mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 19:00:25 +00:00
![Peter Zijlstra](/assets/img/avatar_default.png)
The GCC specific __attribute__((optimize)) attribute does not what is commonly expected and is explicitly recommended against using in production code by the GCC people. Unlike what is often expected, it doesn't add to the optimization flags, but it fully replaces them, loosing any and all optimization flags provided by the compiler commandline. The only guaranteed upon means of inhibiting tail-calls is by placing a volatile asm with side-effects after the call such that the tail-call simply cannot be done. Given the original commit wasn't specific on which calls were the problem, this removal might re-introduce the problem, which can then be re-analyzed and cured properly. Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Ard Biesheuvel <ardb@kernel.org> Acked-by: Miguel Ojeda <ojeda@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Arvind Sankar <nivedita@alum.mit.edu> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ian Rogers <irogers@google.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Kook <keescook@chromium.org> Cc: Martin Liška <mliska@suse.cz> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lore.kernel.org/lkml/20201028081123.GT2628@hirez.programming.kicks-ass.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
218 lines
5.3 KiB
C
218 lines
5.3 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/compiler.h>
|
|
#include <linux/types.h>
|
|
#include <linux/zalloc.h>
|
|
#include <inttypes.h>
|
|
#include <limits.h>
|
|
#include <unistd.h>
|
|
#include "tests.h"
|
|
#include "debug.h"
|
|
#include "machine.h"
|
|
#include "event.h"
|
|
#include "../util/unwind.h"
|
|
#include "perf_regs.h"
|
|
#include "map.h"
|
|
#include "symbol.h"
|
|
#include "thread.h"
|
|
#include "callchain.h"
|
|
#include "util/synthetic-events.h"
|
|
|
|
#if defined (__x86_64__) || defined (__i386__) || defined (__powerpc__)
|
|
#include "arch-tests.h"
|
|
#endif
|
|
|
|
/* For bsearch. We try to unwind functions in shared object. */
|
|
#include <stdlib.h>
|
|
|
|
static int mmap_handler(struct perf_tool *tool __maybe_unused,
|
|
union perf_event *event,
|
|
struct perf_sample *sample,
|
|
struct machine *machine)
|
|
{
|
|
return machine__process_mmap2_event(machine, event, sample);
|
|
}
|
|
|
|
static int init_live_machine(struct machine *machine)
|
|
{
|
|
union perf_event event;
|
|
pid_t pid = getpid();
|
|
|
|
memset(&event, 0, sizeof(event));
|
|
return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
|
|
mmap_handler, machine, true);
|
|
}
|
|
|
|
/*
|
|
* We need to keep these functions global, despite the
|
|
* fact that they are used only locally in this object,
|
|
* in order to keep them around even if the binary is
|
|
* stripped. If they are gone, the unwind check for
|
|
* symbol fails.
|
|
*/
|
|
int test_dwarf_unwind__thread(struct thread *thread);
|
|
int test_dwarf_unwind__compare(void *p1, void *p2);
|
|
int test_dwarf_unwind__krava_3(struct thread *thread);
|
|
int test_dwarf_unwind__krava_2(struct thread *thread);
|
|
int test_dwarf_unwind__krava_1(struct thread *thread);
|
|
|
|
#define MAX_STACK 8
|
|
|
|
static int unwind_entry(struct unwind_entry *entry, void *arg)
|
|
{
|
|
unsigned long *cnt = (unsigned long *) arg;
|
|
char *symbol = entry->ms.sym ? entry->ms.sym->name : NULL;
|
|
static const char *funcs[MAX_STACK] = {
|
|
"test__arch_unwind_sample",
|
|
"test_dwarf_unwind__thread",
|
|
"test_dwarf_unwind__compare",
|
|
"bsearch",
|
|
"test_dwarf_unwind__krava_3",
|
|
"test_dwarf_unwind__krava_2",
|
|
"test_dwarf_unwind__krava_1",
|
|
"test__dwarf_unwind"
|
|
};
|
|
/*
|
|
* The funcs[MAX_STACK] array index, based on the
|
|
* callchain order setup.
|
|
*/
|
|
int idx = callchain_param.order == ORDER_CALLER ?
|
|
MAX_STACK - *cnt - 1 : *cnt;
|
|
|
|
if (*cnt >= MAX_STACK) {
|
|
pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
|
|
return -1;
|
|
}
|
|
|
|
if (!symbol) {
|
|
pr_debug("failed: got unresolved address 0x%" PRIx64 "\n",
|
|
entry->ip);
|
|
return -1;
|
|
}
|
|
|
|
(*cnt)++;
|
|
pr_debug("got: %s 0x%" PRIx64 ", expecting %s\n",
|
|
symbol, entry->ip, funcs[idx]);
|
|
return strcmp((const char *) symbol, funcs[idx]);
|
|
}
|
|
|
|
noinline int test_dwarf_unwind__thread(struct thread *thread)
|
|
{
|
|
struct perf_sample sample;
|
|
unsigned long cnt = 0;
|
|
int err = -1;
|
|
|
|
memset(&sample, 0, sizeof(sample));
|
|
|
|
if (test__arch_unwind_sample(&sample, thread)) {
|
|
pr_debug("failed to get unwind sample\n");
|
|
goto out;
|
|
}
|
|
|
|
err = unwind__get_entries(unwind_entry, &cnt, thread,
|
|
&sample, MAX_STACK);
|
|
if (err)
|
|
pr_debug("unwind failed\n");
|
|
else if (cnt != MAX_STACK) {
|
|
pr_debug("got wrong number of stack entries %lu != %d\n",
|
|
cnt, MAX_STACK);
|
|
err = -1;
|
|
}
|
|
|
|
out:
|
|
zfree(&sample.user_stack.data);
|
|
zfree(&sample.user_regs.regs);
|
|
return err;
|
|
}
|
|
|
|
static int global_unwind_retval = -INT_MAX;
|
|
|
|
noinline int test_dwarf_unwind__compare(void *p1, void *p2)
|
|
{
|
|
/* Any possible value should be 'thread' */
|
|
struct thread *thread = *(struct thread **)p1;
|
|
|
|
if (global_unwind_retval == -INT_MAX) {
|
|
/* Call unwinder twice for both callchain orders. */
|
|
callchain_param.order = ORDER_CALLER;
|
|
|
|
global_unwind_retval = test_dwarf_unwind__thread(thread);
|
|
if (!global_unwind_retval) {
|
|
callchain_param.order = ORDER_CALLEE;
|
|
global_unwind_retval = test_dwarf_unwind__thread(thread);
|
|
}
|
|
}
|
|
|
|
return p1 - p2;
|
|
}
|
|
|
|
noinline int test_dwarf_unwind__krava_3(struct thread *thread)
|
|
{
|
|
struct thread *array[2] = {thread, thread};
|
|
void *fp = &bsearch;
|
|
/*
|
|
* make _bsearch a volatile function pointer to
|
|
* prevent potential optimization, which may expand
|
|
* bsearch and call compare directly from this function,
|
|
* instead of libc shared object.
|
|
*/
|
|
void *(*volatile _bsearch)(void *, void *, size_t,
|
|
size_t, int (*)(void *, void *));
|
|
|
|
_bsearch = fp;
|
|
_bsearch(array, &thread, 2, sizeof(struct thread **),
|
|
test_dwarf_unwind__compare);
|
|
return global_unwind_retval;
|
|
}
|
|
|
|
noinline int test_dwarf_unwind__krava_2(struct thread *thread)
|
|
{
|
|
return test_dwarf_unwind__krava_3(thread);
|
|
}
|
|
|
|
noinline int test_dwarf_unwind__krava_1(struct thread *thread)
|
|
{
|
|
return test_dwarf_unwind__krava_2(thread);
|
|
}
|
|
|
|
int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
|
|
{
|
|
struct machine *machine;
|
|
struct thread *thread;
|
|
int err = -1;
|
|
|
|
machine = machine__new_host();
|
|
if (!machine) {
|
|
pr_err("Could not get machine\n");
|
|
return -1;
|
|
}
|
|
|
|
if (machine__create_kernel_maps(machine)) {
|
|
pr_err("Failed to create kernel maps\n");
|
|
return -1;
|
|
}
|
|
|
|
callchain_param.record_mode = CALLCHAIN_DWARF;
|
|
dwarf_callchain_users = true;
|
|
|
|
if (init_live_machine(machine)) {
|
|
pr_err("Could not init machine\n");
|
|
goto out;
|
|
}
|
|
|
|
if (verbose > 1)
|
|
machine__fprintf(machine, stderr);
|
|
|
|
thread = machine__find_thread(machine, getpid(), getpid());
|
|
if (!thread) {
|
|
pr_err("Could not get thread\n");
|
|
goto out;
|
|
}
|
|
|
|
err = test_dwarf_unwind__krava_1(thread);
|
|
thread__put(thread);
|
|
|
|
out:
|
|
machine__delete_threads(machine);
|
|
machine__delete(machine);
|
|
return err;
|
|
}
|