Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit ac69269a authored by Julian Anastasov's avatar Julian Anastasov Committed by Pablo Neira Ayuso
Browse files

ipvs: do not disable bh for long time 



We used a global BH disable in LOCAL_OUT hook.
Add _bh suffix to all places that need it and remove
the disabling from LOCAL_OUT and sync code.

Functions like ip_defrag need protection from
BH, so add it. As for nf_nat_mangle_tcp_packet, it needs
RCU lock.

Signed-off-by: default avatarJulian Anastasov <ja@ssi.bg>
Signed-off-by: default avatarSimon Horman <horms@verge.net.au>
parent ceec4c38

net/netfilter/ipvs/ip_vs_app.c

+2 −2
Original line number Diff line number Diff line
@@ -352,14 +352,14 @@ static inline void vs_seq_update(struct ip_vs_conn *cp, struct ip_vs_seq *vseq, 
				 unsigned int flag, __u32 seq, int diff)

{

	/* spinlock is to keep updating cp->flags atomic */

	spin_lock(&cp->lock);

	spin_lock_bh(&cp->lock);

	if (!(cp->flags & flag) || after(seq, vseq->init_seq)) {

		vseq->previous_delta = vseq->delta;

		vseq->delta += diff;

		vseq->init_seq = seq;

		cp->flags |= flag;

	}

	spin_unlock(&cp->lock);

	spin_unlock_bh(&cp->lock);

}



static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,

net/netfilter/ipvs/ip_vs_conn.c

+15 −15
Original line number Diff line number Diff line
@@ -86,14 +86,14 @@ struct ip_vs_aligned_lock 
static struct ip_vs_aligned_lock

__ip_vs_conntbl_lock_array[CT_LOCKARRAY_SIZE] __cacheline_aligned;



static inline void ct_write_lock(unsigned int key)

static inline void ct_write_lock_bh(unsigned int key)

{

	spin_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);

	spin_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);

}



static inline void ct_write_unlock(unsigned int key)

static inline void ct_write_unlock_bh(unsigned int key)

{

	spin_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);

	spin_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);

}
@@ -167,7 +167,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) 
	/* Hash by protocol, client address and port */

	hash = ip_vs_conn_hashkey_conn(cp);



	ct_write_lock(hash);

	ct_write_lock_bh(hash);

	spin_lock(&cp->lock);



	if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
@@ -182,7 +182,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) 
	}



	spin_unlock(&cp->lock);

	ct_write_unlock(hash);

	ct_write_unlock_bh(hash);



	return ret;

}
@@ -200,7 +200,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) 
	/* unhash it and decrease its reference counter */

	hash = ip_vs_conn_hashkey_conn(cp);



	ct_write_lock(hash);

	ct_write_lock_bh(hash);

	spin_lock(&cp->lock);



	if (cp->flags & IP_VS_CONN_F_HASHED) {
@@ -212,7 +212,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) 
		ret = 0;



	spin_unlock(&cp->lock);

	ct_write_unlock(hash);

	ct_write_unlock_bh(hash);



	return ret;

}
@@ -227,7 +227,7 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) 


	hash = ip_vs_conn_hashkey_conn(cp);



	ct_write_lock(hash);

	ct_write_lock_bh(hash);

	spin_lock(&cp->lock);



	if (cp->flags & IP_VS_CONN_F_HASHED) {
@@ -242,7 +242,7 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) 
		ret = atomic_read(&cp->refcnt) ? false : true;



	spin_unlock(&cp->lock);

	ct_write_unlock(hash);

	ct_write_unlock_bh(hash);



	return ret;

}
@@ -462,13 +462,13 @@ void ip_vs_conn_put(struct ip_vs_conn *cp) 
void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport)

{

	if (ip_vs_conn_unhash(cp)) {

		spin_lock(&cp->lock);

		spin_lock_bh(&cp->lock);

		if (cp->flags & IP_VS_CONN_F_NO_CPORT) {

			atomic_dec(&ip_vs_conn_no_cport_cnt);

			cp->flags &= ~IP_VS_CONN_F_NO_CPORT;

			cp->cport = cport;

		}

		spin_unlock(&cp->lock);

		spin_unlock_bh(&cp->lock);



		/* hash on new dport */

		ip_vs_conn_hash(cp);
@@ -622,9 +622,9 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) 
	if (dest) {

		struct ip_vs_proto_data *pd;



		spin_lock(&cp->lock);

		spin_lock_bh(&cp->lock);

		if (cp->dest) {

			spin_unlock(&cp->lock);

			spin_unlock_bh(&cp->lock);

			rcu_read_unlock();

			return;

		}
@@ -635,7 +635,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) 
			ip_vs_unbind_app(cp);



		ip_vs_bind_dest(cp, dest);

		spin_unlock(&cp->lock);

		spin_unlock_bh(&cp->lock);



		/* Update its packet transmitter */

		cp->packet_xmit = NULL;

net/netfilter/ipvs/ip_vs_core.c

+8 −29
Original line number Diff line number Diff line
@@ -638,8 +638,11 @@ static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum) 


static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)

{

	int err = ip_defrag(skb, user);

	int err;



	local_bh_disable();

	err = ip_defrag(skb, user);

	local_bh_enable();

	if (!err)

		ip_send_check(ip_hdr(skb));
@@ -1217,13 +1220,7 @@ ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb, 
		   const struct net_device *in, const struct net_device *out,

		   int (*okfn)(struct sk_buff *))

{

	unsigned int verdict;



	/* Disable BH in LOCAL_OUT until all places are fixed */

	local_bh_disable();

	verdict = ip_vs_out(hooknum, skb, AF_INET);

	local_bh_enable();

	return verdict;

	return ip_vs_out(hooknum, skb, AF_INET);

}



#ifdef CONFIG_IP_VS_IPV6
@@ -1250,13 +1247,7 @@ ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb, 
		   const struct net_device *in, const struct net_device *out,

		   int (*okfn)(struct sk_buff *))

{

	unsigned int verdict;



	/* Disable BH in LOCAL_OUT until all places are fixed */

	local_bh_disable();

	verdict = ip_vs_out(hooknum, skb, AF_INET6);

	local_bh_enable();

	return verdict;

	return ip_vs_out(hooknum, skb, AF_INET6);

}



#endif
@@ -1714,13 +1705,7 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb, 
		     const struct net_device *in, const struct net_device *out,

		     int (*okfn)(struct sk_buff *))

{

	unsigned int verdict;



	/* Disable BH in LOCAL_OUT until all places are fixed */

	local_bh_disable();

	verdict = ip_vs_in(hooknum, skb, AF_INET);

	local_bh_enable();

	return verdict;

	return ip_vs_in(hooknum, skb, AF_INET);

}



#ifdef CONFIG_IP_VS_IPV6
@@ -1779,13 +1764,7 @@ ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb, 
		     const struct net_device *in, const struct net_device *out,

		     int (*okfn)(struct sk_buff *))

{

	unsigned int verdict;



	/* Disable BH in LOCAL_OUT until all places are fixed */

	local_bh_disable();

	verdict = ip_vs_in(hooknum, skb, AF_INET6);

	local_bh_enable();

	return verdict;

	return ip_vs_in(hooknum, skb, AF_INET6);

}



#endif

net/netfilter/ipvs/ip_vs_ftp.c

+2 −0
Original line number Diff line number Diff line
@@ -267,10 +267,12 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, 
			 * hopefully it will succeed on the retransmitted

			 * packet.

			 */

			rcu_read_lock();

			ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,

						       iph->ihl * 4,

						       start-data, end-start,

						       buf, buf_len);

			rcu_read_unlock();

			if (ret) {

				ip_vs_nfct_expect_related(skb, ct, n_cp,

							  IPPROTO_TCP, 0, 0);

net/netfilter/ipvs/ip_vs_lblc.c

+2 −2
Original line number Diff line number Diff line
@@ -527,10 +527,10 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) 
	}



	/* If we fail to create a cache entry, we'll just use the valid dest */

	spin_lock(&svc->sched_lock);

	spin_lock_bh(&svc->sched_lock);

	if (!tbl->dead)

		ip_vs_lblc_new(tbl, &iph.daddr, dest);

	spin_unlock(&svc->sched_lock);

	spin_unlock_bh(&svc->sched_lock);



out:

	IP_VS_DBG_BUF(6, "LBLC: destination IP address %s --> server %s:%d\n",