[PATCH v5 0/9] perf c2c: add a function view

[PATCH v5 0/9] perf c2c: add a function view

[Jiebin Sun]

This series adds a new "function view" to perf c2c report, on top of the
existing cacheline view. Existing cacheline-view data and operations remain
unchanged; TAB adds access to a complementary way to inspect the same
cache-to-cache (C2C) data.

v1: https://lore.kernel.org/linux-perf-users/20260626070355.1556721-1-jiebin.sun@intel.com/
v2: https://lore.kernel.org/linux-perf-users/20260710084247.3576706-1-jiebin.sun@intel.com/
v3: https://lore.kernel.org/linux-perf-users/20260717020530.1645123-1-jiebin.sun@intel.com/
v4: https://lore.kernel.org/linux-perf-users/20260724095842.995920-1-jiebin.sun@intel.com/

Changes since v4
================

  - Rebase onto perf-tools-next at 0d40fedcd1b9.

  - Require `iaddr` in --coalesce before entering the function view;
    without it, coalesced samples cannot be reliably attributed.

  - Reuse each source cacheline's existing index as the level-3 identity,
    so same-address sources no longer merge and 'd' finds the original
    entry, without adding fields to the shared C2C structures.

  - Keep same-function reader/writer pairs, which the coalesced view cannot
    reliably tell apart from cross-thread contention.

  - Robustness and cleanup: build the hierarchy only from filtered
    cachelines with a lightweight entry allocator; explicit
    mem_info__new() handling; a local bound in the symbol renderer; a
    NULL-map guard; deterministic tie-breaks; function-view-local row
    recounting; Ctrl-C as an exit key; and expanded man-page docs.

No intended change to cacheline-view data, existing cacheline operations,
or --stdio output.

Changes since v3
================

Reworked the function view into a true function-centric hierarchy, as
discussed with Namhyung:

  - Level 1 is the read-side function itself, aggregating all of its code
    addresses into one entry and sorting by Cycles %.

  - Level 2 is the contending function that writes the shared lines,
    aggregated across cachelines and sorted by store count. Level 3 is the
    specific cachelines.

  - Dedicated code-address and offset columns were removed from the main
    view. Verbose function formatting can still include a representative
    code address, and full code-address information remains available in
    the per-cacheline detail view ('d').

  - Lower-level entries are indented like the normal perf report hierarchy
    view, and entries with no contending writer are pruned.

  - Reorganized the series from 14 mechanical patches into 9 logically
    self-contained patches.

Changes since v2
================

  - Prefix helpers exported from builtin-c2c.c with c2c_, as suggested by
    Namhyung.

Changes since v1
================

  - Add a worked man-page example, as suggested by Namhyung.

In the perf c2c TUI, press TAB in the cacheline view to switch to the
function view. It presents a three-level hierarchy:

  Level 1: read-side function, sorted by Cycles %
  Level 2: functions writing the shared lines, sorted by store count
  Level 3: cachelines where the two functions contend

For example, with dequeue_pushable_task expanded to its level-2 writers and
two of those writers expanded to their level-3 cachelines:

  Shared Data Functions Table     (19 entries, sorted on Cycles %)
     Cycles    Store
          %    count  Function / Contending function / Cacheline
  ----------------------------------------------------------------------
  +  35.67%      876  + [k] cpupri_set
  +  24.31%      424  + [k] pull_rt_task
  -  16.53%      555  - [k] dequeue_pushable_task
                 145    - [k] pull_rt_task
                 145        0xff2d0082809da080
                 139    - [k] enqueue_pushable_task
                  70        0xff2d00a2071f9640
                  69        0xff2d0082809da000

A level-1 store count decomposes into its level-2 writers, and each writer's
count decomposes into its level-3 cachelines (here 145 = 145, 139 = 70 + 69).

Keys in the function view:

  TAB/ESC/q/Ctrl-C   return to the cacheline view
  d                  show details for the selected level-3 cacheline
  e / +              expand / collapse the selected entry
  ?                  help

The function view is a separate hist_browser in
tools/perf/ui/browsers/c2c-function.c. Shared types and helpers used by
both views are factored out of builtin-c2c.c into c2c.h. The hierarchy is
constructed from the existing cacheline histograms into dedicated hists
and rendered with custom column formatters.

Testing: each commit builds individually; the full series builds with and
without SLANG support; perf test c2c passes (one permission-related skip);
cacheline --stdio output is byte-identical to the base commit; and the
perf-c2c man page builds.

Jiebin Sun (9):
  perf c2c: extract shared data structures into c2c.h
  perf c2c: add function view browser skeleton
  perf c2c: add column rendering for function view
  perf c2c: add HPP list parsing for function view columns
  perf c2c: add function view stats merge and memory management
  perf c2c: add function view hierarchy entry creation
  perf c2c: build and finalize the function view hierarchy
  perf c2c: add function view browser UI and cacheline detail
  perf c2c: document function view in perf-c2c man page

 tools/perf/Documentation/perf-c2c.txt |   71 +
 tools/perf/builtin-c2c.c              |  130 +-
 tools/perf/c2c.h                      |  145 ++
 tools/perf/ui/browsers/Build          |    1 +
 tools/perf/ui/browsers/c2c-function.c | 1831 +++++++++++++++++++++++++
 5 files changed, 2059 insertions(+), 119 deletions(-)
 create mode 100644 tools/perf/c2c.h
 create mode 100644 tools/perf/ui/browsers/c2c-function.c


base-commit: 0d40fedcd1b9e809f966c97d40f32943fb89e0d4
-- 
2.52.0

[PATCH v5 v5 1/9] perf c2c: extract shared data structures into c2c.h

[Jiebin Sun]

Move c2c_hists, compute_stats, c2c_hist_entry, perf_c2c, and the shared
column-formatting structures and macros from builtin-c2c.c into a new
shared header c2c.h. This allows the upcoming function view browser
(c2c-function.c) to reuse these types and formatting definitions.

Make the global perf_c2c instance 'c2c' non-static, export
perf_c2c__browse_cacheline(), and export c2c_fmt_free() and
c2c_fmt_equal() for use by the new function view module.

No functional change.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/builtin-c2c.c | 126 ++--------------------------------
 tools/perf/c2c.h         | 144 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 151 insertions(+), 119 deletions(-)
 create mode 100644 tools/perf/c2c.h

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index c9584dbedf77..39f70ef6597b 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -38,6 +38,7 @@
 #include "mem-events.h"
 #include "mem-info.h"
 #include "mem2node.h"
+#include "c2c.h"
 #include "pmus.h"
 #include "session.h"
 #include "sort.h"
@@ -52,75 +53,9 @@
 #include "util/symbol.h"
 #include "util/util.h"
 
-struct c2c_hists {
-	struct hists		hists;
-	struct perf_hpp_list	list;
-	struct c2c_stats	stats;
-};
-
-struct compute_stats {
-	struct stats		 lcl_hitm;
-	struct stats		 rmt_hitm;
-	struct stats		 lcl_peer;
-	struct stats		 rmt_peer;
-	struct stats		 load;
-};
-
-struct c2c_hist_entry {
-	struct c2c_hists	*hists;
-	struct evsel		*evsel;
-	struct c2c_stats	 stats;
-	unsigned long		*cpuset;
-	unsigned long		*nodeset;
-	struct c2c_stats	*node_stats;
-	unsigned int		 cacheline_idx;
-
-	struct compute_stats	 cstats;
-
-	unsigned long		 paddr;
-	unsigned long		 paddr_cnt;
-	bool			 paddr_zero;
-	char			*nodestr;
-
-	/*
-	 * must be at the end,
-	 * because of its callchain dynamic entry
-	 */
-	struct hist_entry	he;
-};
 
 static char const *coalesce_default = "iaddr";
 
-struct perf_c2c {
-	struct perf_tool	tool;
-	struct c2c_hists	hists;
-	struct mem2node		mem2node;
-
-	unsigned long		**nodes;
-	int			 nodes_cnt;
-	int			 cpus_cnt;
-	int			*cpu2node;
-	int			 node_info;
-
-	bool			 show_src;
-	bool			 show_all;
-	bool			 use_stdio;
-	bool			 stats_only;
-	bool			 symbol_full;
-	bool			 stitch_lbr;
-
-	/* Shared cache line stats */
-	struct c2c_stats	shared_clines_stats;
-	int			shared_clines;
-
-	int			 display;
-
-	const char		*coalesce;
-	char			*cl_sort;
-	char			*cl_resort;
-	char			*cl_output;
-};
-
 enum {
 	DISPLAY_LCL_HITM,
 	DISPLAY_RMT_HITM,
@@ -141,7 +76,7 @@ static const struct option c2c_options[] = {
 	OPT_END()
 };
 
-static struct perf_c2c c2c;
+struct perf_c2c c2c;
 
 static void *c2c_he_zalloc(size_t size)
 {
@@ -458,36 +393,6 @@ static const char * const __usage_report[] = {
 
 static const char * const *report_c2c_usage = __usage_report;
 
-#define C2C_HEADER_MAX 2
-
-struct c2c_header {
-	struct {
-		const char *text;
-		int	    span;
-	} line[C2C_HEADER_MAX];
-};
-
-struct c2c_dimension {
-	struct c2c_header	 header;
-	const char		*name;
-	int			 width;
-	struct sort_entry	*se;
-
-	int64_t (*cmp)(struct perf_hpp_fmt *fmt,
-		       struct hist_entry *, struct hist_entry *);
-	int   (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		       struct hist_entry *he);
-	int   (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		       struct hist_entry *he);
-};
-
-struct c2c_fmt {
-	struct perf_hpp_fmt	 fmt;
-	struct c2c_dimension	*dim;
-};
-
-#define SYMBOL_WIDTH 30
-
 static struct c2c_dimension dim_symbol;
 static struct c2c_dimension dim_srcline;
 
@@ -1389,23 +1294,6 @@ cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", width, "");
 }
 
-#define HEADER_LOW(__h)			\
-	{				\
-		.line[1] = {		\
-			.text = __h,	\
-		},			\
-	}
-
-#define HEADER_BOTH(__h0, __h1)		\
-	{				\
-		.line[0] = {		\
-			.text = __h0,	\
-		},			\
-		.line[1] = {		\
-			.text = __h1,	\
-		},			\
-	}
-
 #define HEADER_SPAN(__h0, __h1, __s)	\
 	{				\
 		.line[0] = {		\
@@ -1928,7 +1816,7 @@ static struct c2c_dimension *dimensions[] = {
 	NULL,
 };
 
-static void fmt_free(struct perf_hpp_fmt *fmt)
+void c2c_fmt_free(struct perf_hpp_fmt *fmt)
 {
 	struct c2c_fmt *c2c_fmt;
 
@@ -1936,7 +1824,7 @@ static void fmt_free(struct perf_hpp_fmt *fmt)
 	free(c2c_fmt);
 }
 
-static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+bool c2c_fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 {
 	struct c2c_fmt *c2c_a = container_of(a, struct c2c_fmt, fmt);
 	struct c2c_fmt *c2c_b = container_of(b, struct c2c_fmt, fmt);
@@ -2021,8 +1909,8 @@ static struct c2c_fmt *get_format(const char *name)
 	fmt->header	= c2c_header;
 	fmt->width	= c2c_width;
 	fmt->collapse	= dim->se ? c2c_se_collapse : dim->cmp;
-	fmt->equal	= fmt_equal;
-	fmt->free	= fmt_free;
+	fmt->equal	= c2c_fmt_equal;
+	fmt->free	= c2c_fmt_free;
 
 	return c2c_fmt;
 }
@@ -2710,7 +2598,7 @@ c2c_cacheline_browser__new(struct hists *hists, struct hist_entry *he)
 	return browser;
 }
 
-static int perf_c2c__browse_cacheline(struct hist_entry *he)
+int perf_c2c__browse_cacheline(struct hist_entry *he)
 {
 	struct c2c_hist_entry *c2c_he;
 	struct c2c_hists *c2c_hists;
diff --git a/tools/perf/c2c.h b/tools/perf/c2c.h
new file mode 100644
index 000000000000..ab7adb85d9c0
--- /dev/null
+++ b/tools/perf/c2c.h
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PERF_C2C_H_
+#define _PERF_C2C_H_ 1
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include "util/stat.h"
+#include "util/hist.h"
+#include "util/mem-events.h"
+#include "util/mem2node.h"
+#include "util/tool.h"
+
+struct sort_entry;
+
+struct c2c_hists {
+	struct hists		hists;
+	struct perf_hpp_list	list;
+	struct c2c_stats	stats;
+};
+
+struct compute_stats {
+	struct stats		 lcl_hitm;
+	struct stats		 rmt_hitm;
+	struct stats		 lcl_peer;
+	struct stats		 rmt_peer;
+	struct stats		 load;
+};
+
+struct c2c_hist_entry {
+	struct c2c_hists	*hists;
+	struct evsel		*evsel;
+	struct c2c_stats	 stats;
+	unsigned long		*cpuset;
+	unsigned long		*nodeset;
+	struct c2c_stats	*node_stats;
+	unsigned int		 cacheline_idx;
+
+	struct compute_stats	 cstats;
+
+	unsigned long		 paddr;
+	unsigned long		 paddr_cnt;
+	bool			 paddr_zero;
+	char			*nodestr;
+
+	/*
+	 * must be at the end,
+	 * because of its callchain dynamic entry
+	 */
+	struct hist_entry	he;
+};
+
+struct perf_c2c {
+	struct perf_tool	tool;
+	struct c2c_hists	hists;
+	struct mem2node		mem2node;
+
+	unsigned long		**nodes;
+	int			 nodes_cnt;
+	int			 cpus_cnt;
+	int			*cpu2node;
+	int			 node_info;
+
+	bool			 show_src;
+	bool			 show_all;
+	bool			 use_stdio;
+	bool			 stats_only;
+	bool			 symbol_full;
+	bool			 stitch_lbr;
+
+	/* Shared cache line stats */
+	struct c2c_stats	shared_clines_stats;
+	int			shared_clines;
+
+	int			 display;
+
+	const char		*coalesce;
+	char			*cl_sort;
+	char			*cl_resort;
+	char			*cl_output;
+};
+
+extern struct perf_c2c c2c;
+
+#define C2C_HEADER_MAX 2
+
+struct c2c_header {
+	struct {
+		const char *text;
+		int	    span;
+	} line[C2C_HEADER_MAX];
+};
+
+struct c2c_dimension {
+	struct c2c_header	 header;
+	const char		*name;
+	int			 width;
+	struct sort_entry	*se;
+
+	int64_t (*cmp)(struct perf_hpp_fmt *fmt,
+		       struct hist_entry *left, struct hist_entry *right);
+	int   (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		       struct hist_entry *he);
+	int   (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		       struct hist_entry *he);
+};
+
+struct c2c_fmt {
+	struct perf_hpp_fmt	 fmt;
+	struct c2c_dimension	*dim;
+};
+
+#define SYMBOL_WIDTH 30
+
+#define HEADER_LOW(__h)			\
+	{				\
+		.line[1] = {		\
+			.text = __h,	\
+		},			\
+	}
+
+#define HEADER_BOTH(__h0, __h1)		\
+	{				\
+		.line[0] = {		\
+			.text = __h0,	\
+		},			\
+		.line[1] = {		\
+			.text = __h1,	\
+		},			\
+	}
+
+void c2c_fmt_free(struct perf_hpp_fmt *fmt);
+bool c2c_fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+
+/*
+ * The TUI browsers are only built with SLANG support. Their sole callers
+ * live inside HAVE_SLANG_SUPPORT-guarded code in builtin-c2c.c (stdio mode
+ * forces use_browser=0), so no #else stub is needed -- matching the rest of
+ * perf's TUI entry points.
+ */
+#ifdef HAVE_SLANG_SUPPORT
+int perf_c2c__browse_cacheline(struct hist_entry *he);
+#endif
+
+#endif /* _PERF_C2C_H_ */
-- 
2.52.0

[PATCH v5 v5 2/9] perf c2c: add function view browser skeleton

[Jiebin Sun]

Add the skeleton of the c2c function view: a new TUI browser in
tools/perf/ui/browsers/c2c-function.c reached by pressing TAB in the
cacheline view. This commit wires up the entry point (a stub that will be
filled in by later patches), registers the file in the build, declares
perf_c2c__browse_function_view() in c2c.h, and adds the TAB key handler
and help text to the cacheline browser.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/builtin-c2c.c              |  4 ++
 tools/perf/c2c.h                      |  1 +
 tools/perf/ui/browsers/Build          |  1 +
 tools/perf/ui/browsers/c2c-function.c | 77 +++++++++++++++++++++++++++
 4 files changed, 83 insertions(+)
 create mode 100644 tools/perf/ui/browsers/c2c-function.c

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 39f70ef6597b..92e276eea85c 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2693,6 +2693,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
 	static const char help[] =
 	" d             Display cacheline details \n"
 	" ENTER         Toggle callchains (if present) \n"
+	" TAB           Switch to function view\n"
 	" q             Quit \n";
 
 	browser = perf_c2c_browser__new(hists);
@@ -2714,6 +2715,9 @@ static int perf_c2c__hists_browse(struct hists *hists)
 		case 'd':
 			perf_c2c__browse_cacheline(browser->he_selection);
 			break;
+		case '\t':
+			perf_c2c__browse_function_view();
+			break;
 		case '?':
 			ui_browser__help_window(&browser->b, help);
 			break;
diff --git a/tools/perf/c2c.h b/tools/perf/c2c.h
index ab7adb85d9c0..84676ab1b77f 100644
--- a/tools/perf/c2c.h
+++ b/tools/perf/c2c.h
@@ -139,6 +139,7 @@ bool c2c_fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
  */
 #ifdef HAVE_SLANG_SUPPORT
 int perf_c2c__browse_cacheline(struct hist_entry *he);
+int perf_c2c__browse_function_view(void);
 #endif
 
 #endif /* _PERF_C2C_H_ */
diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build
index a07489e44765..ae67a2161f7d 100644
--- a/tools/perf/ui/browsers/Build
+++ b/tools/perf/ui/browsers/Build
@@ -5,3 +5,4 @@ perf-ui-y += map.o
 perf-ui-y += scripts.o
 perf-ui-y += header.o
 perf-ui-y += res_sample.o
+perf-ui-y += c2c-function.o
diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
new file mode 100644
index 000000000000..c0fd7799e4f8
--- /dev/null
+++ b/tools/perf/ui/browsers/c2c-function.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * C2C Function Browser - function-level cacheline sharing analysis
+ *
+ * Displays a 3-level hierarchy showing which functions share cachelines:
+ *   Level 1: Read-side functions sorted by Cycles % (estimated load cycles)
+ *   Level 2: Functions sampled writing the shared lines read by level 1
+ *   Level 3: The specific cachelines where the two functions contend
+ *
+ * Builds the hierarchy from the existing cacheline histograms
+ * (c2c_hist_entry->hists), reusing the shared c2c data structures.
+ */
+
+#include <errno.h>
+#include <inttypes.h>
+#include <stdlib.h>
+#include <string.h>
+#include <tools/libc_compat.h> /* reallocarray */
+#include <asm/bug.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/zalloc.h>
+
+#include "../browser.h"
+#include "../keysyms.h"
+#include "../libslang.h"
+#include "../ui.h"
+#include "../../util/addr_location.h"
+#include "../../util/cacheline.h"
+#include "../../util/debug.h"
+#include "../../util/hist.h"
+#include "../../util/map.h"
+#include "../../util/mem-events.h"
+#include "../../util/mem-info.h"
+#include "../../util/sort.h"
+#include "../../util/symbol.h"
+#include "../../util/thread.h"
+#include "../../c2c.h"
+#include "hists.h"
+
+struct perf_c2c_ext {
+	struct c2c_hists	function_hists;
+	/* Total estimated cycles across all level-1 entries. */
+	u64			total_cycles;
+};
+
+static struct perf_c2c_ext c2c_ext __maybe_unused;
+
+struct c2c_function_browser {
+	struct hist_browser	hb;
+};
+
+static inline __maybe_unused u64 c2c_hitm_count(const struct c2c_stats *stats)
+{
+	return stats->tot_hitm;
+}
+
+static inline __maybe_unused bool symbol_name_equal(struct symbol *a, struct symbol *b)
+{
+	/* Two unknown symbols compare equal, matching cmp_null() in util/sort.c. */
+	if (!a || !b)
+		return a == b;
+	return arch__compare_symbol_names(a->name, b->name) == 0;
+}
+
+static inline __maybe_unused u64 hist_entry__iaddr(struct hist_entry *he)
+{
+	if (he->mem_info)
+		return mem_info__iaddr(he->mem_info)->addr;
+	return he->ip;
+}
+
+int perf_c2c__browse_function_view(void)
+{
+	ui__warning("C2C function view is not implemented yet.\n");
+	return 0;
+}
-- 
2.52.0

[PATCH v5 v5 3/9] perf c2c: add column rendering for function view

[Jiebin Sun]

Add the function view's column renderers: the Cycles %, Store count and
the single indented identity column (function / cacheline) with per-level
indentation, the width/header helpers, the per-function estimated-cycles
computation, and the dimension table tying each column to its renderer and
comparator.

Clamp the symbol renderer's returned length to its local cell buffer before
using it in subsequent pointer and padding calculations. This keeps the
buffer arithmetic safe if the renderer returns snprintf's would-have-been
length, without changing the normal rendered output.

The HPP list parsing that turns a column string into these dimensions is
added by the next patch; symbols consumed only later are __maybe_unused
for now.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/ui/browsers/c2c-function.c | 346 ++++++++++++++++++++++++++
 1 file changed, 346 insertions(+)

diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
index c0fd7799e4f8..a7825140d049 100644
--- a/tools/perf/ui/browsers/c2c-function.c
+++ b/tools/perf/ui/browsers/c2c-function.c
@@ -70,6 +70,352 @@ static inline __maybe_unused u64 hist_entry__iaddr(struct hist_entry *he)
 	return he->ip;
 }
 
+static inline bool hist_entry__is_cacheline(struct hist_entry *he)
+{
+	return he->parent_he && he->parent_he->parent_he;	/* level 3: cacheline */
+}
+
+/* Spaces of indent per hierarchy level, like the normal report view. */
+#define C2C_FUNC_INDENT 2
+
+/* Width of the folded-sign prefix ("%c ") each identity cell emits. */
+#define C2C_FUNC_FOLD_WIDTH 2
+
+/*
+ * Write he->depth levels of leading indentation into @buf, so lower-level
+ * entries are visually nested under their parent. Returns bytes written.
+ */
+static int hist_entry__indent(struct hist_entry *he, char *buf, size_t size)
+{
+	int indent = he->depth * C2C_FUNC_INDENT;
+
+	if (indent <= 0 || (size_t)indent >= size)
+		return 0;
+
+	return scnprintf(buf, size, "%*s", indent, "");
+}
+
+static int symbol_width(struct hists *hists, struct sort_entry *se)
+{
+	int width = hists__col_len(hists, se->se_width_idx);
+
+	/*
+	 * Cap long symbol names as the cacheline view does. The stored column
+	 * length is grown up front to fit the deepest, longest identity cell
+	 * (including a level-3 cacheline address), so this cap never shrinks the
+	 * column below what the cacheline address needs.
+	 */
+	if (!c2c.symbol_full && width > SYMBOL_WIDTH)
+		width = SYMBOL_WIDTH;
+
+	return width;
+}
+
+static struct c2c_dimension dim_symbol_view;
+
+/*
+ * c2c_width - Calculate width for a C2C column in function view
+ */
+static int c2c_width(struct perf_hpp_fmt *fmt,
+		     struct perf_hpp *hpp __maybe_unused,
+		     struct hists *hists)
+{
+	struct c2c_fmt *c2c_fmt;
+	struct c2c_dimension *dim;
+
+	c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	dim = c2c_fmt->dim;
+
+	if (dim == &dim_symbol_view)
+		return symbol_width(hists, dim->se);
+
+	return dim->se ? hists__col_len(hists, dim->se->se_width_idx) :
+			 dim->width;
+}
+
+static int __maybe_unused c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+				     struct hists *hists, int line, int *span)
+{
+	struct c2c_fmt *c2c_fmt;
+	struct c2c_dimension *dim;
+	const char *text = NULL;
+	int width = c2c_width(fmt, hpp, hists);
+
+	c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	dim = c2c_fmt->dim;
+
+	if (dim->se) {
+		text = dim->header.line[line].text;
+		/* Use the last line from sort_entry if not defined. */
+		if (!text && line == hists->hpp_list->nr_header_lines - 1)
+			text = dim->se->se_header;
+	} else {
+		text = dim->header.line[line].text;
+
+		if (span) {
+			if (*span) {
+				(*span)--;
+				return 0;
+			}
+
+			*span = dim->header.line[line].span;
+		}
+	}
+
+	if (!text)
+		text = "";
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, text);
+}
+
+/*
+ * Return the estimated total cycles for a c2c_hist_entry
+ * (rmt_hitm + lcl_hitm + rmt_peer + lcl_peer + other loads).
+ */
+static u64 c2c_hist_entry__cycles(struct c2c_hist_entry *c2c_he)
+{
+	struct compute_stats *cs = &c2c_he->cstats;
+	double cycles = 0;
+
+	/*
+	 * compute_stats() in builtin-c2c.c routes each load sample into exactly
+	 * one cstats bucket (rmt_hitm, lcl_hitm, rmt_peer, lcl_peer or plain
+	 * load), so each bucket's cycle total is its mean times its own sample
+	 * count. Summing the per-bucket totals avoids both dropping peer-snoop
+	 * cycles and double counting a sample that carries several data-source
+	 * flags (e.g. Arm SPE sets HITM and PEER on the same load), which would
+	 * happen if the mean were multiplied by the non-exclusive stats counts.
+	 */
+	cycles += avg_stats(&cs->rmt_hitm) * cs->rmt_hitm.n;
+	cycles += avg_stats(&cs->lcl_hitm) * cs->lcl_hitm.n;
+	cycles += avg_stats(&cs->rmt_peer) * cs->rmt_peer.n;
+	cycles += avg_stats(&cs->lcl_peer) * cs->lcl_peer.n;
+	cycles += avg_stats(&cs->load)     * cs->load.n;
+
+	return (u64)cycles;
+}
+
+/* Sum c2c_hist_entry__cycles() across all level-1 entries. */
+static u64 __maybe_unused c2c_ext__total_cycles(void)
+{
+	struct rb_node *nd;
+	u64 total = 0;
+
+	for (nd = rb_first_cached(&c2c_ext.function_hists.hists.entries); nd;
+	     nd = rb_next(nd)) {
+		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+		struct c2c_hist_entry *c2c_he = container_of(he, struct c2c_hist_entry, he);
+
+		total += c2c_hist_entry__cycles(c2c_he);
+	}
+	return total;
+}
+
+/*
+ * Store count shown in the column: a level-3 cacheline leaf shows its parent
+ * level-2 writer's stores on that line, not all stores on the line. A level-2
+ * writer shows the sum across its level-3 cachelines. A level-1 reader shows
+ * the sum across all included writers on the cachelines it reads; this is not
+ * the reader function's own store count and is not additive across readers.
+ */
+static u64 hist_entry__displayed_stores(struct hist_entry *he)
+{
+	struct c2c_hist_entry *c2c_he = container_of(he, struct c2c_hist_entry, he);
+	struct rb_node *nd;
+	u64 stores = 0;
+
+	/* Level-2/3 entries already aggregate the stores they represent. */
+	if (he->parent_he)
+		return c2c_he->stats.store;
+
+	for (nd = rb_first_cached(&he->hroot_out); nd; nd = rb_next(nd)) {
+		struct hist_entry *child = rb_entry(nd, struct hist_entry, rb_node);
+		struct c2c_hist_entry *child_c2c;
+
+		child_c2c = container_of(child, struct c2c_hist_entry, he);
+		stores += child_c2c->stats.store;
+	}
+	return stores;
+}
+
+static int
+total_stores_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		   struct hist_entry *he)
+{
+	int width = c2c_width(fmt, hpp, he->hists);
+	u64 total = hist_entry__displayed_stores(he);
+
+	return scnprintf(hpp->buf, hpp->size, "%*" PRIu64, width, total);
+}
+
+/*
+ * symbol_view_entry - Render the unified, indented identity column.
+ *
+ * All three levels share this single column so the hierarchy reads top-down
+ * with progressive indentation, like the normal report hierarchy view. It is
+ * a function-centric view with no dedicated code-address column. Verbose
+ * function rows can still include a representative address:
+ *   L1 read-side function: "- [k] cpupri_set"
+ *   L2 writing function:   "  - [k] pull_rt_task"
+ *   L3 shared cacheline:   "      0xff2d0082809da080"
+ */
+static int
+symbol_view_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		  struct hist_entry *he)
+{
+	int width = c2c_width(fmt, hpp, he->hists);
+	int text_width;
+	int ret;
+	char folded_sign;
+
+	ret = hist_entry__indent(he, hpp->buf, hpp->size);
+
+	folded_sign = he->has_children ? (he->unfolded ? '-' : '+') : ' ';
+	ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%c ", folded_sign);
+
+	text_width = width - ret;
+	if (text_width <= 0)
+		return ret;
+
+	if (hist_entry__is_cacheline(he)) {
+		/* Level 3: the shared cacheline address. */
+		u64 addr = he->mem_info ?
+			cl_address(mem_info__daddr(he->mem_info)->addr, chk_double_cl) : 0;
+		char symbuf[32];
+
+		scnprintf(symbuf, sizeof(symbuf), "0x%" PRIx64, addr);
+		ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%-*.*s",
+				 text_width, text_width, symbuf);
+	} else {
+		/* Level 1 and level 2 are both functions. */
+		size_t cell_size;
+		int len;
+
+		if ((size_t)ret >= hpp->size)
+			return ret;
+
+		cell_size = min_t(size_t, hpp->size - ret,
+				  (size_t)text_width + 1);
+		len = sort_sym.se_snprintf(he, hpp->buf + ret, cell_size,
+					   text_width);
+		/* Do not depend on the callback's return-value semantics. */
+		if (len < 0)
+			len = 0;
+		else
+			len = min_t(size_t, len, cell_size - 1);
+
+		ret += len;
+		if (len < text_width)
+			ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%*s",
+					 text_width - len, "");
+	}
+
+	return ret;
+}
+
+/*
+ * cycles_percent_entry - Render cycles percentage column
+ */
+static int
+cycles_percent_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct hist_entry *he)
+{
+	struct c2c_hist_entry *c2c_he;
+	int width = c2c_width(fmt, hpp, he->hists);
+	u64 fn_cycles, total_cycles;
+	char folded_sign;
+	double pct;
+	int ret, pct_width;
+
+	/* Hide Cycles Percent for child functions and cachelines. */
+	if (he->parent_he)
+		return scnprintf(hpp->buf, hpp->size, "%*s", width, "");
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	fn_cycles = c2c_hist_entry__cycles(c2c_he);
+	/* Populated by build_function_view_hierarchy() once the L1 tree is built. */
+	total_cycles = c2c_ext.total_cycles;
+	pct = total_cycles > 0 ? (double)fn_cycles / total_cycles * 100.0 : 0.0;
+
+	/* Add folded sign only for level-1 entries */
+	folded_sign = he->has_children ? (he->unfolded ? '-' : '+') : ' ';
+	ret = scnprintf(hpp->buf, hpp->size, "%c ", folded_sign);
+
+	pct_width = width - ret;
+	if (pct_width <= 0)
+		return ret;
+	ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%*.2f%%", pct_width - 1, pct);
+	return ret;
+}
+
+/*
+ * cycles_percent_cmp - Comparison function for cycles percentage sorting
+ */
+static int64_t
+cycles_percent_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+		   struct hist_entry *left, struct hist_entry *right)
+{
+	struct c2c_hist_entry *c2c_left = container_of(left, struct c2c_hist_entry, he);
+	struct c2c_hist_entry *c2c_right = container_of(right, struct c2c_hist_entry, he);
+	u64 cycles_left, cycles_right;
+
+	/* Cycles Percent is only shown for level-1 entries; others compare equal. */
+	if (left->parent_he || right->parent_he)
+		return 0;
+
+	cycles_left = c2c_hist_entry__cycles(c2c_left);
+	cycles_right = c2c_hist_entry__cycles(c2c_right);
+
+	return (cycles_left > cycles_right) - (cycles_left < cycles_right);
+}
+
+/*
+ * total_stores_cmp - Comparison function for total stores sorting
+ */
+static int64_t
+total_stores_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+		 struct hist_entry *left, struct hist_entry *right)
+{
+	u64 left_store = hist_entry__displayed_stores(left);
+	u64 right_store = hist_entry__displayed_stores(right);
+
+	return (left_store > right_store) - (left_store < right_store);
+}
+
+/*
+ * Function view dimensions
+ */
+static struct c2c_dimension dim_cycles_percent = {
+	.header		= HEADER_BOTH("Cycles", "%"),
+	.name		= "cycles_percent",
+	.cmp		= cycles_percent_cmp,
+	.entry		= cycles_percent_entry,
+	.width		= 9,
+};
+
+static struct c2c_dimension dim_total_stores = {
+	.header		= HEADER_BOTH("Store", "count"),
+	.name		= "total_stores",
+	.cmp		= total_stores_cmp,
+	.entry		= total_stores_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_symbol_view = {
+	.header		= HEADER_LOW("Function / Contending function / Cacheline"),
+	.name		= "symbol_view",
+	.se		= &sort_sym,
+	.entry		= symbol_view_entry,
+	.width		= SYMBOL_WIDTH,
+};
+
+static struct c2c_dimension *function_view_dimensions[] __maybe_unused = {
+	&dim_cycles_percent,
+	&dim_total_stores,
+	&dim_symbol_view,
+	NULL,
+};
+
 int perf_c2c__browse_function_view(void)
 {
 	ui__warning("C2C function view is not implemented yet.\n");
-- 
2.52.0

[PATCH v5 v5 4/9] perf c2c: add HPP list parsing for function view columns

[Jiebin Sun]

Add the parsing that turns an output/sort column string into the function
view's hpp_list: the dimension lookup, the sort-entry comparator wrappers,
the c2c_fmt allocation, and the init/reinit entry points used by the
hierarchy builder.

Append the sort keys to the output fields with a local
c2c_function_hists__setup_output_field() helper.  The shared
perf_hpp__setup_output_field() registers onto the global perf_hpp_list,
which would leave the function view's local list without output columns
and link its formats into the global list instead, so the function view
keeps its own copy that registers on the local hpp_list.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/ui/browsers/c2c-function.c | 268 +++++++++++++++++++++++++-
 1 file changed, 265 insertions(+), 3 deletions(-)

diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
index a7825140d049..caccb20f0ef4 100644
--- a/tools/perf/ui/browsers/c2c-function.c
+++ b/tools/perf/ui/browsers/c2c-function.c
@@ -133,8 +133,8 @@ static int c2c_width(struct perf_hpp_fmt *fmt,
 			 dim->width;
 }
 
-static int __maybe_unused c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-				     struct hists *hists, int line, int *span)
+static int c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct hists *hists, int line, int *span)
 {
 	struct c2c_fmt *c2c_fmt;
 	struct c2c_dimension *dim;
@@ -409,13 +409,275 @@ static struct c2c_dimension dim_symbol_view = {
 	.width		= SYMBOL_WIDTH,
 };
 
-static struct c2c_dimension *function_view_dimensions[] __maybe_unused = {
+static struct c2c_dimension *function_view_dimensions[] = {
 	&dim_cycles_percent,
 	&dim_total_stores,
 	&dim_symbol_view,
 	NULL,
 };
 
+static struct c2c_dimension *get_function_dimension(const char *name)
+{
+	unsigned int i;
+
+	for (i = 0; function_view_dimensions[i]; i++) {
+		struct c2c_dimension *dim = function_view_dimensions[i];
+
+		if (!strcmp(dim->name, name))
+			return dim;
+	}
+
+	return NULL;
+}
+
+/* Wrappers so sort_entry-backed dimensions sort/collapse via their se. */
+static int64_t c2c_se_cmp(struct perf_hpp_fmt *fmt,
+			  struct hist_entry *a, struct hist_entry *b)
+{
+	struct c2c_fmt *c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	struct c2c_dimension *dim = c2c_fmt->dim;
+
+	return dim->se->se_cmp(a, b);
+}
+
+static int64_t c2c_se_collapse(struct perf_hpp_fmt *fmt,
+			       struct hist_entry *a, struct hist_entry *b)
+{
+	struct c2c_fmt *c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	struct c2c_dimension *dim = c2c_fmt->dim;
+	int64_t (*collapse_fn)(struct hist_entry *a, struct hist_entry *b);
+
+	collapse_fn = dim->se->se_collapse ?: dim->se->se_cmp;
+	return collapse_fn(a, b);
+}
+
+static int64_t c2c_se_sort(struct perf_hpp_fmt *fmt,
+			   struct hist_entry *a, struct hist_entry *b)
+{
+	struct c2c_fmt *c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	struct c2c_dimension *dim = c2c_fmt->dim;
+	int64_t (*sort_fn)(struct hist_entry *a, struct hist_entry *b);
+
+	sort_fn = dim->se->se_sort ?: dim->se->se_cmp;
+	return sort_fn(a, b);
+}
+
+/*
+ * Build the c2c_fmt for @name. Returns:
+ *   0        and *fmtp set     on success;
+ *   -ENOENT  and *fmtp = NULL   if @name is not a function-view dimension;
+ *   -ENOMEM                     if allocation failed (distinct from -ENOENT so
+ *                               the caller does not misreport it as an
+ *                               "invalid field").
+ */
+static int get_function_format(const char *name, struct c2c_fmt **fmtp)
+{
+	struct c2c_dimension *dim = get_function_dimension(name);
+	struct c2c_fmt *c2c_fmt;
+	struct perf_hpp_fmt *fmt;
+
+	*fmtp = NULL;
+
+	if (!dim)
+		return -ENOENT;
+
+	c2c_fmt = zalloc(sizeof(*c2c_fmt));
+	if (!c2c_fmt)
+		return -ENOMEM;
+
+	fmt = &c2c_fmt->fmt;
+
+	c2c_fmt->dim = dim;
+	INIT_LIST_HEAD(&fmt->list);
+	INIT_LIST_HEAD(&fmt->sort_list);
+
+	fmt->cmp	= dim->se ? c2c_se_cmp : dim->cmp;
+	fmt->sort	= dim->se ? c2c_se_sort : dim->cmp;
+	fmt->color	= dim->color;
+	fmt->entry	= dim->entry;
+	fmt->header	= c2c_header;
+	fmt->width	= c2c_width;
+	fmt->collapse	= dim->se ? c2c_se_collapse : dim->cmp;
+	fmt->equal	= c2c_fmt_equal;
+	fmt->free	= c2c_fmt_free;
+
+	*fmtp = c2c_fmt;
+	return 0;
+}
+
+static int
+c2c_function_hists__init_output(struct perf_hpp_list *hpp_list, char *name,
+				struct perf_env *env __maybe_unused)
+{
+	struct c2c_fmt *c2c_fmt;
+	int ret;
+
+	ret = get_function_format(name, &c2c_fmt);
+	if (ret == -ENOMEM)
+		return ret;
+	/* The function view only accepts its own dimensions. */
+	if (ret == -ENOENT)
+		return -EINVAL;
+
+	/*
+	 * Mark symbol-backed columns so hists__has(hists, sym) is correct.
+	 * Only dim_symbol_view carries a sort_entry (.se); the function
+	 * view's field strings are fixed and always include symbol_view, so
+	 * this single check is sufficient (unlike the user-configurable
+	 * cacheline view, which must also test dim_iaddr).
+	 */
+	if (c2c_fmt->dim->se == &sort_sym)
+		hpp_list->sym = 1;
+
+	perf_hpp_list__column_register(hpp_list, &c2c_fmt->fmt);
+	return 0;
+}
+
+static int
+c2c_function_hists__init_sort(struct perf_hpp_list *hpp_list, char *name,
+			      struct perf_env *env __maybe_unused)
+{
+	struct c2c_fmt *c2c_fmt;
+	int ret;
+
+	ret = get_function_format(name, &c2c_fmt);
+	if (ret == -ENOMEM)
+		return ret;
+	/* The function view only accepts its own dimensions. */
+	if (ret == -ENOENT)
+		return -EINVAL;
+
+	/* Mark symbol-backed sort keys so hists__has(hists, sym) is correct. */
+	if (c2c_fmt->dim->se == &sort_sym)
+		hpp_list->sym = 1;
+
+	perf_hpp_list__register_sort_field(hpp_list, &c2c_fmt->fmt);
+	return 0;
+}
+
+typedef int (*hpp_list_add_fn)(struct perf_hpp_list *hpp_list, char *name,
+			       struct perf_env *env);
+
+static int function_hpp_list__add_tokens(struct perf_hpp_list *hpp_list, char *list,
+					 struct perf_env *env, hpp_list_add_fn add)
+{
+	char *tok, *tmp;
+	int ret;
+
+	if (!list)
+		return 0;
+
+	for (tok = strtok_r(list, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		ret = add(hpp_list, tok, env);
+		if (ret) {
+			if (ret == -EINVAL || ret == -ESRCH)
+				pr_err("Invalid c2c function-view field: %s\n", tok);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Append the function view's sort keys to its own output fields, mirroring
+ * perf_hpp__setup_output_field() but on the local @list. The shared helper
+ * registers onto the global perf_hpp_list, which would leave this local list
+ * without output columns, so the function view keeps its own copy here.
+ */
+static void c2c_function_hists__setup_output_field(struct perf_hpp_list *list)
+{
+	struct perf_hpp_fmt *fmt;
+
+	perf_hpp_list__for_each_sort_list(list, fmt) {
+		struct perf_hpp_fmt *pos;
+
+		if (!fmt->entry && !fmt->color)
+			continue;
+
+		perf_hpp_list__for_each_format(list, pos) {
+			if (c2c_fmt_equal(fmt, pos))
+				goto next;
+		}
+
+		perf_hpp_list__column_register(list, fmt);
+next:
+		continue;
+	}
+}
+
+static int
+function_hpp_list__parse(struct perf_hpp_list *hpp_list,
+			 const char *output_str,
+			 const char *sort_str,
+			 struct perf_env *env)
+{
+	char *output = output_str ? strdup(output_str) : NULL;
+	char *sort   = sort_str   ? strdup(sort_str)   : NULL;
+	int ret = 0;
+
+	if ((output_str && !output) || (sort_str && !sort)) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = function_hpp_list__add_tokens(hpp_list, output, env,
+					    c2c_function_hists__init_output);
+	if (ret)
+		goto out;
+
+	ret = function_hpp_list__add_tokens(hpp_list, sort, env,
+					    c2c_function_hists__init_sort);
+	if (ret)
+		goto out;
+
+	c2c_function_hists__setup_output_field(hpp_list);
+out:
+	if (ret)
+		perf_hpp__reset_output_field(hpp_list);
+	free(output);
+	free(sort);
+	return ret;
+}
+
+static int __maybe_unused
+c2c_function_hists__init(struct c2c_hists *hists,
+			 const char *sort,
+			 int nr_header_lines,
+			 struct perf_env *env)
+{
+	__hists__init(&hists->hists, &hists->list);
+
+	perf_hpp_list__init(&hists->list);
+
+	hists->list.nr_header_lines = nr_header_lines;
+
+	return function_hpp_list__parse(&hists->list, /*output=*/NULL, sort, env);
+}
+
+static int __maybe_unused
+c2c_function_hists__reinit(struct c2c_hists *c2c_hists,
+			   const char *output,
+			   const char *sort,
+			   struct perf_env *env)
+{
+	int nr_header_lines = c2c_hists->list.nr_header_lines;
+
+	perf_hpp__reset_output_field(&c2c_hists->list);
+
+	/* Clear stale state flags so a different output/sort set starts fresh. */
+	c2c_hists->list.need_collapse = 0;
+	c2c_hists->list.parent = 0;
+	c2c_hists->list.sym = 0;
+	c2c_hists->list.dso = 0;
+	c2c_hists->list.socket = 0;
+	c2c_hists->list.thread = 0;
+	c2c_hists->list.comm = 0;
+	c2c_hists->list.comm_nodigit = 0;
+	c2c_hists->list.nr_header_lines = nr_header_lines;
+
+	return function_hpp_list__parse(&c2c_hists->list, output, sort, env);
+}
+
 int perf_c2c__browse_function_view(void)
 {
 	ui__warning("C2C function view is not implemented yet.\n");
-- 
2.52.0

[PATCH v5 v5 5/9] perf c2c: add function view stats merge and memory management

[Jiebin Sun]

Add the per-entry stats/cstats aggregation helpers and the
borrowed-reference teardown for hierarchy children, which frees only the
owned resources and never the borrowed thread/ms. Also add a helper for
pruning writer entries with no stores or cacheline children.

These are used by the entry-creation and builder patches that follow and
are __maybe_unused until then.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/ui/browsers/c2c-function.c | 198 ++++++++++++++++++++++++++
 1 file changed, 198 insertions(+)

diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
index caccb20f0ef4..051c38697edd 100644
--- a/tools/perf/ui/browsers/c2c-function.c
+++ b/tools/perf/ui/browsers/c2c-function.c
@@ -678,6 +678,204 @@ c2c_function_hists__reinit(struct c2c_hists *c2c_hists,
 	return function_hpp_list__parse(&c2c_hists->list, output, sort, env);
 }
 
+static void c2c_stats_merge(struct stats *dest, const struct stats *src)
+{
+	double delta;
+
+	if (src->n == 0)
+		return;
+
+	if (dest->n == 0) {
+		*dest = *src;
+		return;
+	}
+
+	delta = src->mean - dest->mean;
+	dest->M2 += src->M2 + delta * delta * dest->n * src->n / (dest->n + src->n);
+	dest->mean = (dest->mean * dest->n + src->mean * src->n) / (dest->n + src->n);
+	dest->n += src->n;
+
+	/* Update min/max */
+	if (src->max > dest->max)
+		dest->max = src->max;
+	if (src->min < dest->min)
+		dest->min = src->min;
+}
+
+/* Merge compute_stats during function aggregation. */
+static void __maybe_unused c2c_add_cstats(struct compute_stats *dest,
+					  const struct compute_stats *src)
+{
+	c2c_stats_merge(&dest->rmt_hitm, &src->rmt_hitm);
+	c2c_stats_merge(&dest->lcl_hitm, &src->lcl_hitm);
+	c2c_stats_merge(&dest->rmt_peer, &src->rmt_peer);
+	c2c_stats_merge(&dest->lcl_peer, &src->lcl_peer);
+	c2c_stats_merge(&dest->load, &src->load);
+}
+
+static bool __maybe_unused hist_entry__add_c2c_stats(struct hist_entry *he,
+						     const struct c2c_stats *stats)
+{
+	u64 nr_events = c2c_hitm_count(stats) + stats->rmt_peer + stats->lcl_peer;
+	u64 weight1 = c2c_hitm_count(stats);
+
+	/*
+	 * Allocate before touching he->stat, so a failure here leaves the
+	 * entry unmodified and the caller can bail out without having
+	 * half-updated the statistics.
+	 */
+	if (symbol_conf.cumulate_callchain && !he->stat_acc) {
+		he->stat_acc = calloc(1, sizeof(struct he_stat));
+		if (!he->stat_acc)
+			return false;
+	}
+
+	he->stat.nr_events += nr_events;
+	he->stat.period += nr_events;
+	he->stat.weight1 += weight1;
+
+	if (!symbol_conf.cumulate_callchain)
+		return true;
+
+	he->stat_acc->nr_events += nr_events;
+	he->stat_acc->period += nr_events;
+	he->stat_acc->weight1 += weight1;
+
+	return true;
+}
+
+static void c2c_he__free_hierarchy(struct hist_entry *he);
+
+/*
+ * Free a function-view histogram entry (hist_entry_ops::free).
+ */
+static void __maybe_unused c2c_function_he_free(void *ptr)
+{
+	struct hist_entry *he = ptr;
+	struct c2c_hist_entry *c2c_he;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+
+	if (c2c_he->hists) {
+		perf_hpp__reset_output_field(&c2c_he->hists->list);
+		hists__delete_all_entries(&c2c_he->hists->hists);
+		zfree(&c2c_he->hists);
+	}
+
+	c2c_he__free_hierarchy(he);
+
+	zfree(&c2c_he->nodeset);
+	zfree(&c2c_he->cpuset);
+	zfree(&c2c_he->nodestr);
+	zfree(&c2c_he->node_stats);
+
+	free(c2c_he);
+}
+
+/*
+ * Free one child entry @child_he and everything below it. Frees exactly the
+ * resources c2c_child_entry__alloc() owns (mem_info clone, stat_acc, hists and
+ * the c2c-specific arrays); the borrowed thread/ms are left untouched.
+ */
+static void c2c_child_he__free(struct hist_entry *child_he)
+{
+	struct c2c_hist_entry *child_c2c = container_of(child_he, struct c2c_hist_entry, he);
+
+	if (child_he->stat_acc)
+		zfree(&child_he->stat_acc);
+
+	if (child_he->mem_info)
+		mem_info__put(child_he->mem_info);
+
+	if (child_c2c->hists) {
+		perf_hpp__reset_output_field(&child_c2c->hists->list);
+		hists__delete_all_entries(&child_c2c->hists->hists);
+		zfree(&child_c2c->hists);
+	}
+
+	zfree(&child_c2c->cpuset);
+	zfree(&child_c2c->nodeset);
+	zfree(&child_c2c->nodestr);
+	zfree(&child_c2c->node_stats);
+
+	c2c_he__free_hierarchy(child_he);
+
+	free(child_c2c);
+}
+
+static void c2c_he__free_hierarchy(struct hist_entry *he)
+{
+	struct rb_node *nd;
+	struct hist_entry *child_he;
+
+	/*
+	 * Children borrow thread and ms from the main cacheline entries, which
+	 * outlive this temporary hierarchy. Do not use hist_entry__delete() here:
+	 * it would put those borrowed references. Free only the resources owned by
+	 * c2c_child_entry__alloc().
+	 *
+	 * A leaf entry stores its callchains in the sorted_chain member, which
+	 * shares a union with the hroot_in/hroot_out child trees, so its
+	 * hroot_out is not a valid subtree to walk. Leaf entries never have a
+	 * child hierarchy here, so stop before touching hroot_out.
+	 */
+	if (he->leaf)
+		return;
+
+	if (RB_EMPTY_ROOT(&he->hroot_out.rb_root))
+		return;
+
+	nd = rb_first_cached(&he->hroot_out);
+	while (nd) {
+		struct rb_node *next = rb_next(nd);
+
+		child_he = rb_entry(nd, struct hist_entry, rb_node);
+		rb_erase_cached(&child_he->rb_node, &he->hroot_out);
+		c2c_child_he__free(child_he);
+
+		nd = next;
+	}
+
+	/* All children erased; clear the tree (and its cached leftmost). */
+	he->hroot_out = RB_ROOT_CACHED;
+}
+
+/*
+ * Drop level-2 writing functions that carry no stores or
+ * no cacheline children. Writers are only added when they store into a shared
+ * line, so this is mainly a safety net. Returns the number of surviving
+ * writers.
+ */
+static int __maybe_unused c2c_he__prune_empty_writers(struct hist_entry *l1_he)
+{
+	struct rb_node *nd;
+	int surviving = 0;
+
+	if (!l1_he->has_children)
+		return 0;
+
+	nd = rb_first_cached(&l1_he->hroot_out);
+	while (nd) {
+		struct rb_node *next = rb_next(nd);
+		struct hist_entry *l2_he = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (l2_he->has_children && hist_entry__displayed_stores(l2_he) > 0) {
+			surviving++;
+		} else {
+			rb_erase_cached(&l2_he->rb_node, &l1_he->hroot_out);
+			c2c_child_he__free(l2_he);
+		}
+		nd = next;
+	}
+
+	if (!surviving) {
+		l1_he->hroot_out = RB_ROOT_CACHED;
+		l1_he->has_children = false;
+		l1_he->unfolded = false;
+	}
+	return surviving;
+}
+
 int perf_c2c__browse_function_view(void)
 {
 	ui__warning("C2C function view is not implemented yet.\n");
-- 
2.52.0

[PATCH v5 v5 6/9] perf c2c: add function view hierarchy entry creation

[Jiebin Sun]

Add the entry-creation layer: the borrowed-reference child allocation and
insertion, and the level-1/2/3 lookup-or-create functions keyed by
function symbol (level 1 read-side, level 2 writer) and by the source
cacheline's existing index (level 3).

Reuse cacheline_idx to preserve the source entry identity without adding
function-view-only state. The browser can later use the same index to find
the original cacheline entry.

These are driven by the hierarchy builder in the next patch and are
__maybe_unused until then.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/ui/browsers/c2c-function.c | 303 ++++++++++++++++++++++++--
 1 file changed, 285 insertions(+), 18 deletions(-)

diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
index 051c38697edd..b3528edb387a 100644
--- a/tools/perf/ui/browsers/c2c-function.c
+++ b/tools/perf/ui/browsers/c2c-function.c
@@ -28,6 +28,7 @@
 #include "../../util/addr_location.h"
 #include "../../util/cacheline.h"
 #include "../../util/debug.h"
+#include "../../util/dso.h"
 #include "../../util/hist.h"
 #include "../../util/map.h"
 #include "../../util/mem-events.h"
@@ -55,12 +56,34 @@ static inline __maybe_unused u64 c2c_hitm_count(const struct c2c_stats *stats)
 	return stats->tot_hitm;
 }
 
-static inline __maybe_unused bool symbol_name_equal(struct symbol *a, struct symbol *b)
+static int64_t c2c_function_cmp(const struct map_symbol *left,
+				const struct map_symbol *right)
 {
-	/* Two unknown symbols compare equal, matching cmp_null() in util/sort.c. */
-	if (!a || !b)
-		return a == b;
-	return arch__compare_symbol_names(a->name, b->name) == 0;
+	const struct dso *left_dso = left->map ? map__dso(left->map) : NULL;
+	const struct dso *right_dso = right->map ? map__dso(right->map) : NULL;
+	int ret;
+
+	if (!left_dso || !right_dso) {
+		if (left_dso != right_dso)
+			return left_dso ? 1 : -1;
+	} else {
+		/*
+		 * Use the same DSO name as _sort__dso_cmp() (short name unless
+		 * verbose), so this matches the DSO comparison the level-1
+		 * entries are deduplicated by; otherwise same-basename DSOs
+		 * could be split or merged inconsistently across levels.
+		 */
+		const char *left_name = verbose > 0 ?
+			dso__long_name(left_dso) : dso__short_name(left_dso);
+		const char *right_name = verbose > 0 ?
+			dso__long_name(right_dso) : dso__short_name(right_dso);
+
+		ret = strcmp(left_name, right_name);
+		if (ret)
+			return ret;
+	}
+
+	return _sort__sym_cmp(left->sym, right->sym);
 }
 
 static inline __maybe_unused u64 hist_entry__iaddr(struct hist_entry *he)
@@ -749,7 +772,7 @@ static void c2c_he__free_hierarchy(struct hist_entry *he);
 /*
  * Free a function-view histogram entry (hist_entry_ops::free).
  */
-static void __maybe_unused c2c_function_he_free(void *ptr)
+static void c2c_function_he_free(void *ptr)
 {
 	struct hist_entry *he = ptr;
 	struct c2c_hist_entry *c2c_he;
@@ -764,18 +787,13 @@ static void __maybe_unused c2c_function_he_free(void *ptr)
 
 	c2c_he__free_hierarchy(he);
 
-	zfree(&c2c_he->nodeset);
-	zfree(&c2c_he->cpuset);
-	zfree(&c2c_he->nodestr);
-	zfree(&c2c_he->node_stats);
-
 	free(c2c_he);
 }
 
 /*
  * Free one child entry @child_he and everything below it. Frees exactly the
- * resources c2c_child_entry__alloc() owns (mem_info clone, stat_acc, hists and
- * the c2c-specific arrays); the borrowed thread/ms are left untouched.
+ * resources c2c_child_entry__alloc() owns; the borrowed thread/ms are left
+ * untouched.
  */
 static void c2c_child_he__free(struct hist_entry *child_he)
 {
@@ -793,11 +811,6 @@ static void c2c_child_he__free(struct hist_entry *child_he)
 		zfree(&child_c2c->hists);
 	}
 
-	zfree(&child_c2c->cpuset);
-	zfree(&child_c2c->nodeset);
-	zfree(&child_c2c->nodestr);
-	zfree(&child_c2c->node_stats);
-
 	c2c_he__free_hierarchy(child_he);
 
 	free(child_c2c);
@@ -876,6 +889,260 @@ static int __maybe_unused c2c_he__prune_empty_writers(struct hist_entry *l1_he)
 	return surviving;
 }
 
+static void *c2c_function_he_zalloc(size_t size)
+{
+	struct c2c_hist_entry *c2c_he = zalloc(sizeof(*c2c_he) + size);
+
+	if (!c2c_he)
+		return NULL;
+
+	init_stats(&c2c_he->cstats.lcl_hitm);
+	init_stats(&c2c_he->cstats.rmt_hitm);
+	init_stats(&c2c_he->cstats.lcl_peer);
+	init_stats(&c2c_he->cstats.rmt_peer);
+	init_stats(&c2c_he->cstats.load);
+
+	return &c2c_he->he;
+}
+
+/* Entry operations for function view */
+static struct hist_entry_ops c2c_function_entry_ops = {
+	.new	= c2c_function_he_zalloc,
+	.free	= c2c_function_he_free,
+};
+
+static struct c2c_hist_entry *
+c2c_child_entry__alloc(struct hist_entry *parent_he, struct hist_entry *src_he,
+		       int depth, u64 ip)
+{
+	struct c2c_hist_entry *child_c2c;
+	struct hist_entry *child_he;
+
+	/* Function-view children never own or display callchains. */
+	child_he = c2c_function_he_zalloc(0);
+	if (!child_he)
+		return NULL;
+
+	child_c2c = container_of(child_he, struct c2c_hist_entry, he);
+	memcpy(&child_he->ms, &src_he->ms, sizeof(struct map_symbol));
+
+	if (src_he->mem_info) {
+		child_he->mem_info = mem_info__clone(src_he->mem_info);
+		if (!child_he->mem_info)
+			goto out_free;
+	}
+
+	child_he->thread = src_he->thread;
+	child_he->cpumode = src_he->cpumode;
+	child_he->cpu = src_he->cpu;
+	child_he->socket = src_he->socket;
+	child_he->level = src_he->level;
+	child_he->ip = ip;
+
+	child_he->parent_he = parent_he;
+	child_he->depth = depth;
+	child_he->leaf = (depth >= 2);
+	child_he->hists = &c2c_ext.function_hists.hists;
+	child_he->filtered = false;
+	child_he->unfolded = false;
+	child_he->has_children = false;
+	child_he->has_no_entry = false;
+	child_he->nr_rows = 0;
+	child_he->row_offset = 0;
+
+	memset(&child_he->stat, 0, sizeof(child_he->stat));
+	child_he->hroot_in = RB_ROOT_CACHED;
+	child_he->hroot_out = RB_ROOT_CACHED;
+	INIT_LIST_HEAD(&child_he->pairs.node);
+	child_he->hpp_list = &c2c_ext.function_hists.list;
+	if (symbol_conf.cumulate_callchain) {
+		child_he->stat_acc = calloc(1, sizeof(struct he_stat));
+		if (!child_he->stat_acc)
+			goto out_free;
+	}
+
+	return child_c2c;
+
+out_free:
+	if (child_he->mem_info)
+		mem_info__put(child_he->mem_info);
+	free(child_c2c);
+	return NULL;
+}
+
+static void
+c2c_child_entry__insert(struct hist_entry *parent_he, struct hist_entry *child_he,
+			struct rb_node **p, struct rb_node *rb_parent, bool leftmost)
+{
+	rb_link_node(&child_he->rb_node, rb_parent, p);
+	rb_insert_color_cached(&child_he->rb_node, &parent_he->hroot_out, leftmost);
+
+	parent_he->has_children = true;
+	parent_he->leaf = false;
+}
+
+static __maybe_unused struct hist_entry *
+c2c_function_hists__level1_entry(struct symbol *sym,
+				 struct hist_entry *detail_he,
+				 struct thread *synthetic_thread)
+{
+	struct addr_location al;
+	struct perf_sample sample = {};
+	struct mem_info *mi;
+	struct hist_entry *he;
+	/*
+	 * Key the level-1 entry by the function, not by a specific code
+	 * address: use the symbol start so every instruction address inside
+	 * the same function collapses into one entry. This makes level 1 a
+	 * true "function view" rather than a per-code-address view.
+	 */
+	u64 sym_start = (sym && detail_he->ms.map) ?
+			map__unmap_ip(detail_he->ms.map, sym->start) : detail_he->ip;
+
+	mi = mem_info__new();
+	if (!mi)
+		return NULL;
+
+	mem_info__iaddr(mi)->addr = sym_start;
+	/* mem_info__put() will map_symbol__exit() these, so take refs. */
+	mem_info__iaddr(mi)->ms.thread = thread__get(detail_he->ms.thread);
+	mem_info__iaddr(mi)->ms.map = map__get(detail_he->ms.map);
+	mem_info__iaddr(mi)->ms.sym = sym;
+	mem_info__daddr(mi)->addr = 0;
+
+	addr_location__init(&al);
+	al.thread = thread__get(synthetic_thread);
+	al.map = map__get(detail_he->ms.map);
+	al.sym = sym;
+	al.addr = sym_start;
+	al.level = detail_he->level;
+	al.cpumode = detail_he->cpumode;
+	al.cpu = 0;
+	al.socket = 0;
+	al.filtered = 0;
+	al.latency = 0;
+
+	/*
+	 * Synthetic sample: period/weight are placeholders only. The real
+	 * c2c counters live in c2c_hist_entry::stats and are added via
+	 * hist_entry__add_c2c_stats(); no function-view column or sort key
+	 * reads he->stat.period/nr_events, so the +1 that __hists__add_entry()
+	 * accrues on each dedup hit has no effect on what is displayed.
+	 */
+	sample.period = 1;
+	sample.weight = 1;
+	sample.ip = sym_start;
+	sample.pid = thread__pid(synthetic_thread);
+	sample.tid = thread__tid(synthetic_thread);
+	sample.cpu = 0;
+
+	/* Add entry - histogram handles dedup */
+	he = hists__add_entry_ops(&c2c_ext.function_hists.hists,
+				  &c2c_function_entry_ops,
+				  &al, NULL, NULL, mi,
+				  NULL, &sample, true);
+
+	addr_location__exit(&al);
+	mem_info__put(mi);
+
+	if (he)
+		he->hpp_list = &c2c_ext.function_hists.list;
+
+	return he;
+}
+
+/*
+ * Level 2: a function that writes a cacheline the level-1 function reads,
+ * keyed by the DSO display name and symbol, consistently with perf's symbol
+ * sort semantics. All code addresses and cachelines for the same writer
+ * function aggregate into one row.
+ */
+static __maybe_unused struct c2c_hist_entry *
+c2c_function_hists__level2_entry(struct c2c_hist_entry *level1_c2c,
+				 struct symbol *sym, struct hist_entry *detail_he)
+{
+	struct hist_entry *level1_he = &level1_c2c->he;
+	struct rb_node **p = &level1_he->hroot_out.rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct c2c_hist_entry *level2_c2c;
+	bool leftmost = true;
+
+	while (*p) {
+		struct hist_entry *iter = rb_entry(*p, struct hist_entry, rb_node);
+		struct map_symbol key = detail_he->ms;
+		int64_t cmp;
+
+		key.sym = sym;
+		parent = *p;
+		cmp = c2c_function_cmp(&key, &iter->ms);
+
+		if (cmp < 0) {
+			p = &parent->rb_left;
+		} else if (cmp > 0) {
+			p = &parent->rb_right;
+			leftmost = false;
+		} else {
+			return container_of(iter, struct c2c_hist_entry, he);
+		}
+	}
+
+	/* Key by the function symbol start so all code addresses collapse. */
+	level2_c2c = c2c_child_entry__alloc(level1_he, detail_he, 1,
+					    (sym && detail_he->ms.map) ?
+						  map__unmap_ip(detail_he->ms.map, sym->start) :
+						  hist_entry__iaddr(detail_he));
+	if (!level2_c2c)
+		return NULL;
+
+	/* Key this level by the looked-up symbol, not detail_he's. */
+	level2_c2c->he.ms.sym = sym;
+	if (level2_c2c->he.mem_info)
+		mem_info__iaddr(level2_c2c->he.mem_info)->ms.sym = sym;
+
+	c2c_child_entry__insert(level1_he, &level2_c2c->he, p, parent, leftmost);
+
+	return level2_c2c;
+}
+
+/* Level 3: one source cacheline where the L1/L2 functions contend. */
+static __maybe_unused struct c2c_hist_entry *
+c2c_function_hists__level3_entry(struct c2c_hist_entry *level2_c2c,
+				 struct c2c_hist_entry *cacheline_src_he)
+{
+	struct hist_entry *level2_he = &level2_c2c->he;
+	struct rb_node **p = &level2_he->hroot_out.rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct c2c_hist_entry *level3_c2c;
+	bool leftmost = true;
+
+	while (*p) {
+		struct hist_entry *iter = rb_entry(*p, struct hist_entry, rb_node);
+		struct c2c_hist_entry *iter_c2c;
+
+		iter_c2c = container_of(iter, struct c2c_hist_entry, he);
+
+		parent = *p;
+		if (cacheline_src_he->cacheline_idx < iter_c2c->cacheline_idx) {
+			p = &parent->rb_left;
+		} else if (cacheline_src_he->cacheline_idx > iter_c2c->cacheline_idx) {
+			p = &parent->rb_right;
+			leftmost = false;
+		} else {
+			return container_of(iter, struct c2c_hist_entry, he);
+		}
+	}
+
+	level3_c2c = c2c_child_entry__alloc(level2_he, &cacheline_src_he->he, 2,
+					    hist_entry__iaddr(&cacheline_src_he->he));
+	if (!level3_c2c)
+		return NULL;
+	level3_c2c->cacheline_idx = cacheline_src_he->cacheline_idx;
+
+	c2c_child_entry__insert(level2_he, &level3_c2c->he, p, parent, leftmost);
+
+	return level3_c2c;
+}
+
 int perf_c2c__browse_function_view(void)
 {
 	ui__warning("C2C function view is not implemented yet.\n");
-- 
2.52.0

[PATCH v5 v5 7/9] perf c2c: build and finalize the function view hierarchy

[Jiebin Sun]

Add the builder that walks the top-level cacheline entries and, for each
read-side function, correlates the functions that write the same lines
(level 2) and the specific cachelines they contend over (level 3) within
each retained detail histogram. Aggregate the write traffic per contending
function, resort by store count, and prune writers/functions with no
contention. The finalize pass computes the global cycle total used as the
Cycles % denominator.

build_function_view_hierarchy() is wired into the browser entry point by
the next patch and is marked __maybe_unused until then.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/ui/browsers/c2c-function.c | 476 +++++++++++++++++++++++++-
 1 file changed, 462 insertions(+), 14 deletions(-)

diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
index b3528edb387a..9a95355eedf5 100644
--- a/tools/perf/ui/browsers/c2c-function.c
+++ b/tools/perf/ui/browsers/c2c-function.c
@@ -45,13 +45,13 @@ struct perf_c2c_ext {
 	u64			total_cycles;
 };
 
-static struct perf_c2c_ext c2c_ext __maybe_unused;
+static struct perf_c2c_ext c2c_ext;
 
 struct c2c_function_browser {
 	struct hist_browser	hb;
 };
 
-static inline __maybe_unused u64 c2c_hitm_count(const struct c2c_stats *stats)
+static inline u64 c2c_hitm_count(const struct c2c_stats *stats)
 {
 	return stats->tot_hitm;
 }
@@ -86,7 +86,7 @@ static int64_t c2c_function_cmp(const struct map_symbol *left,
 	return _sort__sym_cmp(left->sym, right->sym);
 }
 
-static inline __maybe_unused u64 hist_entry__iaddr(struct hist_entry *he)
+static inline u64 hist_entry__iaddr(struct hist_entry *he)
 {
 	if (he->mem_info)
 		return mem_info__iaddr(he->mem_info)->addr;
@@ -219,7 +219,7 @@ static u64 c2c_hist_entry__cycles(struct c2c_hist_entry *c2c_he)
 }
 
 /* Sum c2c_hist_entry__cycles() across all level-1 entries. */
-static u64 __maybe_unused c2c_ext__total_cycles(void)
+static u64 c2c_ext__total_cycles(void)
 {
 	struct rb_node *nd;
 	u64 total = 0;
@@ -662,7 +662,7 @@ function_hpp_list__parse(struct perf_hpp_list *hpp_list,
 	return ret;
 }
 
-static int __maybe_unused
+static int
 c2c_function_hists__init(struct c2c_hists *hists,
 			 const char *sort,
 			 int nr_header_lines,
@@ -677,7 +677,7 @@ c2c_function_hists__init(struct c2c_hists *hists,
 	return function_hpp_list__parse(&hists->list, /*output=*/NULL, sort, env);
 }
 
-static int __maybe_unused
+static int
 c2c_function_hists__reinit(struct c2c_hists *c2c_hists,
 			   const char *output,
 			   const char *sort,
@@ -726,8 +726,8 @@ static void c2c_stats_merge(struct stats *dest, const struct stats *src)
 }
 
 /* Merge compute_stats during function aggregation. */
-static void __maybe_unused c2c_add_cstats(struct compute_stats *dest,
-					  const struct compute_stats *src)
+static void c2c_add_cstats(struct compute_stats *dest,
+			   const struct compute_stats *src)
 {
 	c2c_stats_merge(&dest->rmt_hitm, &src->rmt_hitm);
 	c2c_stats_merge(&dest->lcl_hitm, &src->lcl_hitm);
@@ -736,8 +736,8 @@ static void __maybe_unused c2c_add_cstats(struct compute_stats *dest,
 	c2c_stats_merge(&dest->load, &src->load);
 }
 
-static bool __maybe_unused hist_entry__add_c2c_stats(struct hist_entry *he,
-						     const struct c2c_stats *stats)
+static bool hist_entry__add_c2c_stats(struct hist_entry *he,
+				      const struct c2c_stats *stats)
 {
 	u64 nr_events = c2c_hitm_count(stats) + stats->rmt_peer + stats->lcl_peer;
 	u64 weight1 = c2c_hitm_count(stats);
@@ -859,7 +859,7 @@ static void c2c_he__free_hierarchy(struct hist_entry *he)
  * line, so this is mainly a safety net. Returns the number of surviving
  * writers.
  */
-static int __maybe_unused c2c_he__prune_empty_writers(struct hist_entry *l1_he)
+static int c2c_he__prune_empty_writers(struct hist_entry *l1_he)
 {
 	struct rb_node *nd;
 	int surviving = 0;
@@ -981,7 +981,7 @@ c2c_child_entry__insert(struct hist_entry *parent_he, struct hist_entry *child_h
 	parent_he->leaf = false;
 }
 
-static __maybe_unused struct hist_entry *
+static struct hist_entry *
 c2c_function_hists__level1_entry(struct symbol *sym,
 				 struct hist_entry *detail_he,
 				 struct thread *synthetic_thread)
@@ -1057,7 +1057,7 @@ c2c_function_hists__level1_entry(struct symbol *sym,
  * sort semantics. All code addresses and cachelines for the same writer
  * function aggregate into one row.
  */
-static __maybe_unused struct c2c_hist_entry *
+static struct c2c_hist_entry *
 c2c_function_hists__level2_entry(struct c2c_hist_entry *level1_c2c,
 				 struct symbol *sym, struct hist_entry *detail_he)
 {
@@ -1105,7 +1105,7 @@ c2c_function_hists__level2_entry(struct c2c_hist_entry *level1_c2c,
 }
 
 /* Level 3: one source cacheline where the L1/L2 functions contend. */
-static __maybe_unused struct c2c_hist_entry *
+static struct c2c_hist_entry *
 c2c_function_hists__level3_entry(struct c2c_hist_entry *level2_c2c,
 				 struct c2c_hist_entry *cacheline_src_he)
 {
@@ -1143,6 +1143,454 @@ c2c_function_hists__level3_entry(struct c2c_hist_entry *level2_c2c,
 	return level3_c2c;
 }
 
+/*
+ * Re-sort child entries of @parent_he by total store count, descending.
+ */
+static void c2c_he__resort_by_stores(struct hist_entry *parent_he)
+{
+	struct rb_root_cached new_root = RB_ROOT_CACHED;
+	struct rb_node *nd;
+
+	if (!parent_he->has_children)
+		return;
+
+	/* Extract all nodes and re-insert sorted by displayed store count */
+	while ((nd = rb_first_cached(&parent_he->hroot_out))) {
+		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+		u64 he_store = hist_entry__displayed_stores(he);
+		struct rb_node **p = &new_root.rb_root.rb_node;
+		struct rb_node *parent = NULL;
+		bool leftmost = true;
+		int cmp;
+
+		/* Remove from current tree */
+		rb_erase_cached(&he->rb_node, &parent_he->hroot_out);
+
+		/*
+		 * Insert sorted by store count, descending. Use the displayed
+		 * store count so a level-1 function and level-2 writer (whose own
+		 * stats.store is 0 / partial) sort by the aggregated write traffic
+		 * beneath them, not by their own store field.
+		 */
+		while (*p) {
+			struct hist_entry *iter = rb_entry(*p, struct hist_entry, rb_node);
+			u64 iter_store = hist_entry__displayed_stores(iter);
+
+			parent = *p;
+			if (he_store != iter_store) {
+				cmp = he_store > iter_store ? -1 : 1;
+			} else {
+				/* Stable tie-break: instruction address, name, then cacheline. */
+				u64 a = hist_entry__iaddr(he), b = hist_entry__iaddr(iter);
+
+				if (a != b)
+					cmp = a < b ? -1 : 1;
+				else if (he->ms.sym && iter->ms.sym)
+					cmp = strcmp(he->ms.sym->name,
+						     iter->ms.sym->name);
+				else
+					cmp = (iter->ms.sym ? 1 : 0) - (he->ms.sym ? 1 : 0);
+
+				if (!cmp) {
+					struct c2c_hist_entry *he_c2c;
+					struct c2c_hist_entry *iter_c2c;
+
+					he_c2c = container_of(he, struct c2c_hist_entry, he);
+					iter_c2c = container_of(iter, struct c2c_hist_entry, he);
+					if (he_c2c->cacheline_idx != iter_c2c->cacheline_idx)
+						cmp = he_c2c->cacheline_idx <
+						      iter_c2c->cacheline_idx ? -1 : 1;
+				}
+			}
+
+			if (cmp < 0) {
+				p = &parent->rb_left;
+			} else {
+				p = &parent->rb_right;
+				leftmost = false;
+			}
+		}
+
+		rb_link_node(&he->rb_node, parent, p);
+		rb_insert_color_cached(&he->rb_node, &new_root, leftmost);
+	}
+
+	parent_he->hroot_out = new_root;
+}
+
+/* Initial per-cacheline capacity for the seen[] set; grown on demand. */
+#define DEFAULT_SYMBOLS_PER_CL 64
+
+struct function_seen {
+	struct map_symbol ms;
+};
+
+static bool function_seen__find(const struct function_seen *seen, int nr,
+				const struct map_symbol *ms)
+{
+	int i;
+
+	for (i = 0; i < nr; i++) {
+		if (!c2c_function_cmp(&seen[i].ms, ms))
+			return true;
+	}
+	return false;
+}
+
+/* Aggregate stats from the cacheline-side entry @c2c_b into level 2/3 @dst. */
+static bool c2c_he__add_sharing(struct c2c_hist_entry *dst, struct c2c_hist_entry *src)
+{
+	/* Do the fallible update first so a failure leaves dst unmodified. */
+	if (!hist_entry__add_c2c_stats(&dst->he, &src->stats))
+		return false;
+
+	c2c_add_stats(&dst->stats, &src->stats);
+	c2c_add_cstats(&dst->cstats, &src->cstats);
+	return true;
+}
+
+/*
+ * Process one cacheline: for every function reading it, create/update its
+ * level-1 function entry, then for each function that writes the line
+ * add it as a level-2 writer and add this cacheline as a level-3 child.
+ */
+static int c2c_function__process_cl(struct c2c_hist_entry *cacheline_he,
+				    struct thread *synthetic_thread)
+{
+	struct rb_node *nd_a, *nd_b;
+	struct function_seen *seen = NULL;
+	int nr_seen = 0, nr_alloc = 0;
+	int ret = 0;
+
+	for (nd_a = rb_first_cached(&cacheline_he->hists->hists.entries); nd_a;
+	     nd_a = rb_next(nd_a)) {
+		struct hist_entry *he_a = rb_entry(nd_a, struct hist_entry, rb_node);
+		struct c2c_hist_entry *c2c_a;
+		struct hist_entry *level1_he;
+		struct c2c_hist_entry *level1_c2c;
+
+		if (!he_a->ms.sym || he_a->filtered)
+			continue;
+
+		c2c_a = container_of(he_a, struct c2c_hist_entry, he);
+		if (c2c_a->stats.load == 0)
+			continue;
+
+		level1_he = c2c_function_hists__level1_entry(he_a->ms.sym,
+							     he_a, synthetic_thread);
+		if (!level1_he) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		level1_c2c = container_of(level1_he, struct c2c_hist_entry, he);
+
+		/*
+		 * Aggregate every source entry into its level-1 function parent.
+		 * level1_he is keyed by symbol, so all code addresses inside the
+		 * same function collapse into one parent. When the cacheline view
+		 * splits a function into siblings (different code addresses, or
+		 * --coalesce pid/tid/dso), each sibling holds a DISJOINT slice of the
+		 * traffic, so summing them here is correct accumulation, not
+		 * double counting. The seen[] set below therefore guards only the
+		 * subtree build (to avoid building a function's level-2/3 subtree
+		 * twice for the same cacheline), never this L1 update. Update
+		 * he->stat first; on failure leave the aggregates untouched.
+		 */
+		if (!hist_entry__add_c2c_stats(level1_he, &c2c_a->stats)) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		c2c_add_stats(&level1_c2c->stats, &c2c_a->stats);
+		c2c_add_cstats(&level1_c2c->cstats, &c2c_a->cstats);
+		c2c_add_stats(&c2c_ext.function_hists.stats, &c2c_a->stats);
+
+		/* Build this function's subtree for this cacheline only once. */
+		if (function_seen__find(seen, nr_seen, &he_a->ms))
+			continue;
+
+		if (nr_seen == nr_alloc) {
+			struct function_seen *tmp;
+			int new_alloc = nr_alloc ? nr_alloc * 2 : DEFAULT_SYMBOLS_PER_CL;
+
+			tmp = reallocarray(seen, new_alloc, sizeof(*seen));
+			if (!tmp) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			seen = tmp;
+			nr_alloc = new_alloc;
+		}
+		seen[nr_seen].ms = he_a->ms;
+		nr_seen++;
+
+		for (nd_b = rb_first_cached(&cacheline_he->hists->hists.entries); nd_b;
+		     nd_b = rb_next(nd_b)) {
+			struct hist_entry *he_b = rb_entry(nd_b, struct hist_entry, rb_node);
+			struct c2c_hist_entry *c2c_b, *level2_c2c, *level3_c2c;
+
+			if (!he_b->ms.sym || he_b->filtered)
+				continue;
+
+			c2c_b = container_of(he_b, struct c2c_hist_entry, he);
+
+			/*
+			 * The level-1 function contributes read-side load weight for this
+			 * cacheline. Associate it with functions sampled storing to the
+			 * same line.
+			 * The writer can be the same function; after detail coalescing and
+			 * function-level grouping there is not enough identity to attribute
+			 * that case to a specific thread.
+			 * Only writers are contending functions, so keep the ones
+			 * that actually store into the line.
+			 */
+			if (c2c_b->stats.store == 0)
+				continue;
+
+			/* Level 2: the writing function (aggregated across cachelines). */
+			level2_c2c = c2c_function_hists__level2_entry(level1_c2c, he_b->ms.sym,
+								      he_b);
+			if (!level2_c2c || !c2c_he__add_sharing(level2_c2c, c2c_b)) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			/* Level 3: the specific cacheline they contend over. */
+			level3_c2c = c2c_function_hists__level3_entry(level2_c2c,
+								      cacheline_he);
+			if (!level3_c2c || !c2c_he__add_sharing(level3_c2c, c2c_b)) {
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+	}
+
+out:
+	free(seen);
+	return ret;
+}
+
+/*
+ * Remove a level-1 function that has no contended cachelines left. It is a
+ * normal (owned) hist_entry in function_hists, so mirror hists__delete_entry()
+ * for the no-collapse case: unlink from both trees, fix the counters, then
+ * delete. report_hierarchy is never set and its hroot_out is already empty, so
+ * hist_entry__delete() will not recurse into borrowed children.
+ */
+static void c2c_function__drop_level1(struct hist_entry *he)
+{
+	struct hists *hists = &c2c_ext.function_hists.hists;
+
+	rb_erase_cached(&he->rb_node_in, hists->entries_in);
+	rb_erase_cached(&he->rb_node, &hists->entries);
+
+	--hists->nr_entries;
+	if (!he->filtered)
+		--hists->nr_non_filtered_entries;
+
+	hist_entry__delete(he);
+}
+
+/* Length of the identity text (symbol name or cacheline address) at @he. */
+static int c2c_function__ident_len(struct hist_entry *he)
+{
+	char buf[512];
+	char *symbuf;
+	size_t size;
+	int len;
+
+	if (hist_entry__is_cacheline(he)) {
+		u64 addr = he->mem_info ?
+			cl_address(mem_info__daddr(he->mem_info)->addr, chk_double_cl) : 0;
+
+		return scnprintf(buf, sizeof(buf), "0x%" PRIx64, addr);
+	}
+
+	if (!he->ms.sym)
+		return 0;
+
+	/*
+	 * Match symbol_view_entry(): sort_sym adds the cpumode prefix and, in
+	 * verbose mode, the address and DSO origin before the symbol name.
+	 */
+	size = strlen(he->ms.sym->name) + 64;
+	symbuf = malloc(size);
+	if (!symbuf)
+		return size - 1;
+
+	len = sort_sym.se_snprintf(he, symbuf, size, size - 1);
+	free(symbuf);
+	return len;
+}
+
+/*
+ * Grow the symbol column so the deepest, longest identity cell fits. The
+ * generic hists__calc_col_len() only measures the top-level (L1) entries; the
+ * hand-linked L2 writers and L3 cacheline addresses live in hroot_out and are
+ * never measured, so with a short L1 name the indented L2/L3 text would be
+ * truncated. Account for the per-level indent and the folded-sign prefix.
+ */
+static void c2c_function__update_symbol_width(struct hist_entry *he)
+{
+	struct hists *hists = &c2c_ext.function_hists.hists;
+	int need = he->depth * C2C_FUNC_INDENT + C2C_FUNC_FOLD_WIDTH +
+		   c2c_function__ident_len(he);
+
+	if (need > hists__col_len(hists, HISTC_SYMBOL))
+		hists__set_col_len(hists, HISTC_SYMBOL, need);
+}
+
+/*
+ * Prune writers with no stores, drop functions left with no contending
+ * writer, sort the survivors by store count, then compute the global total.
+ */
+static void c2c_function__finalize(void)
+{
+	struct rb_node *nd_l1;
+
+	nd_l1 = rb_first_cached(&c2c_ext.function_hists.hists.entries);
+	while (nd_l1) {
+		struct hist_entry *he_l1 = rb_entry(nd_l1, struct hist_entry, rb_node);
+		struct rb_node *next_l1 = rb_next(nd_l1);
+		struct rb_node *nd_l2;
+
+		/* Drop writers with no stores before sorting. */
+		if (!he_l1->has_children || !c2c_he__prune_empty_writers(he_l1)) {
+			/* No contending writer: this function is not shared. */
+			c2c_function__drop_level1(he_l1);
+			nd_l1 = next_l1;
+			continue;
+		}
+
+		c2c_he__resort_by_stores(he_l1);
+		c2c_function__update_symbol_width(he_l1);
+
+		for (nd_l2 = rb_first_cached(&he_l1->hroot_out); nd_l2;
+		     nd_l2 = rb_next(nd_l2)) {
+			struct hist_entry *he_l2 = rb_entry(nd_l2, struct hist_entry, rb_node);
+			struct rb_node *nd_l3;
+
+			c2c_function__update_symbol_width(he_l2);
+
+			if (he_l2->has_children)
+				c2c_he__resort_by_stores(he_l2);
+
+			for (nd_l3 = rb_first_cached(&he_l2->hroot_out); nd_l3;
+			     nd_l3 = rb_next(nd_l3)) {
+				struct hist_entry *he_l3 = rb_entry(nd_l3, struct hist_entry,
+								    rb_node);
+
+				c2c_function__update_symbol_width(he_l3);
+			}
+		}
+
+		nd_l1 = next_l1;
+	}
+
+	c2c_ext.total_cycles = c2c_ext__total_cycles();
+}
+
+/*
+ * Release all per-visit function-view state. Keep the hists object itself
+ * initialized so its mutex is initialized exactly once across TAB re-entry.
+ */
+static void c2c_function_hists__reset(void)
+{
+	hists__delete_all_entries(&c2c_ext.function_hists.hists);
+	if (c2c_ext.function_hists.list.fields.next)
+		perf_hpp__reset_output_field(&c2c_ext.function_hists.list);
+
+	memset(&c2c_ext.function_hists.stats, 0,
+	       sizeof(c2c_ext.function_hists.stats));
+	c2c_ext.total_cycles = 0;
+}
+
+/*
+ * Build the three-level function view in a single pass over the cacheline
+ * entries:
+ *   L1: read-side functions (aggregated across all their code addresses)
+ *   L2: writing functions contending with each level-1 function
+ *   L3: shared cachelines for each function pair
+ */
+static int __maybe_unused build_function_view_hierarchy(void)
+{
+	static const char output_fields[] =
+		"cycles_percent,total_stores,symbol_view";
+	static bool hists_initialized;
+	struct rb_node *nd_cl;
+	int ret;
+
+	c2c_function_hists__reset();
+
+	/*
+	 * __hists__init() (called by c2c_function_hists__init()) also
+	 * mutex_init()s the hists lock, so only run it once for this static
+	 * hists; on re-entry just re-parse the columns via reinit().
+	 */
+	if (!hists_initialized) {
+		ret = c2c_function_hists__init(&c2c_ext.function_hists,
+					       "symbol_view", 2, NULL);
+		hists_initialized = true;
+	} else {
+		ret = c2c_function_hists__reinit(&c2c_ext.function_hists,
+						 /*output=*/NULL, "symbol_view", NULL);
+	}
+	if (ret)
+		return ret;
+
+	nd_cl = rb_first_cached(&c2c.hists.hists.entries);
+
+	/* An empty C2C report yields an empty (but valid) function view. */
+	for (; nd_cl; nd_cl = rb_next(nd_cl)) {
+		struct hist_entry *he_cl = rb_entry(nd_cl, struct hist_entry, rb_node);
+		struct c2c_hist_entry *cacheline_he = container_of(he_cl,
+								   struct c2c_hist_entry, he);
+		struct thread *synthetic_thread = he_cl->thread;
+
+		/*
+		 * Detail hists are finalized only for cachelines retained by the
+		 * top-level C2C filter. Among those, include any line with sharing
+		 * activity, not just HITM.
+		 */
+		if (he_cl->filtered ||
+		    (c2c_hitm_count(&cacheline_he->stats) == 0 &&
+		     cacheline_he->stats.tot_peer == 0 &&
+		     cacheline_he->stats.store == 0 &&
+		     cacheline_he->stats.load == 0) ||
+		    !cacheline_he->hists ||
+		    RB_EMPTY_ROOT(&cacheline_he->hists->hists.entries.rb_root) ||
+		    !he_cl->mem_info || !synthetic_thread)
+			continue;
+
+		ret = c2c_function__process_cl(cacheline_he, synthetic_thread);
+		if (ret)
+			goto out_err;
+	}
+
+	ret = c2c_function_hists__reinit(&c2c_ext.function_hists, output_fields,
+					 "cycles_percent", NULL);
+	if (ret)
+		goto out_err;
+
+	hists__collapse_resort(&c2c_ext.function_hists.hists, NULL);
+	hists__output_resort(&c2c_ext.function_hists.hists, NULL);
+
+	c2c_function__finalize();
+
+	return 0;
+
+out_err:
+	/*
+	 * On error, migrate any entries still in entries_in to entries and
+	 * delete them, so a later rebuild does not strand them (the top-level
+	 * __hists__init() memset would otherwise lose the pointers).
+	 */
+	hists__collapse_resort(&c2c_ext.function_hists.hists, NULL);
+	hists__output_resort(&c2c_ext.function_hists.hists, NULL);
+	c2c_function_hists__reset();
+	return ret;
+}
+
 int perf_c2c__browse_function_view(void)
 {
 	ui__warning("C2C function view is not implemented yet.\n");
-- 
2.52.0

[PATCH v5 v5 8/9] perf c2c: add function view browser UI and cacheline detail

[Jiebin Sun]

Add the browser front end: create/run/delete the hist_browser and add the
title. The d shortcut opens the existing per-cacheline detail view for the
selected level-3 cacheline. Level-3 entries retain the source cacheline
index, so the shortcut can locate the original entry without relying on a
potentially ambiguous virtual address.

Require `iaddr` in the cacheline coalescing fields before building the
view. Without it, the detail histograms may already have merged samples
from different functions and cannot support reliable function attribution.

Keep visible-row accounting local to the function view by wrapping the
generic browser refresh callback and recounting the currently reachable
hierarchy before each redraw. This keeps navigation correct when a level-1
row is collapsed while level-3 descendants remain expanded, without adding
C2C-specific hooks to the shared hist_browser or enabling report_hierarchy
and its incompatible ownership rules. Also handle Ctrl-C like the other
function-view exit keys.

Wire the builder into perf_c2c__browse_function_view() and refuse to run
under report_hierarchy, whose hist_entry__delete() recursion would put the
borrowed child references.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/ui/browsers/c2c-function.c | 239 +++++++++++++++++++++++++-
 1 file changed, 236 insertions(+), 3 deletions(-)

diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
index 9a95355eedf5..44fb072fa937 100644
--- a/tools/perf/ui/browsers/c2c-function.c
+++ b/tools/perf/ui/browsers/c2c-function.c
@@ -15,6 +15,7 @@
 #include <inttypes.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/ttydefaults.h>
 #include <tools/libc_compat.h> /* reallocarray */
 #include <asm/bug.h>
 #include <linux/list.h>
@@ -49,6 +50,7 @@ static struct perf_c2c_ext c2c_ext;
 
 struct c2c_function_browser {
 	struct hist_browser	hb;
+	unsigned int		(*orig_refresh)(struct ui_browser *browser);
 };
 
 static inline u64 c2c_hitm_count(const struct c2c_stats *stats)
@@ -93,6 +95,10 @@ static inline u64 hist_entry__iaddr(struct hist_entry *he)
 	return he->ip;
 }
 
+/*
+ * Hierarchy levels (by depth): L1 = read-side function, L2 = the writing
+ * function it contends with, L3 = the specific shared cacheline.
+ */
 static inline bool hist_entry__is_cacheline(struct hist_entry *he)
 {
 	return he->parent_he && he->parent_he->parent_he;	/* level 3: cacheline */
@@ -701,6 +707,7 @@ c2c_function_hists__reinit(struct c2c_hists *c2c_hists,
 	return function_hpp_list__parse(&c2c_hists->list, output, sort, env);
 }
 
+/* Welford online merge of two "stats" (from util/stat.h) accumulators. */
 static void c2c_stats_merge(struct stats *dest, const struct stats *src)
 {
 	double delta;
@@ -1440,6 +1447,58 @@ static void c2c_function__update_symbol_width(struct hist_entry *he)
 		hists__set_col_len(hists, HISTC_SYMBOL, need);
 }
 
+/*
+ * Count visible entries in @root, descending only through visible, unfolded
+ * parents. Match hists__filter_entries(), which drives generic browser
+ * navigation, so the count cannot include rows the browser skips.
+ */
+static u64
+c2c_function__nr_visible_rows(struct rb_root_cached *root, float min_pcnt)
+{
+	struct rb_node *nd;
+	u64 rows = 0;
+
+	for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) {
+		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+
+		/*
+		 * The generic refresh folds filtered parents and therefore hides
+		 * their subtree. A percentage-rejected parent is merely skipped;
+		 * if it is unfolded, qualifying descendants are still rendered.
+		 */
+		if (he->filtered)
+			continue;
+
+		if (hist_entry__get_percent_limit(he) >= min_pcnt)
+			rows++;
+		if (he->has_children && he->unfolded)
+			rows += c2c_function__nr_visible_rows(&he->hroot_out,
+							     min_pcnt);
+	}
+	return rows;
+}
+
+static void
+c2c_function_browser__update_nr_entries(struct c2c_function_browser *browser)
+{
+	u64 nr_entries;
+
+	nr_entries = c2c_function__nr_visible_rows(&browser->hb.hists->entries,
+						   browser->hb.min_pcnt);
+	browser->hb.nr_non_filtered_entries = nr_entries;
+	browser->hb.b.nr_entries = nr_entries;
+}
+
+static unsigned int c2c_function_browser__refresh(struct ui_browser *ui_browser)
+{
+	struct hist_browser *hist_browser = container_of(ui_browser, struct hist_browser, b);
+	struct c2c_function_browser *browser;
+
+	browser = container_of(hist_browser, struct c2c_function_browser, hb);
+	c2c_function_browser__update_nr_entries(browser);
+	return browser->orig_refresh(ui_browser);
+}
+
 /*
  * Prune writers with no stores, drop functions left with no contending
  * writer, sort the survivors by store count, then compute the global total.
@@ -1512,7 +1571,7 @@ static void c2c_function_hists__reset(void)
  *   L2: writing functions contending with each level-1 function
  *   L3: shared cachelines for each function pair
  */
-static int __maybe_unused build_function_view_hierarchy(void)
+static int build_function_view_hierarchy(void)
 {
 	static const char output_fields[] =
 		"cycles_percent,total_stores,symbol_view";
@@ -1591,8 +1650,182 @@ static int __maybe_unused build_function_view_hierarchy(void)
 	return ret;
 }
 
-int perf_c2c__browse_function_view(void)
+static int c2c_function_browser__title(struct hist_browser *browser,
+				       char *bf, size_t size)
 {
-	ui__warning("C2C function view is not implemented yet.\n");
+	scnprintf(bf, size,
+		  "Shared Data Functions Table     (%" PRIu64 " entries, sorted on Cycles %%)",
+		  browser->hists->nr_non_filtered_entries);
 	return 0;
 }
+
+static struct c2c_function_browser *c2c_function_browser__new(struct hists *hists)
+{
+	struct c2c_function_browser *browser;
+
+	if (!hists)
+		return NULL;
+
+	browser = zalloc(sizeof(*browser));
+	if (!browser)
+		return NULL;
+
+	hist_browser__init(&browser->hb, hists);
+	browser->orig_refresh = browser->hb.b.refresh;
+	browser->hb.b.refresh = c2c_function_browser__refresh;
+
+	browser->hb.title = c2c_function_browser__title;
+	browser->hb.c2c_filter = true;
+	browser->hb.show_headers = true;
+	/* Keep title line count consistent with forcing headers on. */
+	browser->hb.b.extra_title_lines = hists->hpp_list->nr_header_lines;
+	browser->hb.min_pcnt = 0.0;
+
+	/*
+	 * Note: symbol_conf.report_hierarchy is deliberately left unset.
+	 * The generic browser still descends into hroot_out children via
+	 * rb_hierarchy_next()/can_goto_child(), which key off he->unfolded,
+	 * so 'e'/'+' expands L1 -> L2 -> L3 correctly. Setting the flag would
+	 * additionally make hist_entry__delete() recurse hroot_out and free
+	 * each child, but our children borrow thread/ms (see
+	 * c2c_child_entry__alloc()), so that would underflow their refcounts.
+	 * Teardown is handled by c2c_he__free_hierarchy() instead.
+	 */
+	return browser;
+}
+
+/*
+ * c2c_function_browser__delete - Free function browser
+ */
+static void c2c_function_browser__delete(struct c2c_function_browser *browser)
+{
+	free(browser);
+}
+
+static int c2c_function_browser__browse_cacheline_detail(struct hist_entry *he_selection)
+{
+	struct c2c_hist_entry *c2c_he;
+	struct rb_node *nd;
+
+	if (!he_selection || !he_selection->parent_he ||
+	    !he_selection->parent_he->parent_he)
+		return -1;
+
+	c2c_he = container_of(he_selection, struct c2c_hist_entry, he);
+
+	for (nd = rb_first_cached(&c2c.hists.hists.entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+		struct c2c_hist_entry *cacheline_he;
+
+		if (he->filtered)
+			continue;
+
+		cacheline_he = container_of(he, struct c2c_hist_entry, he);
+		if (cacheline_he->hists &&
+		    cacheline_he->cacheline_idx == c2c_he->cacheline_idx)
+			return perf_c2c__browse_cacheline(he);
+	}
+
+	return -1;
+}
+
+static bool c2c_function__has_iaddr(void)
+{
+	const char *field = c2c.cl_sort;
+
+	while (field && *field) {
+		const char *end = strchr(field, ',');
+		size_t len = end ? (size_t)(end - field) : strlen(field);
+
+		if (len == sizeof("iaddr") - 1 && !strncmp(field, "iaddr", len))
+			return true;
+		field = end ? end + 1 : NULL;
+	}
+	return false;
+}
+
+/*
+ * perf_c2c__browse_function_view - Browse function view with TAB key support
+ *
+ * Returns: 0 on success, negative error code on failure
+ */
+int perf_c2c__browse_function_view(void)
+{
+	struct c2c_function_browser *sym_browser;
+	bool saved_use_callchain = symbol_conf.use_callchain;
+	int key, ret;
+	static const char help[] =
+	" d             Display details for the selected level-3 cacheline\n"
+	" e/+           Expand/collapse the selected entry\n"
+	" TAB/ESC/q/^C  Return to the cacheline view\n";
+
+	if (!c2c_function__has_iaddr()) {
+		ui__warning("The function view requires iaddr in --coalesce.\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * The level-2/3 children borrow thread/ms (see c2c_child_entry__alloc())
+	 * and are torn down by c2c_he__free_hierarchy(). report_hierarchy would
+	 * make hist_entry__delete() recurse into hroot_out and put those borrowed
+	 * refs (and call a NULL ops->free), so refuse to run if it is ever set.
+	 */
+	if (WARN_ON_ONCE(symbol_conf.report_hierarchy))
+		return -EINVAL;
+
+	/* Disable callchain before building so no callchain structs are allocated. */
+	symbol_conf.use_callchain = false;
+
+	ret = build_function_view_hierarchy();
+	if (ret) {
+		ui__error("Failed to build function view hierarchy (ret=%d)\n", ret);
+		goto out;
+	}
+
+	sym_browser = c2c_function_browser__new(&c2c_ext.function_hists.hists);
+	if (!sym_browser) {
+		ret = -ENOMEM;
+		goto out_reset;
+	}
+
+	/* Reset abort key so we can receive Ctrl-C as a key. */
+	SLang_reset_tty();
+	SLang_init_tty(0, 0, 0);
+	SLtty_set_suspend_state(true);
+
+	while (1) {
+		c2c_function_browser__update_nr_entries(sym_browser);
+		key = hist_browser__run(&sym_browser->hb, "? - help", true, 0);
+
+		switch (key) {
+		case 'q':
+		case K_TAB:
+		case K_ESC:
+		case CTRL('c'):
+			goto browser_done;
+		case 'd':
+			/* Cacheline detail honors the user's callchain setting. */
+			symbol_conf.use_callchain = saved_use_callchain;
+			c2c_function_browser__browse_cacheline_detail(sym_browser->hb.he_selection);
+			/* Preserve any toggle made in the detail view, then
+			 * re-disable callchain for the function view.
+			 */
+			saved_use_callchain = symbol_conf.use_callchain;
+			symbol_conf.use_callchain = false;
+			break;
+		case '?':
+			ui_browser__help_window(&sym_browser->hb.b, help);
+			break;
+		default:
+			break;
+		}
+	}
+
+browser_done:
+	c2c_function_browser__delete(sym_browser);
+out_reset:
+	c2c_function_hists__reset();
+out:
+	symbol_conf.use_callchain = saved_use_callchain;
+	return ret;
+}
-- 
2.52.0

[PATCH v5 v5 9/9] perf c2c: document function view in perf-c2c man page

[Jiebin Sun]

Describe the function view hierarchy (read-side function -> contending
writer function -> shared cachelines), the per-level indentation, and the
keys, with a worked example.

Document that reliable function attribution requires `iaddr` in
`--coalesce`, that the reader and writer may be the same function, and why
the coalesced function view cannot distinguish same-thread from
different-thread accesses in that case. Also document that verbose mode
includes code addresses in function rows.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Wangyang Guo <wangyang.guo@intel.com>
---
 tools/perf/Documentation/perf-c2c.txt | 71 +++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index e57a122b8719..8775889bc0a3 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -365,6 +365,77 @@ TUI OUTPUT
 The TUI output provides interactive interface to navigate
 through cachelines list and to display offset details.
 
+Pressing the 'TAB' key in the cacheline view switches to the function
+view.  The function view shows a three-level hierarchy of the symbolized
+entries retained in the cacheline view, organized around functions rather
+than cachelines.  Levels 1 and 2 normally show function names, while level 3
+shows cacheline addresses.  Lower levels are indented beneath their parents.
+Verbose mode also includes code addresses in function rows, and code addresses
+remain available in the per-cacheline detail view ('d').
+
+The function view requires `iaddr` in the cacheline coalescing fields.  If
+`--coalesce` omits it, TAB reports that the view is unavailable rather than
+attributing already-coalesced samples to an arbitrary function.
+
+  Level 1: the read-side function, sorted by Cycles % (estimated load
+           cycles: HITM, peer-snoop and other-load cycles)
+  Level 2: the functions sampled writing the shared lines read by the
+           level-1 function, sorted by store count.  This can be the same
+           function when it has both read and write samples
+  Level 3: the specific cachelines shared by the reader/writer pair
+
+The Cycles % value is the function's share of event-provided load
+latency/weight estimates from cacheline-detail entries retained in the
+current view.  It can include non-HITM and non-peer loads coalesced into
+entries that pass the C2C filter, so it is not a pure contention-cycle
+percentage.  The share is relative to the functions and entries retained
+for the current report and is not comparable across recordings or different
+`--coalesce` settings.
+
+The store count on a level-1 row is the number of sampled stores by writers
+shown in the function view into the cachelines that function reads, including
+stores from the same function.  It decomposes into the level-2 writer rows;
+each level-2 count in turn decomposes into that writer's stores on its level-3
+cachelines.  A level-3 count is therefore not the cacheline's total store
+count.  The level-1 value is not the number of stores made by the reader and
+is not additive across level-1 rows: two functions reading the same line each
+carry the stores into that line.
+
+Each function aggregates all of its code addresses into a single entry,
+and a level-2 writer aggregates all of its shared cachelines, so a
+reader/writer pair is a single row with its total shown -- there is no
+need to sum a writer's traffic across cachelines by hand.
+
+In the function view the 'd' key opens the detail view of the selected
+level-3 cacheline, 'e'/'+' expands or collapses the current entry, and 'TAB',
+'ESC', 'q' or Ctrl-C returns to the cacheline view.
+
+For example, with the first two read-side functions collapsed and
+dequeue_pushable_task expanded to show the functions writing the lines it
+reads -- two of which are further expanded to their individual cachelines:
+
+  Shared Data Functions Table     (19 entries, sorted on Cycles %)
+     Cycles    Store
+          %    count  Function / Contending function / Cacheline
+  ----------------------------------------------------------------------
+  +  35.67%      876  + [k] cpupri_set
+  +  24.31%      424  + [k] pull_rt_task
+  -  16.53%      555  - [k] dequeue_pushable_task
+                 145    - [k] pull_rt_task
+                 145        0xff2d0082809da080
+                 139    - [k] enqueue_pushable_task
+                  70        0xff2d00a2071f9640
+                  69        0xff2d0082809da000
+
+Here dequeue_pushable_task pays 16.53% of the estimated read-side load-cycle
+cost.  Its store count decomposes into its level-2 writers, and each writer's
+count decomposes into its level-3 cachelines: pull_rt_task's 145 stores fall
+on a single line, while enqueue_pushable_task's 139 stores split across two
+lines (70 and 69).  A writer can be the same function as the reader when it
+has both read and write samples; after cacheline coalescing and
+function-level grouping, the view cannot distinguish same-thread accesses
+from different threads running the same function.
+
 For details please refer to the help window by pressing '?' key.
 
 CREDITS
-- 
2.52.0

Re: [PATCH v5 v5 1/9] perf c2c: extract shared data structures into c2c.h

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] The header `c2c.h` omits the `#else` dummy inline stub for `perf_c2c__browse_cacheline` when `HAVE_SLANG_SUPPORT` is not defined.
--

--- Patch [1]: [PATCH v5 v5 1/9] perf c2c: extract shared data structures into c2c.h ---
commit 36546c8a38f921a241992fc1080e419739637db8
Author: Jiebin Sun <jiebin.sun@intel.com>

perf c2c: extract shared data structures into c2c.h
    
Move c2c_hists, compute_stats, c2c_hist_entry, perf_c2c, and the shared
column-formatting structures and macros from builtin-c2c.c into a new
shared header c2c.h. This allows the upcoming function view browser
(c2c-function.c) to reuse these types and formatting definitions.

> diff --git a/tools/perf/c2c.h b/tools/perf/c2c.h
> new file mode 100644
> index 0000000000000..ab7adb85d9c06
> --- /dev/null
> +++ b/tools/perf/c2c.h
[ ... ]
> +/*
> + * The TUI browsers are only built with SLANG support. Their sole callers
> + * live inside HAVE_SLANG_SUPPORT-guarded code in builtin-c2c.c (stdio mode
> + * forces use_browser=0), so no #else stub is needed -- matching the rest of
> + * perf's TUI entry points.
> + */
> +#ifdef HAVE_SLANG_SUPPORT
> +int perf_c2c__browse_cacheline(struct hist_entry *he);
> +#endif

[Severity: Low]
Should there be an #else fallback stub provided for
perf_c2c__browse_cacheline() in c2c.h?

Even though the comment states current callers are guarded, the subsystem
guidelines require header files to provide compatible dummy inline stubs
when a feature define like HAVE_SLANG_SUPPORT is absent.

> +
> +#endif /* _PERF_C2C_H_ */

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260730090521.2206375-1-jiebin.sun@intel.com?part=1

Re: [PATCH v5 v5 6/9] perf c2c: add function view hierarchy entry creation

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [Medium] Raw pointer assignment of reference-counted structs bypasses lifecycle helpers.
- [Medium] Custom destructor `c2c_child_he__free` leaks lazy-evaluated string fields.
- [Medium] Missing `ops` callback initialization on child histogram entries causes NULL pointer dereference crash risk.
--

--- Patch [6]: [PATCH v5 v5 6/9] perf c2c: add function view hierarchy entry creation ---
commit 53abae650d662cc8bba9920d631a2983397312a7
Author: Jiebin Sun <jiebin.sun@intel.com>

perf c2c: add function view hierarchy entry creation

This commit adds the entry-creation layer for the function view hierarchy.
It introduces child allocation and insertion logic, alongside lookup-or-create
functions for levels 1, 2, and 3 based on function symbol or cacheline index.
These functions are marked as __maybe_unused until integrated by later patches.

> diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
> index 051c38697edd5..b3528edb387a7 100644
> --- a/tools/perf/ui/browsers/c2c-function.c
> +++ b/tools/perf/ui/browsers/c2c-function.c

[ ... ]

> @@ -793,11 +811,6 @@ static void c2c_child_he__free(struct hist_entry *child_he)
>  		zfree(&child_c2c->hists);
>  	}
>  
> -	zfree(&child_c2c->cpuset);
> -	zfree(&child_c2c->nodeset);
> -	zfree(&child_c2c->nodestr);
> -	zfree(&child_c2c->node_stats);
> -
>  	c2c_he__free_hierarchy(child_he);
>  

[Severity: Medium]
Does this custom destructor leak lazy-evaluated string fields like srcline
and srcfile?

If the user resolves source lines in the function view UI, hist_entry__srcline
dynamically allocates strings for srcline and srcfile.

Because this destructor manually cleans up fields instead of using the core
hist_entry__delete destructor, it misses cleaning up child_he->srcline and
child_he->srcfile, creating a memory leak when the hierarchy is torn down.

>  	free(child_c2c);
>  }

[ ... ]

> @@ -876,6 +889,260 @@ static int __maybe_unused c2c_he__prune_empty_writers(struct hist_entry *l1_he)

[ ... ]

> +static struct c2c_hist_entry *
> +c2c_child_entry__alloc(struct hist_entry *parent_he, struct hist_entry *src_he,
> +		       int depth, u64 ip)
> +{
> +	struct c2c_hist_entry *child_c2c;
> +	struct hist_entry *child_he;
> +
> +	/* Function-view children never own or display callchains. */
> +	child_he = c2c_function_he_zalloc(0);
> +	if (!child_he)
> +		return NULL;
> +

[Severity: Medium]
Can this regression cause a NULL pointer dereference?

This allocates a zeroed hist_entry but leaves the ops pointer uninitialized.

If core code ever iterates over the parent's hroot_out subtree and calls
hist_entry__delete on these children, it will unconditionally attempt to
execute ops->free(he).

> +	child_c2c = container_of(child_he, struct c2c_hist_entry, he);
> +	memcpy(&child_he->ms, &src_he->ms, sizeof(struct map_symbol));
> +
> +	if (src_he->mem_info) {
> +		child_he->mem_info = mem_info__clone(src_he->mem_info);
> +		if (!child_he->mem_info)
> +			goto out_free;
> +	}
> +
> +	child_he->thread = src_he->thread;

[Severity: Medium]
Does this code bypass reference count lifecycle helpers?

The map handle inside map_symbol is copied via memcpy, and the thread handle
is assigned via raw pointer assignment instead of using map__get and
thread__get.

If the core code ever iterates over these children and deletes them, it will
call thread__zput on borrowed references, leading to double-frees and
use-after-free crashes.

> +	child_he->cpumode = src_he->cpumode;
> +	child_he->cpu = src_he->cpu;

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260730090521.2206375-1-jiebin.sun@intel.com?part=6

Re: [PATCH v5 v5 8/9] perf c2c: add function view browser UI and cacheline detail

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Raw pointer assignment of reference-counted `struct thread` and `struct map_symbol` bypasses pointer handle validation and reference count lifecycle checking.
--

--- Patch [8]: [PATCH v5 v5 8/9] perf c2c: add function view browser UI and cacheline detail ---
commit 88acf11c42d184996fd7a80ec56730143d63b227
Author: Jiebin Sun <jiebin.sun@intel.com>

perf c2c: add function view browser UI and cacheline detail
    
Add the browser front end: create/run/delete the hist_browser and add the
title. The d shortcut opens the existing per-cacheline detail view for the
selected level-3 cacheline. Level-3 entries retain the source cacheline
index, so the shortcut can locate the original entry without relying on a
potentially ambiguous virtual address.

> diff --git a/tools/perf/ui/browsers/c2c-function.c b/tools/perf/ui/browsers/c2c-function.c
> index 9a95355eedf50..44fb072fa9371 100644
> --- a/tools/perf/ui/browsers/c2c-function.c
> +++ b/tools/perf/ui/browsers/c2c-function.c

[ ... ]

> @@ -1591,8 +1650,182 @@ static int __maybe_unused build_function_view_hierarchy(void)
>  	return ret;
>  }
>  
[ ... ]
> +static struct c2c_function_browser *c2c_function_browser__new(struct hists *hists)
> +{
[ ... ]
> +	/*
> +	 * Note: symbol_conf.report_hierarchy is deliberately left unset.
> +	 * The generic browser still descends into hroot_out children via
> +	 * rb_hierarchy_next()/can_goto_child(), which key off he->unfolded,
> +	 * so 'e'/'+' expands L1 -> L2 -> L3 correctly. Setting the flag would
> +	 * additionally make hist_entry__delete() recurse hroot_out and free
> +	 * each child, but our children borrow thread/ms (see
> +	 * c2c_child_entry__alloc()), so that would underflow their refcounts.
> +	 * Teardown is handled by c2c_he__free_hierarchy() instead.
> +	 */
> +	return browser;
> +}

[Severity: High]
Does this code safely manage the reference counts for struct thread and struct
map_symbol?

The comment mentions that the child entries borrow thread and ms references
from the parent in c2c_child_entry__alloc(). This relies on raw memory copies
and pointer assignments instead of explicit reference acquisitions:

c2c_child_entry__alloc() {
    ...
    memcpy(&child_he->ms, &src_he->ms, sizeof(struct map_symbol));
    ...
    child_he->thread = src_he->thread;
    ...
}

When built with REFCNT_CHECKING, pointer handles are validated to track
lifecycle state. If we bypass the explicit thread__get() and map__get()
lifecycle helpers, could this raw aliasing corrupt the tracking and lead to
use-after-free crashes or false positive traps when the borrowed references
are later used?

> +/*
> + * perf_c2c__browse_function_view - Browse function view with TAB key support
> + *
> + * Returns: 0 on success, negative error code on failure
> + */
> +int perf_c2c__browse_function_view(void)
> +{
[ ... ]
> +	/*
> +	 * The level-2/3 children borrow thread/ms (see c2c_child_entry__alloc())
> +	 * and are torn down by c2c_he__free_hierarchy(). report_hierarchy would
> +	 * make hist_entry__delete() recurse into hroot_out and put those borrowed
> +	 * refs (and call a NULL ops->free), so refuse to run if it is ever set.
> +	 */
> +	if (WARN_ON_ONCE(symbol_conf.report_hierarchy))
> +		return -EINVAL;

[Severity: High]
Given the restrictions mentioned here regarding borrowed references, would it
be safer to update the hierarchy generation to properly acquire reference
counts for the children instead of borrowing them?

This would ensure the pointer handle validation remains correct and avoid
needing these workarounds to prevent refcount underflows.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260730090521.2206375-1-jiebin.sun@intel.com?part=8