linux/tools/perf/util/unwind-libdw.c
Sergei Trofimovich c21986d33d perf unwind-libdw: skip non-regular files
Without the change `perf `hangs up on charaster devices. On my system
it's enough to run system-wide sampler for a few seconds to get the
hangup:

    $ perf record -a -g --call-graph=dwarf
    $ perf report
    # hung

`strace` shows that hangup happens on reading on a character device
`/dev/dri/renderD128`

    $ strace -y -f -p 2780484
    strace: Process 2780484 attached
    pread64(101</dev/dri/renderD128>, strace: Process 2780484 detached

It's call trace descends into `elfutils`:

    $ gdb -p 2780484
    (gdb) bt
    #0  0x00007f5e508f04b7 in __libc_pread64 (fd=101, buf=0x7fff9df7edb0, count=0, offset=0)
        at ../sysdeps/unix/sysv/linux/pread64.c:25
    #1  0x00007f5e52b79515 in read_file () from /<<NIX>>/elfutils-0.192/lib/libelf.so.1
    #2  0x00007f5e52b25666 in libdw_open_elf () from /<<NIX>>/elfutils-0.192/lib/libdw.so.1
    #3  0x00007f5e52b25907 in __libdw_open_file () from /<<NIX>>/elfutils-0.192/lib/libdw.so.1
    #4  0x00007f5e52b120a9 in dwfl_report_elf@@ELFUTILS_0.156 ()
       from /<<NIX>>/elfutils-0.192/lib/libdw.so.1
    #5  0x000000000068bf20 in __report_module (al=al@entry=0x7fff9df80010, ip=ip@entry=139803237033216, ui=ui@entry=0x5369b5e0)
        at util/dso.h:537
    #6  0x000000000068c3d1 in report_module (ip=139803237033216, ui=0x5369b5e0) at util/unwind-libdw.c:114
    #7  frame_callback (state=0x535aef10, arg=0x5369b5e0) at util/unwind-libdw.c:242
    #8  0x00007f5e52b261d3 in dwfl_thread_getframes () from /<<NIX>>/elfutils-0.192/lib/libdw.so.1
    #9  0x00007f5e52b25bdb in get_one_thread_cb () from /<<NIX>>/elfutils-0.192/lib/libdw.so.1
    #10 0x00007f5e52b25faa in dwfl_getthreads () from /<<NIX>>/elfutils-0.192/lib/libdw.so.1
    #11 0x00007f5e52b26514 in dwfl_getthread_frames () from /<<NIX>>/elfutils-0.192/lib/libdw.so.1
    #12 0x000000000068c6ce in unwind__get_entries (cb=cb@entry=0x5d4620 <unwind_entry>, arg=arg@entry=0x10cd5fa0,
        thread=thread@entry=0x1076a290, data=data@entry=0x7fff9df80540, max_stack=max_stack@entry=127,
        best_effort=best_effort@entry=false) at util/thread.h:152
    #13 0x00000000005dae95 in thread__resolve_callchain_unwind (evsel=0x106006d0, thread=0x1076a290, cursor=0x10cd5fa0,
        sample=0x7fff9df80540, max_stack=127, symbols=true) at util/machine.c:2939
    #14 thread__resolve_callchain_unwind (thread=0x1076a290, cursor=0x10cd5fa0, evsel=0x106006d0, sample=0x7fff9df80540,
        max_stack=127, symbols=true) at util/machine.c:2920
    #15 __thread__resolve_callchain (thread=0x1076a290, cursor=0x10cd5fa0, evsel=0x106006d0, evsel@entry=0x7fff9df80440,
        sample=0x7fff9df80540, parent=parent@entry=0x7fff9df804a0, root_al=root_al@entry=0x7fff9df80440, max_stack=127, symbols=true)
        at util/machine.c:2970
    #16 0x00000000005d0cb2 in thread__resolve_callchain (thread=<optimized out>, cursor=<optimized out>, evsel=0x7fff9df80440,
        sample=<optimized out>, parent=0x7fff9df804a0, root_al=0x7fff9df80440, max_stack=127) at util/machine.h:198
    #17 sample__resolve_callchain (sample=<optimized out>, cursor=<optimized out>, parent=parent@entry=0x7fff9df804a0,
        evsel=evsel@entry=0x106006d0, al=al@entry=0x7fff9df80440, max_stack=max_stack@entry=127) at util/callchain.c:1127
    #18 0x0000000000617e08 in hist_entry_iter__add (iter=iter@entry=0x7fff9df80480, al=al@entry=0x7fff9df80440, max_stack_depth=127,
        arg=arg@entry=0x7fff9df81ae0) at util/hist.c:1255
    #19 0x000000000045d2d0 in process_sample_event (tool=0x7fff9df81ae0, event=<optimized out>, sample=0x7fff9df80540,
        evsel=0x106006d0, machine=<optimized out>) at builtin-report.c:334
    #20 0x00000000005e3bb1 in perf_session__deliver_event (session=0x105ff2c0, event=0x7f5c7d735ca0, tool=0x7fff9df81ae0,
        file_offset=2914716832, file_path=0x105ffbf0 "perf.data") at util/session.c:1367
    #21 0x00000000005e8d93 in do_flush (oe=0x105ffa50, show_progress=false) at util/ordered-events.c:245
    #22 __ordered_events__flush (oe=0x105ffa50, how=OE_FLUSH__ROUND, timestamp=<optimized out>) at util/ordered-events.c:324
    #23 0x00000000005e1f64 in perf_session__process_user_event (session=0x105ff2c0, event=0x7f5c7d752b18, file_offset=2914835224,
        file_path=0x105ffbf0 "perf.data") at util/session.c:1419
    #24 0x00000000005e47c7 in reader__read_event (rd=rd@entry=0x7fff9df81260, session=session@entry=0x105ff2c0,
    --Type <RET> for more, q to quit, c to continue without paging--
    quit
        prog=prog@entry=0x7fff9df81220) at util/session.c:2132
    #25 0x00000000005e4b37 in reader__process_events (rd=0x7fff9df81260, session=0x105ff2c0, prog=0x7fff9df81220)
        at util/session.c:2181
    #26 __perf_session__process_events (session=0x105ff2c0) at util/session.c:2226
    #27 perf_session__process_events (session=session@entry=0x105ff2c0) at util/session.c:2390
    #28 0x0000000000460add in __cmd_report (rep=0x7fff9df81ae0) at builtin-report.c:1076
    #29 cmd_report (argc=<optimized out>, argv=<optimized out>) at builtin-report.c:1827
    #30 0x00000000004c5a40 in run_builtin (p=p@entry=0xd8f7f8 <commands+312>, argc=argc@entry=1, argv=argv@entry=0x7fff9df844b0)
        at perf.c:351
    #31 0x00000000004c5d63 in handle_internal_command (argc=argc@entry=1, argv=argv@entry=0x7fff9df844b0) at perf.c:404
    #32 0x0000000000442de3 in run_argv (argcp=<synthetic pointer>, argv=<synthetic pointer>) at perf.c:448
    #33 main (argc=<optimized out>, argv=0x7fff9df844b0) at perf.c:556

The hangup happens because nothing in` perf` or `elfutils` checks if a
mapped file is easily readable.

The change conservatively skips all non-regular files.

Signed-off-by: Sergei Trofimovich <slyich@gmail.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20250505174419.2814857-1-slyich@gmail.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-24 10:27:50 -07:00

331 lines
7.7 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <elfutils/libdw.h>
#include <elfutils/libdwfl.h>
#include <inttypes.h>
#include <errno.h>
#include "debug.h"
#include "dso.h"
#include "unwind.h"
#include "unwind-libdw.h"
#include "machine.h"
#include "map.h"
#include "symbol.h"
#include "thread.h"
#include <linux/types.h>
#include <linux/zalloc.h>
#include "event.h"
#include "perf_regs.h"
#include "callchain.h"
#include "util/env.h"
static char *debuginfo_path;
static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
const char *modname __maybe_unused, Dwarf_Addr base __maybe_unused,
const char *file_name, const char *debuglink_file __maybe_unused,
GElf_Word debuglink_crc __maybe_unused, char **debuginfo_file_name)
{
const struct dso *dso = *userdata;
assert(dso);
if (dso__symsrc_filename(dso) && strcmp(file_name, dso__symsrc_filename(dso)))
*debuginfo_file_name = strdup(dso__symsrc_filename(dso));
return -1;
}
static const Dwfl_Callbacks offline_callbacks = {
.find_debuginfo = __find_debuginfo,
.debuginfo_path = &debuginfo_path,
.section_address = dwfl_offline_section_address,
// .find_elf is not set as we use dwfl_report_elf() instead.
};
static int __report_module(struct addr_location *al, u64 ip,
struct unwind_info *ui)
{
Dwfl_Module *mod;
struct dso *dso = NULL;
Dwarf_Addr base;
/*
* Some callers will use al->sym, so we can't just use the
* cheaper thread__find_map() here.
*/
thread__find_symbol(ui->thread, PERF_RECORD_MISC_USER, ip, al);
if (al->map)
dso = map__dso(al->map);
if (!dso)
return 0;
/*
* The generated JIT DSO files only map the code segment without
* ELF headers. Since JIT codes used to be packed in a memory
* segment, calculating the base address using pgoff falls into
* a different code in another DSO. So just use the map->start
* directly to pick the correct one.
*/
if (!strncmp(dso__long_name(dso), "/tmp/jitted-", 12))
base = map__start(al->map);
else
base = map__start(al->map) - map__pgoff(al->map);
mod = dwfl_addrmodule(ui->dwfl, ip);
if (mod) {
Dwarf_Addr s;
dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
if (s != base)
mod = NULL;
}
if (!mod) {
char filename[PATH_MAX];
__symbol__join_symfs(filename, sizeof(filename), dso__long_name(dso));
/* Don't hang up on device files like /dev/dri/renderD128. */
if (is_regular_file(filename)) {
mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1,
base, false);
}
}
if (!mod) {
char filename[PATH_MAX];
if (dso__build_id_filename(dso, filename, sizeof(filename), false))
mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1,
base, false);
}
if (mod) {
void **userdatap;
dwfl_module_info(mod, &userdatap, NULL, NULL, NULL, NULL, NULL, NULL);
*userdatap = dso;
}
return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
}
static int report_module(u64 ip, struct unwind_info *ui)
{
struct addr_location al;
int res;
addr_location__init(&al);
res = __report_module(&al, ip, ui);
addr_location__exit(&al);
return res;
}
/*
* 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 = &ui->entries[ui->idx++];
struct addr_location al;
addr_location__init(&al);
if (__report_module(&al, ip, ui)) {
addr_location__exit(&al);
return -1;
}
e->ip = ip;
e->ms.maps = al.maps;
e->ms.map = al.map;
e->ms.sym = al.sym;
pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
al.sym ? al.sym->name : "''",
ip,
al.map ? map__map_ip(al.map, ip) : (u64) 0);
addr_location__exit(&al);
return 0;
}
static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
{
/* We want only single thread to be processed. */
if (*thread_argp != NULL)
return 0;
*thread_argp = arg;
return dwfl_pid(dwfl);
}
static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
Dwarf_Word *data)
{
struct addr_location al;
ssize_t size;
struct dso *dso;
addr_location__init(&al);
if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) {
pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
goto out_fail;
}
dso = map__dso(al.map);
if (!dso)
goto out_fail;
size = dso__data_read_addr(dso, al.map, ui->machine, addr, (u8 *) data, sizeof(*data));
addr_location__exit(&al);
return !(size == sizeof(*data));
out_fail:
addr_location__exit(&al);
return -1;
}
static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result,
void *arg)
{
struct unwind_info *ui = arg;
const char *arch = perf_env__arch(ui->machine->env);
struct stack_dump *stack = &ui->sample->user_stack;
u64 start, end;
int offset;
int ret;
if (!ui->sample->user_regs)
return false;
ret = perf_reg_value(&start, ui->sample->user_regs,
perf_arch_reg_sp(arch));
if (ret)
return false;
end = start + stack->size;
/* Check overflow. */
if (addr + sizeof(Dwarf_Word) < addr)
return false;
if (addr < start || addr + sizeof(Dwarf_Word) > end) {
ret = access_dso_mem(ui, addr, result);
if (ret) {
pr_debug("unwind: access_mem 0x%" PRIx64 " not inside range"
" 0x%" PRIx64 "-0x%" PRIx64 "\n",
addr, start, end);
return false;
}
return true;
}
offset = addr - start;
*result = *(Dwarf_Word *)&stack->data[offset];
pr_debug("unwind: access_mem addr 0x%" PRIx64 ", val %lx, offset %d\n",
addr, (unsigned long)*result, offset);
return true;
}
static const Dwfl_Thread_Callbacks callbacks = {
.next_thread = next_thread,
.memory_read = memory_read,
.set_initial_registers = libdw__arch_set_initial_registers,
};
static int
frame_callback(Dwfl_Frame *state, void *arg)
{
struct unwind_info *ui = arg;
Dwarf_Addr pc;
bool isactivation;
if (!dwfl_frame_pc(state, &pc, NULL)) {
if (!ui->best_effort)
pr_err("%s", dwfl_errmsg(-1));
return DWARF_CB_ABORT;
}
// report the module before we query for isactivation
report_module(pc, ui);
if (!dwfl_frame_pc(state, &pc, &isactivation)) {
if (!ui->best_effort)
pr_err("%s", dwfl_errmsg(-1));
return DWARF_CB_ABORT;
}
if (!isactivation)
--pc;
return entry(pc, ui) || !(--ui->max_stack) ?
DWARF_CB_ABORT : DWARF_CB_OK;
}
int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
struct perf_sample *data,
int max_stack,
bool best_effort)
{
struct unwind_info *ui, ui_buf = {
.sample = data,
.thread = thread,
.machine = maps__machine((thread__maps(thread))),
.cb = cb,
.arg = arg,
.max_stack = max_stack,
.best_effort = best_effort
};
const char *arch = perf_env__arch(ui_buf.machine->env);
Dwarf_Word ip;
int err = -EINVAL, i;
if (!data->user_regs || !data->user_regs->regs)
return -EINVAL;
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_arch_reg_ip(arch));
if (err)
goto out;
err = report_module(ip, ui);
if (err)
goto out;
err = !dwfl_attach_state(ui->dwfl, EM_NONE, thread__tid(thread), &callbacks, ui);
if (err)
goto out;
err = dwfl_getthread_frames(ui->dwfl, thread__tid(thread), frame_callback, ui);
if (err && ui->max_stack != 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);
free(ui);
return 0;
}