perf tools powerpc: Adjust callchain based on DWARF debug info
When saving the callchain on Power, the kernel conservatively saves excess
entries in the callchain. A few of these entries are needed in some cases
but not others. We should use the DWARF debug information to determine
when the entries are needed.
Eg: the value in the link register (LR) is needed only when it holds the
return address of a function. At other times it must be ignored.
If the unnecessary entries are not ignored, we end up with duplicate arcs
in the call-graphs.
Use the DWARF debug information to determine if any callchain entries
should be ignored when building call-graphs.
Callgraph before the patch:
14.67% 2234 sprintft libc-2.18.so [.] __random
|
--- __random
|
|--61.12%-- __random
| |
| |--97.15%-- rand
| | do_my_sprintf
| | main
| | generic_start_main.isra.0
| | __libc_start_main
| | 0x0
| |
| --2.85%-- do_my_sprintf
| main
| generic_start_main.isra.0
| __libc_start_main
| 0x0
|
--38.88%-- rand
|
|--94.01%-- rand
| do_my_sprintf
| main
| generic_start_main.isra.0
| __libc_start_main
| 0x0
|
--5.99%-- do_my_sprintf
main
generic_start_main.isra.0
__libc_start_main
0x0
Callgraph after the patch:
14.67% 2234 sprintft libc-2.18.so [.] __random
|
--- __random
|
|--95.93%-- rand
| do_my_sprintf
| main
| generic_start_main.isra.0
| __libc_start_main
| 0x0
|
--4.07%-- do_my_sprintf
main
generic_start_main.isra.0
__libc_start_main
0x0
TODO: For split-debug info objects like glibc, we can only determine
the call-frame-address only when both .eh_frame and .debug_info
sections are available. We should be able to determin the CFA
even without the .eh_frame section.
Fix suggested by Anton Blanchard.
Thanks to valuable input on DWARF debug information from Ulrich Weigand.
Reported-by: Maynard Johnson <maynard@us.ibm.com>
Tested-by: Maynard Johnson <maynard@us.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20140625154903.GA29607@us.ibm.com
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
This commit is contained in:
Sukadev Bhattiprolu
Jiri Olsa
parent
21da83fb6c
commit
a60335ba32
|
|
@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1
|
|||
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
|
||||
endif
|
||||
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
|
||||
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
|
||||
|
|
|
|||
|
|
@ -0,0 +1,266 @@
|
|||
/*
|
||||
* Use DWARF Debug information to skip unnecessary callchain entries.
|
||||
*
|
||||
* Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation.
|
||||
* Copyright (C) 2014 Ulrich Weigand, IBM Corporation.
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or
|
||||
* modify it under the terms of the GNU General Public License
|
||||
* as published by the Free Software Foundation; either version
|
||||
* 2 of the License, or (at your option) any later version.
|
||||
*/
|
||||
#include <inttypes.h>
|
||||
#include <dwarf.h>
|
||||
#include <elfutils/libdwfl.h>
|
||||
|
||||
#include "util/thread.h"
|
||||
#include "util/callchain.h"
|
||||
|
||||
/*
|
||||
* When saving the callchain on Power, the kernel conservatively saves
|
||||
* excess entries in the callchain. A few of these entries are needed
|
||||
* in some cases but not others. If the unnecessary entries are not
|
||||
* ignored, we end up with duplicate arcs in the call-graphs. Use
|
||||
* DWARF debug information to skip over any unnecessary callchain
|
||||
* entries.
|
||||
*
|
||||
* See function header for arch_adjust_callchain() below for more details.
|
||||
*
|
||||
* The libdwfl code in this file is based on code from elfutils
|
||||
* (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc).
|
||||
*/
|
||||
static char *debuginfo_path;
|
||||
|
||||
static const Dwfl_Callbacks offline_callbacks = {
|
||||
.debuginfo_path = &debuginfo_path,
|
||||
.find_debuginfo = dwfl_standard_find_debuginfo,
|
||||
.section_address = dwfl_offline_section_address,
|
||||
};
|
||||
|
||||
|
||||
/*
|
||||
* Use the DWARF expression for the Call-frame-address and determine
|
||||
* if return address is in LR and if a new frame was allocated.
|
||||
*/
|
||||
static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
|
||||
{
|
||||
Dwarf_Op ops_mem[2];
|
||||
Dwarf_Op dummy;
|
||||
Dwarf_Op *ops = &dummy;
|
||||
size_t nops;
|
||||
int result;
|
||||
|
||||
result = dwarf_frame_register(frame, ra_regno, ops_mem, &ops, &nops);
|
||||
if (result < 0) {
|
||||
pr_debug("dwarf_frame_register() %s\n", dwarf_errmsg(-1));
|
||||
return -1;
|
||||
}
|
||||
|
||||
/*
|
||||
* Check if return address is on the stack.
|
||||
*/
|
||||
if (nops != 0 || ops != NULL)
|
||||
return 0;
|
||||
|
||||
/*
|
||||
* Return address is in LR. Check if a frame was allocated
|
||||
* but not-yet used.
|
||||
*/
|
||||
result = dwarf_frame_cfa(frame, &ops, &nops);
|
||||
if (result < 0) {
|
||||
pr_debug("dwarf_frame_cfa() returns %d, %s\n", result,
|
||||
dwarf_errmsg(-1));
|
||||
return -1;
|
||||
}
|
||||
|
||||
/*
|
||||
* If call frame address is in r1, no new frame was allocated.
|
||||
*/
|
||||
if (nops == 1 && ops[0].atom == DW_OP_bregx && ops[0].number == 1 &&
|
||||
ops[0].number2 == 0)
|
||||
return 1;
|
||||
|
||||
/*
|
||||
* A new frame was allocated but has not yet been used.
|
||||
*/
|
||||
return 2;
|
||||
}
|
||||
|
||||
/*
|
||||
* Get the DWARF frame from the .eh_frame section.
|
||||
*/
|
||||
static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
|
||||
{
|
||||
int result;
|
||||
Dwarf_Addr bias;
|
||||
Dwarf_CFI *cfi;
|
||||
Dwarf_Frame *frame;
|
||||
|
||||
cfi = dwfl_module_eh_cfi(mod, &bias);
|
||||
if (!cfi) {
|
||||
pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
|
||||
return NULL;
|
||||
}
|
||||
|
||||
result = dwarf_cfi_addrframe(cfi, pc, &frame);
|
||||
if (result) {
|
||||
pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
|
||||
return NULL;
|
||||
}
|
||||
|
||||
return frame;
|
||||
}
|
||||
|
||||
/*
|
||||
* Get the DWARF frame from the .debug_frame section.
|
||||
*/
|
||||
static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
|
||||
{
|
||||
Dwarf_CFI *cfi;
|
||||
Dwarf_Addr bias;
|
||||
Dwarf_Frame *frame;
|
||||
int result;
|
||||
|
||||
cfi = dwfl_module_dwarf_cfi(mod, &bias);
|
||||
if (!cfi) {
|
||||
pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
|
||||
return NULL;
|
||||
}
|
||||
|
||||
result = dwarf_cfi_addrframe(cfi, pc, &frame);
|
||||
if (result) {
|
||||
pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
|
||||
return NULL;
|
||||
}
|
||||
|
||||
return frame;
|
||||
}
|
||||
|
||||
/*
|
||||
* Return:
|
||||
* 0 if return address for the program counter @pc is on stack
|
||||
* 1 if return address is in LR and no new stack frame was allocated
|
||||
* 2 if return address is in LR and a new frame was allocated (but not
|
||||
* yet used)
|
||||
* -1 in case of errors
|
||||
*/
|
||||
static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
|
||||
{
|
||||
int rc = -1;
|
||||
Dwfl *dwfl;
|
||||
Dwfl_Module *mod;
|
||||
Dwarf_Frame *frame;
|
||||
int ra_regno;
|
||||
Dwarf_Addr start = pc;
|
||||
Dwarf_Addr end = pc;
|
||||
bool signalp;
|
||||
|
||||
dwfl = dwfl_begin(&offline_callbacks);
|
||||
if (!dwfl) {
|
||||
pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (dwfl_report_offline(dwfl, "", exec_file, -1) == NULL) {
|
||||
pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1));
|
||||
goto out;
|
||||
}
|
||||
|
||||
mod = dwfl_addrmodule(dwfl, pc);
|
||||
if (!mod) {
|
||||
pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1));
|
||||
goto out;
|
||||
}
|
||||
|
||||
/*
|
||||
* To work with split debug info files (eg: glibc), check both
|
||||
* .eh_frame and .debug_frame sections of the ELF header.
|
||||
*/
|
||||
frame = get_eh_frame(mod, pc);
|
||||
if (!frame) {
|
||||
frame = get_dwarf_frame(mod, pc);
|
||||
if (!frame)
|
||||
goto out;
|
||||
}
|
||||
|
||||
ra_regno = dwarf_frame_info(frame, &start, &end, &signalp);
|
||||
if (ra_regno < 0) {
|
||||
pr_debug("Return address register unavailable: %s\n",
|
||||
dwarf_errmsg(-1));
|
||||
goto out;
|
||||
}
|
||||
|
||||
rc = check_return_reg(ra_regno, frame);
|
||||
|
||||
out:
|
||||
dwfl_end(dwfl);
|
||||
return rc;
|
||||
}
|
||||
|
||||
/*
|
||||
* The callchain saved by the kernel always includes the link register (LR).
|
||||
*
|
||||
* 0: PERF_CONTEXT_USER
|
||||
* 1: Program counter (Next instruction pointer)
|
||||
* 2: LR value
|
||||
* 3: Caller's caller
|
||||
* 4: ...
|
||||
*
|
||||
* The value in LR is only needed when it holds a return address. If the
|
||||
* return address is on the stack, we should ignore the LR value.
|
||||
*
|
||||
* Further, when the return address is in the LR, if a new frame was just
|
||||
* allocated but the LR was not saved into it, then the LR contains the
|
||||
* caller, slot 4: contains the caller's caller and the contents of slot 3:
|
||||
* (chain->ips[3]) is undefined and must be ignored.
|
||||
*
|
||||
* Use DWARF debug information to determine if any entries need to be skipped.
|
||||
*
|
||||
* Return:
|
||||
* index: of callchain entry that needs to be ignored (if any)
|
||||
* -1 if no entry needs to be ignored or in case of errors
|
||||
*/
|
||||
int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
|
||||
struct ip_callchain *chain)
|
||||
{
|
||||
struct addr_location al;
|
||||
struct dso *dso = NULL;
|
||||
int rc;
|
||||
u64 ip;
|
||||
u64 skip_slot = -1;
|
||||
|
||||
if (chain->nr < 3)
|
||||
return skip_slot;
|
||||
|
||||
ip = chain->ips[2];
|
||||
|
||||
thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER,
|
||||
MAP__FUNCTION, ip, &al);
|
||||
|
||||
if (al.map)
|
||||
dso = al.map->dso;
|
||||
|
||||
if (!dso) {
|
||||
pr_debug("%" PRIx64 " dso is NULL\n", ip);
|
||||
return skip_slot;
|
||||
}
|
||||
|
||||
rc = check_return_addr(dso->long_name, ip);
|
||||
|
||||
pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
|
||||
dso->long_name, chain->nr, ip, rc);
|
||||
|
||||
if (rc == 0) {
|
||||
/*
|
||||
* Return address on stack. Ignore LR value in callchain
|
||||
*/
|
||||
skip_slot = 2;
|
||||
} else if (rc == 2) {
|
||||
/*
|
||||
* New frame allocated but return address still in LR.
|
||||
* Ignore the caller's caller entry in callchain.
|
||||
*/
|
||||
skip_slot = 3;
|
||||
}
|
||||
return skip_slot;
|
||||
}
|
||||
|
|
@ -48,6 +48,10 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
|
|||
NO_LIBDW_DWARF_UNWIND := 1
|
||||
endif
|
||||
|
||||
ifeq ($(ARCH),powerpc)
|
||||
CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
|
||||
endif
|
||||
|
||||
ifeq ($(LIBUNWIND_LIBS),)
|
||||
NO_LIBUNWIND := 1
|
||||
else
|
||||
|
|
|
|||
|
|
@ -176,4 +176,17 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
|
|||
dest->first = src->curr;
|
||||
dest->nr -= src->pos;
|
||||
}
|
||||
|
||||
#ifdef HAVE_SKIP_CALLCHAIN_IDX
|
||||
extern int arch_skip_callchain_idx(struct machine *machine,
|
||||
struct thread *thread, struct ip_callchain *chain);
|
||||
#else
|
||||
static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
|
||||
struct thread *thread __maybe_unused,
|
||||
struct ip_callchain *chain __maybe_unused)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* __PERF_CALLCHAIN_H */
|
||||
|
|
|
|||
|
|
@ -1281,7 +1281,9 @@ static int machine__resolve_callchain_sample(struct machine *machine,
|
|||
u8 cpumode = PERF_RECORD_MISC_USER;
|
||||
int chain_nr = min(max_stack, (int)chain->nr);
|
||||
int i;
|
||||
int j;
|
||||
int err;
|
||||
int skip_idx __maybe_unused;
|
||||
|
||||
callchain_cursor_reset(&callchain_cursor);
|
||||
|
||||
|
|
@ -1290,14 +1292,26 @@ static int machine__resolve_callchain_sample(struct machine *machine,
|
|||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Based on DWARF debug information, some architectures skip
|
||||
* a callchain entry saved by the kernel.
|
||||
*/
|
||||
skip_idx = arch_skip_callchain_idx(machine, thread, chain);
|
||||
|
||||
for (i = 0; i < chain_nr; i++) {
|
||||
u64 ip;
|
||||
struct addr_location al;
|
||||
|
||||
if (callchain_param.order == ORDER_CALLEE)
|
||||
ip = chain->ips[i];
|
||||
j = i;
|
||||
else
|
||||
ip = chain->ips[chain->nr - i - 1];
|
||||
j = chain->nr - i - 1;
|
||||
|
||||
#ifdef HAVE_SKIP_CALLCHAIN_IDX
|
||||
if (j == skip_idx)
|
||||
continue;
|
||||
#endif
|
||||
ip = chain->ips[j];
|
||||
|
||||
if (ip >= PERF_CONTEXT_MAX) {
|
||||
switch (ip) {
|
||||
|
|
|
|||
Loading…
Reference in New Issue