mirror of
https://github.com/nxp-imx/linux-imx.git
synced 2025-07-19 07:39:54 +02:00
d9f21b3613
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>
117 lines
3.0 KiB
C
117 lines
3.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_NET_AFUNIX_H
|
|
#define __LINUX_NET_AFUNIX_H
|
|
|
|
#include <linux/socket.h>
|
|
#include <linux/un.h>
|
|
#include <linux/mutex.h>
|
|
#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(struct scm_fp_list *fpl);
|
|
struct sock *unix_peer_get(struct sock *sk);
|
|
|
|
#define UNIX_HASH_MOD (256 - 1)
|
|
#define UNIX_HASH_SIZE (256 * 2)
|
|
#define UNIX_HASH_BITS 8
|
|
|
|
extern unsigned int unix_tot_inflight;
|
|
|
|
struct unix_address {
|
|
refcount_t refcnt;
|
|
int len;
|
|
struct sockaddr_un name[];
|
|
};
|
|
|
|
struct unix_skb_parms {
|
|
struct pid *pid; /* Skb credentials */
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
struct scm_fp_list *fp; /* Passed files */
|
|
#ifdef CONFIG_SECURITY_NETWORK
|
|
u32 secid; /* Security ID */
|
|
#endif
|
|
u32 consumed;
|
|
} __randomize_layout;
|
|
|
|
struct scm_stat {
|
|
atomic_t nr_fds;
|
|
};
|
|
|
|
#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb))
|
|
|
|
#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock)
|
|
#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock)
|
|
#define unix_state_lock_nested(s) \
|
|
spin_lock_nested(&unix_sk(s)->lock, \
|
|
SINGLE_DEPTH_NESTING)
|
|
|
|
/* The AF_UNIX socket */
|
|
struct unix_sock {
|
|
/* WARNING: sk has to be the first member */
|
|
struct sock sk;
|
|
struct unix_address *addr;
|
|
struct path path;
|
|
struct mutex iolock, bindlock;
|
|
struct sock *peer;
|
|
struct list_head link;
|
|
unsigned long inflight;
|
|
spinlock_t lock;
|
|
unsigned long gc_flags;
|
|
#define UNIX_GC_CANDIDATE 0
|
|
#define UNIX_GC_MAYBE_CYCLE 1
|
|
struct socket_wq peer_wq;
|
|
wait_queue_entry_t peer_wake;
|
|
struct scm_stat scm_stat;
|
|
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
|
|
struct sk_buff *oob_skb;
|
|
#endif
|
|
};
|
|
|
|
#define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
|
|
#define unix_peer(sk) (unix_sk(sk)->peer)
|
|
|
|
#define peer_wait peer_wq.wait
|
|
|
|
long unix_inq_len(struct sock *sk);
|
|
long unix_outq_len(struct sock *sk);
|
|
|
|
int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
|
|
int flags);
|
|
int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
|
|
int flags);
|
|
#ifdef CONFIG_SYSCTL
|
|
int unix_sysctl_register(struct net *net);
|
|
void unix_sysctl_unregister(struct net *net);
|
|
#else
|
|
static inline int unix_sysctl_register(struct net *net) { return 0; }
|
|
static inline void unix_sysctl_unregister(struct net *net) {}
|
|
#endif
|
|
|
|
#ifdef CONFIG_BPF_SYSCALL
|
|
extern struct proto unix_dgram_proto;
|
|
extern struct proto unix_stream_proto;
|
|
|
|
int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
|
|
int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
|
|
void __init unix_bpf_build_proto(void);
|
|
#else
|
|
static inline void __init unix_bpf_build_proto(void)
|
|
{}
|
|
#endif
|
|
#endif
|