From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/net/unix/af_unix.c | 122 ++++++++++++++++++++++++++--------------
1 files changed, 78 insertions(+), 44 deletions(-)
diff --git a/kernel/net/unix/af_unix.c b/kernel/net/unix/af_unix.c
index 82279db..440ab64 100644
--- a/kernel/net/unix/af_unix.c
+++ b/kernel/net/unix/af_unix.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* NET4: Implementation of BSD Unix domain sockets.
*
* Authors: Alan Cox, <alan@lxorguk.ukuu.org.uk>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*
* Fixes:
* Linus Torvalds : Assorted bug cures.
@@ -48,7 +44,6 @@
* Arnaldo C. Melo : Remove MOD_{INC,DEC}_USE_COUNT,
* the core infrastructure is doing that
* for all net proto families now (2.5.69+)
- *
*
* Known differences from reference BSD that was tested:
*
@@ -295,11 +290,9 @@
if (u->addr->len == len &&
!memcmp(u->addr->name, sunname, len))
- goto found;
+ return s;
}
- s = NULL;
-found:
- return s;
+ return NULL;
}
static inline struct sock *unix_find_socket_byname(struct net *net,
@@ -445,7 +438,7 @@
* -ECONNREFUSED. Otherwise, if we haven't queued any skbs
* to other and its full, we will hang waiting for POLLOUT.
*/
- if (unix_recvq_full(other) && !sock_flag(other, SOCK_DEAD))
+ if (unix_recvq_full_lockless(other) && !sock_flag(other, SOCK_DEAD))
return 1;
if (connected)
@@ -536,7 +529,7 @@
/* Clear state */
unix_state_lock(sk);
sock_orphan(sk);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
path = u->path;
u->path.dentry = NULL;
u->path.mnt = NULL;
@@ -554,7 +547,7 @@
if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
unix_state_lock(skpair);
/* No more writes */
- skpair->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
skpair->sk_err = ECONNRESET;
unix_state_unlock(skpair);
@@ -594,7 +587,7 @@
* What the above comment does talk about? --ANK(980817)
*/
- if (unix_tot_inflight)
+ if (READ_ONCE(unix_tot_inflight))
unix_gc(); /* Garbage collect fds */
}
@@ -643,7 +636,6 @@
int err;
struct sock *sk = sock->sk;
struct unix_sock *u = unix_sk(sk);
- struct pid *old_pid = NULL;
err = -EOPNOTSUPP;
if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
@@ -664,7 +656,6 @@
out_unlock:
unix_state_unlock(sk);
- put_pid(old_pid);
out:
return err;
}
@@ -706,12 +697,27 @@
if (mutex_lock_interruptible(&u->iolock))
return -EINTR;
- sk->sk_peek_off = val;
+ WRITE_ONCE(sk->sk_peek_off, val);
mutex_unlock(&u->iolock);
return 0;
}
+#ifdef CONFIG_PROC_FS
+static void unix_show_fdinfo(struct seq_file *m, struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct unix_sock *u;
+
+ if (sk) {
+ u = unix_sk(sock->sk);
+ seq_printf(m, "scm_fds: %u\n",
+ atomic_read(&u->scm_stat.nr_fds));
+ }
+}
+#else
+#define unix_show_fdinfo NULL
+#endif
static const struct proto_ops unix_stream_ops = {
.family = PF_UNIX,
@@ -729,14 +735,13 @@
#endif
.listen = unix_listen,
.shutdown = unix_shutdown,
- .setsockopt = sock_no_setsockopt,
- .getsockopt = sock_no_getsockopt,
.sendmsg = unix_stream_sendmsg,
.recvmsg = unix_stream_recvmsg,
.mmap = sock_no_mmap,
.sendpage = unix_stream_sendpage,
.splice_read = unix_stream_splice_read,
.set_peek_off = unix_set_peek_off,
+ .show_fdinfo = unix_show_fdinfo,
};
static const struct proto_ops unix_dgram_ops = {
@@ -755,13 +760,12 @@
#endif
.listen = sock_no_listen,
.shutdown = unix_shutdown,
- .setsockopt = sock_no_setsockopt,
- .getsockopt = sock_no_getsockopt,
.sendmsg = unix_dgram_sendmsg,
.recvmsg = unix_dgram_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
.set_peek_off = unix_set_peek_off,
+ .show_fdinfo = unix_show_fdinfo,
};
static const struct proto_ops unix_seqpacket_ops = {
@@ -780,13 +784,12 @@
#endif
.listen = unix_listen,
.shutdown = unix_shutdown,
- .setsockopt = sock_no_setsockopt,
- .getsockopt = sock_no_getsockopt,
.sendmsg = unix_seqpacket_sendmsg,
.recvmsg = unix_seqpacket_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
.set_peek_off = unix_set_peek_off,
+ .show_fdinfo = unix_show_fdinfo,
};
static struct proto unix_proto = {
@@ -824,6 +827,7 @@
mutex_init(&u->bindlock); /* single task binding lock */
init_waitqueue_head(&u->peer_wait);
init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
+ memset(&u->scm_stat, 0, sizeof(struct scm_stat));
unix_insert_socket(unix_sockets_unbound(sk), sk);
out:
if (sk == NULL)
@@ -854,7 +858,7 @@
*/
case SOCK_RAW:
sock->type = SOCK_DGRAM;
- /* fall through */
+ fallthrough;
case SOCK_DGRAM:
sock->ops = &unix_dgram_ops;
break;
@@ -895,7 +899,6 @@
if (err)
return err;
- err = 0;
if (u->addr)
goto out;
@@ -1223,6 +1226,7 @@
}
static long unix_wait_for_peer(struct sock *other, long timeo)
+ __releases(&unix_sk(other)->lock)
{
struct unix_sock *u = unix_sk(other);
int sched;
@@ -1232,7 +1236,7 @@
sched = !sock_flag(other, SOCK_DEAD) &&
!(other->sk_shutdown & RCV_SHUTDOWN) &&
- unix_recvq_full(other);
+ unix_recvq_full_lockless(other);
unix_state_unlock(other);
@@ -1655,6 +1659,24 @@
unix_secdata_eq(scm, skb);
}
+static void scm_stat_add(struct sock *sk, struct sk_buff *skb)
+{
+ struct scm_fp_list *fp = UNIXCB(skb).fp;
+ struct unix_sock *u = unix_sk(sk);
+
+ if (unlikely(fp && fp->count))
+ atomic_add(fp->count, &u->scm_stat.nr_fds);
+}
+
+static void scm_stat_del(struct sock *sk, struct sk_buff *skb)
+{
+ struct scm_fp_list *fp = UNIXCB(skb).fp;
+ struct unix_sock *u = unix_sk(sk);
+
+ if (unlikely(fp && fp->count))
+ atomic_sub(fp->count, &u->scm_stat.nr_fds);
+}
+
/*
* Send AF_UNIX data.
*/
@@ -1841,6 +1863,7 @@
if (sock_flag(other, SOCK_RCVTSTAMP))
__net_timestamp(skb);
maybe_add_creds(skb, sock, other);
+ scm_stat_add(other, skb);
skb_queue_tail(&other->sk_receive_queue, skb);
unix_state_unlock(other);
other->sk_data_ready(other);
@@ -1943,6 +1966,7 @@
goto pipe_err_free;
maybe_add_creds(skb, sock, other);
+ scm_stat_add(other, skb);
skb_queue_tail(&other->sk_receive_queue, skb);
unix_state_unlock(other);
other->sk_data_ready(other);
@@ -1984,6 +2008,7 @@
if (false) {
alloc_skb:
+ spin_unlock(&other->sk_receive_queue.lock);
unix_state_unlock(other);
mutex_unlock(&unix_sk(other)->iolock);
newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
@@ -2023,6 +2048,7 @@
init_scm = false;
}
+ spin_lock(&other->sk_receive_queue.lock);
skb = skb_peek_tail(&other->sk_receive_queue);
if (tail && tail == skb) {
skb = newskb;
@@ -2053,14 +2079,11 @@
refcount_add(size, &sk->sk_wmem_alloc);
if (newskb) {
- err = unix_scm_to_skb(&scm, skb, false);
- if (err)
- goto err_state_unlock;
- spin_lock(&other->sk_receive_queue.lock);
+ unix_scm_to_skb(&scm, skb, false);
__skb_queue_tail(&other->sk_receive_queue, newskb);
- spin_unlock(&other->sk_receive_queue.lock);
}
+ spin_unlock(&other->sk_receive_queue.lock);
unix_state_unlock(other);
mutex_unlock(&unix_sk(other)->iolock);
@@ -2129,8 +2152,8 @@
struct unix_sock *u = unix_sk(sk);
struct sk_buff *skb, *last;
long timeo;
+ int skip;
int err;
- int peeked, skip;
err = -EOPNOTSUPP;
if (flags&MSG_OOB)
@@ -2142,17 +2165,21 @@
mutex_lock(&u->iolock);
skip = sk_peek_offset(sk, flags);
- skb = __skb_try_recv_datagram(sk, flags, NULL, &peeked, &skip,
- &err, &last);
- if (skb)
+ skb = __skb_try_recv_datagram(sk, &sk->sk_receive_queue, flags,
+ &skip, &err, &last);
+ if (skb) {
+ if (!(flags & MSG_PEEK))
+ scm_stat_del(sk, skb);
break;
+ }
mutex_unlock(&u->iolock);
if (err != -EAGAIN)
break;
} while (timeo &&
- !__skb_wait_for_more_packets(sk, &err, &timeo, last));
+ !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue,
+ &err, &timeo, last));
if (!skb) { /* implies iolock unlocked */
unix_state_lock(sk);
@@ -2437,8 +2464,10 @@
sk_peek_offset_bwd(sk, chunk);
- if (UNIXCB(skb).fp)
+ if (UNIXCB(skb).fp) {
+ scm_stat_del(sk, skb);
unix_detach_fds(&scm, skb);
+ }
if (unix_skb_len(skb))
break;
@@ -2551,7 +2580,7 @@
++mode;
unix_state_lock(sk);
- sk->sk_shutdown |= mode;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode);
other = unix_peer(sk);
if (other)
sock_hold(other);
@@ -2568,7 +2597,7 @@
if (mode&SEND_SHUTDOWN)
peer_mode |= RCV_SHUTDOWN;
unix_state_lock(other);
- other->sk_shutdown |= peer_mode;
+ WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode);
unix_state_unlock(other);
other->sk_state_change(other);
if (peer_mode == SHUTDOWN_MASK)
@@ -2687,16 +2716,18 @@
{
struct sock *sk = sock->sk;
__poll_t mask;
+ u8 shutdown;
sock_poll_wait(file, sock, wait);
mask = 0;
+ shutdown = READ_ONCE(sk->sk_shutdown);
/* exceptional events? */
if (sk->sk_err)
mask |= EPOLLERR;
- if (sk->sk_shutdown == SHUTDOWN_MASK)
+ if (shutdown == SHUTDOWN_MASK)
mask |= EPOLLHUP;
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
/* readable? */
@@ -2724,18 +2755,20 @@
struct sock *sk = sock->sk, *other;
unsigned int writable;
__poll_t mask;
+ u8 shutdown;
sock_poll_wait(file, sock, wait);
mask = 0;
+ shutdown = READ_ONCE(sk->sk_shutdown);
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
- if (sk->sk_shutdown == SHUTDOWN_MASK)
+ if (shutdown == SHUTDOWN_MASK)
mask |= EPOLLHUP;
/* readable? */
@@ -2949,7 +2982,7 @@
{
int rc = -1;
- BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb));
+ BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb));
rc = proto_register(&unix_proto, 1);
if (rc != 0) {
@@ -2978,4 +3011,5 @@
module_exit(af_unix_exit);
MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(VFS_internal_I_am_really_a_filesystem_and_am_NOT_a_driver);
MODULE_ALIAS_NETPROTO(PF_UNIX);
--
Gitblit v1.6.2