lkml.org 
[lkml]   [2014]   [Jan]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 7/9] perf, tools: Add overlap detection for report branch-call-stack mode
Date
From: Andi Kleen <ak@linux.intel.com>

Add a simple heuristic to detect overlap of LBR entries and the call
stack when in lbr-as-callgraph mode. The return address in the
normal callstack is one off compared to the from entry in the
branch stack. Handle this with a simple "assume call instruction
is not longer than 8 bytes" heuristic. With that we can remove
any redundant call in the callstack that is already in the branch
stack.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/util/machine.c | 21 +++++++++++++++------
1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 853639c..1f167fe 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1349,6 +1349,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
int chain_nr = min(max_stack, (int)chain->nr);
int i;
int err;
+ int first_call = 0;

callchain_cursor_reset(&callchain_cursor);

@@ -1362,8 +1363,6 @@ static int machine__resolve_callchain_sample(struct machine *machine,
* Limitations for now:
* - No extra filters
* - No annotations (should annotate somehow)
- * - When the sample is near the beginning of the function
- * we may overlap with the real callstack.
*/

if (branch->nr > PERF_MAX_BRANCH_DEPTH) {
@@ -1372,13 +1371,23 @@ static int machine__resolve_callchain_sample(struct machine *machine,
}

if (callchain_param.branch_callstack) {
- int nr = min(max_stack, branch->nr);
+ int nr = min(max_stack, (int)branch->nr);
struct branch_entry be[nr];

for (i = 0; i < nr; i++) {
- if (callchain_param.order == ORDER_CALLEE)
+ if (callchain_param.order == ORDER_CALLEE) {
be[i] = branch->entries[i];
- else
+ /*
+ * Check for overlap into the callchain.
+ * The return address is one off compared to
+ * the branch entry. To adjust for this
+ * assume the calling instruction is not longer
+ * than 8 bytes.
+ */
+ if (be[i].from < chain->ips[first_call] &&
+ be[i].from >= chain->ips[first_call] - 8)
+ first_call++;
+ } else
be[i] = branch->entries[branch->nr - i - 1];
}

@@ -1405,7 +1414,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
return 0;
}

- for (i = 0; i < chain_nr; i++) {
+ for (i = first_call; i < chain_nr; i++) {
u64 ip;

if (callchain_param.order == ORDER_CALLEE)
--
1.8.3.1


\
 
 \ /
  Last update: 2014-01-11 21:21    [W:0.428 / U:0.084 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site