From ec06f9b9b23f29c8f25367fc43c85c327229d5ca Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 22 Sep 2016 17:36:45 +0200 Subject: [PATCH] perf c2c report: Add cacheline hists processing Store cacheline related entries in nested hist object for each cacheline data. Nested entries are sorted by 'offset' within related cacheline. We will allow specific sort keys to be configured for nested cacheline data entries in following patches. Signed-off-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Don Zickus Cc: Joe Mario Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1474558645-19956-18-git-send-email-jolsa@kernel.org [ he__get_hists() should return NULL when c2c_hists__init() fails ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-c2c.c | 92 +++++++++++++++++++++++++++++++++++++--- 1 file changed, 86 insertions(+), 6 deletions(-) diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 29fb9573e292..df413b564361 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -61,6 +61,34 @@ static struct hist_entry_ops c2c_entry_ops = { .free = c2c_he_free, }; +static int c2c_hists__init(struct c2c_hists *hists, + const char *sort); + +static struct hists* +he__get_hists(struct hist_entry *he, + const char *sort) +{ + struct c2c_hist_entry *c2c_he; + struct c2c_hists *hists; + int ret; + + c2c_he = container_of(he, struct c2c_hist_entry, he); + if (c2c_he->hists) + return &c2c_he->hists->hists; + + hists = c2c_he->hists = zalloc(sizeof(*hists)); + if (!hists) + return NULL; + + ret = c2c_hists__init(hists, sort); + if (ret) { + free(hists); + return NULL; + } + + return &hists->hists; +} + static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -70,7 +98,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct hists *hists = &c2c.hists.hists; struct hist_entry *he; struct addr_location al; - struct mem_info *mi; + struct mem_info *mi, *mi_dup; int ret; if (machine__resolve(machine, &al, sample) < 0) { @@ -83,19 +111,50 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, if (mi == NULL) return -ENOMEM; + mi_dup = memdup(mi, sizeof(*mi)); + if (!mi_dup) + goto free_mi; + he = hists__add_entry_ops(hists, &c2c_entry_ops, &al, NULL, NULL, mi, sample, true); - if (he == NULL) { - free(mi); - return -ENOMEM; - } + if (he == NULL) + goto free_mi_dup; hists__inc_nr_samples(hists, he->filtered); ret = hist_entry__append_callchain(he, sample); + if (!ret) { + mi = mi_dup; + + mi_dup = memdup(mi, sizeof(*mi)); + if (!mi_dup) + goto free_mi; + + hists = he__get_hists(he, "offset"); + if (!hists) + goto free_mi_dup; + + he = hists__add_entry_ops(hists, &c2c_entry_ops, + &al, NULL, NULL, mi, + sample, true); + if (he == NULL) + goto free_mi_dup; + + hists__inc_nr_samples(hists, he->filtered); + ret = hist_entry__append_callchain(he, sample); + } + +out: addr_location__put(&al); return ret; + +free_mi_dup: + free(mi_dup); +free_mi: + free(mi); + ret = -ENOMEM; + goto out; } static struct perf_c2c c2c = { @@ -400,6 +459,27 @@ static int c2c_hists__reinit(struct c2c_hists *c2c_hists, return hpp_list__parse(&c2c_hists->list, output, sort); } +static int filter_cb(struct hist_entry *he __maybe_unused) +{ + return 0; +} + +static int resort_cl_cb(struct hist_entry *he) +{ + struct c2c_hist_entry *c2c_he; + struct c2c_hists *c2c_hists; + + c2c_he = container_of(he, struct c2c_hist_entry, he); + c2c_hists = c2c_he->hists; + + if (c2c_hists) { + hists__collapse_resort(&c2c_hists->hists, NULL); + hists__output_resort_cb(&c2c_hists->hists, NULL, filter_cb); + } + + return 0; +} + static int perf_c2c__report(int argc, const char **argv) { struct perf_session *session; @@ -458,7 +538,7 @@ static int perf_c2c__report(int argc, const char **argv) ui_progress__init(&prog, c2c.hists.hists.nr_entries, "Sorting..."); hists__collapse_resort(&c2c.hists.hists, NULL); - hists__output_resort(&c2c.hists.hists, &prog); + hists__output_resort_cb(&c2c.hists.hists, &prog, resort_cl_cb); ui_progress__finish(); -- 2.39.5