af_unix: Relax race in unix_autobind().
When we bind an AF_UNIX socket without a name specified, the kernel selects
an available one from 0x00000 to 0xFFFFF. unix_autobind() starts searching
from a number in the 'static' variable and increments it after acquiring
two locks.
If multiple processes try autobind, they obtain the same lock and check if
a socket in the hash list has the same name. If not, one process uses it,
and all except one end up retrying the _next_ number (actually not, it may
be incremented by the other processes). The more we autobind sockets in
parallel, the longer the latency gets. We can avoid such a race by
searching for a name from a random number.
These show latency in unix_autobind() while 64 CPUs are simultaneously
autobind-ing 1024 sockets for each.
Without this patch:
usec : count distribution
0 : 1176 |*** |
2 : 3655 |*********** |
4 : 4094 |************* |
6 : 3831 |************ |
8 : 3829 |************ |
10 : 3844 |************ |
12 : 3638 |*********** |
14 : 2992 |********* |
16 : 2485 |******* |
18 : 2230 |******* |
20 : 2095 |****** |
22 : 1853 |***** |
24 : 1827 |***** |
26 : 1677 |***** |
28 : 1473 |**** |
30 : 1573 |***** |
32 : 1417 |**** |
34 : 1385 |**** |
36 : 1345 |**** |
38 : 1344 |**** |
40 : 1200 |*** |
With this patch:
usec : count distribution
0 : 1855 |****** |
2 : 6464 |********************* |
4 : 9936 |******************************** |
6 : 12107 |****************************************|
8 : 10441 |********************************** |
10 : 7264 |*********************** |
12 : 4254 |************** |
14 : 2538 |******** |
16 : 1596 |***** |
18 : 1088 |*** |
20 : 800 |** |
22 : 670 |** |
24 : 601 |* |
26 : 562 |* |
28 : 525 |* |
30 : 446 |* |
32 : 378 |* |
34 : 337 |* |
36 : 317 |* |
38 : 314 |* |
40 : 298 | |
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
committed by
Jakub Kicinski
parent
afd20b9290
commit
9acbc584c3
@@ -1074,8 +1074,7 @@ static int unix_autobind(struct sock *sk)
|
||||
unsigned int new_hash, old_hash = sk->sk_hash;
|
||||
struct unix_sock *u = unix_sk(sk);
|
||||
struct unix_address *addr;
|
||||
unsigned int retries = 0;
|
||||
static u32 ordernum = 1;
|
||||
u32 lastnum, ordernum;
|
||||
int err;
|
||||
|
||||
err = mutex_lock_interruptible(&u->bindlock);
|
||||
@@ -1091,32 +1090,35 @@ static int unix_autobind(struct sock *sk)
|
||||
if (!addr)
|
||||
goto out;
|
||||
|
||||
addr->len = offsetof(struct sockaddr_un, sun_path) + 6;
|
||||
addr->name->sun_family = AF_UNIX;
|
||||
refcount_set(&addr->refcnt, 1);
|
||||
|
||||
ordernum = prandom_u32();
|
||||
lastnum = ordernum & 0xFFFFF;
|
||||
retry:
|
||||
addr->len = sprintf(addr->name->sun_path + 1, "%05x", ordernum) +
|
||||
offsetof(struct sockaddr_un, sun_path) + 1;
|
||||
ordernum = (ordernum + 1) & 0xFFFFF;
|
||||
sprintf(addr->name->sun_path + 1, "%05x", ordernum);
|
||||
|
||||
new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type);
|
||||
unix_table_double_lock(old_hash, new_hash);
|
||||
ordernum = (ordernum+1)&0xFFFFF;
|
||||
|
||||
if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len,
|
||||
new_hash)) {
|
||||
unix_table_double_unlock(old_hash, new_hash);
|
||||
|
||||
/*
|
||||
* __unix_find_socket_byname() may take long time if many names
|
||||
/* __unix_find_socket_byname() may take long time if many names
|
||||
* are already in use.
|
||||
*/
|
||||
cond_resched();
|
||||
/* Give up if all names seems to be in use. */
|
||||
if (retries++ == 0xFFFFF) {
|
||||
|
||||
if (ordernum == lastnum) {
|
||||
/* Give up if all names seems to be in use. */
|
||||
err = -ENOSPC;
|
||||
kfree(addr);
|
||||
unix_release_addr(addr);
|
||||
goto out;
|
||||
}
|
||||
|
||||
goto retry;
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user