perf report: Add support for PERF_SAMPLE_CODE_PAGE_SIZE

Add a new sort dimension "code_page_size" for common sort.
With this option applied, perf can sort and report by sample's code page
size.

For example:

  # perf report --stdio --sort=comm,symbol,code_page_size
  # To display the perf.data header info, please use
  # --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 3K of event 'mem-loads:uP'
  # Event count (approx.): 1470769
  #
  # Overhead  Command  Symbol                        Code Page Size IPC [IPC Coverage]
  # ........  .......  ............................  .............. ....................
  #
      69.56%  dtlb     [.] GetTickCount              4K              -   -
      17.93%  dtlb     [.] Calibrate                 4K              -   -
      11.40%  dtlb     [.] __gettimeofday            4K              -   -
  #

Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210105195752.43489-6-kan.liang@linux.intel.com
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-report.txt

@@ -108,6 +108,7 @@ OPTIONS
 	- period: Raw number of event count of sample
 	- time: Separate the samples by time stamp with the resolution specified by
 	--time-quantum (default 100ms). Specify with overhead and before it.
+	- code_page_size: the code page size of sampled code address (ip)
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)

tools/perf/util/hist.c

@@ -212,6 +212,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__new_col_len(hists, HISTC_TIME, 16);
 	else
 		hists__new_col_len(hists, HISTC_TIME, 12);
+	hists__new_col_len(hists, HISTC_CODE_PAGE_SIZE, 6);
 
 	if (h->srcline) {
 		len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header));
@@ -718,6 +719,7 @@ __hists__add_entry(struct hists *hists,
 		.cpumode = al->cpumode,
 		.ip	 = al->addr,
 		.level	 = al->level,
+		.code_page_size = sample->code_page_size,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,

tools/perf/util/hist.h

@@ -53,6 +53,7 @@ enum hist_column {
 	HISTC_DSO_TO,
 	HISTC_LOCAL_WEIGHT,
 	HISTC_GLOBAL_WEIGHT,
+	HISTC_CODE_PAGE_SIZE,
 	HISTC_MEM_DADDR_SYMBOL,
 	HISTC_MEM_DADDR_DSO,
 	HISTC_MEM_PHYS_DADDR,

tools/perf/util/sort.c

@@ -1491,6 +1491,31 @@ struct sort_entry sort_mem_data_page_size = {
 	.se_width_idx	= HISTC_MEM_DATA_PAGE_SIZE,
 };
 
+static int64_t
+sort__code_page_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = left->code_page_size;
+	uint64_t r = right->code_page_size;
+
+	return (int64_t)(r - l);
+}
+
+static int hist_entry__code_page_size_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+	char str[PAGE_SIZE_NAME_LEN];
+
+	return repsep_snprintf(bf, size, "%-*s", width,
+			       get_page_size_name(he->code_page_size, str));
+}
+
+struct sort_entry sort_code_page_size = {
+	.se_header	= "Code Page Size",
+	.se_cmp		= sort__code_page_size_cmp,
+	.se_snprintf	= hist_entry__code_page_size_snprintf,
+	.se_width_idx	= HISTC_CODE_PAGE_SIZE,
+};
+
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1735,6 +1760,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 	DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
 	DIM(SORT_TIME, "time", sort_time),
+	DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
 };
 
 #undef DIM

tools/perf/util/sort.h

@@ -106,6 +106,7 @@ struct hist_entry {
 	u64			transaction;
 	s32			socket;
 	s32			cpu;
+	u64			code_page_size;
 	u8			cpumode;
 	u8			depth;
 
@@ -229,6 +230,7 @@ enum sort_type {
 	SORT_CGROUP_ID,
 	SORT_SYM_IPC_NULL,
 	SORT_TIME,
+	SORT_CODE_PAGE_SIZE,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,