github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-28 17:13:52 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

Merge branch 'tcp-remove-net-core-request_sock-c-and-no-longer-inline-__reqsk_free'

Browse Source 
Eric Dumazet says:

====================
tcp: remove net/core/request_sock.c and no longer inline __reqsk_free()

After DCCP removal, net/core/request_sock.c makes no more sense.

Move reqsk_queue_alloc() and reqsk_fastopen_remove() to TCP files.

Then put __reqsk_free() out of line to save ~2 Kbytes of text.
====================

Link: https://patch.msgid.link/20260204055147.1682705-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Jakub Kicinski 2026-02-05 09:23:08 -08:00
commit 047c5265ec
5 changed files with 107 additions and 138 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
include/net/request_sock.h
View File

@ -123,14 +123,7 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb,
return sk;
}
static inline void __reqsk_free(struct request_sock *req)
{
req->rsk_ops->destructor(req);
if (req->rsk_listener)
sock_put(req->rsk_listener);
kfree(req->saved_syn);
kmem_cache_free(req->rsk_ops->slab, req);
}
void __reqsk_free(struct request_sock *req);
static inline void reqsk_free(struct request_sock *req)
{
@ -196,8 +189,6 @@ struct request_sock_queue {
*/
};
void reqsk_queue_alloc(struct request_sock_queue *queue);
void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
bool reset);

2
net/core/Makefile
View File

@ -3,7 +3,7 @@
# Makefile for the Linux networking core.
#
obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \
obj-y := sock.o skbuff.o datagram.o stream.o scm.o \
gen_stats.o gen_estimator.o net_namespace.o secure_seq.o \
flow_dissector.o

127
net/core/request_sock.c
View File

@ -1,127 +0,0 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* NET Generic infrastructure for Network protocols.
*
* Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* From code originally in include/net/tcp.h
*/
#include <linux/module.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/tcp.h>
#include <linux/vmalloc.h>
#include <net/request_sock.h>
/*
* Maximum number of SYN_RECV sockets in queue per LISTEN socket.
* One SYN_RECV socket costs about 80bytes on a 32bit machine.
* It would be better to replace it with a global counter for all sockets
* but then some measure against one socket starving all other sockets
* would be needed.
*
* The minimum value of it is 128. Experiments with real servers show that
* it is absolutely not enough even at 100conn/sec. 256 cures most
* of problems.
* This value is adjusted to 128 for low memory machines,
* and it will increase in proportion to the memory of machine.
* Note : Dont forget somaxconn that may limit backlog too.
*/
void reqsk_queue_alloc(struct request_sock_queue *queue)
{
queue->fastopenq.rskq_rst_head = NULL;
queue->fastopenq.rskq_rst_tail = NULL;
queue->fastopenq.qlen = 0;
queue->rskq_accept_head = NULL;
}
/*
* This function is called to set a Fast Open socket's "fastopen_rsk" field
* to NULL when a TFO socket no longer needs to access the request_sock.
* This happens only after 3WHS has been either completed or aborted (e.g.,
* RST is received).
*
* Before TFO, a child socket is created only after 3WHS is completed,
* hence it never needs to access the request_sock. things get a lot more
* complex with TFO. A child socket, accepted or not, has to access its
* request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts,
* until 3WHS is either completed or aborted. Afterwards the req will stay
* until either the child socket is accepted, or in the rare case when the
* listener is closed before the child is accepted.
*
* In short, a request socket is only freed after BOTH 3WHS has completed
* (or aborted) and the child socket has been accepted (or listener closed).
* When a child socket is accepted, its corresponding req->sk is set to
* NULL since it's no longer needed. More importantly, "req->sk == NULL"
* will be used by the code below to determine if a child socket has been
* accepted or not, and the check is protected by the fastopenq->lock
* described below.
*
* Note that fastopen_rsk is only accessed from the child socket's context
* with its socket lock held. But a request_sock (req) can be accessed by
* both its child socket through fastopen_rsk, and a listener socket through
* icsk_accept_queue.rskq_accept_head. To protect the access a simple spin
* lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created.
* only in the rare case when both the listener and the child locks are held,
* e.g., in inet_csk_listen_stop() do we not need to acquire the lock.
* The lock also protects other fields such as fastopenq->qlen, which is
* decremented by this function when fastopen_rsk is no longer needed.
*
* Note that another solution was to simply use the existing socket lock
* from the listener. But first socket lock is difficult to use. It is not
* a simple spin lock - one must consider sock_owned_by_user() and arrange
* to use sk_add_backlog() stuff. But what really makes it infeasible is the
* locking hierarchy violation. E.g., inet_csk_listen_stop() may try to
* acquire a child's lock while holding listener's socket lock.
*
* This function also sets "treq->tfo_listener" to false.
* treq->tfo_listener is used by the listener so it is protected by the
* fastopenq->lock in this function.
*/
void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
bool reset)
{
struct sock *lsk = req->rsk_listener;
struct fastopen_queue *fastopenq;
fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq;
RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL);
spin_lock_bh(&fastopenq->lock);
fastopenq->qlen--;
tcp_rsk(req)->tfo_listener = false;
if (req->sk) /* the child socket hasn't been accepted yet */
goto out;
if (!reset || lsk->sk_state != TCP_LISTEN) {
/* If the listener has been closed don't bother with the
* special RST handling below.
*/
spin_unlock_bh(&fastopenq->lock);
reqsk_put(req);
return;
}
/* Wait for 60secs before removing a req that has triggered RST.
* This is a simple defense against TFO spoofing attack - by
* counting the req against fastopen.max_qlen, and disabling
* TFO when the qlen exceeds max_qlen.
*
* For more details see CoNext'11 "TCP Fast Open" paper.
*/
req->rsk_timer.expires = jiffies + 60*HZ;
if (fastopenq->rskq_rst_head == NULL)
fastopenq->rskq_rst_head = req;
else
fastopenq->rskq_rst_tail->dl_next = req;
req->dl_next = NULL;
fastopenq->rskq_rst_tail = req;
fastopenq->qlen++;
out:
spin_unlock_bh(&fastopenq->lock);
}

19
net/ipv4/inet_connection_sock.c
View File

@ -919,6 +919,16 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
}
EXPORT_SYMBOL(inet_reqsk_alloc);
void __reqsk_free(struct request_sock *req)
{
req->rsk_ops->destructor(req);
if (req->rsk_listener)
sock_put(req->rsk_listener);
kfree(req->saved_syn);
kmem_cache_free(req->rsk_ops->slab, req);
}
EXPORT_SYMBOL_GPL(__reqsk_free);
static struct request_sock *inet_reqsk_clone(struct request_sock *req,
struct sock *sk)
{
@ -1314,6 +1324,15 @@ static int inet_ulp_can_listen(const struct sock *sk)
return 0;
}
static void reqsk_queue_alloc(struct request_sock_queue *queue)
{
queue->fastopenq.rskq_rst_head = NULL;
queue->fastopenq.rskq_rst_tail = NULL;
queue->fastopenq.qlen = 0;
queue->rskq_accept_head = NULL;
}
int inet_csk_listen_start(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);

86
net/ipv4/tcp_fastopen.c
View File

@ -5,6 +5,92 @@
#include <net/tcp.h>
#include <net/busy_poll.h>
/*
* This function is called to set a Fast Open socket's "fastopen_rsk" field
* to NULL when a TFO socket no longer needs to access the request_sock.
* This happens only after 3WHS has been either completed or aborted (e.g.,
* RST is received).
*
* Before TFO, a child socket is created only after 3WHS is completed,
* hence it never needs to access the request_sock. things get a lot more
* complex with TFO. A child socket, accepted or not, has to access its
* request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts,
* until 3WHS is either completed or aborted. Afterwards the req will stay
* until either the child socket is accepted, or in the rare case when the
* listener is closed before the child is accepted.
*
* In short, a request socket is only freed after BOTH 3WHS has completed
* (or aborted) and the child socket has been accepted (or listener closed).
* When a child socket is accepted, its corresponding req->sk is set to
* NULL since it's no longer needed. More importantly, "req->sk == NULL"
* will be used by the code below to determine if a child socket has been
* accepted or not, and the check is protected by the fastopenq->lock
* described below.
*
* Note that fastopen_rsk is only accessed from the child socket's context
* with its socket lock held. But a request_sock (req) can be accessed by
* both its child socket through fastopen_rsk, and a listener socket through
* icsk_accept_queue.rskq_accept_head. To protect the access a simple spin
* lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created.
* only in the rare case when both the listener and the child locks are held,
* e.g., in inet_csk_listen_stop() do we not need to acquire the lock.
* The lock also protects other fields such as fastopenq->qlen, which is
* decremented by this function when fastopen_rsk is no longer needed.
*
* Note that another solution was to simply use the existing socket lock
* from the listener. But first socket lock is difficult to use. It is not
* a simple spin lock - one must consider sock_owned_by_user() and arrange
* to use sk_add_backlog() stuff. But what really makes it infeasible is the
* locking hierarchy violation. E.g., inet_csk_listen_stop() may try to
* acquire a child's lock while holding listener's socket lock.
*
* This function also sets "treq->tfo_listener" to false.
* treq->tfo_listener is used by the listener so it is protected by the
* fastopenq->lock in this function.
*/
void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
bool reset)
{
struct sock *lsk = req->rsk_listener;
struct fastopen_queue *fastopenq;
fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq;
RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL);
spin_lock_bh(&fastopenq->lock);
fastopenq->qlen--;
tcp_rsk(req)->tfo_listener = false;
if (req->sk) /* the child socket hasn't been accepted yet */
goto out;
if (!reset || lsk->sk_state != TCP_LISTEN) {
/* If the listener has been closed don't bother with the
* special RST handling below.
*/
spin_unlock_bh(&fastopenq->lock);
reqsk_put(req);
return;
}
/* Wait for 60secs before removing a req that has triggered RST.
* This is a simple defense against TFO spoofing attack - by
* counting the req against fastopen.max_qlen, and disabling
* TFO when the qlen exceeds max_qlen.
*
* For more details see CoNext'11 "TCP Fast Open" paper.
*/
req->rsk_timer.expires = jiffies + 60*HZ;
if (fastopenq->rskq_rst_head == NULL)
fastopenq->rskq_rst_head = req;
else
fastopenq->rskq_rst_tail->dl_next = req;
req->dl_next = NULL;
fastopenq->rskq_rst_tail = req;
fastopenq->qlen++;
out:
spin_unlock_bh(&fastopenq->lock);
}
void tcp_fastopen_init_key_once(struct net *net)
{
u8 key[TCP_FASTOPEN_KEY_LENGTH];