tracing: Save off entry when peeking at next entry

In order to have the iterator read the buffer even when it's still updating,
it requires that the ring buffer iterator saves each event in a separate
location outside the ring buffer such that its use is immutable.

There's one use case that saves off the event returned from the ring buffer
interator and calls it again to look at the next event, before going back to
use the first event. As the ring buffer iterator will only have a single
copy, this use case will no longer be supported.

Instead, have the one use case create its own buffer to store the first
event when looking at the next event. This way, when looking at the first
event again, it wont be corrupted by the second read.

Link: http://lkml.kernel.org/r/[email protected]

Signed-off-by: Steven Rostedt (VMware) <[email protected]>

Author: rostedt

include/linux/trace_events.h

@@ -85,6 +85,8 @@ struct trace_iterator {
 	struct mutex		mutex;
 	struct ring_buffer_iter	**buffer_iter;
 	unsigned long		iter_flags;
+	void			*temp;	/* temp holder */
+	unsigned int		temp_size;
 
 	/* trace_seq for __print_flags() and __print_symbolic() etc. */
 	struct trace_seq	tmp_seq;

kernel/trace/trace.c

@@ -3466,7 +3466,31 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts)
 {
-	return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
+	/* __find_next_entry will reset ent_size */
+	int ent_size = iter->ent_size;
+	struct trace_entry *entry;
+
+	/*
+	 * The __find_next_entry() may call peek_next_entry(), which may
+	 * call ring_buffer_peek() that may make the contents of iter->ent
+	 * undefined. Need to copy iter->ent now.
+	 */
+	if (iter->ent && iter->ent != iter->temp) {
+		if (!iter->temp || iter->temp_size < iter->ent_size) {
+			kfree(iter->temp);
+			iter->temp = kmalloc(iter->ent_size, GFP_KERNEL);
+			if (!iter->temp)
+				return NULL;
+		}
+		memcpy(iter->temp, iter->ent, iter->ent_size);
+		iter->temp_size = iter->ent_size;
+		iter->ent = iter->temp;
+	}
+	entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts);
+	/* Put back the original ent_size */
+	iter->ent_size = ent_size;
+
+	return entry;
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
@@ -4197,6 +4221,18 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	if (!iter->buffer_iter)
 		goto release;
 
+	/*
+	 * trace_find_next_entry() may need to save off iter->ent.
+	 * It will place it into the iter->temp buffer. As most
+	 * events are less than 128, allocate a buffer of that size.
+	 * If one is greater, then trace_find_next_entry() will
+	 * allocate a new buffer to adjust for the bigger iter->ent.
+	 * It's not critical if it fails to get allocated here.
+	 */
+	iter->temp = kmalloc(128, GFP_KERNEL);
+	if (iter->temp)
+		iter->temp_size = 128;
+
 	/*
 	 * We make a copy of the current tracer to avoid concurrent
 	 * changes on it while we are reading.
@@ -4269,6 +4305,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
  fail:
 	mutex_unlock(&trace_types_lock);
 	kfree(iter->trace);
+	kfree(iter->temp);
 	kfree(iter->buffer_iter);
 release:
 	seq_release_private(inode, file);
@@ -4344,6 +4381,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 
 	mutex_destroy(&iter->mutex);
 	free_cpumask_var(iter->started);
+	kfree(iter->temp);
 	kfree(iter->trace);
 	kfree(iter->buffer_iter);
 	seq_release_private(inode, file);

kernel/trace/trace_output.c

@@ -617,22 +617,19 @@ int trace_print_context(struct trace_iterator *iter)
 
 int trace_print_lat_context(struct trace_iterator *iter)
 {
+	struct trace_entry *entry, *next_entry;
 	struct trace_array *tr = iter->tr;
-	/* trace_find_next_entry will reset ent_size */
-	int ent_size = iter->ent_size;
 	struct trace_seq *s = &iter->seq;
-	u64 next_ts;
-	struct trace_entry *entry = iter->ent,
-			   *next_entry = trace_find_next_entry(iter, NULL,
-							       &next_ts);
 	unsigned long verbose = (tr->trace_flags & TRACE_ITER_VERBOSE);
+	u64 next_ts;
 
-	/* Restore the original ent_size */
-	iter->ent_size = ent_size;
-
+	next_entry = trace_find_next_entry(iter, NULL, &next_ts);
 	if (!next_entry)
 		next_ts = iter->ts;
 
+	/* trace_find_next_entry() may change iter->ent */
+	entry = iter->ent;
+
 	if (verbose) {
 		char comm[TASK_COMM_LEN];