unlikely(&ftrace_exports_enabled))
+			ftrace_exports(event);
 		__buffer_unlock_commit(buffer, event);
+	}
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -2216,8 +2439,8 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 
 	size *= sizeof(unsigned long);
 
-	event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
-					  sizeof(*entry) + size, flags, pc);
+	event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
+					    sizeof(*entry) + size, flags, pc);
 	if (!event)
 		goto out;
 	entry = ring_buffer_event_data(event);
@@ -2318,8 +2541,8 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 
 	__this_cpu_inc(user_stack_count);
 
-	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
-					  sizeof(*entry), flags, pc);
+	event = __trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
+					    sizeof(*entry), flags, pc);
 	if (!event)
 		goto out_drop_count;
 	entry	= ring_buffer_event_data(event);
@@ -2489,8 +2712,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	local_save_flags(flags);
 	size = sizeof(*entry) + sizeof(u32) * len;
 	buffer = tr->trace_buffer.buffer;
-	event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
-					  flags, pc);
+	event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
+					    flags, pc);
 	if (!event)
 		goto out;
 	entry = ring_buffer_event_data(event);
@@ -2545,8 +2768,8 @@ __trace_array_vprintk(struct ring_buffer *buffer,
 
 	local_save_flags(flags);
 	size = sizeof(*entry) + len + 1;
-	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
-					  flags, pc);
+	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+					    flags, pc);
 	if (!event)
 		goto out;
 	entry = ring_buffer_event_data(event);
@@ -4055,6 +4278,7 @@ static const char readme_msg[] =
 	"     x86-tsc:   TSC cycle counter\n"
 #endif
 	"\n  trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
+	"\n  trace_marker_raw\t\t- Writes into this file writes binary data into the kernel buffer\n"
 	"  tracing_cpumask\t- Limit which CPUs to trace\n"
 	"  instances\t\t- Make sub-buffers with: mkdir instances/foo\n"
 	"\t\t\t  Remove sub-buffer with rmdir\n"
@@ -4066,7 +4290,7 @@ static const char readme_msg[] =
 	"\n  available_filter_functions - list of functions that can be filtered on\n"
 	"  set_ftrace_filter\t- echo function name in here to only trace these\n"
 	"\t\t\t  functions\n"
-	"\t     accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+	"\t     accepts: func_full_name or glob-matching-pattern\n"
 	"\t     modules: Can select a group via module\n"
 	"\t      Format: :mod:<module-name>\n"
 	"\t     example: echo :mod:ext3 > set_ftrace_filter\n"
@@ -5519,21 +5743,18 @@ static ssize_t
 tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
 {
-	unsigned long addr = (unsigned long)ubuf;
 	struct trace_array *tr = filp->private_data;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
 	struct print_entry *entry;
 	unsigned long irq_flags;
-	struct page *pages[2];
-	void *map_page[2];
-	int nr_pages = 1;
+	const char faulted[] = "<faulted>";
 	ssize_t written;
-	int offset;
 	int size;
 	int len;
-	int ret;
-	int i;
+
+/* Used in tracing_mark_raw_write() as well */
+#define FAULTED_SIZE (sizeof(faulted) - 1) /* '\0' is already accounted for */
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -5544,60 +5765,33 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (cnt > TRACE_BUF_SIZE)
 		cnt = TRACE_BUF_SIZE;
 
-	/*
-	 * Userspace is injecting traces into the kernel trace buffer.
-	 * We want to be as non intrusive as possible.
-	 * To do so, we do not want to allocate any special buffers
-	 * or take any locks, but instead write the userspace data
-	 * straight into the ring buffer.
-	 *
-	 * First we need to pin the userspace buffer into memory,
-	 * which, most likely it is, because it just referenced it.
-	 * But there's no guarantee that it is. By using get_user_pages_fast()
-	 * and kmap_atomic/kunmap_atomic() we can get access to the
-	 * pages directly. We then write the data directly into the
-	 * ring buffer.
-	 */
 	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
 
-	/* check if we cross pages */
-	if ((addr & PAGE_MASK) != ((addr + cnt) & PAGE_MASK))
-		nr_pages = 2;
-
-	offset = addr & (PAGE_SIZE - 1);
-	addr &= PAGE_MASK;
-
-	ret = get_user_pages_fast(addr, nr_pages, 0, pages);
-	if (ret < nr_pages) {
-		while (--ret >= 0)
-			put_page(pages[ret]);
-		written = -EFAULT;
-		goto out;
-	}
+	local_save_flags(irq_flags);
+	size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */
 
-	for (i = 0; i < nr_pages; i++)
-		map_page[i] = kmap_atomic(pages[i]);
+	/* If less than "<faulted>", then make sure we can still add that */
+	if (cnt < FAULTED_SIZE)
+		size += FAULTED_SIZE - cnt;
 
-	local_save_flags(irq_flags);
-	size = sizeof(*entry) + cnt + 2; /* possible \n added */
 	buffer = tr->trace_buffer.buffer;
-	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
-					  irq_flags, preempt_count());
-	if (!event) {
+	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+					    irq_flags, preempt_count());
+	if (unlikely(!event))
 		/* Ring buffer disabled, return as if not open for write */
-		written = -EBADF;
-		goto out_unlock;
-	}
+		return -EBADF;
 
 	entry = ring_buffer_event_data(event);
 	entry->ip = _THIS_IP_;
 
-	if (nr_pages == 2) {
-		len = PAGE_SIZE - offset;
-		memcpy(&entry->buf, map_page[0] + offset, len);
-		memcpy(&entry->buf[len], map_page[1], cnt - len);
+	len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt);
+	if (len) {
+		memcpy(&entry->buf, faulted, FAULTED_SIZE);
+		cnt = FAULTED_SIZE;
+		written = -EFAULT;
 	} else
-		memcpy(&entry->buf, map_page[0] + offset, cnt);
+		written = cnt;
+	len = cnt;
 
 	if (entry->buf[cnt - 1] != '\n') {
 		entry->buf[cnt] = '\n';
@@ -5607,16 +5801,73 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 
 	__buffer_unlock_commit(buffer, event);
 
-	written = cnt;
+	if (written > 0)
+		*fpos += written;
 
-	*fpos += written;
+	return written;
+}
+
+/* Limit it for now to 3K (including tag) */
+#define RAW_DATA_MAX_SIZE (1024*3)
+
+static ssize_t
+tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
+					size_t cnt, loff_t *fpos)
+{
+	struct trace_array *tr = filp->private_data;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	struct raw_data_entry *entry;
+	const char faulted[] = "<faulted>";
+	unsigned long irq_flags;
+	ssize_t written;
+	int size;
+	int len;
+
+#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int))
+
+	if (tracing_disabled)
+		return -EINVAL;
+
+	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
+		return -EINVAL;
+
+	/* The marker must at least have a tag id */
+	if (cnt < sizeof(unsigned int) || cnt > RAW_DATA_MAX_SIZE)
+		return -EINVAL;
+
+	if (cnt > TRACE_BUF_SIZE)
+		cnt = TRACE_BUF_SIZE;
+
+	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
+
+	local_save_flags(irq_flags);
+	size = sizeof(*entry) + cnt;
+	if (cnt < FAULT_SIZE_ID)
+		size += FAULT_SIZE_ID - cnt;
+
+	buffer = tr->trace_buffer.buffer;
+	event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size,
+					    irq_flags, preempt_count());
+	if (!event)
+		/* Ring buffer disabled, return as if not open for write */
+		return -EBADF;
+
+	entry = ring_buffer_event_data(event);
+
+	len = __copy_from_user_inatomic(&entry->id, ubuf, cnt);
+	if (len) {
+		entry->id = -1;
+		memcpy(&entry->buf, faulted, FAULTED_SIZE);
+		written = -EFAULT;
+	} else
+		written = cnt;
+
+	__buffer_unlock_commit(buffer, event);
+
+	if (written > 0)
+		*fpos += written;
 
- out_unlock:
-	for (i = nr_pages - 1; i >= 0; i--) {
-		kunmap_atomic(map_page[i]);
-		put_page(pages[i]);
-	}
- out:
 	return written;
 }
 
@@ -5946,6 +6197,13 @@ static const struct file_operations tracing_mark_fops = {
 	.release	= tracing_release_generic_tr,
 };
 
+static const struct file_operations tracing_mark_raw_fops = {
+	.open		= tracing_open_generic_tr,
+	.write		= tracing_mark_raw_write,
+	.llseek		= generic_file_llseek,
+	.release	= tracing_release_generic_tr,
+};
+
 static const struct file_operations trace_clock_fops = {
 	.open		= tracing_clock_open,
 	.read		= seq_read,
@@ -7215,6 +7473,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("trace_marker", 0220, d_tracer,
 			  tr, &tracing_mark_fops);
 
+	trace_create_file("trace_marker_raw", 0220, d_tracer,
+			  tr, &tracing_mark_raw_fops);
+
 	trace_create_file("trace_clock", 0644, d_tracer, tr,
 			  &trace_clock_fops);
 
@@ -7752,6 +8013,8 @@ void __init trace_init(void)
 			kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
 		if (WARN_ON(!tracepoint_print_iter))
 			tracepoint_printk = 0;
+		else
+			static_key_enable(&tracepoint_printk_key.key);
 	}
 	tracer_alloc_buffers();
 	trace_event_init();
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index fd24b1f9ac43..c2234494f40c 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -15,6 +15,7 @@
 #include <linux/trace_events.h>
 #include <linux/compiler.h>
 #include <linux/trace_seq.h>
+#include <linux/glob.h>
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */