ring-buffer: add counters for commit overrun and nmi dropped entries

The WARN_ON in the ring buffer when a commit is preempted and the
buffer is filled by preceding writes can happen in normal operations.
The WARN_ON makes it look like a bug, not to mention, because
it does not stop tracing and calls printk which can also recurse, this
is prone to deadlock (the WARN_ON is not in a position to recurse).

This patch removes the WARN_ON and replaces it with a counter that
can be retrieved by a tracer. This counter is called commit_overrun.

While at it, I added a nmi_dropped counter to count any time an NMI entry
is dropped because the NMI could not take the spinlock.

[ Impact: prevent deadlock by printing normal case warning ]

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

2 files changed, 51 insertions, 3 deletions

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 1c2f80911fbe..f1345828c7c5 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -153,6 +153,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer);
 unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3e86da9b2a09..26e1359fe193 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -402,6 +402,8 @@ struct ring_buffer_per_cpu {
         struct buffer_page              *tail_page;     /* write to tail */
         struct buffer_page              *commit_page;   /* committed pages */
         struct buffer_page              *reader_page;
+        unsigned long                   nmi_dropped;
+        unsigned long                   commit_overrun;
         unsigned long                   overrun;
         unsigned long                   entries;
         u64                             write_stamp;
@@ -1216,8 +1218,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
                  * simply fail.
                  */
                 if (unlikely(in_nmi())) {
-                        if (!__raw_spin_trylock(&cpu_buffer->lock))
+                        if (!__raw_spin_trylock(&cpu_buffer->lock)) {
+                                cpu_buffer->nmi_dropped++;
                                 goto out_reset;
+                        }
                 } else
                         __raw_spin_lock(&cpu_buffer->lock);
 
@@ -1238,8 +1242,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
                  * about it.
                  */
                 if (unlikely(next_page == commit_page)) {
-                        /* This can easily happen on small ring buffers */
-                        WARN_ON_ONCE(buffer->pages > 2);
+                        cpu_buffer->commit_overrun++;
                         goto out_reset;
                 }
 
@@ -1926,6 +1929,47 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
 /**
+ * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        unsigned long ret;
+
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
+                return 0;
+
+        cpu_buffer = buffer->buffers[cpu];
+        ret = cpu_buffer->nmi_dropped;
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
+
+/**
+ * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long
+ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        unsigned long ret;
+
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
+                return 0;
+
+        cpu_buffer = buffer->buffers[cpu];
+        ret = cpu_buffer->commit_overrun;
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);
+
+/**
  * ring_buffer_entries - get the number of entries in a buffer
  * @buffer: The ring buffer
  *
@@ -2595,6 +2639,8 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
         local_set(&cpu_buffer->reader_page->page->commit, 0);
         cpu_buffer->reader_page->read = 0;
 
+        cpu_buffer->nmi_dropped = 0;
+        cpu_buffer->commit_overrun = 0;
         cpu_buffer->overrun = 0;
         cpu_buffer->entries = 0;