[PATCH 4/3] perf tools: Add callchain order support for libdw DWARF unwinder

[Jiri Olsa <jolsa@redhat.com>]

On Tue, Nov 17, 2015 at 04:05:36PM +0100, Jiri Olsa wrote:

SNIP

> Tested on x86_64. The change is in generic code only,
> so it should not affect other archs. Still it would be
> nice to have some confirmation.. Wang Nan? ;-)
> 
> It'd be nice to have this for libdw unwind as well,
> but it looks like it's out of reach for perf code.. Jan?
> 
> Also available in:
>   git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
>   perf/callchain_1

adding also libdw support.. test with 'make NO_LIBUNWIND=1'

Also available in:
  git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  perf/callchain_3

thanks,
jirka


---
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

    13.63%  ls       [kernel.vmlinux]  [k] __rb_insert_augmented
                 |
                 ---__rb_insert_augmented
                    __vma_link_rb
                    vma_link
                    do_brk
                    vm_brk
                    load_elf_binary
                    search_binary_handler
                    do_execveat_common.isra.29
                    sys_execve
                    return_from_execve

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

    13.63%  ls       [kernel.vmlinux]  [k] __rb_insert_augmented
                 |
                 ---return_from_execve
                    sys_execve
                    do_execveat_common.isra.29
                    search_binary_handler
                    load_elf_binary
                    vm_brk
                    do_brk
                    vma_link
                    __vma_link_rb
                    __rb_insert_augmented

Reported-by: Milian Wolff <milian.wolff@kdab.com>
Link: http://lkml.kernel.org/n/tip-zk99ay9s71whl9qd9if28u8z@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/unwind-libdw.c | 53 ++++++++++++++++++++++++++++++------------
 tools/perf/util/unwind-libdw.h |  2 ++
 2 files changed, 40 insertions(+), 15 deletions(-)

diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 2dcfe9a7c8d0..db8142ba7cb9 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "perf_regs.h"
+#include "callchain.h"
 
 static char *debuginfo_path;
 
@@ -52,25 +53,28 @@ static int report_module(u64 ip, struct unwind_info *ui)
 	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)
@@ -168,7 +172,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			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,
@@ -177,35 +181,54 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 		.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;
 }
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 417a1426f3ad..58328669ed16 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -16,6 +16,8 @@ struct unwind_info {
 	unwind_entry_cb_t	cb;
 	void			*arg;
 	int			max_stack;
+	int			idx;
+	struct unwind_entry	entries[];
 };
 
 #endif /* __PERF_UNWIND_LIBDW_H */
-- 
2.4.3