perf c2c: Add new tool to analyze cacheline contention on NUMA systems

index 774f6ec884d5..9a027a0cc037 100644
@@ -43,6 +43,9 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	int ret = 0;
 	size_t len;
 
+	if (!is_regular_file(filename))
+		return -1;
+
 	switch (type) {
 	case DSO_BINARY_TYPE__DEBUGLINK: {
 		char *debuglink;

@@ -53,11 +56,6 @@ int dso__read_binary_type_filename(const struct dso *dso,
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
-
-		ret = -1;
-		if (!is_regular_file(filename))
-			break;
-
 		ret = filename__read_debuglink(filename, debuglink,
 					       size - (debuglink - filename));
 		}

index 19c9c558454f..827a58ce29f0 100644
@@ -1466,9 +1466,6 @@ int dso__load(struct dso *dso, struct map *map)
 						   root_dir, name, PATH_MAX))
 			continue;
 
-		if (!is_regular_file(name))
-			continue;
-
 		/* Name is now the name of the next image to try */
 		if (symsrc__init(ss, dso, name, symtab_type) < 0)
 			continue;

index 774f6ec884d5..d2c6cdd9d42b 100644
@@ -363,6 +363,9 @@ static int __open_dso(struct dso *dso, struct machine *machine)
 		return -EINVAL;
 	}
 
+	if (!is_regular_file(name))
+		return -EINVAL;
+
 	fd = do_open(name);
 	free(name);
 	return fd;

index 21fd573106ed..f3225a2e6eee 100644
@@ -1728,7 +1728,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
 	data->period = evsel->attr.sample_period;
-	data->weight = 0;
 	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {

@@ -1935,7 +1934,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		}
 	}
 
-	data->weight = 0;
 	if (type & PERF_SAMPLE_WEIGHT) {
 		OVERFLOW_CHECK_u64(array);
 		data->weight = *array;

index a57131e61fe3..cb0371106c21 100644
@@ -373,7 +373,8 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	return 0;
 }
 
-static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
+				struct perf_hpp_list *hpp_list)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;

@@ -384,7 +385,7 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
-	hists__for_each_format(he->hists, fmt) {
+	perf_hpp_list__for_each_format(hpp_list, fmt) {
 		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 

@@ -509,7 +510,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	if (symbol_conf.report_hierarchy)
 		return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
 
-	hist_entry__snprintf(he, &hpp);
+	hist_entry__snprintf(he, &hpp, hists->hpp_list);
 
 	ret = fprintf(fp, "%s\n", bf);
 

index cb0371106c21..0a32b48eda80 100644
@@ -699,7 +699,7 @@ hists__fprintf_standard_headers(struct hists *hists,
 
 static int hists__fprintf_headers(struct hists *hists, FILE *fp)
 {
-	char bf[96];
+	char bf[1024];
 	struct perf_hpp dummy_hpp = {
 		.buf	= bf,
 		.size	= sizeof(bf),

index bbc368e7d1e4..502fcee91973 100644
@@ -9,6 +9,7 @@
 #include "mem-events.h"
 #include "debug.h"
 #include "symbol.h"
+#include "sort.h"
 
 unsigned int perf_mem_events__loads_ldlat = 30;
 

@@ -268,3 +269,100 @@ int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_in
 
 	return i;
 }
+
+int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
+{
+	union perf_mem_data_src *data_src = &mi->data_src;
+	u64 daddr  = mi->daddr.addr;
+	u64 op     = data_src->mem_op;
+	u64 lvl    = data_src->mem_lvl;
+	u64 snoop  = data_src->mem_snoop;
+	u64 lock   = data_src->mem_lock;
+	int err = 0;
+
+#define P(a, b) PERF_MEM_##a##_##b
+
+	stats->nr_entries++;
+
+	if (lock & P(LOCK, LOCKED)) stats->locks++;
+
+	if (op & P(OP, LOAD)) {
+		/* load */
+		stats->load++;
+
+		if (!daddr) {
+			stats->ld_noadrs++;
+			return -1;
+		}
+
+		if (lvl & P(LVL, HIT)) {
+			if (lvl & P(LVL, UNC)) stats->ld_uncache++;
+			if (lvl & P(LVL, IO))  stats->ld_io++;
+			if (lvl & P(LVL, LFB)) stats->ld_fbhit++;
+			if (lvl & P(LVL, L1 )) stats->ld_l1hit++;
+			if (lvl & P(LVL, L2 )) stats->ld_l2hit++;
+			if (lvl & P(LVL, L3 )) {
+				if (snoop & P(SNOOP, HITM))
+					stats->lcl_hitm++;
+				else
+					stats->ld_llchit++;
+			}
+
+			if (lvl & P(LVL, LOC_RAM)) {
+				stats->lcl_dram++;
+				if (snoop & P(SNOOP, HIT))
+					stats->ld_shared++;
+				else
+					stats->ld_excl++;
+			}
+
+			if ((lvl & P(LVL, REM_RAM1)) ||
+			    (lvl & P(LVL, REM_RAM2))) {
+				stats->rmt_dram++;
+				if (snoop & P(SNOOP, HIT))
+					stats->ld_shared++;
+				else
+					stats->ld_excl++;
+			}
+		}
+
+		if ((lvl & P(LVL, REM_CCE1)) ||
+		    (lvl & P(LVL, REM_CCE2))) {
+			if (snoop & P(SNOOP, HIT))
+				stats->rmt_hit++;
+			else if (snoop & P(SNOOP, HITM))
+				stats->rmt_hitm++;
+		}
+
+		if ((lvl & P(LVL, MISS)))
+			stats->ld_miss++;
+
+	} else if (op & P(OP, STORE)) {
+		/* store */
+		stats->store++;
+
+		if (!daddr) {
+			stats->st_noadrs++;
+			return -1;
+		}
+
+		if (lvl & P(LVL, HIT)) {
+			if (lvl & P(LVL, UNC)) stats->st_uncache++;
+			if (lvl & P(LVL, L1 )) stats->st_l1hit++;
+		}
+		if (lvl & P(LVL, MISS))
+			if (lvl & P(LVL, L1)) stats->st_l1miss++;
+	} else {
+		/* unparsable data_src? */
+		stats->noparse++;
+		return -1;
+	}
+
+	if (!mi->daddr.map || !mi->iaddr.map) {
+		stats->nomap++;
+		return -1;
+	}
+
+#undef P
+	return err;
+}

index 7f69bf9d789d..27c6bb5abafb 100644
@@ -2,6 +2,10 @@
 #define __PERF_MEM_EVENTS_H
 
 #include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <linux/types.h>
+#include "stat.h"
 
 struct perf_mem_event {
 	bool		record;

@@ -33,4 +37,36 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 
 int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);
 
+struct c2c_stats {
+	int	nr_entries;
+
+	int	locks;               /* count of 'lock' transactions */
+	int	store;               /* count of all stores in trace */
+	int	st_uncache;          /* stores to uncacheable address */
+	int	st_noadrs;           /* cacheable store with no address */
+	int	st_l1hit;            /* count of stores that hit L1D */
+	int	st_l1miss;           /* count of stores that miss L1D */
+	int	load;                /* count of all loads in trace */
+	int	ld_excl;             /* exclusive loads, rmt/lcl DRAM - snp none/miss */
+	int	ld_shared;           /* shared loads, rmt/lcl DRAM - snp hit */
+	int	ld_uncache;          /* loads to uncacheable address */
+	int	ld_io;               /* loads to io address */
+	int	ld_miss;             /* loads miss */
+	int	ld_noadrs;           /* cacheable load with no address */
+	int	ld_fbhit;            /* count of loads hitting Fill Buffer */
+	int	ld_l1hit;            /* count of loads that hit L1D */
+	int	ld_l2hit;            /* count of loads that hit L2D */
+	int	ld_llchit;           /* count of loads that hit LLC */
+	int	lcl_hitm;            /* count of loads with local HITM  */
+	int	rmt_hitm;            /* count of loads with remote HITM */
+	int	rmt_hit;             /* count of loads with remote hit clean; */
+	int	lcl_dram;            /* count of loads miss to local DRAM */
+	int	rmt_dram;            /* count of loads miss to remote DRAM */
+	int	nomap;               /* count of load/stores with no phys adrs */
+	int	noparse;             /* count of unparsable data sources */
+};
+
+struct hist_entry;
+int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi);
+
 #endif /* __PERF_MEM_EVENTS_H */

index 502fcee91973..e50773286ef6 100644
@@ -366,3 +366,33 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 #undef P
 	return err;
 }
+
+void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add)
+{
+	stats->nr_entries	+= add->nr_entries;
+
+	stats->locks		+= add->locks;
+	stats->store		+= add->store;
+	stats->st_uncache	+= add->st_uncache;
+	stats->st_noadrs	+= add->st_noadrs;
+	stats->st_l1hit		+= add->st_l1hit;
+	stats->st_l1miss	+= add->st_l1miss;
+	stats->load		+= add->load;
+	stats->ld_excl		+= add->ld_excl;
+	stats->ld_shared	+= add->ld_shared;
+	stats->ld_uncache	+= add->ld_uncache;
+	stats->ld_io		+= add->ld_io;
+	stats->ld_miss		+= add->ld_miss;
+	stats->ld_noadrs	+= add->ld_noadrs;
+	stats->ld_fbhit		+= add->ld_fbhit;
+	stats->ld_l1hit		+= add->ld_l1hit;
+	stats->ld_l2hit		+= add->ld_l2hit;
+	stats->ld_llchit	+= add->ld_llchit;
+	stats->lcl_hitm		+= add->lcl_hitm;
+	stats->rmt_hitm		+= add->rmt_hitm;
+	stats->rmt_hit		+= add->rmt_hit;
+	stats->lcl_dram		+= add->lcl_dram;
+	stats->rmt_dram		+= add->rmt_dram;
+	stats->nomap		+= add->nomap;
+	stats->noparse		+= add->noparse;
+}

index 27c6bb5abafb..30b3757ee326 100644
@@ -68,5 +68,6 @@ struct c2c_stats {
 
 struct hist_entry;
 int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi);
+void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add);
 
 #endif /* __PERF_MEM_EVENTS_H */

index 1884d7f9b9d2..9e1f6f75a50f 100644
@@ -2748,7 +2748,7 @@ static int setup_output_list(struct perf_hpp_list *list, char *str)
 	return ret;
 }
 
-static void reset_dimensions(void)
+void reset_dimensions(void)
 {
 	unsigned int i;
 

index 28c0524c8702..3f743bf2acd4 100644
@@ -268,4 +268,5 @@ int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, i
 bool is_strict_order(const char *order);
 
 int hpp_dimension__add_output(unsigned col);
+void reset_dimensions(void);
 #endif	/* __PERF_SORT_H */

index 9e1f6f75a50f..9f7c1ea9e3ad 100644
@@ -2308,9 +2308,9 @@ int hpp_dimension__add_output(unsigned col)
 	return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]);
 }
 
-static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
-			       struct perf_evlist *evlist,
-			       int level)
+int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+			struct perf_evlist *evlist,
+			int level)
 {
 	unsigned int i;
 

@@ -2685,7 +2685,7 @@ void sort__setup_elide(FILE *output)
 	}
 }
 
-static int output_field_add(struct perf_hpp_list *list, char *tok)
+int output_field_add(struct perf_hpp_list *list, char *tok)
 {
 	unsigned int i;
 

index 3f743bf2acd4..ac7998048b1e 100644
@@ -269,4 +269,8 @@ bool is_strict_order(const char *order);
 
 int hpp_dimension__add_output(unsigned col);
 void reset_dimensions(void);
+int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+			struct perf_evlist *evlist,
+			int level);
+int output_field_add(struct perf_hpp_list *list, char *tok);
 #endif	/* __PERF_SORT_H */

index 9f7c1ea9e3ad..452e15a10dd2 100644
@@ -867,7 +867,7 @@ struct sort_entry sort_cycles = {
 };
 
 /* --sort daddr_sym */
-static int64_t
+int64_t
 sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	uint64_t l = 0, r = 0;

@@ -896,7 +896,7 @@ static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf,
 					 width);
 }
 
-static int64_t
+int64_t
 sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	uint64_t l = 0, r = 0;

@@ -1062,7 +1062,7 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static int64_t
+int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	u64 l, r;

index ac7998048b1e..d4ef567dcd7b 100644
@@ -273,4 +273,10 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			struct perf_evlist *evlist,
 			int level);
 int output_field_add(struct perf_hpp_list *list, char *tok);
+int64_t
+sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right);
+int64_t
+sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right);
+int64_t
+sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right);
 #endif	/* __PERF_SORT_H */

index 35e44b1879e3..77cf7a80e8d6 100644
@@ -1080,7 +1080,7 @@ struct hpp_arg {
 	bool current_entry;
 };
 
-static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
+int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	struct hpp_arg *arg = hpp->ptr;
 	int ret, len;

index b47fafc8ee2a..84ad92ad24be 100644
@@ -237,7 +237,7 @@ static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
-static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
+int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	va_list args;
 	ssize_t ssize = hpp->size;

index a002c93fe422..ef9985cba1de 100644
@@ -484,5 +484,7 @@ static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
 #define HIERARCHY_INDENT  3
 
 bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit);
+int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...);
+int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...);
 
 #endif	/* __PERF_HIST_H */

index 0a32b48eda80..3434d571ddd1 100644
@@ -373,8 +373,8 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	return 0;
 }
 
-static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
-				struct perf_hpp_list *hpp_list)
+int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
+			 struct perf_hpp_list *hpp_list)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;

index ef9985cba1de..aa5ddfa1fa22 100644
@@ -486,5 +486,7 @@ static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
 bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit);
 int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...);
 int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...);
+int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
+			 struct perf_hpp_list *hpp_list);
 
 #endif	/* __PERF_HIST_H */

index 3434d571ddd1..f6d5ac8772f4 100644
@@ -697,7 +697,7 @@ hists__fprintf_standard_headers(struct hists *hists,
 	return hpp_list->nr_header_lines + 2;
 }
 
-static int hists__fprintf_headers(struct hists *hists, FILE *fp)
+int hists__fprintf_headers(struct hists *hists, FILE *fp)
 {
 	char bf[1024];
 	struct perf_hpp dummy_hpp = {

index aa5ddfa1fa22..0e3493e33175 100644
@@ -488,5 +488,6 @@ int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...);
 int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...);
 int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
 			 struct perf_hpp_list *hpp_list);
+int hists__fprintf_headers(struct hists *hists, FILE *fp);
 
 #endif	/* __PERF_HIST_H */

new file mode 100644
index 000000000000..8252ed0ba5d0
@@ -0,0 +1,23 @@
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include "util.h"
+#include "debug.h"
+#include "builtin.h"
+#include <subcmd/parse-options.h>
+
+static const char * const c2c_usage[] = {
+	"perf c2c",
+	NULL
+};
+
+int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	const struct option c2c_options[] = {
+	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, c2c_options, c2c_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+	return 0;
+}

index 41c24010ab43..0bcf68e98ccc 100644
@@ -18,6 +18,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix);
 int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
 int cmd_buildid_list(int argc, const char **argv, const char *prefix);
 int cmd_config(int argc, const char **argv, const char *prefix);
+int cmd_c2c(int argc, const char **argv, const char *prefix);
 int cmd_diff(int argc, const char **argv, const char *prefix);
 int cmd_evlist(int argc, const char **argv, const char *prefix);
 int cmd_help(int argc, const char **argv, const char *prefix);

index 64c06961bfe4..aa23b3347d6b 100644
@@ -43,6 +43,7 @@ static struct cmd_struct commands[] = {
 	{ "buildid-cache", cmd_buildid_cache, 0 },
 	{ "buildid-list", cmd_buildid_list, 0 },
 	{ "config",	cmd_config,	0 },
+	{ "c2c",	cmd_c2c,	0 },
 	{ "diff",	cmd_diff,	0 },
 	{ "evlist",	cmd_evlist,	0 },
 	{ "help",	cmd_help,	0 },

index 8252ed0ba5d0..58924c67f818 100644
@@ -4,12 +4,116 @@
 #include "debug.h"
 #include "builtin.h"
 #include <subcmd/parse-options.h>
+#include "mem-events.h"
 
 static const char * const c2c_usage[] = {
 	"perf c2c",
 	NULL
 };
 
+static int parse_record_events(const struct option *opt __maybe_unused,
+			       const char *str, int unset __maybe_unused)
+{
+	bool *event_set = (bool *) opt->value;
+
+	*event_set = true;
+	return perf_mem_events__parse(str);
+}
+
+
+static const char * const __usage_record[] = {
+	"perf c2c record [<options>] [<command>]",
+	"perf c2c record [<options>] -- <command> [<options>]",
+	NULL
+};
+
+static const char * const *record_mem_usage = __usage_record;
+
+static int perf_c2c__record(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+	int ret;
+	bool all_user = false, all_kernel = false;
+	bool event_set = false;
+	struct option options[] = {
+	OPT_CALLBACK('e', "event", &event_set, "event",
+		     "event selector. Use 'perf mem record -e list' to list available events",
+		     parse_record_events),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show counter open errors, etc)"),
+	OPT_BOOLEAN('u', "all-user", &all_user, "collect only user level data"),
+	OPT_BOOLEAN('k', "all-kernel", &all_kernel, "collect only kernel level data"),
+	OPT_UINTEGER('l', "ldlat", &perf_mem_events__loads_ldlat, "setup mem-loads latency"),
+	OPT_END()
+	};
+
+	if (perf_mem_events__init()) {
+		pr_err("failed: memory events not supported\n");
+		return -1;
+	}
+
+	argc = parse_options(argc, argv, options, record_mem_usage,
+			     PARSE_OPT_KEEP_UNKNOWN);
+
+	rec_argc = argc + 10; /* max number of arguments */
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	if (!rec_argv)
+		return -1;
+
+	rec_argv[i++] = "record";
+
+	if (!event_set) {
+		perf_mem_events[PERF_MEM_EVENTS__LOAD].record  = true;
+		perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+	}
+
+	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
+		rec_argv[i++] = "-W";
+
+	rec_argv[i++] = "-d";
+	rec_argv[i++] = "--sample-cpu";
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		if (!perf_mem_events[j].record)
+			continue;
+
+		if (!perf_mem_events[j].supported) {
+			pr_err("failed: event '%s' not supported\n",
+			       perf_mem_events[j].name);
+			return -1;
+		}
+
+		rec_argv[i++] = "-e";
+		rec_argv[i++] = perf_mem_events__name(j);
+	};
+
+	if (all_user)
+		rec_argv[i++] = "--all-user";
+
+	if (all_kernel)
+		rec_argv[i++] = "--all-kernel";
+
+	for (j = 0; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	if (verbose > 0) {
+		pr_debug("calling: ");
+
+		j = 0;
+
+		while (rec_argv[j]) {
+			pr_debug("%s ", rec_argv[j]);
+			j++;
+		}
+		pr_debug("\n");
+	}
+
+	ret = cmd_record(i, rec_argv, NULL);
+	free(rec_argv);
+	return ret;
+}
+
 int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const struct option c2c_options[] = {

@@ -19,5 +123,15 @@ int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, c2c_options, c2c_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (!argc)
+		usage_with_options(c2c_usage, c2c_options);
+
+	if (!strncmp(argv[0], "rec", 3)) {
+		return perf_c2c__record(argc, argv);
+	} else {
+		usage_with_options(c2c_usage, c2c_options);
+	}
+
 	return 0;
 }

index 58924c67f818..3fac3a294bdd 100644
@@ -5,12 +5,74 @@
 #include "builtin.h"
 #include <subcmd/parse-options.h>
 #include "mem-events.h"
+#include "session.h"
+#include "hist.h"
+#include "tool.h"
+#include "data.h"
+
+struct perf_c2c {
+	struct perf_tool tool;
+};
+
+static struct perf_c2c c2c;
 
 static const char * const c2c_usage[] = {
-	"perf c2c",
+	"perf c2c {record|report}",
 	NULL
 };
 
+static const char * const __usage_report[] = {
+	"perf c2c report",
+	NULL
+};
+
+static const char * const *report_c2c_usage = __usage_report;
+
+static int perf_c2c__report(int argc, const char **argv)
+{
+	struct perf_session *session;
+	struct perf_data_file file = {
+		.mode = PERF_DATA_MODE_READ,
+	};
+	const struct option c2c_options[] = {
+	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
+		   "file", "vmlinux pathname"),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show counter open errors, etc)"),
+	OPT_STRING('i', "input", &input_name, "file",
+		   "the input file to process"),
+	OPT_END()
+	};
+	int err = 0;
+
+	argc = parse_options(argc, argv, c2c_options, report_c2c_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+	if (!argc)
+		usage_with_options(report_c2c_usage, c2c_options);
+
+	file.path = input_name;
+
+	session = perf_session__new(&file, 0, &c2c.tool);
+	if (session == NULL) {
+		pr_debug("No memory for session\n");
+		goto out;
+	}
+
+	if (symbol__init(&session->header.env) < 0)
+		goto out_session;
+
+	/* No pipe support at the moment. */
+	if (perf_data_file__is_pipe(session->file)) {
+		pr_debug("No pipe support at the moment.\n");
+		goto out_session;
+	}
+
+out_session:
+	perf_session__delete(session);
+out:
+	return err;
+}
+
 static int parse_record_events(const struct option *opt __maybe_unused,
 			       const char *str, int unset __maybe_unused)
 {

@@ -129,6 +191,8 @@ int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (!strncmp(argv[0], "rec", 3)) {
 		return perf_c2c__record(argc, argv);
+	} else if (!strncmp(argv[0], "rep", 3)) {
+		return perf_c2c__report(argc, argv);
 	} else {
 		usage_with_options(c2c_usage, c2c_options);
 	}

index 3fac3a294bdd..63c0e2d8d2d8 100644
@@ -10,8 +10,14 @@
 #include "tool.h"
 #include "data.h"
 
+struct c2c_hists {
+	struct hists		hists;
+	struct perf_hpp_list	list;
+};
+
 struct perf_c2c {
-	struct perf_tool tool;
+	struct perf_tool	tool;
+	struct c2c_hists	hists;
 };
 
 static struct perf_c2c c2c;

@@ -28,6 +34,231 @@ 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;
+
+	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;
+};
+
+static int c2c_width(struct perf_hpp_fmt *fmt,
+		     struct perf_hpp *hpp __maybe_unused,
+		     struct hists *hists __maybe_unused)
+{
+	struct c2c_fmt *c2c_fmt;
+
+	c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	return c2c_fmt->dim->width;
+}
+
+static int c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct hists *hists __maybe_unused, int line, int *span)
+{
+	struct c2c_fmt *c2c_fmt;
+	struct c2c_dimension *dim;
+	int len = c2c_width(fmt, hpp, hists);
+	const char *text;
+
+	c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	dim = c2c_fmt->dim;
+
+	text = dim->header.line[line].text;
+	if (text == NULL)
+		text = "";
+
+	if (*span) {
+		(*span)--;
+		return 0;
+	} else {
+		*span = dim->header.line[line].span;
+	}
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, text);
+}
+
+static struct c2c_dimension *dimensions[] = {
+	NULL,
+};
+
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	struct c2c_fmt *c2c_fmt;
+
+	c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	free(c2c_fmt);
+}
+
+static bool 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);
+
+	return c2c_a->dim == c2c_b->dim;
+}
+
+static struct c2c_dimension *get_dimension(const char *name)
+{
+	unsigned int i;
+
+	for (i = 0; dimensions[i]; i++) {
+		struct c2c_dimension *dim = dimensions[i];
+
+		if (!strcmp(dim->name, name))
+			return dim;
+	};
+
+	return NULL;
+}
+
+static struct c2c_fmt *get_format(const char *name)
+{
+	struct c2c_dimension *dim = get_dimension(name);
+	struct c2c_fmt *c2c_fmt;
+	struct perf_hpp_fmt *fmt;
+
+	if (!dim)
+		return NULL;
+
+	c2c_fmt = zalloc(sizeof(*c2c_fmt));
+	if (!c2c_fmt)
+		return NULL;
+
+	c2c_fmt->dim = dim;
+
+	fmt = &c2c_fmt->fmt;
+	INIT_LIST_HEAD(&fmt->list);
+	INIT_LIST_HEAD(&fmt->sort_list);
+
+	fmt->cmp	= dim->cmp;
+	fmt->sort	= dim->cmp;
+	fmt->entry	= dim->entry;
+	fmt->header	= c2c_header;
+	fmt->width	= c2c_width;
+	fmt->collapse	= dim->cmp;
+	fmt->equal	= fmt_equal;
+	fmt->free	= fmt_free;
+
+	return c2c_fmt;
+}
+
+static int c2c_hists__init_output(struct perf_hpp_list *hpp_list, char *name)
+{
+	struct c2c_fmt *c2c_fmt = get_format(name);
+
+	if (!c2c_fmt)
+		return -1;
+
+	perf_hpp_list__column_register(hpp_list, &c2c_fmt->fmt);
+	return 0;
+}
+
+static int c2c_hists__init_sort(struct perf_hpp_list *hpp_list, char *name)
+{
+	struct c2c_fmt *c2c_fmt = get_format(name);
+
+	if (!c2c_fmt)
+		return -1;
+
+	perf_hpp_list__register_sort_field(hpp_list, &c2c_fmt->fmt);
+	return 0;
+}
+
+#define PARSE_LIST(_list, _fn)							\
+	do {									\
+		char *tmp, *tok;						\
+		ret = 0;							\
+										\
+		if (!_list)							\
+			break;							\
+										\
+		for (tok = strtok_r((char *)_list, ", ", &tmp);			\
+				tok; tok = strtok_r(NULL, ", ", &tmp)) {	\
+			ret = _fn(hpp_list, tok);				\
+			if (ret == -EINVAL) {					\
+				error("Invalid --fields key: `%s'", tok);	\
+				break;						\
+			} else if (ret == -ESRCH) {				\
+				error("Unknown --fields key: `%s'", tok);	\
+				break;						\
+			}							\
+		}								\
+	} while (0)
+
+static int hpp_list__parse(struct perf_hpp_list *hpp_list,
+			   const char *output_,
+			   const char *sort_)
+{
+	char *output = output_ ? strdup(output_) : NULL;
+	char *sort   = sort_   ? strdup(sort_) : NULL;
+	int ret;
+
+	PARSE_LIST(output, c2c_hists__init_output);
+	PARSE_LIST(sort,   c2c_hists__init_sort);
+
+	/* copy sort keys to output fields */
+	perf_hpp__setup_output_field(hpp_list);
+
+	/*
+	 * We dont need other sorting keys other than those
+	 * we already specified. It also really slows down
+	 * the processing a lot with big number of output
+	 * fields, so switching this off for c2c.
+	 */
+
+#if 0
+	/* and then copy output fields to sort keys */
+	perf_hpp__append_sort_keys(&hists->list);
+#endif
+
+	free(output);
+	free(sort);
+	return ret;
+}
+
+static int c2c_hists__init(struct c2c_hists *hists,
+			   const char *sort)
+{
+	__hists__init(&hists->hists, &hists->list);
+
+	/*
+	 * Initialize only with sort fields, we need to resort
+	 * later anyway, and that's where we add output fields
+	 * as well.
+	 */
+	perf_hpp_list__init(&hists->list);
+
+	return hpp_list__parse(&hists->list, NULL, sort);
+}
+
+__maybe_unused
+static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
+			     const char *output,
+			     const char *sort)
+{
+	perf_hpp__reset_output_field(&c2c_hists->list);
+	return hpp_list__parse(&c2c_hists->list, output, sort);
+}
+
 static int perf_c2c__report(int argc, const char **argv)
 {
 	struct perf_session *session;

@@ -52,6 +283,12 @@ static int perf_c2c__report(int argc, const char **argv)
 
 	file.path = input_name;
 
+	err = c2c_hists__init(&c2c.hists, "dcacheline");
+	if (err) {
+		pr_debug("Failed to initialize hists\n");
+		goto out;
+	}
+
 	session = perf_session__new(&file, 0, &c2c.tool);
 	if (session == NULL) {
 		pr_debug("No memory for session\n");

index 63c0e2d8d2d8..6b58b537bc9d 100644
@@ -9,6 +9,7 @@
 #include "hist.h"
 #include "tool.h"
 #include "data.h"
+#include "sort.h"
 
 struct c2c_hists {
 	struct hists		hists;

@@ -47,6 +48,7 @@ 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 *);

@@ -66,34 +68,47 @@ static int c2c_width(struct perf_hpp_fmt *fmt,
 		     struct hists *hists __maybe_unused)
 {
 	struct c2c_fmt *c2c_fmt;
+	struct c2c_dimension *dim;
 
 	c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
-	return c2c_fmt->dim->width;
+	dim = c2c_fmt->dim;
+
+	return dim->se ? hists__col_len(hists, dim->se->se_width_idx) :
+			 c2c_fmt->dim->width;
 }
 
 static int c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-		      struct hists *hists __maybe_unused, int line, int *span)
+		      struct hists *hists, int line, int *span)
 {
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
 	struct c2c_fmt *c2c_fmt;
 	struct c2c_dimension *dim;
-	int len = c2c_width(fmt, hpp, hists);
-	const char *text;
+	const char *text = NULL;
+	int width = c2c_width(fmt, hpp, hists);
 
 	c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
 	dim = c2c_fmt->dim;
 
-	text = dim->header.line[line].text;
-	if (text == NULL)
-		text = "";
-
-	if (*span) {
-		(*span)--;
-		return 0;
+	if (dim->se) {
+		text = dim->header.line[line].text;
+		/* Use the last line from sort_entry if not defined. */
+		if (!text && (line == hpp_list->nr_header_lines - 1))
+			text = dim->se->se_header;
 	} else {
-		*span = dim->header.line[line].span;
+		text = dim->header.line[line].text;
+
+		if (*span) {
+			(*span)--;
+			return 0;
+		} else {
+			*span = dim->header.line[line].span;
+		}
 	}
 
-	return scnprintf(hpp->buf, hpp->size, "%*s", len, text);
+	if (text == NULL)
+		text = "";
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, text);
 }
 
 static struct c2c_dimension *dimensions[] = {

@@ -130,6 +145,39 @@ static struct c2c_dimension *get_dimension(const char *name)
 	return NULL;
 }
 
+static int c2c_se_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			struct hist_entry *he)
+{
+	struct c2c_fmt *c2c_fmt = container_of(fmt, struct c2c_fmt, fmt);
+	struct c2c_dimension *dim = c2c_fmt->dim;
+	size_t len = fmt->user_len;
+
+	if (!len)
+		len = hists__col_len(he->hists, dim->se->se_width_idx);
+
+	return dim->se->se_snprintf(he, hpp->buf, hpp->size, len);
+}
+
+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 *, struct hist_entry *);
+
+	collapse_fn = dim->se->se_collapse ?: dim->se->se_cmp;
+	return collapse_fn(a, b);
+}
+
 static struct c2c_fmt *get_format(const char *name)
 {
 	struct c2c_dimension *dim = get_dimension(name);

@@ -149,12 +197,12 @@ static struct c2c_fmt *get_format(const char *name)
 	INIT_LIST_HEAD(&fmt->list);
 	INIT_LIST_HEAD(&fmt->sort_list);
 
-	fmt->cmp	= dim->cmp;
-	fmt->sort	= dim->cmp;
-	fmt->entry	= dim->entry;
+	fmt->cmp	= dim->se ? c2c_se_cmp   : dim->cmp;
+	fmt->sort	= dim->se ? c2c_se_cmp   : dim->cmp;
+	fmt->entry	= dim->se ? c2c_se_entry : dim->entry;
 	fmt->header	= c2c_header;
 	fmt->width	= c2c_width;
-	fmt->collapse	= dim->cmp;
+	fmt->collapse	= dim->se ? c2c_se_collapse : dim->cmp;
 	fmt->equal	= fmt_equal;
 	fmt->free	= fmt_free;
 

index 6b58b537bc9d..a3481f86e2ae 100644
@@ -213,8 +213,10 @@ static int c2c_hists__init_output(struct perf_hpp_list *hpp_list, char *name)
 {
 	struct c2c_fmt *c2c_fmt = get_format(name);
 
-	if (!c2c_fmt)
-		return -1;
+	if (!c2c_fmt) {
+		reset_dimensions();
+		return output_field_add(hpp_list, name);
+	}
 
 	perf_hpp_list__column_register(hpp_list, &c2c_fmt->fmt);
 	return 0;

@@ -224,8 +226,10 @@ static int c2c_hists__init_sort(struct perf_hpp_list *hpp_list, char *name)
 {
 	struct c2c_fmt *c2c_fmt = get_format(name);
 
-	if (!c2c_fmt)
-		return -1;
+	if (!c2c_fmt) {
+		reset_dimensions();
+		return sort_dimension__add(hpp_list, name, NULL, 0);
+	}
 
 	perf_hpp_list__register_sort_field(hpp_list, &c2c_fmt->fmt);
 	return 0;

index a3481f86e2ae..29fb9573e292 100644
@@ -16,6 +16,15 @@ struct c2c_hists {
 	struct perf_hpp_list	list;
 };
 
+struct c2c_hist_entry {
+	struct c2c_hists	*hists;
+	/*
+	 * 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;

@@ -23,6 +32,86 @@ struct perf_c2c {
 
 static struct perf_c2c c2c;
 
+static void *c2c_he_zalloc(size_t size)
+{
+	struct c2c_hist_entry *c2c_he;
+
+	c2c_he = zalloc(size + sizeof(*c2c_he));
+	if (!c2c_he)
+		return NULL;
+
+	return &c2c_he->he;
+}
+
+static void c2c_he_free(void *he)
+{
+	struct c2c_hist_entry *c2c_he;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	if (c2c_he->hists) {
+		hists__delete_entries(&c2c_he->hists->hists);
+		free(c2c_he->hists);
+	}
+
+	free(c2c_he);
+}
+
+static struct hist_entry_ops c2c_entry_ops = {
+	.new	= c2c_he_zalloc,
+	.free	= c2c_he_free,
+};
+
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel __maybe_unused,
+				struct machine *machine)
+{
+	struct hists *hists = &c2c.hists.hists;
+	struct hist_entry *he;
+	struct addr_location al;
+	struct mem_info *mi;
+	int ret;
+
+	if (machine__resolve(machine, &al, sample) < 0) {
+		pr_debug("problem processing %d event, skipping it.\n",
+			 event->header.type);
+		return -1;
+	}
+
+	mi = sample__resolve_mem(sample, &al);
+	if (mi == NULL)
+		return -ENOMEM;
+
+	he = hists__add_entry_ops(hists, &c2c_entry_ops,
+				  &al, NULL, NULL, mi,
+				  sample, true);
+	if (he == NULL) {
+		free(mi);
+		return -ENOMEM;
+	}
+
+	hists__inc_nr_samples(hists, he->filtered);
+	ret = hist_entry__append_callchain(he, sample);
+
+	addr_location__put(&al);
+	return ret;
+}
+
+static struct perf_c2c c2c = {
+	.tool = {
+		.sample		= process_sample_event,
+		.mmap		= perf_event__process_mmap,
+		.mmap2		= perf_event__process_mmap2,
+		.comm		= perf_event__process_comm,
+		.exit		= perf_event__process_exit,
+		.fork		= perf_event__process_fork,
+		.lost		= perf_event__process_lost,
+		.ordered_events	= true,
+		.ordering_requires_timestamps = true,
+	},
+};
+
 static const char * const c2c_usage[] = {
 	"perf c2c {record|report}",
 	NULL

@@ -314,6 +403,7 @@ static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
 static int perf_c2c__report(int argc, const char **argv)
 {
 	struct perf_session *session;
+	struct ui_progress prog;
 	struct perf_data_file file = {
 		.mode = PERF_DATA_MODE_READ,
 	};

@@ -330,9 +420,12 @@ static int perf_c2c__report(int argc, const char **argv)
 
 	argc = parse_options(argc, argv, c2c_options, report_c2c_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc)
+	if (argc)
 		usage_with_options(report_c2c_usage, c2c_options);
 
+	if (!input_name || !strlen(input_name))
+		input_name = "perf.data";
+
 	file.path = input_name;
 
 	err = c2c_hists__init(&c2c.hists, "dcacheline");

@@ -356,6 +449,19 @@ static int perf_c2c__report(int argc, const char **argv)
 		goto out_session;
 	}
 
+	err = perf_session__process_events(session);
+	if (err) {
+		pr_err("failed to process sample\n");
+		goto out_session;
+	}
+
+	ui_progress__init(&prog, c2c.hists.hists.nr_entries, "Sorting...");
+
+	hists__collapse_resort(&c2c.hists.hists, NULL);
+	hists__output_resort(&c2c.hists.hists, &prog);
+
+	ui_progress__finish();
+
 out_session:
 	perf_session__delete(session);
 out:

index 29fb9573e292..cd0406ab8b5d 100644
@@ -61,6 +61,32 @@ static struct hist_entry_ops c2c_entry_ops = {
 	.free	= c2c_he_free,
 };
 
+static int c2c_hists__init(struct c2c_hists *hists,
+			   const char *sort);
+
+static struct hists*
+he__get_hists(struct hist_entry *he,
+	      const char *sort)
+{
+	struct c2c_hist_entry *c2c_he;
+	struct c2c_hists *hists;
+	int ret;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	if (c2c_he->hists)
+		return &c2c_he->hists->hists;
+
+	hists = c2c_he->hists = zalloc(sizeof(*hists));
+	if (!hists)
+		return NULL;
+
+	ret = c2c_hists__init(hists, sort);
+	if (ret)
+		free(hists);
+
+	return &hists->hists;
+}
+
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
 				struct perf_sample *sample,

@@ -70,7 +96,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	struct hists *hists = &c2c.hists.hists;
 	struct hist_entry *he;
 	struct addr_location al;
-	struct mem_info *mi;
+	struct mem_info *mi, *mi_dup;
 	int ret;
 
 	if (machine__resolve(machine, &al, sample) < 0) {

@@ -83,19 +109,50 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (mi == NULL)
 		return -ENOMEM;
 
+	mi_dup = memdup(mi, sizeof(*mi));
+	if (!mi_dup)
+		goto free_mi;
+
 	he = hists__add_entry_ops(hists, &c2c_entry_ops,
 				  &al, NULL, NULL, mi,
 				  sample, true);
-	if (he == NULL) {
-		free(mi);
-		return -ENOMEM;
-	}
+	if (he == NULL)
+		goto free_mi_dup;
 
 	hists__inc_nr_samples(hists, he->filtered);
 	ret = hist_entry__append_callchain(he, sample);
 
+	if (!ret) {
+		mi = mi_dup;
+
+		mi_dup = memdup(mi, sizeof(*mi));
+		if (!mi_dup)
+			goto free_mi;
+
+		hists = he__get_hists(he, "offset");
+		if (!hists)
+			goto free_mi_dup;
+
+		he = hists__add_entry_ops(hists, &c2c_entry_ops,
+					  &al, NULL, NULL, mi,
+					  sample, true);
+		if (he == NULL)
+			goto free_mi_dup;
+
+		hists__inc_nr_samples(hists, he->filtered);
+		ret = hist_entry__append_callchain(he, sample);
+	}
+
+out:
 	addr_location__put(&al);
 	return ret;
+
+free_mi_dup:
+	free(mi_dup);
+free_mi:
+	free(mi);
+	ret = -ENOMEM;
+	goto out;
 }
 
 static struct perf_c2c c2c = {

@@ -400,6 +457,27 @@ static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
 	return hpp_list__parse(&c2c_hists->list, output, sort);
 }
 
+static int filter_cb(struct hist_entry *he __maybe_unused)
+{
+	return 0;
+}
+
+static int resort_cl_cb(struct hist_entry *he)
+{
+	struct c2c_hist_entry *c2c_he;
+	struct c2c_hists *c2c_hists;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	c2c_hists = c2c_he->hists;
+
+	if (c2c_hists) {
+		hists__collapse_resort(&c2c_hists->hists, NULL);
+		hists__output_resort_cb(&c2c_hists->hists, NULL, filter_cb);
+	}
+
+	return 0;
+}
+
 static int perf_c2c__report(int argc, const char **argv)
 {
 	struct perf_session *session;

@@ -458,7 +536,7 @@ static int perf_c2c__report(int argc, const char **argv)
 	ui_progress__init(&prog, c2c.hists.hists.nr_entries, "Sorting...");
 
 	hists__collapse_resort(&c2c.hists.hists, NULL);
-	hists__output_resort(&c2c.hists.hists, &prog);
+	hists__output_resort_cb(&c2c.hists.hists, &prog, resort_cl_cb);
 
 	ui_progress__finish();
 

index cd0406ab8b5d..7bf6248dbd75 100644
@@ -14,10 +14,12 @@
 struct c2c_hists {
 	struct hists		hists;
 	struct perf_hpp_list	list;
+	struct c2c_stats	stats;
 };
 
 struct c2c_hist_entry {
 	struct c2c_hists	*hists;
+	struct c2c_stats	 stats;
 	/*
 	 * must be at the end,
 	 * because of its callchain dynamic entry

@@ -64,9 +66,9 @@ static struct hist_entry_ops c2c_entry_ops = {
 static int c2c_hists__init(struct c2c_hists *hists,
 			   const char *sort);
 
-static struct hists*
-he__get_hists(struct hist_entry *he,
-	      const char *sort)
+static struct c2c_hists*
+he__get_c2c_hists(struct hist_entry *he,
+		  const char *sort)
 {
 	struct c2c_hist_entry *c2c_he;
 	struct c2c_hists *hists;

@@ -74,7 +76,7 @@ he__get_hists(struct hist_entry *he,
 
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
 	if (c2c_he->hists)
-		return &c2c_he->hists->hists;
+		return c2c_he->hists;
 
 	hists = c2c_he->hists = zalloc(sizeof(*hists));
 	if (!hists)

@@ -84,7 +86,7 @@ he__get_hists(struct hist_entry *he,
 	if (ret)
 		free(hists);
 
-	return &hists->hists;
+	return hists;
 }
 
 static int process_sample_event(struct perf_tool *tool __maybe_unused,

@@ -93,7 +95,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel __maybe_unused,
 				struct machine *machine)
 {
-	struct hists *hists = &c2c.hists.hists;
+	struct c2c_hists *c2c_hists = &c2c.hists;
+	struct c2c_hist_entry *c2c_he;
+	struct c2c_stats stats = { 0 };
 	struct hist_entry *he;
 	struct addr_location al;
 	struct mem_info *mi, *mi_dup;

@@ -113,13 +117,19 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (!mi_dup)
 		goto free_mi;
 
-	he = hists__add_entry_ops(hists, &c2c_entry_ops,
+	c2c_decode_stats(&stats, 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;
 
-	hists__inc_nr_samples(hists, he->filtered);
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	c2c_add_stats(&c2c_he->stats, &stats);
+	c2c_add_stats(&c2c_hists->stats, &stats);
+
+	hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
 	ret = hist_entry__append_callchain(he, sample);
 
 	if (!ret) {

@@ -129,17 +139,21 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		if (!mi_dup)
 			goto free_mi;
 
-		hists = he__get_hists(he, "offset");
-		if (!hists)
+		c2c_hists = he__get_c2c_hists(he, "offset");
+		if (!c2c_hists)
 			goto free_mi_dup;
 
-		he = hists__add_entry_ops(hists, &c2c_entry_ops,
+		he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops,
 					  &al, NULL, NULL, mi,
 					  sample, true);
 		if (he == NULL)
 			goto free_mi_dup;
 
-		hists__inc_nr_samples(hists, he->filtered);
+		c2c_he = container_of(he, struct c2c_hist_entry, he);
+		c2c_add_stats(&c2c_he->stats, &stats);
+		c2c_add_stats(&c2c_hists->stats, &stats);
+
+		hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
 		ret = hist_entry__append_callchain(he, sample);
 	}
 

index 7bf6248dbd75..c21124e6bb63 100644
@@ -271,6 +271,46 @@ static int c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", width, text);
 }
 
+#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] = {		\
+			.text = __h0,	\
+			.span = __s,	\
+		},			\
+		.line[1] = {		\
+			.text = __h1,	\
+		},			\
+	}
+
+#define HEADER_SPAN_LOW(__h)		\
+	{				\
+		.line[1] = {		\
+			.text = __h,	\
+		},			\
+	}
+
+#undef HEADER_LOW
+#undef HEADER_BOTH
+#undef HEADER_SPAN
+#undef HEADER_SPAN_LOW
+
 static struct c2c_dimension *dimensions[] = {
 	NULL,
 };

index c21124e6bb63..060ee1050da9 100644
@@ -1,5 +1,6 @@
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/stringify.h>
 #include "util.h"
 #include "debug.h"
 #include "builtin.h"

@@ -7,6 +8,7 @@
 #include "mem-events.h"
 #include "session.h"
 #include "hist.h"
+#include "sort.h"
 #include "tool.h"
 #include "data.h"
 #include "sort.h"

@@ -271,6 +273,33 @@ static int c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", width, text);
 }
 
+static char *hex_str(u64 val)
+{
+	static char buf[20];
+
+	snprintf(buf, 20, "0x%" PRIx64, val);
+	return buf;
+}
+
+static int64_t
+dcacheline_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+	       struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__dcacheline_cmp(left, right);
+}
+
+static int dcacheline_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			    struct hist_entry *he)
+{
+	uint64_t addr = 0;
+	int width = c2c_width(fmt, hpp, he->hists);
+
+	if (he->mem_info)
+		addr = cl_address(he->mem_info->daddr.addr);
+
+	return snprintf(hpp->buf, hpp->size, "%*s", width, hex_str(addr));
+}
+
 #define HEADER_LOW(__h)			\
 	{				\
 		.line[1] = {		\

@@ -306,12 +335,21 @@ static int c2c_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		},			\
 	}
 
+static struct c2c_dimension dim_dcacheline = {
+	.header		= HEADER_LOW("Cacheline"),
+	.name		= "dcacheline",
+	.cmp		= dcacheline_cmp,
+	.entry		= dcacheline_entry,
+	.width		= 18,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN
 #undef HEADER_SPAN_LOW
 
 static struct c2c_dimension *dimensions[] = {
+	&dim_dcacheline,
 	NULL,
 };
 

index 060ee1050da9..086e337e9d7d 100644
@@ -300,6 +300,32 @@ static int dcacheline_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return snprintf(hpp->buf, hpp->size, "%*s", width, hex_str(addr));
 }
 
+static int offset_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			struct hist_entry *he)
+{
+	uint64_t addr = 0;
+	int width = c2c_width(fmt, hpp, he->hists);
+
+	if (he->mem_info)
+		addr = cl_offset(he->mem_info->daddr.al_addr);
+
+	return snprintf(hpp->buf, hpp->size, "%*s", width, hex_str(addr));
+}
+
+static int64_t
+offset_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+	   struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = 0, r = 0;
+
+	if (left->mem_info)
+		l = cl_offset(left->mem_info->daddr.addr);
+	if (right->mem_info)
+		r = cl_offset(right->mem_info->daddr.addr);
+
+	return (int64_t)(r - l);
+}
+
 #define HEADER_LOW(__h)			\
 	{				\
 		.line[1] = {		\

@@ -343,6 +369,14 @@ static struct c2c_dimension dim_dcacheline = {
 	.width		= 18,
 };
 
+static struct c2c_dimension dim_offset = {
+	.header		= HEADER_BOTH("Data address", "Offset"),
+	.name		= "offset",
+	.cmp		= offset_cmp,
+	.entry		= offset_entry,
+	.width		= 18,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN

@@ -350,6 +384,7 @@ static struct c2c_dimension dim_dcacheline = {
 
 static struct c2c_dimension *dimensions[] = {
 	&dim_dcacheline,
+	&dim_offset,
 	NULL,
 };
 

index 086e337e9d7d..a97e6d6c3b9b 100644
@@ -326,6 +326,26 @@ offset_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	return (int64_t)(r - l);
 }
 
+static int
+iaddr_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+	    struct hist_entry *he)
+{
+	uint64_t addr = 0;
+	int width = c2c_width(fmt, hpp, he->hists);
+
+	if (he->mem_info)
+		addr = he->mem_info->iaddr.addr;
+
+	return snprintf(hpp->buf, hpp->size, "%*s", width, hex_str(addr));
+}
+
+static int64_t
+iaddr_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+	  struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__iaddr_cmp(left, right);
+}
+
 #define HEADER_LOW(__h)			\
 	{				\
 		.line[1] = {		\

@@ -377,6 +397,14 @@ static struct c2c_dimension dim_offset = {
 	.width		= 18,
 };
 
+static struct c2c_dimension dim_iaddr = {
+	.header		= HEADER_LOW("Code address"),
+	.name		= "iaddr",
+	.cmp		= iaddr_cmp,
+	.entry		= iaddr_entry,
+	.width		= 18,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN

@@ -385,6 +413,7 @@ static struct c2c_dimension dim_offset = {
 static struct c2c_dimension *dimensions[] = {
 	&dim_dcacheline,
 	&dim_offset,
+	&dim_iaddr,
 	NULL,
 };
 

index a97e6d6c3b9b..a48fcc91e9fd 100644
@@ -346,6 +346,70 @@ iaddr_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	return sort__iaddr_cmp(left, right);
 }
 
+static int
+tot_hitm_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);
+	unsigned int tot_hitm;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	tot_hitm = c2c_he->stats.lcl_hitm + c2c_he->stats.rmt_hitm;
+
+	return snprintf(hpp->buf, hpp->size, "%*u", width, tot_hitm);
+}
+
+static int64_t
+tot_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+	     struct hist_entry *left, struct hist_entry *right)
+{
+	struct c2c_hist_entry *c2c_left;
+	struct c2c_hist_entry *c2c_right;
+	unsigned int tot_hitm_left;
+	unsigned int tot_hitm_right;
+
+	c2c_left  = container_of(left, struct c2c_hist_entry, he);
+	c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+	tot_hitm_left  = c2c_left->stats.lcl_hitm + c2c_left->stats.rmt_hitm;
+	tot_hitm_right = c2c_right->stats.lcl_hitm + c2c_right->stats.rmt_hitm;
+
+	return tot_hitm_left - tot_hitm_right;
+}
+
+#define STAT_FN_ENTRY(__f)					\
+static int							\
+__f ## _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);	\
+	return snprintf(hpp->buf, hpp->size, "%*u", width,	\
+			c2c_he->stats.__f);			\
+}
+
+#define STAT_FN_CMP(__f)						\
+static int64_t								\
+__f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused,			\
+	    struct hist_entry *left, struct hist_entry *right)		\
+{									\
+	struct c2c_hist_entry *c2c_left, *c2c_right;			\
+									\
+	c2c_left  = container_of(left, struct c2c_hist_entry, he);	\
+	c2c_right = container_of(right, struct c2c_hist_entry, he);	\
+	return c2c_left->stats.__f - c2c_right->stats.__f;		\
+}
+
+#define STAT_FN(__f)		\
+	STAT_FN_ENTRY(__f)	\
+	STAT_FN_CMP(__f)
+
+STAT_FN(rmt_hitm)
+STAT_FN(lcl_hitm)
+
 #define HEADER_LOW(__h)			\
 	{				\
 		.line[1] = {		\

@@ -405,6 +469,46 @@ static struct c2c_dimension dim_iaddr = {
 	.width		= 18,
 };
 
+static struct c2c_dimension dim_tot_hitm = {
+	.header		= HEADER_SPAN("----- LLC Load Hitm -----", "Total", 2),
+	.name		= "tot_hitm",
+	.cmp		= tot_hitm_cmp,
+	.entry		= tot_hitm_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_lcl_hitm = {
+	.header		= HEADER_SPAN_LOW("Lcl"),
+	.name		= "lcl_hitm",
+	.cmp		= lcl_hitm_cmp,
+	.entry		= lcl_hitm_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_rmt_hitm = {
+	.header		= HEADER_SPAN_LOW("Rmt"),
+	.name		= "rmt_hitm",
+	.cmp		= rmt_hitm_cmp,
+	.entry		= rmt_hitm_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_cl_rmt_hitm = {
+	.header		= HEADER_SPAN("----- HITM -----", "Rmt", 1),
+	.name		= "cl_rmt_hitm",
+	.cmp		= rmt_hitm_cmp,
+	.entry		= rmt_hitm_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_cl_lcl_hitm = {
+	.header		= HEADER_SPAN_LOW("Lcl"),
+	.name		= "cl_lcl_hitm",
+	.cmp		= lcl_hitm_cmp,
+	.entry		= lcl_hitm_entry,
+	.width		= 7,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN

@@ -414,6 +518,11 @@ static struct c2c_dimension *dimensions[] = {
 	&dim_dcacheline,
 	&dim_offset,
 	&dim_iaddr,
+	&dim_tot_hitm,
+	&dim_lcl_hitm,
+	&dim_rmt_hitm,
+	&dim_cl_lcl_hitm,
+	&dim_cl_rmt_hitm,
 	NULL,
 };
 

index a48fcc91e9fd..eb8bb158ad8a 100644
@@ -409,6 +409,9 @@ __f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused,			\
 
 STAT_FN(rmt_hitm)
 STAT_FN(lcl_hitm)
+STAT_FN(store)
+STAT_FN(st_l1hit)
+STAT_FN(st_l1miss)
 
 #define HEADER_LOW(__h)			\
 	{				\

@@ -509,6 +512,46 @@ static struct c2c_dimension dim_cl_lcl_hitm = {
 	.width		= 7,
 };
 
+static struct c2c_dimension dim_stores = {
+	.header		= HEADER_SPAN("---- Store Reference ----", "Total", 2),
+	.name		= "stores",
+	.cmp		= store_cmp,
+	.entry		= store_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_stores_l1hit = {
+	.header		= HEADER_SPAN_LOW("L1Hit"),
+	.name		= "stores_l1hit",
+	.cmp		= st_l1hit_cmp,
+	.entry		= st_l1hit_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_stores_l1miss = {
+	.header		= HEADER_SPAN_LOW("L1Miss"),
+	.name		= "stores_l1miss",
+	.cmp		= st_l1miss_cmp,
+	.entry		= st_l1miss_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_cl_stores_l1hit = {
+	.header		= HEADER_SPAN("-- Store Refs --", "L1 Hit", 1),
+	.name		= "cl_stores_l1hit",
+	.cmp		= st_l1hit_cmp,
+	.entry		= st_l1hit_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_cl_stores_l1miss = {
+	.header		= HEADER_SPAN_LOW("L1 Miss"),
+	.name		= "cl_stores_l1miss",
+	.cmp		= st_l1miss_cmp,
+	.entry		= st_l1miss_entry,
+	.width		= 7,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN

@@ -523,6 +566,11 @@ static struct c2c_dimension *dimensions[] = {
 	&dim_rmt_hitm,
 	&dim_cl_lcl_hitm,
 	&dim_cl_rmt_hitm,
+	&dim_stores,
+	&dim_stores_l1hit,
+	&dim_stores_l1miss,
+	&dim_cl_stores_l1hit,
+	&dim_cl_stores_l1miss,
 	NULL,
 };
 

index eb8bb158ad8a..8279033d9d83 100644
@@ -412,6 +412,9 @@ STAT_FN(lcl_hitm)
 STAT_FN(store)
 STAT_FN(st_l1hit)
 STAT_FN(st_l1miss)
+STAT_FN(ld_fbhit)
+STAT_FN(ld_l1hit)
+STAT_FN(ld_l2hit)
 
 #define HEADER_LOW(__h)			\
 	{				\

@@ -552,6 +555,30 @@ static struct c2c_dimension dim_cl_stores_l1miss = {
 	.width		= 7,
 };
 
+static struct c2c_dimension dim_ld_fbhit = {
+	.header		= HEADER_SPAN("----- Core Load Hit -----", "FB", 2),
+	.name		= "ld_fbhit",
+	.cmp		= ld_fbhit_cmp,
+	.entry		= ld_fbhit_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_ld_l1hit = {
+	.header		= HEADER_SPAN_LOW("L1"),
+	.name		= "ld_l1hit",
+	.cmp		= ld_l1hit_cmp,
+	.entry		= ld_l1hit_entry,
+	.width		= 7,
+};
+
+static struct c2c_dimension dim_ld_l2hit = {
+	.header		= HEADER_SPAN_LOW("L2"),
+	.name		= "ld_l2hit",
+	.cmp		= ld_l2hit_cmp,
+	.entry		= ld_l2hit_entry,
+	.width		= 7,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN

@@ -571,6 +598,9 @@ static struct c2c_dimension *dimensions[] = {
 	&dim_stores_l1miss,
 	&dim_cl_stores_l1hit,
 	&dim_cl_stores_l1miss,
+	&dim_ld_fbhit,
+	&dim_ld_l1hit,
+	&dim_ld_l2hit,
 	NULL,
 };
 

index 8279033d9d83..2cb5252c0623 100644
@@ -415,6 +415,8 @@ STAT_FN(st_l1miss)
 STAT_FN(ld_fbhit)
 STAT_FN(ld_l1hit)
 STAT_FN(ld_l2hit)
+STAT_FN(ld_llchit)
+STAT_FN(rmt_hit)
 
 #define HEADER_LOW(__h)			\
 	{				\

@@ -579,6 +581,22 @@ static struct c2c_dimension dim_ld_l2hit = {
 	.width		= 7,
 };
 
+static struct c2c_dimension dim_ld_llchit = {
+	.header		= HEADER_SPAN("-- LLC Load Hit --", "Llc", 1),
+	.name		= "ld_lclhit",
+	.cmp		= ld_llchit_cmp,
+	.entry		= ld_llchit_entry,
+	.width		= 8,
+};
+
+static struct c2c_dimension dim_ld_rmthit = {
+	.header		= HEADER_SPAN_LOW("Rmt"),
+	.name		= "ld_rmthit",
+	.cmp		= rmt_hit_cmp,
+	.entry		= rmt_hit_entry,
+	.width		= 8,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN

@@ -601,6 +619,8 @@ static struct c2c_dimension *dimensions[] = {
 	&dim_ld_fbhit,
 	&dim_ld_l1hit,
 	&dim_ld_l2hit,
+	&dim_ld_llchit,
+	&dim_ld_rmthit,
 	NULL,
 };
 

index 2cb5252c0623..e7e7890882c4 100644
@@ -418,6 +418,44 @@ STAT_FN(ld_l2hit)
 STAT_FN(ld_llchit)
 STAT_FN(rmt_hit)
 
+static uint64_t llc_miss(struct c2c_stats *stats)
+{
+	uint64_t llcmiss;
+
+	llcmiss = stats->lcl_dram +
+		  stats->rmt_dram +
+		  stats->rmt_hitm +
+		  stats->rmt_hit;
+
+	return llcmiss;
+}
+
+static int
+ld_llcmiss_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);
+
+	return snprintf(hpp->buf, hpp->size, "%*lu", width,
+			llc_miss(&c2c_he->stats));
+}
+
+static int64_t
+ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+	       struct hist_entry *left, struct hist_entry *right)
+{
+	struct c2c_hist_entry *c2c_left;
+	struct c2c_hist_entry *c2c_right;
+
+	c2c_left  = container_of(left, struct c2c_hist_entry, he);
+	c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+	return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats);
+}
+
 #define HEADER_LOW(__h)			\
 	{				\
 		.line[1] = {		\

@@ -597,6 +635,14 @@ static struct c2c_dimension dim_ld_rmthit = {
 	.width		= 8,
 };
 
+static struct c2c_dimension dim_ld_llcmiss = {
+	.header		= HEADER_BOTH("LLC", "Ld Miss"),
+	.name		= "ld_llcmiss",
+	.cmp		= ld_llcmiss_cmp,
+	.entry		= ld_llcmiss_entry,
+	.width		= 7,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN

@@ -621,6 +667,7 @@ static struct c2c_dimension *dimensions[] = {
 	&dim_ld_l2hit,
 	&dim_ld_llchit,
 	&dim_ld_rmthit,
+	&dim_ld_llcmiss,
 	NULL,
 };
 

index e7e7890882c4..3f2f348479e3 100644
@@ -456,6 +456,61 @@ ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats);
 }
 
+static uint64_t total_records(struct c2c_stats *stats)
+{
+	uint64_t lclmiss, ldcnt, total;
+
+	lclmiss  = stats->lcl_dram +
+		   stats->rmt_dram +
+		   stats->rmt_hitm +
+		   stats->rmt_hit;
+
+	ldcnt    = lclmiss +
+		   stats->ld_fbhit +
+		   stats->ld_l1hit +
+		   stats->ld_l2hit +
+		   stats->ld_llchit +
+		   stats->lcl_hitm;
+
+	total    = ldcnt +
+		   stats->st_l1hit +
+		   stats->st_l1miss;
+
+	return total;
+}
+
+static int
+tot_recs_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);
+	uint64_t tot_recs;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	tot_recs = total_records(&c2c_he->stats);
+
+	return snprintf(hpp->buf, hpp->size, "%*" PRIu64, width, tot_recs);
+}
+
+static int64_t
+tot_recs_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+	     struct hist_entry *left, struct hist_entry *right)
+{
+	struct c2c_hist_entry *c2c_left;
+	struct c2c_hist_entry *c2c_right;
+	uint64_t tot_recs_left;
+	uint64_t tot_recs_right;
+
+	c2c_left  = container_of(left, struct c2c_hist_entry, he);
+	c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+	tot_recs_left  = total_records(&c2c_left->stats);
+	tot_recs_right = total_records(&c2c_right->stats);
+
+	return tot_recs_left - tot_recs_right;
+}
+
 #define HEADER_LOW(__h)			\
 	{				\
 		.line[1] = {		\

@@ -643,6 +698,14 @@ static struct c2c_dimension dim_ld_llcmiss = {
 	.width		= 7,
 };
 
+static struct c2c_dimension dim_tot_recs = {
+	.header		= HEADER_BOTH("Total", "records"),
+	.name		= "tot_recs",
+	.cmp		= tot_recs_cmp,
+	.entry		= tot_recs_entry,
+	.width		= 7,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN

@@ -668,6 +731,7 @@ static struct c2c_dimension *dimensions[] = {
 	&dim_ld_llchit,
 	&dim_ld_rmthit,
 	&dim_ld_llcmiss,
+	&dim_tot_recs,
 	NULL,
 };
 

index 3f2f348479e3..c5ca6daec2d6 100644
@@ -511,6 +511,57 @@ tot_recs_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	return tot_recs_left - tot_recs_right;
 }
 
+static uint64_t total_loads(struct c2c_stats *stats)
+{
+	uint64_t lclmiss, ldcnt;
+
+	lclmiss  = stats->lcl_dram +
+		   stats->rmt_dram +
+		   stats->rmt_hitm +
+		   stats->rmt_hit;
+
+	ldcnt    = lclmiss +
+		   stats->ld_fbhit +
+		   stats->ld_l1hit +
+		   stats->ld_l2hit +
+		   stats->ld_llchit +
+		   stats->lcl_hitm;
+
+	return ldcnt;
+}
+
+static int
+tot_loads_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);
+	uint64_t tot_recs;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	tot_recs = total_loads(&c2c_he->stats);
+
+	return snprintf(hpp->buf, hpp->size, "%*" PRIu64, width, tot_recs);
+}
+
+static int64_t
+tot_loads_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+	      struct hist_entry *left, struct hist_entry *right)
+{
+	struct c2c_hist_entry *c2c_left;
+	struct c2c_hist_entry *c2c_right;
+	uint64_t tot_recs_left;
+	uint64_t tot_recs_right;
+
+	c2c_left  = container_of(left, struct c2c_hist_entry, he);
+	c2c_right = container_of(right, struct c2c_hist_entry, he);
+
+	tot_recs_left  = total_loads(&c2c_left->stats);
+	tot_recs_right = total_loads(&c2c_right->stats);
+
+	return tot_recs_left - tot_recs_right;
+}
+
 #define HEADER_LOW(__h)			\
 	{				\
 		.line[1] = {		\

@@ -706,6 +757,14 @@ static struct c2c_dimension dim_tot_recs = {
 	.width		= 7,
 };
 
+static struct c2c_dimension dim_tot_loads = {
+	.header		= HEADER_BOTH("Total", "Loads"),
+	.name		= "tot_loads",
+	.cmp		= tot_loads_cmp,
+	.entry		= tot_loads_entry,
+	.width		= 7,
+};
+
 #undef HEADER_LOW
 #undef HEADER_BOTH
 #undef HEADER_SPAN