perf thread: Save previous sample for LBR stitching approach

To retrieve the overwritten LBRs from previous sample for LBR stitching
approach, perf has to save the previous sample.

Only allocate the struct lbr_stitch once, when LBR stitching approach is
enabled and kernel supports hw_idx.

Signed-off-by: Kan Liang <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexey Budankov <[email protected]>
Cc: Mathieu Poirier <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Pavel Gerasimov <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Vitaly Slobodskoy <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
[ Use zalloc()/zfree() for thread->lbr_stitch ]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: Kan Liang

tools/perf/util/machine.c

@@ -2292,6 +2292,21 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
 	return 0;
 }
 
+static bool alloc_lbr_stitch(struct thread *thread)
+{
+	if (thread->lbr_stitch)
+		return true;
+
+	thread->lbr_stitch = zalloc(sizeof(*thread->lbr_stitch));
+	if (!thread->lbr_stitch)
+		goto err;
+
+err:
+	pr_warning("Failed to allocate space for stitched LBRs. Disable LBR stitch\n");
+	thread->lbr_stitch_enable = false;
+	return false;
+}
+
 /*
  * Recolve LBR callstack chain sample
  * Return:
@@ -2308,6 +2323,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 {
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = min(max_stack, (int)chain->nr), i;
+	struct lbr_stitch *lbr_stitch;
 	u64 branch_from = 0;
 	int err;
 
@@ -2320,6 +2336,13 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	if (i == chain_nr)
 		return 0;
 
+	if (thread->lbr_stitch_enable && !sample->no_hw_idx &&
+	    alloc_lbr_stitch(thread)) {
+		lbr_stitch = thread->lbr_stitch;
+
+		memcpy(&lbr_stitch->prev_sample, sample, sizeof(*sample));
+	}
+
 	if (callchain_param.order == ORDER_CALLEE) {
 		/* Add kernel ip */
 		err = lbr_callchain_add_kernel_ip(thread, cursor, sample,

tools/perf/util/thread.c

@@ -111,6 +111,7 @@ void thread__delete(struct thread *thread)
 
 	exit_rwsem(&thread->namespaces_lock);
 	exit_rwsem(&thread->comm_lock);
+	thread__free_stitch_list(thread);
 	free(thread);
 }
 

tools/perf/util/thread.h

@@ -5,6 +5,7 @@
 #include <linux/refcount.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
@@ -13,13 +14,18 @@
 #include <strlist.h>
 #include <intlist.h>
 #include "rwsem.h"
+#include "event.h"
 
 struct addr_location;
 struct map;
 struct perf_record_namespaces;
 struct thread_stack;
 struct unwind_libunwind_ops;
 
+struct lbr_stitch {
+	struct perf_sample		prev_sample;
+};
+
 struct thread {
 	union {
 		struct rb_node	 rb_node;
@@ -49,6 +55,7 @@ struct thread {
 
 	/* LBR call stack stitch */
 	bool			lbr_stitch_enable;
+	struct lbr_stitch	*lbr_stitch;
 };
 
 struct machine;
@@ -145,4 +152,9 @@ static inline bool thread__is_filtered(struct thread *thread)
 	return false;
 }
 
+static inline void thread__free_stitch_list(struct thread *thread)
+{
+	zfree(&thread->lbr_stitch);
+}
+
 #endif	/* __PERF_THREAD_H */