perf report: Add 'type' sort key

The 'type' sort key is to aggregate hist entries by data type they
access.  Add mem_type field to hist_entry struct to save the type.  If
hist_entry__get_data_type() returns NULL, it'd use the 'unknown_type'
instance.

Committer testing:

Before:

  # perf mem record  sleep 2s
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.037 MB perf.data (4 samples) ]
  root@number:/home/acme/Downloads# perf report --stdio -s type
  Error:
  Unknown --sort key: `type'
   Usage: perf report [<options>]

      -s, --sort <key[,key2...]>
                            sort by key(s): overhead overhead_sys overhead_us overhead_guest_sys
                            overhead_guest_us overhead_children sample period
                            pid comm dso symbol parent cpu socket srcline srcfile
                            local_weight weight transaction trace symbol_size
                            dso_size cgroup cgroup_id ipc_null time code_page_size
                            local_ins_lat ins_lat local_p_stage_cyc p_stage_cyc
                            addr local_retire_lat retire_lat simd dso_from dso_to
                            symbol_from symbol_to mispredict abort in_tx cycles
                            srcline_from srcline_to ipc_lbr addr_from addr_to
                            symbol_daddr dso_daddr locked tlb mem snoop dcacheline
                            symbol_iaddr phys_daddr data_page_size blocked
  #

After:

  # perf report --stdio -s type
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 4  of event 'cpu_atom/mem-loads,ldlat=30/P'
  # Event count (approx.): 7
  #
  # Overhead  Data Type
  # ........  .........
  #
     100.00%  (unknown)

  #
  # (Tip: Print event counts in CSV format with: perf stat -x,)
  #
  # rpm -q kernel-debuginfo
  kernel-debuginfo-6.6.4-200.fc39.x86_64
  # uname -r
  6.6.4-200.fc39.x86_64
  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: linux-toolchains@vger.kernel.org>
Cc: linux-trace-devel@vger.kernel.org>
Link: https://lore.kernel.org/r/20231213001323.718046-9-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-report.txt

@@ -118,6 +118,7 @@ OPTIONS
 	- retire_lat: On X86, this reports pipeline stall of this instruction compared
 	  to the previous instruction in cycles. And currently supported only on X86
 	- simd: Flags describing a SIMD operation. "e" for empty Arm SVE predicate. "p" for partial Arm SVE predicate
+	- type: Data type of sample memory access.
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)

tools/perf/util/annotate-data.h

@@ -22,6 +22,8 @@ struct annotated_data_type {
 	int type_size;
 };
 
+extern struct annotated_data_type unknown_type;
+
 #ifdef HAVE_DWARF_SUPPORT
 
 /* Returns data type at the location (ip, reg, offset) */

tools/perf/util/hist.h

@@ -82,6 +82,7 @@ enum hist_column {
 	HISTC_ADDR_TO,
 	HISTC_ADDR,
 	HISTC_SIMD,
+	HISTC_TYPE,
 	HISTC_NR_COLS, /* Last entry */
 };
 

tools/perf/util/sort.c

@@ -24,6 +24,7 @@
 #include "strbuf.h"
 #include "mem-events.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "event.h"
 #include "time-utils.h"
 #include "cgroup.h"
@@ -2094,7 +2095,7 @@ struct sort_entry sort_dso_size = {
 	.se_width_idx	= HISTC_DSO_SIZE,
 };
 
-/* --sort dso_size */
+/* --sort addr */
 
 static int64_t
 sort__addr_cmp(struct hist_entry *left, struct hist_entry *right)
@@ -2131,6 +2132,69 @@ struct sort_entry sort_addr = {
 	.se_width_idx	= HISTC_ADDR,
 };
 
+/* --sort type */
+
+struct annotated_data_type unknown_type = {
+	.type_name = (char *)"(unknown)",
+};
+
+static int64_t
+sort__type_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__addr_cmp(left, right);
+}
+
+static void sort__type_init(struct hist_entry *he)
+{
+	if (he->mem_type)
+		return;
+
+	he->mem_type = hist_entry__get_data_type(he);
+	if (he->mem_type == NULL)
+		he->mem_type = &unknown_type;
+}
+
+static int64_t
+sort__type_collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	struct annotated_data_type *left_type = left->mem_type;
+	struct annotated_data_type *right_type = right->mem_type;
+
+	if (!left_type) {
+		sort__type_init(left);
+		left_type = left->mem_type;
+	}
+
+	if (!right_type) {
+		sort__type_init(right);
+		right_type = right->mem_type;
+	}
+
+	return strcmp(left_type->type_name, right_type->type_name);
+}
+
+static int64_t
+sort__type_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__type_collapse(left, right);
+}
+
+static int hist_entry__type_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*s", width, he->mem_type->type_name);
+}
+
+struct sort_entry sort_type = {
+	.se_header	= "Data Type",
+	.se_cmp		= sort__type_cmp,
+	.se_collapse	= sort__type_collapse,
+	.se_sort	= sort__type_sort,
+	.se_init	= sort__type_init,
+	.se_snprintf	= hist_entry__type_snprintf,
+	.se_width_idx	= HISTC_TYPE,
+};
+
 
 struct sort_dimension {
 	const char		*name;
@@ -2185,7 +2249,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_ADDR, "addr", sort_addr),
 	DIM(SORT_LOCAL_RETIRE_LAT, "local_retire_lat", sort_local_p_stage_cyc),
 	DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc),
-	DIM(SORT_SIMD, "simd", sort_simd)
+	DIM(SORT_SIMD, "simd", sort_simd),
+	DIM(SORT_ANNOTATE_DATA_TYPE, "type", sort_type),
 };
 
 #undef DIM

tools/perf/util/sort.h

@@ -15,6 +15,7 @@
 
 struct option;
 struct thread;
+struct annotated_data_type;
 
 extern regex_t parent_regex;
 extern const char *sort_order;
@@ -34,6 +35,7 @@ extern struct sort_entry sort_dso_to;
 extern struct sort_entry sort_sym_from;
 extern struct sort_entry sort_sym_to;
 extern struct sort_entry sort_srcline;
+extern struct sort_entry sort_type;
 extern const char default_mem_sort_order[];
 extern bool chk_double_cl;
 
@@ -154,6 +156,7 @@ struct hist_entry {
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
 	struct hist_entry_ops	*ops;
+	struct annotated_data_type *mem_type;
 	union {
 		/* this is for hierarchical entry structure */
 		struct {
@@ -243,6 +246,7 @@ enum sort_type {
 	SORT_LOCAL_RETIRE_LAT,
 	SORT_GLOBAL_RETIRE_LAT,
 	SORT_SIMD,
+	SORT_ANNOTATE_DATA_TYPE,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,