1 files changed, 55 insertions, 24 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 91874a95060d..5af2842dea96 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 /* Missed count stored at end */
 #define RB_MISSED_STORED        (1 << 30)
 
+#define RB_MISSED_FLAGS         (RB_MISSED_EVENTS|RB_MISSED_STORED)
+
 struct buffer_data_page {
         u64              time_stamp;    /* page time stamp */
         local_t          commit;        /* write committed index */
@@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
  */
 size_t ring_buffer_page_len(void *page)
 {
-        return local_read(&((struct buffer_data_page *)page)->commit)
+        struct buffer_data_page *bpage = page;
+
+        return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
                 + BUF_PAGE_HDR_SIZE;
 }
 
@@ -1799,12 +1803,6 @@ void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
 
-static __always_inline void *
-__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
-{
-        return bpage->data + index;
-}
-
 static __always_inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
 {
         return bpage->page->data + index;
@@ -2536,29 +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.
+ *
+ *  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.
  *
- *  Normal context.
- *  SoftIRQ context
- *  IRQ context
- *  NMI context
+ * (binary)
+ *  101 - 1 = 100
+ *  101 & 100 = 100 (clearing bit zero)
  *
- * 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.
+ *  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;
 }
@@ -2566,9 +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;
 }
 
 /**
@@ -4406,8 +4431,13 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
 {
         struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
         struct buffer_data_page *bpage = data;
+        struct page *page = virt_to_page(bpage);
         unsigned long flags;
 
+        /* If the page is still in use someplace else, we can't reuse it */
+        if (page_ref_count(page) > 1)
+                goto out;
+
         local_irq_save(flags);
         arch_spin_lock(&cpu_buffer->lock);
 
@@ -4419,6 +4449,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
         arch_spin_unlock(&cpu_buffer->lock);
         local_irq_restore(flags);
 
+ out:
         free_page((unsigned long)bpage);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);