3 files changed, 60 insertions, 19 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 904c952ac383..f54dc62b599c 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -355,7 +355,7 @@ config PROFILE_ANNOTATED_BRANCHES
 	  on if you need to profile the system's use of these macros.
 
 config PROFILE_ALL_BRANCHES
-	bool "Profile all if conditionals"
+	bool "Profile all if conditionals" if !FORTIFY_SOURCE
 	select TRACE_BRANCH_PROFILING
 	help
 	  This tracer profiles all branch conditions. Every if ()
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9ab18995ff1e..5af2842dea96 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2534,29 +2534,58 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * The lock and unlock are done within a preempt disable section.
  * The current_context per_cpu variable can only be modified
  * by the current task between lock and unlock. But it can
- * be modified more than once via an interrupt. There are four
- * different contexts that we need to consider.
+ * be modified more than once via an interrupt. To pass this
+ * information from the lock to the unlock without having to
+ * access the 'in_interrupt()' functions again (which do show
+ * a bit of overhead in something as critical as function tracing,
+ * we use a bitmask trick.
  *
- *  Normal context.
- *  SoftIRQ context
- *  IRQ context
- *  NMI context
+ *  bit 0 =  NMI context
+ *  bit 1 =  IRQ context
+ *  bit 2 =  SoftIRQ context
+ *  bit 3 =  normal context.
  *
- * If for some reason the ring buffer starts to recurse, we
- * only allow that to happen at most 4 times (one for each
- * context). If it happens 5 times, then we consider this a
- * recusive loop and do not let it go further.
+ * This works because this is the order of contexts that can
+ * preempt other contexts. A SoftIRQ never preempts an IRQ
+ * context.
+ *
+ * When the context is determined, the corresponding bit is
+ * checked and set (if it was set, then a recursion of that context
+ * happened).
+ *
+ * On unlock, we need to clear this bit. To do so, just subtract
+ * 1 from the current_context and AND it to itself.
+ *
+ * (binary)
+ *  101 - 1 = 100
+ *  101 & 100 = 100 (clearing bit zero)
+ *
+ *  1010 - 1 = 1001
+ *  1010 & 1001 = 1000 (clearing bit 1)
+ *
+ * The least significant bit can be cleared this way, and it
+ * just so happens that it is the same bit corresponding to
+ * the current context.
  */
 
 static __always_inline int
 trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	if (cpu_buffer->current_context >= 4)
+	unsigned int val = cpu_buffer->current_context;
+	unsigned long pc = preempt_count();
+	int bit;
+
+	if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
+		bit = RB_CTX_NORMAL;
+	else
+		bit = pc & NMI_MASK ? RB_CTX_NMI :
+			pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
+
+	if (unlikely(val & (1 << bit)))
 		return 1;
 
-	cpu_buffer->current_context++;
-	/* Interrupts must see this update */
-	barrier();
+	val |= (1 << bit);
+	cpu_buffer->current_context = val;
 
 	return 0;
 }
@@ -2564,9 +2593,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 static __always_inline void
 trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	/* Don't let the dec leak out */
-	barrier();
-	cpu_buffer->current_context--;
+	cpu_buffer->current_context &= cpu_buffer->current_context - 1;
 }
 
 /**
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index ec0f9aa4e151..1b87157edbff 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2213,6 +2213,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 {
 	struct trace_event_call *call, *p;
 	const char *last_system = NULL;
+	bool first = false;
 	int last_i;
 	int i;
 
@@ -2220,15 +2221,28 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
 		/* events are usually grouped together with systems */
 		if (!last_system || call->class->system != last_system) {
+			first = true;
 			last_i = 0;
 			last_system = call->class->system;
 		}
 
+		/*
+		 * Since calls are grouped by systems, the likelyhood that the
+		 * next call in the iteration belongs to the same system as the
+		 * previous call is high. As an optimization, we skip seaching
+		 * for a map[] that matches the call's system if the last call
+		 * was from the same system. That's what last_i is for. If the
+		 * call has the same system as the previous call, then last_i
+		 * will be the index of the first map[] that has a matching
+		 * system.
+		 */
 		for (i = last_i; i < len; i++) {
 			if (call->class->system == map[i]->system) {
 				/* Save the first system if need be */
-				if (!last_i)
+				if (first) {
 					last_i = i;
+					first = false;
+				}
 				update_event_printk(call, map[i]);
 			}
 		}