Commit d9f28735 authored by David Laight's avatar David Laight Committed by Jakub Kicinski
Browse files

Use READ/WRITE_ONCE() for IP local_port_range. 



Commit 227b60f5 added a seqlock to ensure that the low and high
port numbers were always updated together.
This is overkill because the two 16bit port numbers can be held in
a u32 and read/written in a single instruction.

More recently 91d0b78c added support for finer per-socket limits.
The user-supplied value is 'high << 16 | low' but they are held
separately and the socket options protected by the socket lock.

Use a u32 containing 'high << 16 | low' for both the 'net' and 'sk'
fields and use READ_ONCE()/WRITE_ONCE() to ensure both values are
always updated together.

Change (the now trival) inet_get_local_port_range() to a static inline
to optimise the calling code.
(In particular avoiding returning integers by reference.)

Signed-off-by: default avatarDavid Laight <david.laight@aculab.com>
Reviewed-by: default avatarEric Dumazet <edumazet@google.com>
Reviewed-by: default avatarDavid Ahern <dsahern@kernel.org>
Acked-by: default avatarMat Martineau <martineau@kernel.org>
Reviewed-by: default avatarKuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/4e505d4198e946a8be03fb1b4c3072b0@AcuMS.aculab.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 36b0bdb6

include/net/inet_sock.h

+1 −4
Original line number Diff line number Diff line
@@ -234,10 +234,7 @@ struct inet_sock { 
	int			uc_index;

	int			mc_index;

	__be32			mc_addr;

	struct {

		__u16 lo;

		__u16 hi;

	}			local_port_range;

	u32			local_port_range;	/* high << 16 | low */



	struct ip_mc_socklist __rcu	*mc_list;

	struct inet_cork_full	cork;

include/net/ip.h

+7 −1
Original line number Diff line number Diff line
@@ -349,7 +349,13 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o 
	} \

}



void inet_get_local_port_range(const struct net *net, int *low, int *high);

static inline void inet_get_local_port_range(const struct net *net, int *low, int *high)

{

	u32 range = READ_ONCE(net->ipv4.ip_local_ports.range);



	*low = range & 0xffff;

	*high = range >> 16;

}

void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);



#ifdef CONFIG_SYSCTL

include/net/netns/ipv4.h

+1 −2
Original line number Diff line number Diff line
@@ -19,8 +19,7 @@ struct hlist_head; 
struct fib_table;

struct sock;

struct local_ports {

	seqlock_t	lock;

	int		range[2];

	u32		range;	/* high << 16 | low */

	bool		warned;

};

net/ipv4/af_inet.c

+1 −3
Original line number Diff line number Diff line
@@ -1847,9 +1847,7 @@ static __net_init int inet_init_net(struct net *net) 
	/*

	 * Set defaults for local port range

	 */

	seqlock_init(&net->ipv4.ip_local_ports.lock);

	net->ipv4.ip_local_ports.range[0] =  32768;

	net->ipv4.ip_local_ports.range[1] =  60999;

	net->ipv4.ip_local_ports.range = 60999u << 16 | 32768u;



	seqlock_init(&net->ipv4.ping_group_range.lock);

	/*

net/ipv4/inet_connection_sock.c

+10 −19
Original line number Diff line number Diff line
@@ -117,34 +117,25 @@ bool inet_rcv_saddr_any(const struct sock *sk) 
	return !sk->sk_rcv_saddr;

}



void inet_get_local_port_range(const struct net *net, int *low, int *high)

{

	unsigned int seq;



	do {

		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);



		*low = net->ipv4.ip_local_ports.range[0];

		*high = net->ipv4.ip_local_ports.range[1];

	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));

}

EXPORT_SYMBOL(inet_get_local_port_range);



void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)

{

	const struct inet_sock *inet = inet_sk(sk);

	const struct net *net = sock_net(sk);

	int lo, hi, sk_lo, sk_hi;

	u32 sk_range;



	inet_get_local_port_range(net, &lo, &hi);



	sk_lo = inet->local_port_range.lo;

	sk_hi = inet->local_port_range.hi;

	sk_range = READ_ONCE(inet->local_port_range);

	if (unlikely(sk_range)) {

		sk_lo = sk_range & 0xffff;

		sk_hi = sk_range >> 16;



	if (unlikely(lo <= sk_lo && sk_lo <= hi))

		if (lo <= sk_lo && sk_lo <= hi)

			lo = sk_lo;

	if (unlikely(lo <= sk_hi && sk_hi <= hi))

		if (lo <= sk_hi && sk_hi <= hi)

			hi = sk_hi;

	}



	*low = lo;

	*high = hi;