linux: Revert the use of sched_getaffinity on get_nproc (BZ #28310)

The use of sched_getaffinity on get_nproc and
sysconf (_SC_NPROCESSORS_ONLN) done in 903bc7dcc2 (BZ #27645)
breaks the top command in common hypervisor configurations and also
other monitoring tools.

The main issue using sched_getaffinity changed the symbols semantic
from system-wide scope of online CPUs to per-process one (which can
be changed with kernel cpusets or book parameters in VM).

This patch reverts mostly of the 903bc7dcc2, with the
exceptions:

  * No more cached values and atomic updates, since they are inherent
    racy.

  * No /proc/cpuinfo fallback, since /proc/stat is already used and
    it would require to revert more arch-specific code.

  * The alloca is replace with a static buffer of 1024 bytes.

So the implementation first consult the sysfs, and fallbacks to procfs.

Checked on x86_64-linux-gnu.

Reviewed-by: Florian Weimer <fweimer@redhat.com>
(cherry picked from commit 342298278e)
This commit is contained in:
Adhemerval Zanella 2021-09-06 14:19:51 -03:00 committed by Florian Weimer
parent cda99af14e
commit 822662cf2a
2 changed files with 135 additions and 5 deletions

1
NEWS
View File

@ -13,6 +13,7 @@ The following bugs are resolved with this release:
[19193] nptl: pthread_kill, pthread_cancel should not fail after exit
[28036] Incorrect types for pthread_mutexattr_set/getrobust_np
[28182] _TIME_BITS=64 in C++ has issues with fcntl, ioctl, prctl
[28310] Do not use affinity mask for sysconf (_SC_NPROCESSORS_CONF)
[28361] nptl: Avoid setxid deadlock with blocked signals in thread exit
[28407] pthread_kill assumes that kill and tgkill are equivalent

View File

@ -18,6 +18,8 @@
<https://www.gnu.org/licenses/>. */
#include <array_length.h>
#include <assert.h>
#include <ctype.h>
#include <dirent.h>
#include <errno.h>
#include <ldsodefs.h>
@ -30,7 +32,7 @@
#include <sysdep.h>
int
__get_nprocs (void)
__get_nprocs_sched (void)
{
enum
{
@ -53,14 +55,141 @@ __get_nprocs (void)
atomics are needed). */
return 2;
}
libc_hidden_def (__get_nprocs)
weak_alias (__get_nprocs, get_nprocs)
static char *
next_line (int fd, char *const buffer, char **cp, char **re,
char *const buffer_end)
{
char *res = *cp;
char *nl = memchr (*cp, '\n', *re - *cp);
if (nl == NULL)
{
if (*cp != buffer)
{
if (*re == buffer_end)
{
memmove (buffer, *cp, *re - *cp);
*re = buffer + (*re - *cp);
*cp = buffer;
ssize_t n = __read_nocancel (fd, *re, buffer_end - *re);
if (n < 0)
return NULL;
*re += n;
nl = memchr (*cp, '\n', *re - *cp);
while (nl == NULL && *re == buffer_end)
{
/* Truncate too long lines. */
*re = buffer + 3 * (buffer_end - buffer) / 4;
n = __read_nocancel (fd, *re, buffer_end - *re);
if (n < 0)
return NULL;
nl = memchr (*re, '\n', n);
**re = '\n';
*re += n;
}
}
else
nl = memchr (*cp, '\n', *re - *cp);
res = *cp;
}
if (nl == NULL)
nl = *re - 1;
}
*cp = nl + 1;
assert (*cp <= *re);
return res == *re ? NULL : res;
}
int
__get_nprocs_sched (void)
__get_nprocs (void)
{
return __get_nprocs ();
enum { buffer_size = 1024 };
char buffer[buffer_size];
char *buffer_end = buffer + buffer_size;
char *cp = buffer_end;
char *re = buffer_end;
const int flags = O_RDONLY | O_CLOEXEC;
/* This file contains comma-separated ranges. */
int fd = __open_nocancel ("/sys/devices/system/cpu/online", flags);
char *l;
int result = 0;
if (fd != -1)
{
l = next_line (fd, buffer, &cp, &re, buffer_end);
if (l != NULL)
do
{
char *endp;
unsigned long int n = strtoul (l, &endp, 10);
if (l == endp)
{
result = 0;
break;
}
unsigned long int m = n;
if (*endp == '-')
{
l = endp + 1;
m = strtoul (l, &endp, 10);
if (l == endp)
{
result = 0;
break;
}
}
result += m - n + 1;
l = endp;
if (l < re && *l == ',')
++l;
}
while (l < re && *l != '\n');
__close_nocancel_nostatus (fd);
if (result > 0)
return result;
}
cp = buffer_end;
re = buffer_end;
/* Default to an SMP system in case we cannot obtain an accurate
number. */
result = 2;
fd = __open_nocancel ("/proc/stat", flags);
if (fd != -1)
{
result = 0;
while ((l = next_line (fd, buffer, &cp, &re, buffer_end)) != NULL)
/* The current format of /proc/stat has all the cpu* entries
at the front. We assume here that stays this way. */
if (strncmp (l, "cpu", 3) != 0)
break;
else if (isdigit (l[3]))
++result;
__close_nocancel_nostatus (fd);
}
return result;
}
libc_hidden_def (__get_nprocs)
weak_alias (__get_nprocs, get_nprocs)
/* On some architectures it is possible to distinguish between configured