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/ipv4/inet_connection_sock.c | 195 ++++++++++++++++++++++++------------------------
1 files changed, 97 insertions(+), 98 deletions(-)
diff --git a/kernel/net/ipv4/inet_connection_sock.c b/kernel/net/ipv4/inet_connection_sock.c
index 439a55d..4fbc23e 100644
--- a/kernel/net/ipv4/inet_connection_sock.c
+++ b/kernel/net/ipv4/inet_connection_sock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
@@ -6,11 +7,6 @@
* Support for INET connection oriented protocols.
*
* Authors: See the TCP sources
- *
- * 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.
*/
#include <linux/module.h>
@@ -140,7 +136,7 @@
{
struct sock *sk2;
bool reuse = sk->sk_reuse;
- bool reuseport = !!sk->sk_reuseport && reuseport_ok;
+ bool reuseport = !!sk->sk_reuseport;
kuid_t uid = sock_i_uid((struct sock *)sk);
/*
@@ -151,21 +147,29 @@
*/
sk_for_each_bound(sk2, &tb->owners) {
- if (sk != sk2 &&
- (!sk->sk_bound_dev_if ||
- !sk2->sk_bound_dev_if ||
- sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
- if ((!reuse || !sk2->sk_reuse ||
- sk2->sk_state == TCP_LISTEN) &&
- (!reuseport || !sk2->sk_reuseport ||
- rcu_access_pointer(sk->sk_reuseport_cb) ||
- (sk2->sk_state != TCP_TIME_WAIT &&
- !uid_eq(uid, sock_i_uid(sk2))))) {
- if (inet_rcv_saddr_equal(sk, sk2, true))
- break;
- }
- if (!relax && reuse && sk2->sk_reuse &&
+ int bound_dev_if2;
+
+ if (sk == sk2)
+ continue;
+ bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if);
+ if ((!sk->sk_bound_dev_if ||
+ !bound_dev_if2 ||
+ sk->sk_bound_dev_if == bound_dev_if2)) {
+ if (reuse && sk2->sk_reuse &&
sk2->sk_state != TCP_LISTEN) {
+ if ((!relax ||
+ (!reuseport_ok &&
+ reuseport && sk2->sk_reuseport &&
+ !rcu_access_pointer(sk->sk_reuseport_cb) &&
+ (sk2->sk_state == TCP_TIME_WAIT ||
+ uid_eq(uid, sock_i_uid(sk2))))) &&
+ inet_rcv_saddr_equal(sk, sk2, true))
+ break;
+ } else if (!reuseport_ok ||
+ !reuseport || !sk2->sk_reuseport ||
+ rcu_access_pointer(sk->sk_reuseport_cb) ||
+ (sk2->sk_state != TCP_TIME_WAIT &&
+ !uid_eq(uid, sock_i_uid(sk2)))) {
if (inet_rcv_saddr_equal(sk, sk2, true))
break;
}
@@ -185,10 +189,14 @@
int port = 0;
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
+ bool relax = false;
int i, low, high, attempt_half;
struct inet_bind_bucket *tb;
u32 remaining, offset;
+ int l3mdev;
+ l3mdev = inet_sk_bound_l3mdev(sk);
+ports_exhausted:
attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
other_half_scan:
inet_get_local_port_range(net, &low, &high);
@@ -224,8 +232,9 @@
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == port) {
- if (!inet_csk_bind_conflict(sk, tb, false, false))
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
+ if (!inet_csk_bind_conflict(sk, tb, relax, false))
goto success;
goto next_port;
}
@@ -244,6 +253,12 @@
/* OK we now try the upper half of the range */
attempt_half = 2;
goto other_half_scan;
+ }
+
+ if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) {
+ /* We still have a chance to connect to different destinations */
+ relax = true;
+ goto ports_exhausted;
}
return NULL;
success:
@@ -348,6 +363,9 @@
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb = NULL;
+ int l3mdev;
+
+ l3mdev = inet_sk_bound_l3mdev(sk);
if (!port) {
head = inet_csk_find_open_port(sk, &tb, &port);
@@ -361,11 +379,12 @@
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == port)
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port)
goto tb_found;
tb_not_found:
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
- net, head, port);
+ net, head, port, l3mdev);
if (!tb)
goto fail_unlock;
tb_found:
@@ -549,7 +568,7 @@
{
struct inet_connection_sock *icsk = inet_csk(sk);
- icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0;
+ icsk->icsk_pending = icsk->icsk_ack.pending = 0;
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
sk_stop_timer(sk, &icsk->icsk_delack_timer);
@@ -587,7 +606,7 @@
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
htons(ireq->ir_num), sk->sk_uid);
- security_req_classify_flow(req, flowi4_to_flowi(fl4));
+ security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
@@ -625,7 +644,7 @@
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
htons(ireq->ir_num), sk->sk_uid);
- security_req_classify_flow(req, flowi4_to_flowi(fl4));
+ security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
@@ -641,27 +660,20 @@
}
EXPORT_SYMBOL_GPL(inet_csk_route_child_sock);
-#if IS_ENABLED(CONFIG_IPV6)
-#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
-#else
-#define AF_INET_FAMILY(fam) true
-#endif
-
/* Decide when to expire the request and when to resend SYN-ACK */
-static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
- const int max_retries,
- const u8 rskq_defer_accept,
- int *expire, int *resend)
+static void syn_ack_recalc(struct request_sock *req,
+ const int max_syn_ack_retries,
+ const u8 rskq_defer_accept,
+ int *expire, int *resend)
{
if (!rskq_defer_accept) {
- *expire = req->num_timeout >= thresh;
+ *expire = req->num_timeout >= max_syn_ack_retries;
*resend = 1;
return;
}
- *expire = req->num_timeout >= thresh &&
- (!inet_rsk(req)->acked || req->num_timeout >= max_retries);
- /*
- * Do not resend while waiting for data after ACK,
+ *expire = req->num_timeout >= max_syn_ack_retries &&
+ (!inet_rsk(req)->acked || req->num_timeout >= rskq_defer_accept);
+ /* Do not resend while waiting for data after ACK,
* start to resend on end of deferring period to give
* last chance for data or ACK to create established socket.
*/
@@ -680,8 +692,7 @@
EXPORT_SYMBOL(inet_rtx_syn_ack);
/* return true if req was found in the ehash table */
-static bool reqsk_queue_unlink(struct request_sock_queue *queue,
- struct request_sock *req)
+static bool reqsk_queue_unlink(struct request_sock *req)
{
struct inet_hashinfo *hashinfo = req_to_sk(req)->sk_prot->h.hashinfo;
bool found = false;
@@ -700,7 +711,7 @@
bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
{
- bool unlinked = reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req);
+ bool unlinked = reqsk_queue_unlink(req);
if (unlinked) {
reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
@@ -724,15 +735,12 @@
struct net *net = sock_net(sk_listener);
struct inet_connection_sock *icsk = inet_csk(sk_listener);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
- int qlen, expire = 0, resend = 0;
- int max_retries, thresh;
- u8 defer_accept;
+ int max_syn_ack_retries, qlen, expire = 0, resend = 0;
if (inet_sk_state_load(sk_listener) != TCP_LISTEN)
goto drop;
- max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
- thresh = max_retries;
+ max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
/* Normally all the openreqs are young and become mature
* (i.e. converted to established socket) for first timeout.
* If synack was not acknowledged for 1 second, it means
@@ -751,20 +759,17 @@
* ones are about to clog our table.
*/
qlen = reqsk_queue_len(queue);
- if ((qlen << 1) > max(8U, sk_listener->sk_max_ack_backlog)) {
+ if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) {
int young = reqsk_queue_len_young(queue) << 1;
- while (thresh > 2) {
+ while (max_syn_ack_retries > 2) {
if (qlen < young)
break;
- thresh--;
+ max_syn_ack_retries--;
young <<= 1;
}
}
- defer_accept = READ_ONCE(queue->rskq_defer_accept);
- if (defer_accept)
- max_retries = defer_accept;
- syn_ack_recalc(req, thresh, max_retries, defer_accept,
+ syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept),
&expire, &resend);
req->rsk_ops->syn_ack_timeout(req);
if (!expire &&
@@ -786,14 +791,10 @@
static void reqsk_queue_hash_req(struct request_sock *req,
unsigned long timeout)
{
- req->num_retrans = 0;
- req->num_timeout = 0;
- req->sk = NULL;
-
timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
mod_timer(&req->rsk_timer, jiffies + timeout);
- inet_ehash_insert(req_to_sk(req), NULL);
+ inet_ehash_insert(req_to_sk(req), NULL, NULL);
/* before letting lookups find us, make sure all req fields
* are committed to memory and refcnt initialized.
*/
@@ -808,6 +809,18 @@
inet_csk_reqsk_queue_added(sk);
}
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
+
+static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk,
+ const gfp_t priority)
+{
+ struct inet_connection_sock *icsk = inet_csk(newsk);
+
+ if (!icsk->icsk_ulp_ops)
+ return;
+
+ if (icsk->icsk_ulp_ops->clone)
+ icsk->icsk_ulp_ops->clone(req, newsk, priority);
+}
/**
* inet_csk_clone_lock - clone an inet socket, and lock its clone
@@ -845,9 +858,12 @@
newicsk->icsk_retransmits = 0;
newicsk->icsk_backoff = 0;
newicsk->icsk_probes_out = 0;
+ newicsk->icsk_probes_tstamp = 0;
/* Deinitialize accept_queue to trap illegal accesses. */
memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
+
+ inet_clone_ulp(req, newsk, priority);
security_inet_csk_clone(newsk, req);
}
@@ -895,23 +911,33 @@
/* sk_clone_lock locked the socket and set refcnt to 2 */
bh_unlock_sock(sk);
sock_put(sk);
-
- /* The below has to be done to allow calling inet_csk_destroy_sock */
- sock_set_flag(sk, SOCK_DEAD);
- percpu_counter_inc(sk->sk_prot->orphan_count);
+ inet_csk_prepare_for_destroy_sock(sk);
inet_sk(sk)->inet_num = 0;
}
EXPORT_SYMBOL(inet_csk_prepare_forced_close);
+
+static int inet_ulp_can_listen(const struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone)
+ return -EINVAL;
+
+ return 0;
+}
int inet_csk_listen_start(struct sock *sk, int backlog)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
- int err = -EADDRINUSE;
+ int err;
+
+ err = inet_ulp_can_listen(sk);
+ if (unlikely(err))
+ return err;
reqsk_queue_alloc(&icsk->icsk_accept_queue);
- sk->sk_max_ack_backlog = backlog;
sk->sk_ack_backlog = 0;
inet_csk_delack_init(sk);
@@ -920,6 +946,7 @@
* It is OK, because this socket enters to hash table only
* after validation is complete.
*/
+ err = -EADDRINUSE;
inet_sk_state_store(sk, TCP_LISTEN);
if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
inet->inet_sport = htons(inet->inet_num);
@@ -946,7 +973,7 @@
percpu_counter_inc(sk->sk_prot->orphan_count);
if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
- BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+ BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req);
BUG_ON(sk != req->rsk_listener);
/* Paranoid, to prevent race condition if
@@ -955,7 +982,7 @@
* Also to satisfy an assertion in
* tcp_v4_destroy_sock().
*/
- tcp_sk(child)->fastopen_rsk = NULL;
+ RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL);
}
inet_csk_destroy_sock(child);
}
@@ -1061,34 +1088,6 @@
sin->sin_port = inet->inet_dport;
}
EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr);
-
-#ifdef CONFIG_COMPAT
-int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- const struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (icsk->icsk_af_ops->compat_getsockopt)
- return icsk->icsk_af_ops->compat_getsockopt(sk, level, optname,
- optval, optlen);
- return icsk->icsk_af_ops->getsockopt(sk, level, optname,
- optval, optlen);
-}
-EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt);
-
-int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- const struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (icsk->icsk_af_ops->compat_setsockopt)
- return icsk->icsk_af_ops->compat_setsockopt(sk, level, optname,
- optval, optlen);
- return icsk->icsk_af_ops->setsockopt(sk, level, optname,
- optval, optlen);
-}
-EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt);
-#endif
static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl)
{
--
Gitblit v1.6.2