Commit 5a3ae68b authored by Cong Wang's avatar Cong Wang Committed by Zheng Zengkai
Browse files

skmsg: Introduce a spinlock to protect ingress_msg 

mainline inclusion
from mainline-v5.13-rc1
commit b01fd6e8
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I545NW

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b01fd6e802b6d0a635176f943315670b679d8d7b



--------------------------------

Currently we rely on lock_sock to protect ingress_msg,
it is too big for this, we can actually just use a spinlock
to protect this list like protecting other skb queues.

__tcp_bpf_recvmsg() is still special because of peeking,
it still has to use lock_sock.

Signed-off-by: default avatarCong Wang <cong.wang@bytedance.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarJakub Sitnicki <jakub@cloudflare.com>
Acked-by: default avatarJohn Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-3-xiyou.wangcong@gmail.com



Conflicts:
	net/core/skmsg.c
Signed-off-by: default avatarWang Yufen <wangyufen@huawei.com>
Reviewed-by: default avatarYue Haibing <yuehaibing@huawei.com>
Reviewed-by: default avatarLiu Jian <liujian56@huawei.com>
Reviewed-by: default avatarWei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: default avatarZheng Zengkai <zhengzengkai@huawei.com>
parent 401ab829

include/linux/skmsg.h

+46 −0
Original line number Diff line number Diff line
@@ -99,6 +99,7 @@ struct sk_psock { 
	struct sk_psock_parser		parser;

	struct sk_buff_head		ingress_skb;

	struct list_head		ingress_msg;

	spinlock_t			ingress_lock;

	unsigned long			state;

	struct list_head		link;

	spinlock_t			link_lock;
@@ -298,7 +299,45 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) 
static inline void sk_psock_queue_msg(struct sk_psock *psock,

				      struct sk_msg *msg)

{

	spin_lock_bh(&psock->ingress_lock);

	list_add_tail(&msg->list, &psock->ingress_msg);

	spin_unlock_bh(&psock->ingress_lock);

}



static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock)

{

	struct sk_msg *msg;



	spin_lock_bh(&psock->ingress_lock);

	msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);

	if (msg)

		list_del(&msg->list);

	spin_unlock_bh(&psock->ingress_lock);

	return msg;

}



static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock)

{

	struct sk_msg *msg;



	spin_lock_bh(&psock->ingress_lock);

	msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);

	spin_unlock_bh(&psock->ingress_lock);

	return msg;

}



static inline struct sk_msg *sk_psock_next_msg(struct sk_psock *psock,

					       struct sk_msg *msg)

{

	struct sk_msg *ret;



	spin_lock_bh(&psock->ingress_lock);

	if (list_is_last(&msg->list, &psock->ingress_msg))

		ret = NULL;

	else

		ret = list_next_entry(msg, list);

	spin_unlock_bh(&psock->ingress_lock);

	return ret;

}



static inline bool sk_psock_queue_empty(const struct sk_psock *psock)
@@ -306,6 +345,13 @@ static inline bool sk_psock_queue_empty(const struct sk_psock *psock) 
	return psock ? list_empty(&psock->ingress_msg) : true;

}



static inline void kfree_sk_msg(struct sk_msg *msg)

{

	if (msg->skb)

		consume_skb(msg->skb);

	kfree(msg);

}



static inline void sk_psock_report_error(struct sk_psock *psock, int err)

{

	struct sock *sk = psock->sk;

net/core/skmsg.c

+3 −0
Original line number Diff line number Diff line
@@ -598,6 +598,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) 


	INIT_WORK(&psock->work, sk_psock_backlog);

	INIT_LIST_HEAD(&psock->ingress_msg);

	spin_lock_init(&psock->ingress_lock);

	skb_queue_head_init(&psock->ingress_skb);



	sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
@@ -639,7 +640,9 @@ void __sk_psock_purge_ingress_msg(struct sk_psock *psock) 
static void sk_psock_zap_ingress(struct sk_psock *psock)

{

	skb_queue_purge(&psock->ingress_skb);

	spin_lock_bh(&psock->ingress_lock);

	__sk_psock_purge_ingress_msg(psock);

	spin_unlock_bh(&psock->ingress_lock);

}



static void sk_psock_link_destroy(struct sk_psock *psock)

net/ipv4/tcp_bpf.c

+6 −12
Original line number Diff line number Diff line
@@ -18,9 +18,7 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, 
	struct sk_msg *msg_rx;

	int i, copied = 0;



	msg_rx = list_first_entry_or_null(&psock->ingress_msg,

					  struct sk_msg, list);



	msg_rx = sk_psock_peek_msg(psock);

	while (copied != len) {

		struct scatterlist *sge;
@@ -68,22 +66,18 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, 
		} while (i != msg_rx->sg.end);



		if (unlikely(peek)) {

			if (msg_rx == list_last_entry(&psock->ingress_msg,

						      struct sk_msg, list))

			msg_rx = sk_psock_next_msg(psock, msg_rx);

			if (!msg_rx)

				break;

			msg_rx = list_next_entry(msg_rx, list);

			continue;

		}



		msg_rx->sg.start = i;

		if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {

			list_del(&msg_rx->list);

			if (msg_rx->skb)

				consume_skb(msg_rx->skb);

			kfree(msg_rx);

			msg_rx = sk_psock_dequeue_msg(psock);

			kfree_sk_msg(msg_rx);

		}

		msg_rx = list_first_entry_or_null(&psock->ingress_msg,

						  struct sk_msg, list);

		msg_rx = sk_psock_peek_msg(psock);

	}



	return copied;