perf probe: Ignore tail calls to probed functions

perf probe currently errors out if there are any tail calls to probed
functions:

[root@rhel71be]# perf probe do_fork
Failed to find probe point in any functions.
  Error: Failed to add events.

Fix this by teaching perf to ignore tail calls.

Without patch:

  [root@rhel71be perf]# ./perf probe -v do_fork
  probe-definition(0): do_fork symbol:do_fork file:(null) line:0 offset:0
  return:0 lazy:(null)
  0 arguments
  Looking at the vmlinux_path (7 entries long)
  symsrc__init: build id mismatch for /boot/vmlinux.
  Using /usr/lib/debug/lib/modules/3.10.0-201.el7.ppc64/vmlinux for symbols
  Open Debuginfo file:
  /usr/lib/debug/lib/modules/3.10.0-201.el7.ppc64/vmlinux
  Try to find probe point from debuginfo.
  found inline addr: 0xc0000000000bb9b0
  Probe point found: do_fork+0
  found inline addr: 0xc0000000000bbe20
  Probe point found: kernel_thread+48
  found inline addr: 0xc0000000000bbe5c
  Probe point found: sys_fork+28
  found inline addr: 0xc0000000000bbfac
  Probe point found: sys_vfork+44
  found inline addr: 0xc0000000000bc27c
  Failed to find probe point in any functions.
  An error occurred in debuginfo analysis (-2).
  Error: Failed to add events. Reason: No such file or directory (Code: -2)

With patch:

  [root@rhel71be perf]# ./perf probe -v do_fork
  probe-definition(0): do_fork symbol:do_fork file:(null) line:0 offset:0
  return:0 lazy:(null)
  0 arguments
  Looking at the vmlinux_path (7 entries long)
  symsrc__init: build id mismatch for /boot/vmlinux.
  Using /usr/lib/debug/lib/modules/3.10.0-201.el7.ppc64/vmlinux for symbols
  Open Debuginfo file:
  /usr/lib/debug/lib/modules/3.10.0-201.el7.ppc64/vmlinux
  Try to find probe point from debuginfo.
  found inline addr: 0xc0000000000bb9b0
  Probe point found: do_fork+0
  found inline addr: 0xc0000000000bbe20
  Probe point found: kernel_thread+48
  found inline addr: 0xc0000000000bbe5c
  Probe point found: sys_fork+28
  found inline addr: 0xc0000000000bbfac
  Probe point found: sys_vfork+44
  found inline addr: 0xc0000000000bc27c
  Ignoring tail call from SyS_clone
  Found 4 probe_trace_events.
  Opening /sys/kernel/debug/tracing/kprobe_events write=1
  No kprobe blacklist support, ignored
  Added new events:
  Writing event: p:probe/do_fork _text+768432
  Failed to write event: Invalid argument
    Error: Failed to add events. Reason: Invalid argument (Code: -22)

[Ignore the error about failure to write event - this kernel is missing
a patch to resolve _text properly]

The reason to ignore tail calls is that the address does not belong to
any function frame. In the example above, the address in SyS_clone is
0xc0000000000bc27c, but looking at the debug-info:

 <1><830081>: Abbrev Number: 133 (DW_TAG_subprogram)
    <830083>   DW_AT_external    : 1
    <830083>   DW_AT_name        : (indirect string, offset: 0x3cea3): SyS_clone
    <830087>   DW_AT_decl_file   : 7
    <830088>   DW_AT_decl_line   : 1689
    <83008a>   DW_AT_prototyped  : 1
    <83008a>   DW_AT_type        : <0x8110eb>
    <83008e>   DW_AT_low_pc      : 0xc0000000000bc270
    <830096>   DW_AT_high_pc     : 0xc
    <83009e>   DW_AT_frame_base  : 1 byte block: 9c 	(DW_OP_call_frame_cfa)
    <8300a0>   DW_AT_GNU_all_call_sites: 1
    <8300a0>   DW_AT_sibling     : <0x830178>
<snip>
 <3><830147>: Abbrev Number: 125 (DW_TAG_GNU_call_site)
    <830148>   DW_AT_low_pc      : 0xc0000000000bc27c
    <830150>   DW_AT_GNU_tail_call: 1
    <830150>   DW_AT_abstract_origin: <0x82e7e1>

The frame ends at 0xc0000000000bc27c. I suppose this is why this
particular call is a "tail" call. FWIW, systemtap seems to ignore these
as well and requires users to explicitly place probes at these call
sites if necessary. I print out the caller so that users know.

Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Link: http://lkml.kernel.org/r/1430394151-15928-1-git-send-email-naveen.n.rao@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

3 files changed, 50 insertions, 3 deletions

diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index afa0971..eb47abd 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -433,6 +433,43 @@ struct __addr_die_search_param {
 	Dwarf_Die	*die_mem;
 };
 
+static int __die_search_func_tail_cb(Dwarf_Die *fn_die, void *data)
+{
+	struct __addr_die_search_param *ad = data;
+	Dwarf_Addr addr = 0;
+
+	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+	    !dwarf_highpc(fn_die, &addr) &&
+	    addr == ad->addr) {
+		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+		return DWARF_CB_ABORT;
+	}
+	return DWARF_CB_OK;
+}
+
+/**
+ * die_find_tailfunc - Search for a non-inlined function with tail call at
+ * given address
+ * @cu_die: a CU DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search for a non-inlined function DIE with tail call at @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem)
+{
+	struct __addr_die_search_param ad;
+	ad.addr = addr;
+	ad.die_mem = die_mem;
+	/* dwarf_getscopes can't find subprogram. */
+	if (!dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0))
+		return NULL;
+	else
+		return die_mem;
+}
+
 /* die_find callback for non-inlined function search */
 static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index c154c0b8..c42ec36 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -85,6 +85,10 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
 extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
+/* Search a non-inlined function with tail call at given address */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem);
+
 /* Search the top inlined function including given address */
 extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 					  Dwarf_Die *die_mem);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 590a24a..c50da39 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -674,9 +674,15 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	/* If not a real subprogram, find a real one */
 	if (!die_is_func_def(sc_die)) {
 		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
-			pr_warning("Failed to find probe point in any "
-				   "functions.\n");
-			return -ENOENT;
+			if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
+				pr_warning("Ignoring tail call from %s\n",
+						dwarf_diename(&pf->sp_die));
+				return 0;
+			} else {
+				pr_warning("Failed to find probe point in any "
+					   "functions.\n");
+				return -ENOENT;
+			}
 		}
 	} else
 		memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));