Files
linux/tools/perf/arch/powerpc/util/skip-callchain-idx.c
Ian Rogers b7a2b011e9 perf powerpc: Unify the skip-callchain-idx libdw with that for addr2line
Rather than have 2 Dwfl unify the Dwfl in skip-callchain-idx with that
is used by libdw__addr2line().

Rename that variable in 'struct dso' from 'a2l_libdw' to just 'libdw' as
it is now used in more than addr2line.

The Dwfl in skip-callchain-idx uses a map address when being read with
dwfl_report_elf (rather than dwfl_report_offline that addr2line
uses).

skip-callchain-idx is wrong as the map address can vary between
processes because of ASLR, ie it should need a different Dwfl per
process.

In the code after this patch the base address becomes 0 and the mapped
PC is used with the dwfl functions.

This should increase the accuracy of skip-callchain-idx, but the impact
has only been build tested.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Haibo Xu <haibo1.xu@intel.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Krzysztof Łopatowski <krzysztof.m.lopatowski@gmail.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Wielaard <mark@klomp.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2026-01-20 13:04:38 -03:00

258 lines
6.2 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Use DWARF Debug information to skip unnecessary callchain entries.
*
* Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation.
* Copyright (C) 2014 Ulrich Weigand, IBM Corporation.
*/
#include <inttypes.h>
#include <dwarf.h>
#include <elfutils/libdwfl.h>
#include "util/thread.h"
#include "util/callchain.h"
#include "util/debug.h"
#include "util/dso.h"
#include "util/event.h" // struct ip_callchain
#include "util/map.h"
#include "util/symbol.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).
*/
/*
* 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[3];
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 return address
* is in a register (typically R0), it is yet to be saved on
* the stack.
*/
if ((nops != 0 || ops != NULL) &&
!(nops == 1 && ops[0].atom == DW_OP_regx &&
ops[0].number2 == 0 && ops[0].offset == 0))
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-bias, &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-bias, &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(struct dso *dso, Dwarf_Addr mapped_pc)
{
int rc = -1;
Dwfl *dwfl;
Dwfl_Module *mod;
Dwarf_Frame *frame;
int ra_regno;
Dwarf_Addr start = mapped_pc;
Dwarf_Addr end = mapped_pc;
bool signalp;
dwfl = dso__libdw_dwfl(dso);
if (!dwfl)
return -1;
mod = dwfl_addrmodule(dwfl, mapped_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, mapped_pc);
if (!frame) {
frame = get_dwarf_frame(mod, mapped_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:
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 thread *thread, struct ip_callchain *chain)
{
struct addr_location al;
struct dso *dso = NULL;
int rc;
u64 ip;
u64 skip_slot = -1;
if (!chain || chain->nr < 3)
return skip_slot;
addr_location__init(&al);
ip = chain->ips[1];
thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
if (al.map)
dso = map__dso(al.map);
if (!dso) {
pr_debug("%" PRIx64 " dso is NULL\n", ip);
addr_location__exit(&al);
return skip_slot;
}
rc = check_return_addr(dso, map__map_ip(al.map, ip));
pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n",
dso__long_name(dso), al.sym->name, 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;
}
addr_location__exit(&al);
return skip_slot;
}