If more than 16000 inflight AF_UNIX sockets exist and the garbage
collector is not running, unix_(dgram|stream)_sendmsg() call unix_gc().
Also, they wait for unix_gc() to complete.
In unix_gc(), all inflight AF_UNIX sockets are traversed at least once,
and more if they are the GC candidate. Thus, sendmsg() significantly
slows down with too many inflight AF_UNIX sockets.
However, if a process sends data with no AF_UNIX FD, the sendmsg() call
does not need to wait for GC. After this change, only the process that
meets the condition below will be blocked under such a situation.
1) cmsg contains AF_UNIX socket
2) more than 32 AF_UNIX sent by the same user are still inflight
Note that even a sendmsg() call that does not meet the condition but has
AF_UNIX FD will be blocked later in unix_scm_to_skb() by the spinlock,
but we allow that as a bonus for sane users.
The results below are the time spent in unix_dgram_sendmsg() sending 1
byte of data with no FD 4096 times on a host where 32K inflight AF_UNIX
sockets exist.
Without series: the sane sendmsg() needs to wait gc unreasonably.
$ sudo /usr/share/bcc/tools/funclatency -p 11165 unix_dgram_sendmsg
Tracing 1 functions for "unix_dgram_sendmsg"... Hit Ctrl-C to end.
^C
nsecs : count distribution
[...]
524288 ->
1048575 : 0 | |
1048576 ->
2097151 : 3881 |****************************************|
2097152 ->
4194303 : 214 |** |
4194304 ->
8388607 : 1 | |
avg =
1825567 nsecs, total:
7477526027 nsecs, count: 4096
With series: the sane sendmsg() can finish much faster.
$ sudo /usr/share/bcc/tools/funclatency -p 8702 unix_dgram_sendmsg
Tracing 1 functions for "unix_dgram_sendmsg"... Hit Ctrl-C to end.
^C
nsecs : count distribution
[...]
128 -> 255 : 0 | |
256 -> 511 : 4092 |****************************************|
512 -> 1023 : 2 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 0 | |
4096 -> 8191 : 1 | |
8192 -> 16383 : 1 | |
avg = 410 nsecs, total:
1680510 nsecs, count: 4096
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240123170856.41348-6-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
#include <linux/refcount.h>
#include <net/sock.h>
+#if IS_ENABLED(CONFIG_UNIX)
+struct unix_sock *unix_get_socket(struct file *filp);
+#else
+static inline struct unix_sock *unix_get_socket(struct file *filp)
+{
+ return NULL;
+}
+#endif
+
void unix_inflight(struct user_struct *user, struct file *fp);
void unix_notinflight(struct user_struct *user, struct file *fp);
void unix_destruct_scm(struct sk_buff *skb);
void io_uring_destruct_scm(struct sk_buff *skb);
void unix_gc(void);
-void wait_for_unix_gc(void);
-struct unix_sock *unix_get_socket(struct file *filp);
+void wait_for_unix_gc(struct scm_fp_list *fpl);
struct sock *unix_peer_get(struct sock *sk);
#define UNIX_HASH_MOD (256 - 1)
struct scm_fp_list {
short count;
+ short count_unix;
short max;
struct user_struct *user;
struct file *fp[SCM_MAX_FD];
#include <net/compat.h>
#include <net/scm.h>
#include <net/cls_cgroup.h>
+#include <net/af_unix.h>
/*
return -ENOMEM;
*fplp = fpl;
fpl->count = 0;
+ fpl->count_unix = 0;
fpl->max = SCM_MAX_FD;
fpl->user = NULL;
}
fput(file);
return -EINVAL;
}
+ if (unix_get_socket(file))
+ fpl->count_unix++;
+
*fpp++ = file;
fpl->count++;
}
long timeo;
int err;
- wait_for_unix_gc();
err = scm_send(sock, msg, &scm, false);
if (err < 0)
return err;
+ wait_for_unix_gc(scm.fp);
+
err = -EOPNOTSUPP;
if (msg->msg_flags&MSG_OOB)
goto out;
bool fds_sent = false;
int data_len;
- wait_for_unix_gc();
err = scm_send(sock, msg, &scm, false);
if (err < 0)
return err;
+ wait_for_unix_gc(scm.fp);
+
err = -EOPNOTSUPP;
if (msg->msg_flags & MSG_OOB) {
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
}
#define UNIX_INFLIGHT_TRIGGER_GC 16000
+#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8)
-void wait_for_unix_gc(void)
+void wait_for_unix_gc(struct scm_fp_list *fpl)
{
/* If number of inflight sockets is insane,
* force a garbage collect right now.
!READ_ONCE(gc_in_progress))
unix_gc();
+ /* Penalise users who want to send AF_UNIX sockets
+ * but whose sockets have not been received yet.
+ */
+ if (!fpl || !fpl->count_unix ||
+ READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER)
+ return;
+
if (READ_ONCE(gc_in_progress))
flush_work(&unix_gc_work);
}