perf tools: Assorted fixes

index 1eedb1815c4c..c3603d4c0c57 100644
@@ -400,8 +400,10 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
-	if (evname != NULL)
-		ret += fprintf(fp, " of event '%s'", evname);
+	if (evname != NULL) {
+		ret += fprintf(fp, " of event%s '%s'",
+			       evsel->nr_members > 1 ? "s" : "", evname);
+	}
 
 	if (rep->time_str)
 		ret += fprintf(fp, " (time slices: %s)", rep->time_str);

@@ -1175,8 +1177,17 @@ int cmd_report(int argc, const char **argv)
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (group_set && !session->evlist->nr_groups)
+	/*
+	 * Events in data file are not collect in groups, but we still want
+	 * the group display. Set the artificial group and set the leader's
+	 * forced_leader flag to notify the display code.
+	 */
+	if (group_set && !session->evlist->nr_groups) {
+		struct perf_evsel *leader = perf_evlist__first(session->evlist);
+
 		perf_evlist__set_leader(session->evlist);
+		leader->forced_leader = true;
+	}
 
 	if (itrace_synth_opts.last_branch)
 		has_br_stack = true;

index de2bde232cb3..8b4e82548f8e 100644
@@ -2261,8 +2261,9 @@ static int perf_evsel_browser_title(struct hist_browser *browser,
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	printed = scnprintf(bf, size,
-			   "Samples: %lu%c of event '%s',%s%sEvent count (approx.): %" PRIu64,
-			   nr_samples, unit, ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
+			   "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64,
+			   nr_samples, unit, evsel->nr_members > 1 ? "s" : "",
+			   ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
 
 
 	if (hists->uid_filter_str)

index f1f883bb41a8..8948a8c1c187 100644
@@ -621,22 +621,34 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel)
 	return evsel->group_name ?: "anon group";
 }
 
+/*
+ * Returns the group details for the specified leader,
+ * with following rules.
+ *
+ *  For record -e '{cycles,instructions}'
+ *    'anon group { cycles:u, instructions:u }'
+ *
+ *  For record -e 'cycles,instructions' and report --group
+ *    'cycles:u, instructions:u'
+ */
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 {
-	int ret;
+	int ret = 0;
 	struct perf_evsel *pos;
 	const char *group_name = perf_evsel__group_name(evsel);
 
-	ret = scnprintf(buf, size, "%s", group_name);
+	if (!evsel->forced_leader)
+		ret = scnprintf(buf, size, "%s { ", group_name);
 
-	ret += scnprintf(buf + ret, size - ret, " { %s",
+	ret += scnprintf(buf + ret, size - ret, "%s",
 			 perf_evsel__name(evsel));
 
 	for_each_group_member(pos, evsel)
 		ret += scnprintf(buf + ret, size - ret, ", %s",
 				 perf_evsel__name(pos));
 
-	ret += scnprintf(buf + ret, size - ret, " }");
+	if (!evsel->forced_leader)
+		ret += scnprintf(buf + ret, size - ret, " }");
 
 	return ret;
 }

index 92ba001b627f..bb17afc429d9 100644
@@ -125,6 +125,7 @@ struct perf_evsel {
 	bool			per_pkg;
 	bool			precise_max;
 	bool			ignore_missing_thread;
+	bool			forced_leader;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;

index a326e0d8b5b6..e0c3cad0fd8d 100644
@@ -2318,7 +2318,12 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 	if (ret == -1)
 		return -1;
 
-	fprintf(fp, "# captured on: %s", ctime(&st.st_ctime));
+	fprintf(fp, "# captured on    : %s", ctime(&st.st_ctime));
+
+	fprintf(fp, "# header version : %u\n", header->version);
+	fprintf(fp, "# data offset    : %" PRIu64 "\n", header->data_offset);
+	fprintf(fp, "# data size      : %" PRIu64 "\n", header->data_size);
+	fprintf(fp, "# feat offset    : %" PRIu64 "\n", header->feat_offset);
 
 	perf_header__process_sections(header, fd, &hd,
 				      perf_file_section__fprintf_info);

index 14d82f0fe5cc..b2ebd9b3feba 100644
@@ -854,7 +854,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	int status = 0;
 	unsigned long waking = 0;
 	const bool forks = argc > 0;
-	struct machine *machine;
 	struct perf_tool *tool = &rec->tool;
 	struct record_opts *opts = &rec->opts;
 	struct perf_data *data = &rec->data;

@@ -959,8 +958,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
-	machine = &session->machines.host;
-
 	err = record__synthesize(rec, false);
 	if (err < 0)
 		goto out_child;

@@ -988,6 +985,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 * Let the child rip
 	 */
 	if (forks) {
+		struct machine *machine = &session->machines.host;
 		union perf_event *event;
 		pid_t tgid;
 

index b2ebd9b3feba..68caf54aa191 100644
@@ -71,7 +71,6 @@ struct record {
 	struct auxtrace_record	*itr;
 	struct perf_evlist	*evlist;
 	struct perf_session	*session;
-	const char		*progname;
 	int			realtime_prio;
 	bool			no_buildid;
 	bool			no_buildid_set;

@@ -861,8 +860,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	bool disabled = false, draining = false;
 	int fd;
 
-	rec->progname = argv[0];
-
 	atexit(record__sig_exit);
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);

index 44a8456cea10..7d968892ee39 100644
@@ -536,7 +536,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 			 * This mem info was allocated from sample__resolve_mem
 			 * and will not be used anymore.
 			 */
-			zfree(&entry->mem_info);
+			mem_info__zput(entry->mem_info);
 
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or

@@ -1139,7 +1139,7 @@ void hist_entry__delete(struct hist_entry *he)
 	if (he->mem_info) {
 		map__zput(he->mem_info->iaddr.map);
 		map__zput(he->mem_info->daddr.map);
-		zfree(&he->mem_info);
+		mem_info__zput(he->mem_info);
 	}
 
 	zfree(&he->stat_acc);

index 12b7427444a3..d46c98d6dedd 100644
@@ -1697,7 +1697,7 @@ static void ip__resolve_data(struct thread *thread,
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 				     struct addr_location *al)
 {
-	struct mem_info *mi = zalloc(sizeof(*mi));
+	struct mem_info *mi = mem_info__aloc();
 
 	if (!mi)
 		return NULL;

index a1a312d99f30..117cd25cd21a 100644
@@ -2221,3 +2221,25 @@ int symbol__config_symfs(const struct option *opt __maybe_unused,
 	free(bf);
 	return 0;
 }
+
+struct mem_info *mem_info__get(struct mem_info *mi)
+{
+	if (mi)
+		refcount_inc(&mi->refcnt);
+	return mi;
+}
+
+void mem_info__put(struct mem_info *mi)
+{
+	if (mi && refcount_dec_and_test(&mi->refcnt))
+		free(mi);
+}
+
+struct mem_info *mem_info__aloc(void)
+{
+	struct mem_info *mi = zalloc(sizeof(*mi));
+
+	if (mi)
+		refcount_set(&mi->refcnt, 1);
+	return mi;
+}

index 0563f33c1eb3..7e3ac7f35d63 100644
@@ -200,9 +200,10 @@ struct branch_info {
 };
 
 struct mem_info {
-	struct addr_map_symbol iaddr;
-	struct addr_map_symbol daddr;
-	union perf_mem_data_src data_src;
+	struct addr_map_symbol	iaddr;
+	struct addr_map_symbol	daddr;
+	union perf_mem_data_src	data_src;
+	refcount_t		refcnt;
 };
 
 struct addr_location {

@@ -389,4 +390,16 @@ int sdt_notes__get_count(struct list_head *start);
 #define SDT_NOTE_NAME "stapsdt"
 #define NR_ADDR 3
 
+struct mem_info *mem_info__aloc(void);
+struct mem_info *mem_info__get(struct mem_info *mi);
+void   mem_info__put(struct mem_info *mi);
+
+static inline void __mem_info__zput(struct mem_info **mi)
+{
+	mem_info__put(*mi);
+	*mi = NULL;
+}
+
+#define mem_info__zput(mi) __mem_info__zput(&mi)
+
 #endif /* __PERF_SYMBOL */

index 539c3d460158..98d243fa0c06 100644
@@ -237,9 +237,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (mi == NULL)
 		return -ENOMEM;
 
-	mi_dup = memdup(mi, sizeof(*mi));
-	if (!mi_dup)
-		goto free_mi;
+	/*
+	 * The mi object is released in hists__add_entry_ops,
+	 * if it gets sorted out into existing data, so we need
+	 * to take the copy now.
+	 */
+	mi_dup = mem_info__get(mi);
 
 	c2c_decode_stats(&stats, mi);
 

@@ -247,7 +250,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				  &al, NULL, NULL, mi,
 				  sample, true);
 	if (he == NULL)
-		goto free_mi_dup;
+		goto free_mi;
 
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
 	c2c_add_stats(&c2c_he->stats, &stats);

@@ -272,19 +275,15 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 		mi = mi_dup;
 
-		mi_dup = memdup(mi, sizeof(*mi));
-		if (!mi_dup)
-			goto free_mi;
-
 		c2c_hists = he__get_c2c_hists(he, c2c.cl_sort, 2);
 		if (!c2c_hists)
-			goto free_mi_dup;
+			goto free_mi;
 
 		he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops,
 					  &al, NULL, NULL, mi,
 					  sample, true);
 		if (he == NULL)
-			goto free_mi_dup;
+			goto free_mi;
 
 		c2c_he = container_of(he, struct c2c_hist_entry, he);
 		c2c_add_stats(&c2c_he->stats, &stats);

@@ -303,10 +302,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	addr_location__put(&al);
 	return ret;
 
-free_mi_dup:
-	free(mi_dup);
 free_mi:
-	free(mi);
+	mem_info__put(mi_dup);
+	mem_info__put(mi);
 	ret = -ENOMEM;
 	goto out;
 }

index ca160270fdfa..63440cc8d618 100644
@@ -98,7 +98,7 @@ static inline int test_and_set_bit(int nr, unsigned long *addr)
 
 /**
  * bitmap_alloc - Allocate bitmap
- * @nr: Bit to set
+ * @nbits: Number of bits
  */
 static inline unsigned long *bitmap_alloc(int nbits)
 {

index bf970f57dce0..c4ef2e523367 100644
@@ -27,6 +27,12 @@ struct numa_node {
 	struct cpu_map	*map;
 };
 
+struct memory_node {
+	u64		 node;
+	u64		 size;
+	unsigned long	*set;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;

@@ -43,6 +49,7 @@ struct perf_env {
 	int			nr_sibling_cores;
 	int			nr_sibling_threads;
 	int			nr_numa_nodes;
+	int			nr_memory_nodes;
 	int			nr_pmu_mappings;
 	int			nr_groups;
 	char			*cmdline;

@@ -54,6 +61,8 @@ struct perf_env {
 	struct cpu_cache_level	*caches;
 	int			 caches_cnt;
 	struct numa_node	*numa_nodes;
+	struct memory_node	*memory_nodes;
+	unsigned long long	 memory_bsize;
 };
 
 extern struct perf_env perf_env;

353 lines not on this page · raw message

index 942bdec6d70d..90d4577a92dc 100644
@@ -36,6 +36,7 @@ enum {
 	HEADER_STAT,
 	HEADER_CACHE,
 	HEADER_SAMPLE_TIME,
+	HEADER_MEM_TOPOLOGY,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };

129 lines not on this page · raw message

new file mode 100644
index 000000000000..e27333755a2c
@@ -0,0 +1,19 @@
+#ifndef __MEM2NODE_H
+#define __MEM2NODE_H
+
+#include <linux/rbtree.h>
+#include "env.h"
+
+struct entry;
+
+struct mem2node {
+	struct rb_root	 root;
+	struct entry	*entry;
+	int		 cnt;
+};
+
+int  mem2node__init(struct mem2node *map, struct perf_env *env);
+void mem2node__exit(struct mem2node *map);
+int  mem2node__node(struct mem2node *map, u64 addr);
+
+#endif /* __MEM2NODE_H */

index fafa014240cd..09071ef4434f 100644
@@ -271,6 +271,10 @@ static struct test generic_tests[] = {
 		.func = test__unit_number__scnprint,
 	},
 	{
+		.desc = "mem2node",
+		.func = test__mem2node,
+	},
+	{
 		.func = NULL,
 	},
 };

73 lines not on this page · raw message

index 2862b80bc288..2e169819e647 100644
@@ -102,6 +102,7 @@ int test__clang(struct test *test, int subtest);
 const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
 int test__unit_number__scnprint(struct test *test, int subtest);
+int test__mem2node(struct test *t, int subtest);
 
 bool test__bp_signal_is_supported(void);
 

index 98d243fa0c06..95765a1db903 100644
@@ -2704,7 +2704,7 @@ static int perf_c2c__record(int argc, const char **argv)
 	argc = parse_options(argc, argv, options, record_mem_usage,
 			     PARSE_OPT_KEEP_UNKNOWN);
 
-	rec_argc = argc + 10; /* max number of arguments */
+	rec_argc = argc + 11; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	if (!rec_argv)
 		return -1;

@@ -2720,6 +2720,7 @@ static int perf_c2c__record(int argc, const char **argv)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
+	rec_argv[i++] = "--phys-data";
 	rec_argv[i++] = "--sample-cpu";
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {

index 95765a1db903..43ce55550c9d 100644
@@ -1839,20 +1839,24 @@ static inline int valid_hitm_or_store(struct hist_entry *he)
 	return has_hitm || c2c_he->stats.store;
 }
 
-static void calc_width(struct hist_entry *he)
+static void calc_width(struct c2c_hist_entry *c2c_he)
 {
 	struct c2c_hists *c2c_hists;
 
-	c2c_hists = container_of(he->hists, struct c2c_hists, hists);
-	hists__calc_col_len(&c2c_hists->hists, he);
+	c2c_hists = container_of(c2c_he->he.hists, struct c2c_hists, hists);
+	hists__calc_col_len(&c2c_hists->hists, &c2c_he->he);
 }
 
 static int filter_cb(struct hist_entry *he)
 {
+	struct c2c_hist_entry *c2c_he;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+
 	if (c2c.show_src && !he->srcline)
 		he->srcline = hist_entry__get_srcline(he);
 
-	calc_width(he);
+	calc_width(c2c_he);
 
 	if (!valid_hitm_or_store(he))
 		he->filtered = HIST_FILTER__C2C;

@@ -1869,7 +1873,7 @@ static int resort_cl_cb(struct hist_entry *he)
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
 	c2c_hists = c2c_he->hists;
 
-	calc_width(he);
+	calc_width(c2c_he);
 
 	if (display && c2c_hists) {
 		static unsigned int idx;

index 43ce55550c9d..821112e8ba97 100644
@@ -1873,12 +1873,11 @@ static int resort_cl_cb(struct hist_entry *he)
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
 	c2c_hists = c2c_he->hists;
 
-	calc_width(c2c_he);
-
 	if (display && c2c_hists) {
 		static unsigned int idx;
 
 		c2c_he->cacheline_idx = idx++;
+		calc_width(c2c_he);
 
 		c2c_hists__reinit(c2c_hists, c2c.cl_output, c2c.cl_resort);
 

index 821112e8ba97..45c047fdd7ac 100644
@@ -32,6 +32,7 @@
 #include "evsel.h"
 #include "ui/browsers/hists.h"
 #include "thread.h"
+#include "mem2node.h"
 
 struct c2c_hists {
 	struct hists		hists;

@@ -49,6 +50,7 @@ struct c2c_hist_entry {
 	struct c2c_hists	*hists;
 	struct c2c_stats	 stats;
 	unsigned long		*cpuset;
+	unsigned long		*nodeset;
 	struct c2c_stats	*node_stats;
 	unsigned int		 cacheline_idx;
 

@@ -59,6 +61,11 @@ struct c2c_hist_entry {
 	 * because of its callchain dynamic entry
 	 */
 	struct hist_entry	he;
+
+	unsigned long		 paddr;
+	unsigned long		 paddr_cnt;
+	bool			 paddr_zero;
+	char			*nodestr;
 };
 
 static char const *coalesce_default = "pid,iaddr";

@@ -66,6 +73,7 @@ static char const *coalesce_default = "pid,iaddr";
 struct perf_c2c {
 	struct perf_tool	tool;
 	struct c2c_hists	hists;
+	struct mem2node		mem2node;
 
 	unsigned long		**nodes;
 	int			 nodes_cnt;

@@ -123,6 +131,10 @@ static void *c2c_he_zalloc(size_t size)
 	if (!c2c_he->cpuset)
 		return NULL;
 
+	c2c_he->nodeset = bitmap_alloc(c2c.nodes_cnt);
+	if (!c2c_he->nodeset)
+		return NULL;
+
 	c2c_he->node_stats = zalloc(c2c.nodes_cnt * sizeof(*c2c_he->node_stats));
 	if (!c2c_he->node_stats)
 		return NULL;

@@ -145,6 +157,8 @@ static void c2c_he_free(void *he)
 	}
 
 	free(c2c_he->cpuset);
+	free(c2c_he->nodeset);
+	free(c2c_he->nodestr);
 	free(c2c_he->node_stats);
 	free(c2c_he);
 }

@@ -194,6 +208,28 @@ static void c2c_he__set_cpu(struct c2c_hist_entry *c2c_he,
 	set_bit(sample->cpu, c2c_he->cpuset);
 }
 
+static void c2c_he__set_node(struct c2c_hist_entry *c2c_he,
+			     struct perf_sample *sample)
+{
+	int node;
+
+	if (!sample->phys_addr) {
+		c2c_he->paddr_zero = true;
+		return;
+	}
+
+	node = mem2node__node(&c2c.mem2node, sample->phys_addr);
+	if (WARN_ONCE(node < 0, "WARNING: failed to find node\n"))
+		return;
+
+	set_bit(node, c2c_he->nodeset);
+
+	if (c2c_he->paddr != sample->phys_addr) {
+		c2c_he->paddr_cnt++;
+		c2c_he->paddr = sample->phys_addr;
+	}
+}
+
 static void compute_stats(struct c2c_hist_entry *c2c_he,
 			  struct c2c_stats *stats,
 			  u64 weight)

@@ -257,6 +293,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	c2c_add_stats(&c2c_hists->stats, &stats);
 
 	c2c_he__set_cpu(c2c_he, sample);
+	c2c_he__set_node(c2c_he, sample);
 
 	hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
 	ret = hist_entry__append_callchain(he, sample);

@@ -293,6 +330,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		compute_stats(c2c_he, &stats, sample->weight);
 
 		c2c_he__set_cpu(c2c_he, sample);
+		c2c_he__set_node(c2c_he, sample);
 
 		hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
 		ret = hist_entry__append_callchain(he, sample);

@@ -455,6 +493,20 @@ static int dcacheline_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", width, HEX_STR(buf, addr));
 }
 
+static int
+dcacheline_node_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);
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	if (WARN_ON_ONCE(!c2c_he->nodestr))
+		return 0;
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, c2c_he->nodestr);
+}
+
 static int offset_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			struct hist_entry *he)
 {

@@ -1207,6 +1259,14 @@ static struct c2c_dimension dim_dcacheline = {
 	.width		= 18,
 };
 
+static struct c2c_dimension dim_dcacheline_node = {
+	.header		= HEADER_LOW("Node"),
+	.name		= "dcacheline_node",
+	.cmp		= empty_cmp,
+	.entry		= dcacheline_node_entry,
+	.width		= 4,
+};
+
 static struct c2c_header header_offset_tui = HEADER_LOW("Off");
 
 static struct c2c_dimension dim_offset = {

@@ -1217,6 +1277,14 @@ static struct c2c_dimension dim_offset = {
 	.width		= 18,
 };
 
+static struct c2c_dimension dim_offset_node = {
+	.header		= HEADER_LOW("Node"),
+	.name		= "offset_node",
+	.cmp		= empty_cmp,
+	.entry		= dcacheline_node_entry,
+	.width		= 4,
+};
+
 static struct c2c_dimension dim_iaddr = {
 	.header		= HEADER_LOW("Code address"),
 	.name		= "iaddr",

@@ -1536,7 +1604,9 @@ static struct c2c_dimension dim_dcacheline_num_empty = {
 
 static struct c2c_dimension *dimensions[] = {
 	&dim_dcacheline,
+	&dim_dcacheline_node,
 	&dim_offset,
+	&dim_offset_node,
 	&dim_iaddr,
 	&dim_tot_hitm,
 	&dim_lcl_hitm,

@@ -1839,12 +1909,44 @@ static inline int valid_hitm_or_store(struct hist_entry *he)
 	return has_hitm || c2c_he->stats.store;
 }
 
+static void set_node_width(struct c2c_hist_entry *c2c_he, int len)
+{
+	struct c2c_dimension *dim;
+
+	dim = &c2c.hists == c2c_he->hists ?
+	      &dim_dcacheline_node : &dim_offset_node;
+
+	if (len > dim->width)
+		dim->width = len;
+}
+
+static int set_nodestr(struct c2c_hist_entry *c2c_he)
+{
+	char buf[30];
+	int len;
+
+	if (c2c_he->nodestr)
+		return 0;
+
+	if (bitmap_weight(c2c_he->nodeset, c2c.nodes_cnt)) {
+		len = bitmap_scnprintf(c2c_he->nodeset, c2c.nodes_cnt,
+				      buf, sizeof(buf));
+	} else {
+		len = scnprintf(buf, sizeof(buf), "N/A");
+	}
+
+	set_node_width(c2c_he, len);
+	c2c_he->nodestr = strdup(buf);
+	return c2c_he->nodestr ? 0 : -ENOMEM;
+}
+
 static void calc_width(struct c2c_hist_entry *c2c_he)
 {
 	struct c2c_hists *c2c_hists;
 
 	c2c_hists = container_of(c2c_he->he.hists, struct c2c_hists, hists);
 	hists__calc_col_len(&c2c_hists->hists, &c2c_he->he);
+	set_nodestr(c2c_he);
 }
 
 static int filter_cb(struct hist_entry *he)

@@ -2474,7 +2576,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		"percent_lcl_hitm,"
 		"percent_stores_l1hit,"
 		"percent_stores_l1miss,"
-		"offset,",
+		"offset,offset_node,",
 		add_pid   ? "pid," : "",
 		add_tid   ? "tid," : "",
 		add_iaddr ? "iaddr," : "",

@@ -2603,17 +2705,21 @@ static int perf_c2c__report(int argc, const char **argv)
 		goto out;
 	}
 
-	err = setup_callchain(session->evlist);
+	err = mem2node__init(&c2c.mem2node, &session->header.env);
 	if (err)
 		goto out_session;
 
+	err = setup_callchain(session->evlist);
+	if (err)
+		goto out_mem2node;
+
 	if (symbol__init(&session->header.env) < 0)
-		goto out_session;
+		goto out_mem2node;
 
 	/* No pipe support at the moment. */
 	if (perf_data__is_pipe(session->data)) {
 		pr_debug("No pipe support at the moment.\n");
-		goto out_session;
+		goto out_mem2node;
 	}
 
 	if (c2c.use_stdio)

@@ -2626,12 +2732,13 @@ static int perf_c2c__report(int argc, const char **argv)
 	err = perf_session__process_events(session);
 	if (err) {
 		pr_err("failed to process sample\n");
-		goto out_session;
+		goto out_mem2node;
 	}
 
 	c2c_hists__reinit(&c2c.hists,
 			"cl_idx,"
 			"dcacheline,"
+			"dcacheline_node,"
 			"tot_recs,"
 			"percent_hitm,"
 			"tot_hitm,lcl_hitm,rmt_hitm,"

@@ -2657,6 +2764,8 @@ static int perf_c2c__report(int argc, const char **argv)
 
 	perf_c2c_display(session);
 
+out_mem2node:
+	mem2node__exit(&c2c.mem2node);
 out_session:
 	perf_session__delete(session);
 out:

index 45c047fdd7ac..3790a7e0c51d 100644
@@ -1252,7 +1252,7 @@ cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	}
 
 static struct c2c_dimension dim_dcacheline = {
-	.header		= HEADER_LOW("Cacheline"),
+	.header		= HEADER_SPAN("--- Cacheline ----", "Address", 1),
 	.name		= "dcacheline",
 	.cmp		= dcacheline_cmp,
 	.entry		= dcacheline_entry,

@@ -1267,10 +1267,10 @@ static struct c2c_dimension dim_dcacheline_node = {
 	.width		= 4,
 };
 
-static struct c2c_header header_offset_tui = HEADER_LOW("Off");
+static struct c2c_header header_offset_tui = HEADER_SPAN("-----", "Off", 1);
 
 static struct c2c_dimension dim_offset = {
-	.header		= HEADER_BOTH("Data address", "Offset"),
+	.header		= HEADER_SPAN("--- Data address -", "Offset", 1),
 	.name		= "offset",
 	.cmp		= offset_cmp,
 	.entry		= offset_entry,

@@ -2453,14 +2453,66 @@ static void perf_c2c_display(struct perf_session *session)
 }
 #endif /* HAVE_SLANG_SUPPORT */
 
-static void ui_quirks(void)
+static char *fill_line(const char *orig, int len)
 {
+	int i, j, olen = strlen(orig);
+	char *buf;
+
+	buf = zalloc(len + 1);
+	if (!buf)
+		return NULL;
+
+	j = len / 2 - olen / 2;
+
+	for (i = 0; i < j - 1; i++) {
+		buf[i] = '-';
+	}
+
+	buf[i++] = ' ';
+
+	strcpy(buf + i, orig);
+
+	i += olen;
+
+	buf[i++] = ' ';
+
+	for (; i < len; i++) {
+		buf[i] = '-';
+	}
+
+	return buf;
+}
+
+static int ui_quirks(void)
+{
+	const char *nodestr = "Data address";
+	char *buf;
+
 	if (!c2c.use_stdio) {
 		dim_offset.width  = 5;
 		dim_offset.header = header_offset_tui;
+		nodestr = "CL";
 	}
 
 	dim_percent_hitm.header = percent_hitm_header[c2c.display];
+
+	/* Fix the zero line for dcacheline column. */
+	buf = fill_line("Cacheline", dim_dcacheline.width +
+				     dim_dcacheline_node.width + 2);
+	if (!buf)
+		return -ENOMEM;
+
+	dim_dcacheline.header.line[0].text = buf;
+
+	/* Fix the zero line for offset column. */
+	buf = fill_line(nodestr, dim_offset.width +
+			      dim_offset_node.width + 2);
+	if (!buf)
+		return -ENOMEM;
+
+	dim_offset.header.line[0].text = buf;
+
+	return 0;
 }
 
 #define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"

@@ -2760,7 +2812,10 @@ static int perf_c2c__report(int argc, const char **argv)
 
 	ui_progress__finish();
 
-	ui_quirks();
+	if (ui_quirks()) {
+		pr_err("failed to setup UI\n");
+		goto out_mem2node;
+	}
 
 	perf_c2c_display(session);
 

index 3790a7e0c51d..5a0f5067dfe9 100644
@@ -507,6 +507,17 @@ dcacheline_node_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", width, c2c_he->nodestr);
 }
 
+static int
+dcacheline_node_count(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);
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	return scnprintf(hpp->buf, hpp->size, "%*lu", width, c2c_he->paddr_cnt);
+}
+
 static int offset_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			struct hist_entry *he)
 {

@@ -1252,7 +1263,7 @@ cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	}
 
 static struct c2c_dimension dim_dcacheline = {
-	.header		= HEADER_SPAN("--- Cacheline ----", "Address", 1),
+	.header		= HEADER_SPAN("--- Cacheline ----", "Address", 2),
 	.name		= "dcacheline",
 	.cmp		= dcacheline_cmp,
 	.entry		= dcacheline_entry,

@@ -1267,10 +1278,18 @@ static struct c2c_dimension dim_dcacheline_node = {
 	.width		= 4,
 };
 
-static struct c2c_header header_offset_tui = HEADER_SPAN("-----", "Off", 1);
+static struct c2c_dimension dim_dcacheline_count = {
+	.header		= HEADER_LOW("PA cnt"),
+	.name		= "dcacheline_count",
+	.cmp		= empty_cmp,
+	.entry		= dcacheline_node_count,
+	.width		= 6,
+};
+
+static struct c2c_header header_offset_tui = HEADER_SPAN("-----", "Off", 2);
 
 static struct c2c_dimension dim_offset = {
-	.header		= HEADER_SPAN("--- Data address -", "Offset", 1),
+	.header		= HEADER_SPAN("--- Data address -", "Offset", 2),
 	.name		= "offset",
 	.cmp		= offset_cmp,
 	.entry		= offset_entry,

@@ -1605,6 +1624,7 @@ static struct c2c_dimension dim_dcacheline_num_empty = {
 static struct c2c_dimension *dimensions[] = {
 	&dim_dcacheline,
 	&dim_dcacheline_node,
+	&dim_dcacheline_count,
 	&dim_offset,
 	&dim_offset_node,
 	&dim_iaddr,

@@ -2498,7 +2518,8 @@ static int ui_quirks(void)
 
 	/* Fix the zero line for dcacheline column. */
 	buf = fill_line("Cacheline", dim_dcacheline.width +
-				     dim_dcacheline_node.width + 2);
+				     dim_dcacheline_node.width +
+				     dim_dcacheline_count.width + 4);
 	if (!buf)
 		return -ENOMEM;
 

@@ -2506,7 +2527,8 @@ static int ui_quirks(void)
 
 	/* Fix the zero line for offset column. */
 	buf = fill_line(nodestr, dim_offset.width +
-			      dim_offset_node.width + 2);
+			         dim_offset_node.width +
+				 dim_dcacheline_count.width + 4);
 	if (!buf)
 		return -ENOMEM;
 

@@ -2628,7 +2650,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		"percent_lcl_hitm,"
 		"percent_stores_l1hit,"
 		"percent_stores_l1miss,"
-		"offset,offset_node,",
+		"offset,offset_node,dcacheline_count,",
 		add_pid   ? "pid," : "",
 		add_tid   ? "tid," : "",
 		add_iaddr ? "iaddr," : "",

@@ -2791,6 +2813,7 @@ static int perf_c2c__report(int argc, const char **argv)
 			"cl_idx,"
 			"dcacheline,"
 			"dcacheline_node,"
+			"dcacheline_count,"
 			"tot_recs,"
 			"percent_hitm,"
 			"tot_hitm,lcl_hitm,rmt_hitm,"