ring-buffer: User context bit recursion checking

Using context bit recursion checking, we can help increase the
performance of the ring buffer.

Before this patch:

 # echo function > /debug/tracing/current_tracer
 # for i in `seq 10`; do ./hackbench 50; done
Time: 10.285
Time: 10.407
Time: 10.243
Time: 10.372
Time: 10.380
Time: 10.198
Time: 10.272
Time: 10.354
Time: 10.248
Time: 10.253

(average: 10.3012)

Now we have:

 # echo function > /debug/tracing/current_tracer
 # for i in `seq 10`; do ./hackbench 50; done
Time: 9.712
Time: 9.824
Time: 9.861
Time: 9.827
Time: 9.962
Time: 9.905
Time: 9.886
Time: 10.088
Time: 9.861
Time: 9.834

(average: 9.876)

 a 4% savings!

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

2 files changed, 67 insertions, 31 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6ff9cc4658ed..481e26269281 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2432,41 +2432,76 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 
 #ifdef CONFIG_TRACING
 
-#define TRACE_RECURSIVE_DEPTH 16
+/*
+ * 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. 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.
+ *
+ *  bit 0 =  NMI context
+ *  bit 1 =  IRQ context
+ *  bit 2 =  SoftIRQ context
+ *  bit 3 =  normal context.
+ *
+ * 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 DEFINE_PER_CPU(unsigned int, current_context);
 
-/* Keep this code out of the fast path cache */
-static noinline void trace_recursive_fail(void)
+static __always_inline int trace_recursive_lock(void)
 {
-        /* Disable all tracing before we do anything else */
-        tracing_off_permanent();
-
-        printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
-                    "HC[%lu]:SC[%lu]:NMI[%lu]\n",
-                    trace_recursion_buffer(),
-                    hardirq_count() >> HARDIRQ_SHIFT,
-                    softirq_count() >> SOFTIRQ_SHIFT,
-                    in_nmi());
+        unsigned int val = this_cpu_read(current_context);
+        int bit;
 
-        WARN_ON_ONCE(1);
-}
-
-static inline int trace_recursive_lock(void)
-{
-        trace_recursion_inc();
+        if (in_interrupt()) {
+                if (in_nmi())
+                        bit = 0;
+                else if (in_irq())
+                        bit = 1;
+                else
+                        bit = 2;
+        } else
+                bit = 3;
 
-        if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH))
-                return 0;
+        if (unlikely(val & (1 << bit)))
+                return 1;
 
-        trace_recursive_fail();
+        val |= (1 << bit);
+        this_cpu_write(current_context, val);
 
-        return -1;
+        return 0;
 }
 
-static inline void trace_recursive_unlock(void)
+static __always_inline void trace_recursive_unlock(void)
 {
-        WARN_ON_ONCE(!trace_recursion_buffer());
+        unsigned int val = this_cpu_read(current_context);
 
-        trace_recursion_dec();
+        val--;
+        val &= this_cpu_read(current_context);
+        this_cpu_write(current_context, val);
 }
 
 #else
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c203a51dd412..04a2c7ab1735 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -291,11 +291,6 @@ struct tracer {
 
 
 /* Only current can touch trace_recursion */
-#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
-#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
-
-/* Ring buffer has the 10 LSB bits to count */
-#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
 
 /*
  * For function tracing recursion:
@@ -323,7 +318,13 @@ struct tracer {
  * caller, and we can skip the current check.
  */
 enum {
-        TRACE_FTRACE_BIT = 11,
+        TRACE_BUFFER_BIT,
+        TRACE_BUFFER_NMI_BIT,
+        TRACE_BUFFER_IRQ_BIT,
+        TRACE_BUFFER_SIRQ_BIT,
+
+        /* Start of function recursion bits */
+        TRACE_FTRACE_BIT,
         TRACE_FTRACE_NMI_BIT,
         TRACE_FTRACE_IRQ_BIT,
         TRACE_FTRACE_SIRQ_BIT,