6 files changed, 66 insertions, 19 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 294b8a271a04..fc4da2d97f9b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2397,6 +2397,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	write &= RB_WRITE_MASK;
 	tail = write - length;
 
+	/*
+	 * If this is the first commit on the page, then it has the same
+	 * timestamp as the page itself.
+	 */
+	if (!tail)
+		delta = 0;
+
 	/* See if we shot pass the end of this buffer page */
 	if (unlikely(write > BUF_PAGE_SIZE))
 		return rb_move_tail(cpu_buffer, length, tail,
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index a5457d577b98..0434ff1b808e 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -40,8 +40,8 @@ static int write_iteration = 50;
 module_param(write_iteration, uint, 0644);
 MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
 
-static int producer_nice = 19;
-static int consumer_nice = 19;
+static int producer_nice = MAX_NICE;
+static int consumer_nice = MAX_NICE;
 
 static int producer_fifo = -1;
 static int consumer_fifo = -1;
@@ -308,7 +308,7 @@ static void ring_buffer_producer(void)
 
 	/* Let the user know that the test is running at low priority */
 	if (producer_fifo < 0 && consumer_fifo < 0 &&
-	    producer_nice == 19 && consumer_nice == 19)
+	    producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
 		trace_printk("WARNING!!! This test is running at lowest priority.\n");
 
 	trace_printk("Time:     %lld (usecs)\n", time);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 815c878f409b..24c1f2382557 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1600,15 +1600,31 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
+static struct ring_buffer *temp_buffer;
+
 struct ring_buffer_event *
 trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 			  struct ftrace_event_file *ftrace_file,
 			  int type, unsigned long len,
 			  unsigned long flags, int pc)
 {
+	struct ring_buffer_event *entry;
+
 	*current_rb = ftrace_file->tr->trace_buffer.buffer;
-	return trace_buffer_lock_reserve(*current_rb,
+	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
+	 * to store the trace event for the tigger to use. It's recusive
+	 * safe and will not be recorded anywhere.
+	 */
+	if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) {
+		*current_rb = temp_buffer;
+		entry = trace_buffer_lock_reserve(*current_rb,
+						  type, len, flags, pc);
+	}
+	return entry;
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
@@ -6494,11 +6510,16 @@ __init static int tracer_alloc_buffers(void)
 
 	raw_spin_lock_init(&global_trace.start_lock);
 
+	/* Used for event triggers */
+	temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
+	if (!temp_buffer)
+		goto out_free_cpumask;
+
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
-		goto out_free_cpumask;
+		goto out_free_temp_buffer;
 	}
 
 	if (global_trace.buffer_disabled)
@@ -6540,6 +6561,8 @@ __init static int tracer_alloc_buffers(void)
 
 	return 0;
 
+out_free_temp_buffer:
+	ring_buffer_free(temp_buffer);
 out_free_cpumask:
 	free_percpu(global_trace.trace_buffer.data);
 #ifdef CONFIG_TRACER_MAX_TRACE
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index e854f420e033..c894614de14d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -31,9 +31,25 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 	}
 
 	/* The ftrace function trace is allowed only for root. */
-	if (ftrace_event_is_function(tp_event) &&
-	    perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	if (ftrace_event_is_function(tp_event)) {
+		if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		/*
+		 * We don't allow user space callchains for  function trace
+		 * event, due to issues with page faults while tracing page
+		 * fault handler and its overall trickiness nature.
+		 */
+		if (!p_event->attr.exclude_callchain_user)
+			return -EINVAL;
+
+		/*
+		 * Same reason to disable user stack dump as for user space
+		 * callchains above.
+		 */
+		if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER)
+			return -EINVAL;
+	}
 
 	/* No tracing, just counting, so no obvious leak */
 	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e71ffd4eccb5..7b16d40bd64d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
 
 DEFINE_MUTEX(event_mutex);
 
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_common_fields);
 
@@ -1777,6 +1771,16 @@ static void trace_module_add_events(struct module *mod)
 {
 	struct ftrace_event_call **call, **start, **end;
 
+	if (!mod->num_trace_events)
+		return;
+
+	/* Don't add infrastructure for mods without tracepoints */
+	if (trace_module_has_bad_taint(mod)) {
+		pr_err("%s: module has bad taint, not creating trace events\n",
+		       mod->name);
+		return;
+	}
+
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7c3e3e72e2b6..ee0a5098ac43 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
+		char *type_str = #type"["__stringify(len)"]";		\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		mutex_lock(&event_storage_mutex);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
+		ret = trace_define_field(event_call, type_str, #item,	\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
 				 is_signed_type(type), filter_type);	\
-		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);