perf tools: Introduce new sort type "socket" for the processor socket

This patch enable perf report to sort by processor socket:

  $ perf report --stdio --sort socket,comm,dso,symbol
  # To display the perf.data header info, please use --header/--header-only options.
  #
  # Total Lost Samples: 0
  #
  # Samples: 686  of event 'cycles'
  # Event count (approx.): 349215462
  #
  # Overhead SOCKET Command Shared Object    Symbol
  # ........ ...... ....... ................ ............................
  #
    97.05%    000   test    test             [.] plusB_c
     0.98%    000   test    test             [.] plusA_c
     0.93%    001   perf    [kernel.vmlinux] [k] smp_call_function_single
     0.19%    001   perf    [kernel.vmlinux] [k] page_fault
     0.19%    001   swapper [kernel.vmlinux] [k] pm_qos_request
     0.16%    000   test    [kernel.vmlinux] [k] add_mm_counter_fast
Signed-off-by: NKan Liang <kan.liang@intel.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1441377946-44429-2-git-send-email-kan.liang@intel.com
[ Fix col calc, un-allcapsify col header & read the topology when not using perf.data ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-report.txt

@@ -68,7 +68,7 @@ OPTIONS
 --sort=::
 	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, srcline, weight, local_weight.
+	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
 
 	Each key has following meaning:
 
@@ -79,6 +79,7 @@ OPTIONS
 	- parent: name of function matched to the parent regex filter. Unmatched
 	entries are displayed as "[other]".
 	- cpu: cpu number the task ran at the time of sample
+	- socket: processor socket number the task ran at the time of sample
 	- srcline: filename and line number executed at the time of sample.  The
 	DWARF debugging info must be provided.
 	- srcfile: file name of the source file of the same. Requires dwarf

tools/perf/builtin-top.c

@@ -963,6 +963,13 @@ static int __cmd_top(struct perf_top *top)
 
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
 				    top->evlist->threads, false, opts->proc_map_timeout);
+
+	if (sort__has_socket) {
+		ret = perf_env__read_cpu_topology_map(&perf_env);
+		if (ret < 0)
+			goto out_err_cpu_topo;
+	}
+
 	ret = perf_top__start_counters(top);
 	if (ret)
 		goto out_delete;
@@ -1020,6 +1027,14 @@ static int __cmd_top(struct perf_top *top)
 	top->session = NULL;
 
 	return ret;
+
+out_err_cpu_topo: {
+	char errbuf[BUFSIZ];
+	const char *err = strerror_r(-ret, errbuf, sizeof(errbuf));
+
+	ui__error("Could not read the CPU topology map: %s\n", err);
+	goto out_delete;
+}
 }
 
 static int

tools/perf/util/hist.c

@@ -145,6 +145,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	}
 
 	hists__new_col_len(hists, HISTC_CPU, 3);
+	hists__new_col_len(hists, HISTC_SOCKET, 6);
 	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
 	hists__new_col_len(hists, HISTC_MEM_TLB, 22);
 	hists__new_col_len(hists, HISTC_MEM_SNOOP, 12);

tools/perf/util/hist.h

@@ -29,6 +29,7 @@ enum hist_column {
 	HISTC_COMM,
 	HISTC_PARENT,
 	HISTC_CPU,
+	HISTC_SOCKET,
 	HISTC_SRCLINE,
 	HISTC_SRCFILE,
 	HISTC_MISPREDICT,

tools/perf/util/sort.c

@@ -21,6 +21,7 @@ int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
 int		sort__has_sym = 0;
 int		sort__has_dso = 0;
+int		sort__has_socket = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
 
@@ -421,6 +422,27 @@ struct sort_entry sort_cpu = {
 	.se_width_idx	= HISTC_CPU,
 };
 
+/* --sort socket */
+
+static int64_t
+sort__socket_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->socket - left->socket;
+}
+
+static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket);
+}
+
+struct sort_entry sort_socket = {
+	.se_header      = "Socket",
+	.se_cmp	        = sort__socket_cmp,
+	.se_snprintf    = hist_entry__socket_snprintf,
+	.se_width_idx	= HISTC_SOCKET,
+};
+
 /* sort keys for branch stacks */
 
 static int64_t
@@ -1248,6 +1270,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_SYM, "symbol", sort_sym),
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
+	DIM(SORT_SOCKET, "socket", sort_socket),
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
 	DIM(SORT_SRCFILE, "srcfile", sort_srcfile),
 	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
@@ -1550,6 +1573,8 @@ int sort_dimension__add(const char *tok)
 
 		} else if (sd->entry == &sort_dso) {
 			sort__has_dso = 1;
+		} else if (sd->entry == &sort_socket) {
+			sort__has_socket = 1;
 		}
 
 		return __sort_dimension__add(sd);

tools/perf/util/sort.h

@@ -34,6 +34,7 @@ extern int have_ignore_callees;
 extern int sort__need_collapse;
 extern int sort__has_parent;
 extern int sort__has_sym;
+extern int sort__has_socket;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
@@ -173,6 +174,7 @@ enum sort_type {
 	SORT_SYM,
 	SORT_PARENT,
 	SORT_CPU,
+	SORT_SOCKET,
 	SORT_SRCLINE,
 	SORT_SRCFILE,
 	SORT_LOCAL_WEIGHT,