perf tools: Add 'addr' sort key

Sometimes users want to see actual (virtual) address of sampled instructions.
Add a new 'addr' sort key to display the raw addresses.

$ perf record -o- true | perf report -i- -s addr
# To display the perf.data header info, please use --header/--header-only options.
#
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.000 MB - ]
#
# Total Lost Samples: 0
#
# Samples: 12 of event 'cycles:u'
# Event count (approx.): 252512
#
# Overhead Address
# ........ ..................
#
42.96% 0x7f96f08443d7
29.55% 0x7f96f0859b50
14.76% 0x7f96f0852e02
8.30% 0x7f96f0855028
4.43% 0xffffffff8de01087

Note that it just compares and displays the sample ip. Each process can
have a different memory layout and the ip will be different even if they run
the same binary. So this sort key is mostly meaningful for per-process
profile data.

Signed-off-by: Namhyung Kim <[e-mail]>
Acked-by: Ian Rogers <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/Documentation/perf-report.txt

···
 	Sort histogram entries by given key(s) - multiple keys can be specified
 	in CSV format.  Following sort keys are available:
 	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight,
-	local_weight, cgroup_id.
+	local_weight, cgroup_id, addr.
 
 	Each key has following meaning:
 
···
 	- local_ins_lat: Local instruction latency version
 	- p_stage_cyc: On powerpc, this presents the number of cycles spent in a
 	  pipeline stage. And currently supported only on powerpc.
+	- addr: (Full) virtual address of the sampled instruction
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)

tools/perf/util/hist.c

···
 	hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13);
 	hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13);
 	hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13);
+	hists__new_col_len(hists, HISTC_ADDR, BITS_PER_LONG / 4 + 2);
 
 	if (symbol_conf.nanosecs)
 		hists__new_col_len(hists, HISTC_TIME, 16);

tools/perf/util/hist.h

···
 	HISTC_GLOBAL_P_STAGE_CYC,
 	HISTC_ADDR_FROM,
 	HISTC_ADDR_TO,
+	HISTC_ADDR,
 	HISTC_NR_COLS, /* Last entry */
 };
 

tools/perf/util/sort.c

···
 	.se_width_idx	= HISTC_DSO_SIZE,
 };
 
+/* --sort dso_size */
+
+static int64_t
+sort__addr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	u64 left_ip = left->ip;
+	u64 right_ip = right->ip;
+	struct map *left_map = left->ms.map;
+	struct map *right_map = right->ms.map;
+
+	if (left_map)
+		left_ip = left_map->unmap_ip(left_map, left_ip);
+	if (right_map)
+		right_ip = right_map->unmap_ip(right_map, right_ip);
+
+	return _sort__addr_cmp(left_ip, right_ip);
+}
+
+static int hist_entry__addr_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width)
+{
+	u64 ip = he->ip;
+	struct map *map = he->ms.map;
+
+	if (map)
+		ip = map->unmap_ip(map, ip);
+
+	return repsep_snprintf(bf, size, "%-#*llx", width, ip);
+}
+
+struct sort_entry sort_addr = {
+	.se_header	= "Address",
+	.se_cmp		= sort__addr_cmp,
+	.se_snprintf	= hist_entry__addr_snprintf,
+	.se_width_idx	= HISTC_ADDR,
+};
+
 
 struct sort_dimension {
 	const char		*name;
···
 	DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
 	DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc),
 	DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc),
+	DIM(SORT_ADDR, "addr", sort_addr),
 };
 
 #undef DIM

tools/perf/util/sort.h

···
 	SORT_GLOBAL_INS_LAT,
 	SORT_LOCAL_PIPELINE_STAGE_CYC,
 	SORT_GLOBAL_PIPELINE_STAGE_CYC,
+	SORT_ADDR,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,