[PATCH 49/60] perf machine: Refine the function for LBR call stack reconstruction
From: Arnaldo Carvalho de Melo
Date: Mon Apr 20 2020 - 07:57:08 EST
From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
LBR only collect the user call stack. To reconstruct a call stack, both
kernel call stack and user call stack are required. The function
resolve_lbr_callchain_sample() mix the kernel call stack and user call
stack.
Now, with the help of HW idx, perf tool can reconstruct a more complete
call stack by adding some user call stack from previous sample. However,
current implementation is hard to be extended to support it.
Current code path for resolve_lbr_callchain_sample()
for (j = 0; j < mix_chain_nr; j++) {
if (ORDER_CALLEE) {
if (kernel callchain)
Fill callchain info
else if (LBR callchain)
Fill callchain info
} else {
if (LBR callchain)
Fill callchain info
else if (kernel callchain)
Fill callchain info
}
add_callchain_ip();
}
With the patch,
if (ORDER_CALLEE) {
for (j = 0; j < NUM of kernel callchain) {
Fill callchain info
add_callchain_ip();
}
for (; j < mix_chain_nr) {
Fill callchain info
add_callchain_ip();
}
} else {
for (; j < NUM of LBR callchain) {
Fill callchain info
add_callchain_ip();
}
for (j = 0; j < mix_chain_nr) {
Fill callchain info
add_callchain_ip();
}
}
No functional changes.
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Acked-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Pavel Gerasimov <pavel.gerasimov@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ravi Bangoria <ravi.bangoria@xxxxxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@xxxxxxxxx>
Link: http://lore.kernel.org/lkml/20200319202517.23423-7-kan.liang@xxxxxxxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/util/machine.c | 111 ++++++++++++++++++++++++++------------
1 file changed, 76 insertions(+), 35 deletions(-)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index be1bd9277471..0da540e6f803 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2214,6 +2214,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
bool branch;
struct branch_flags *flags;
int mix_chain_nr;
+ int err;
for (i = 0; i < chain_nr; i++) {
if (chain->ips[i] == PERF_CONTEXT_USER)
@@ -2239,50 +2240,90 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
*/
mix_chain_nr = i + 1 + lbr_nr + 1;
- for (j = 0; j < mix_chain_nr; j++) {
- int err;
-
- branch = false;
- flags = NULL;
-
- if (callchain_param.order == ORDER_CALLEE) {
- if (j < i + 1)
- ip = chain->ips[j];
- else if (j > i + 1) {
- k = j - i - 2;
- ip = entries[k].from;
- branch = true;
- flags = &entries[k].flags;
- } else {
- ip = entries[0].to;
- branch = true;
- flags = &entries[0].flags;
- branch_from = entries[0].from;
- }
- } else {
- if (j < lbr_nr) {
- k = lbr_nr - j - 1;
- ip = entries[k].from;
- branch = true;
- flags = &entries[k].flags;
- } else if (j > lbr_nr)
- ip = chain->ips[i + 1 - (j - lbr_nr)];
- else {
- ip = entries[0].to;
- branch = true;
- flags = &entries[0].flags;
- branch_from = entries[0].from;
- }
+ if (callchain_param.order == ORDER_CALLEE) {
+ /* Add kernel ip */
+ for (j = 0; j < i + 1; j++) {
+ ip = chain->ips[j];
+ branch = false;
+ flags = NULL;
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ branch, flags, NULL,
+ branch_from);
+ if (err)
+ goto error;
}
+ /* Add LBR ip from first entries.to */
+ ip = entries[0].to;
+ branch = true;
+ flags = &entries[0].flags;
+ branch_from = entries[0].from;
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ branch, flags, NULL,
+ branch_from);
+ if (err)
+ goto error;
+ /* Add LBR ip from entries.from one by one. */
+ for (j = i + 2; j < mix_chain_nr; j++) {
+ k = j - i - 2;
+ ip = entries[k].from;
+ branch = true;
+ flags = &entries[k].flags;
+
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ branch, flags, NULL,
+ branch_from);
+ if (err)
+ goto error;
+ }
+ } else {
+ /* Add LBR ip from entries.from one by one. */
+ for (j = 0; j < lbr_nr; j++) {
+ k = lbr_nr - j - 1;
+ ip = entries[k].from;
+ branch = true;
+ flags = &entries[k].flags;
+
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ branch, flags, NULL,
+ branch_from);
+ if (err)
+ goto error;
+ }
+
+ /* Add LBR ip from first entries.to */
+ ip = entries[0].to;
+ branch = true;
+ flags = &entries[0].flags;
+ branch_from = entries[0].from;
err = add_callchain_ip(thread, cursor, parent,
root_al, &cpumode, ip,
branch, flags, NULL,
branch_from);
if (err)
- return (err < 0) ? err : 0;
+ goto error;
+
+ /* Add kernel ip */
+ for (j = lbr_nr + 1; j < mix_chain_nr; j++) {
+ ip = chain->ips[i + 1 - (j - lbr_nr)];
+ branch = false;
+ flags = NULL;
+ err = add_callchain_ip(thread, cursor, parent,
+ root_al, &cpumode, ip,
+ branch, flags, NULL,
+ branch_from);
+ if (err)
+ goto error;
+ }
}
return 1;
+
+error:
+ return (err < 0) ? err : 0;
}
static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
--
2.21.1