----- On Dec 16, 2015, at 5:09 PM, Mathieu Desnoyers mathieu.desnoyers@xxxxxxxxxxxx wrote:
> When testing liburcu on a 3.18 Linux kernel, 2-core MIPS (cpu model :
> Ingenic JZRISC V4.15 FPU V0.0), we notice that a blocked sys_futex
> FUTEX_WAIT returns -1, errno=ENOSYS when interrupted by a SA_RESTART
> signal handler. This spurious ENOSYS behavior causes hangs in liburcu
> 0.9.x. Running a MIPS 3.18 kernel under a QEMU emulator exhibits the
> same behavior. This might affect earlier kernels.
>
> This issue appears to be fixed in 3.18.y stable kernels and 3.19, but
> nevertheless, we should try to handle this kernel bug more gracefully
> than a user-space hang due to unexpected spurious ENOSYS return value.
It's actually fixed in 3.19, but not in 3.18.y stable kernels. The
Linux kernel upstream fix commit is:
e967ef02 "MIPS: Fix restart of indirect syscalls"
I've created a small test program that could also be used on parisc
to check if it suffers from the same issue (see attached).
On bogus mips kernels, we see the following output:
[OK] Test program with pid: 5748 SIGUSR1 handler
[FAIL] futex returns -1, Function not implemented
Let me know if someone can try it out on a parisc kernel.
Thanks!
Mathieu
>
> Therefore, fallback on the "async-safe" version of compat_futex in those
> situations where FUTEX_WAIT returns ENOSYS. This async-safe fallback has
> the nice property of being OK to use concurrently with other FUTEX_WAKE
> and FUTEX_WAIT futex() calls, because it's simply a busy-wait scheme.
>
> We suspect that parisc might be affected by a similar issue (Debian
> build bots reported a similar hang on both mips and parisc), but we do
> not have access to the hardware required to test this hypothesis.
>
> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
> CC: Michael Jeanson <mjeanson@xxxxxxxxxxxx>
> CC: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
> CC: Ralf Baechle <ralf@xxxxxxxxxxxxxx>
> CC: linux-mips@xxxxxxxxxxxxxx
> CC: linux-kernel@xxxxxxxxxxxxxxx
> CC: "James E.J. Bottomley" <jejb@xxxxxxxxxxxxxxxx>
> CC: Helge Deller <deller@xxxxxx>
> CC: linux-parisc@xxxxxxxxxxxxxxx
> ---
> compat_futex.c | 2 ++
> urcu/futex.h | 12 +++++++++++-
> 2 files changed, 13 insertions(+), 1 deletion(-)
>
> diff --git a/compat_futex.c b/compat_futex.c
> index b7f78f0..9e918fe 100644
> --- a/compat_futex.c
> +++ b/compat_futex.c
> @@ -111,6 +111,8 @@ end:
> * _ASYNC SIGNAL-SAFE_.
> * For now, timeout, uaddr2 and val3 are unused.
> * Waiter will busy-loop trying to read the condition.
> + * It is OK to use compat_futex_async() on a futex address on which
> + * futex() WAKE operations are also performed.
> */
>
> int compat_futex_async(int32_t *uaddr, int op, int32_t val,
> diff --git a/urcu/futex.h b/urcu/futex.h
> index 4d16cfa..a17eda8 100644
> --- a/urcu/futex.h
> +++ b/urcu/futex.h
> @@ -73,7 +73,17 @@ static inline int futex_noasync(int32_t *uaddr, int op,
> int32_t val,
>
> ret = futex(uaddr, op, val, timeout, uaddr2, val3);
> if (caa_unlikely(ret < 0 && errno == ENOSYS)) {
> - return compat_futex_noasync(uaddr, op, val, timeout,
> + /*
> + * The fallback on ENOSYS is the async-safe version of
> + * the compat futex implementation, because the
> + * async-safe compat implementation allows being used
> + * concurrently with calls to futex(). Indeed, sys_futex
> + * FUTEX_WAIT, on some architectures (e.g. mips), within
> + * a given process, spuriously return ENOSYS due to
> + * signal restart bugs on some kernel versions (e.g.
> + * Linux kernel 3.18 and possibly earlier).
> + */
> + return compat_futex_async(uaddr, op, val, timeout,
> uaddr2, val3);
> }
> return ret;
> --
> 2.1.4
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
#define _GNU_SOURCE
#include <stdio.h>
#include <sys/types.h>
#include <unistd.h>
#include <signal.h>
#include <stdlib.h>
#include <errno.h>
#include <sys/syscall.h>
static int value = -1;
#define FUTEX_WAIT 0
#define FUTEX_WAKE 1
static int futex(int32_t *uaddr, int op, int32_t val,
const struct timespec *timeout, int32_t *uaddr2, int32_t val3)
{
return syscall(__NR_futex, uaddr, op, val, timeout,
uaddr2, val3);
}
static void sighandler(int signo, siginfo_t *siginfo, void *context)
{
fprintf(stderr, "[OK] Test program with pid: %d SIGUSR1 handler\n",
getpid());
}
int main(int argc, char **argv)
{
struct sigaction act;
pid_t pid, wait_pid;
int ret;
fprintf(stderr, "Testing futex sigrestart. Stop with CTRL-c.\n",
getpid());
act.sa_sigaction = sighandler;
act.sa_flags = SA_SIGINFO | SA_RESTART;
//act.sa_flags = SA_SIGINFO;
sigemptyset(&act.sa_mask);
ret = sigaction(SIGUSR1, &act, NULL);
if (ret)
abort();
pid = fork();
if (pid > 0) {
/* parent */
for (;;) {
ret = kill(pid, SIGUSR1);
if (ret) {
perror("kill");
abort();
}
sleep(1);
}
} else {
if (pid < 0) {
abort();
}
/* child */
for (;;) {
ret = futex(&value, FUTEX_WAIT, -1, NULL, NULL, 0);
if (ret < 0) {
fprintf(stderr, "[FAIL] futex returns %d, %s\n",
ret, strerror(errno));
} else {
fprintf(stderr, "[FAIL] futex returns %d (unexpected)\n",
ret);
}
}
}
return 0;
}
