perf callchain: Add order support for libdw DWARF unwinder

As reported by Milian, currently for DWARF unwind (both libdw and
libunwind) we display callchain in callee order only.

Adding the support to follow callchain order setup to libdw DWARF
unwinder, so we could get following output for report:

$ perf record --call-graph dwarf ls
...

$ perf report --no-children --stdio

21.12% ls libc-2.21.so [.] __strcoll_l
|
---__strcoll_l
mpsort_with_tmp
mpsort_with_tmp
mpsort_with_tmp
sort_files
main
__libc_start_main
_start

$ perf report --stdio --no-children -g caller

21.12% ls libc-2.21.so [.] __strcoll_l
|
---_start
__libc_start_main
main
sort_files
mpsort_with_tmp
mpsort_with_tmp
mpsort_with_tmp
__strcoll_l

Reported-and-Tested-by: Milian Wolff <[e-mail]>
Signed-off-by: Jiri Olsa <[e-mail]>
Tested-by: Wang Nan <[e-mail]>
Cc: David Ahern <[e-mail]>
Cc: Jan Kratochvil <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/util/unwind-libdw.c

···
 #include <linux/types.h>
 #include "event.h"
 #include "perf_regs.h"
+#include "callchain.h"
 
 static char *debuginfo_path;
 
···
 	return __report_module(&al, ip, ui);
 }
 
+/*
+ * Store all entries within entries array,
+ * we will process it after we finish unwind.
+ */
 static int entry(u64 ip, struct unwind_info *ui)
 
 {
-	struct unwind_entry e;
+	struct unwind_entry *e = &ui->entries[ui->idx++];
 	struct addr_location al;
 
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e.ip  = ip;
-	e.map = al.map;
-	e.sym = al.sym;
+	e->ip  = ip;
+	e->map = al.map;
+	e->sym = al.sym;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
 		 al.sym ? al.sym->name : "''",
 		 ip,
 		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
-
-	return ui->cb(&e, ui->arg);
+	return 0;
 }
 
 static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
···
 			struct perf_sample *data,
 			int max_stack)
 {
-	struct unwind_info ui = {
+	struct unwind_info *ui, ui_buf = {
 		.sample		= data,
 		.thread		= thread,
 		.machine	= thread->mg->machine,
···
 		.max_stack	= max_stack,
 	};
 	Dwarf_Word ip;
-	int err = -EINVAL;
+	int err = -EINVAL, i;
 
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ui.dwfl = dwfl_begin(&offline_callbacks);
-	if (!ui.dwfl)
+	ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack);
+	if (!ui)
+		return -ENOMEM;
+
+	*ui = ui_buf;
+
+	ui->dwfl = dwfl_begin(&offline_callbacks);
+	if (!ui->dwfl)
 		goto out;
 
 	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
 	if (err)
 		goto out;
 
-	err = report_module(ip, &ui);
+	err = report_module(ip, ui);
 	if (err)
 		goto out;
 
-	if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+	if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui))
 		goto out;
 
-	err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-	if (err && !ui.max_stack)
+	if (err && !ui->max_stack)
 		err = 0;
+
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < ui->idx && !err; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = ui->idx - i - 1;
+
+		err = ui->entries[j].ip ? ui->cb(&ui->entries[j], ui->arg) : 0;
+	}
 
  out:
 	if (err)
 		pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
 
-	dwfl_end(ui.dwfl);
+	dwfl_end(ui->dwfl);
+	free(ui);
 	return 0;
 }

tools/perf/util/unwind-libdw.h

···
 	unwind_entry_cb_t	cb;
 	void			*arg;
 	int			max_stack;
+	int			idx;
+	struct unwind_entry	entries[];
 };
 
 #endif /* __PERF_UNWIND_LIBDW_H */