linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Kan Liang <kan.liang@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-perf-users@vger.kernel.org
Subject: [PATCH 1/4] perf hist: Remove formats in hierarchy when cancel children
Date: Mon, 31 Mar 2025 00:37:19 -0700	[thread overview]
Message-ID: <20250331073722.4695-2-namhyung@kernel.org> (raw)
In-Reply-To: <20250331073722.4695-1-namhyung@kernel.org>

This is to support hierarchy options with custom output fields.
Currently perf_hpp__cancel_cumulate() only removes accumulated
overhead and latency fields from the global perf_hpp_list.

This is not used in the hierarchy mode because each evsel's hist
has its own separate hpp_list.  So it needs to remove the fields
from the lists too.  Pass evlist to the function so that it can
iterate the evsels.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-report.c |  2 +-
 tools/perf/builtin-top.c    |  2 +-
 tools/perf/ui/hist.c        | 20 +++++++++++++++++++-
 tools/perf/util/hist.h      |  2 +-
 4 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b030ce72e13ea8d1..c9138e1379808097 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -413,7 +413,7 @@ static int report__setup_sample_type(struct report *rep)
 		/* Silently ignore if callchain is missing */
 		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 			symbol_conf.cumulate_callchain = false;
-			perf_hpp__cancel_cumulate();
+			perf_hpp__cancel_cumulate(session->evlist);
 		}
 	}
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1061f4eebc3f6414..f9f31391bddba074 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1790,7 +1790,7 @@ int cmd_top(int argc, const char **argv)
 
 	if (!callchain_param.enabled) {
 		symbol_conf.cumulate_callchain = false;
-		perf_hpp__cancel_cumulate();
+		perf_hpp__cancel_cumulate(top.evlist);
 	}
 
 	if (symbol_conf.cumulate_callchain && !callchain_param.order_set)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index ae3b7fe1dadc8f22..1d3f944ed35ed152 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -699,9 +699,10 @@ static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 	fmt_free(format);
 }
 
-void perf_hpp__cancel_cumulate(void)
+void perf_hpp__cancel_cumulate(struct evlist *evlist)
 {
 	struct perf_hpp_fmt *fmt, *acc, *ovh, *acc_lat, *tmp;
+	struct evsel *evsel;
 
 	if (is_strict_order(field_order))
 		return;
@@ -719,6 +720,23 @@ void perf_hpp__cancel_cumulate(void)
 		if (fmt_equal(ovh, fmt))
 			fmt->name = "Overhead";
 	}
+
+	evlist__for_each_entry(evlist, evsel) {
+		struct hists *hists = evsel__hists(evsel);
+		struct perf_hpp_list_node *node;
+
+		list_for_each_entry(node, &hists->hpp_formats, list) {
+			perf_hpp_list__for_each_format_safe(&node->hpp, fmt, tmp) {
+				if (fmt_equal(acc, fmt) || fmt_equal(acc_lat, fmt)) {
+					perf_hpp__column_unregister(fmt);
+					continue;
+				}
+
+				if (fmt_equal(ovh, fmt))
+					fmt->name = "Overhead";
+			}
+		}
+	}
 }
 
 void perf_hpp__cancel_latency(void)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 317d06cca8b88e3e..8cc94928fcb35a5b 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -581,7 +581,7 @@ enum {
 };
 
 void perf_hpp__init(void);
-void perf_hpp__cancel_cumulate(void);
+void perf_hpp__cancel_cumulate(struct evlist *evlist);
 void perf_hpp__cancel_latency(void);
 void perf_hpp__setup_output_field(struct perf_hpp_list *list);
 void perf_hpp__reset_output_field(struct perf_hpp_list *list);
-- 
2.49.0


  reply	other threads:[~2025-03-31  7:37 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-31  7:37 [PATCH 0/4] perf report: Support custom output fields in hierarchy mode Namhyung Kim
2025-03-31  7:37 ` Namhyung Kim [this message]
2025-03-31  7:37 ` [PATCH 2/4] perf hist: Remove formats in hierarchy when cancel latency Namhyung Kim
2025-03-31  7:37 ` [PATCH 3/4] perf hist: Set levels in output_field_add() Namhyung Kim
2025-03-31  7:37 ` [PATCH 4/4] perf hist: Allow custom output fields in hierarchy mode Namhyung Kim
2025-04-23 20:46 ` [PATCH 0/4] perf report: Support " Arnaldo Carvalho de Melo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250331073722.4695-2-namhyung@kernel.org \
    --to=namhyung@kernel.org \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=irogers@google.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).