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

Commit 227b60f5 authored by Stephen Hemminger's avatar Stephen Hemminger Committed by David S. Miller
Browse files

[INET]: local port range robustness 



Expansion of original idea from Denis V. Lunev <den@openvz.org>

Add robustness and locking to the local_port_range sysctl.
1. Enforce that low < high when setting.
2. Use seqlock to ensure atomic update.

The locking might seem like overkill, but there are
cases where sysadmin might want to change value in the
middle of a DoS attack.

Signed-off-by: default avatarStephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 06393009

drivers/infiniband/core/cma.c

+12 −10
Original line number Diff line number Diff line
@@ -1866,13 +1866,14 @@ static int cma_alloc_port(struct idr *ps, struct rdma_id_private *id_priv, 
static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)

{

	struct rdma_bind_list *bind_list;

	int port, ret;

	int port, ret, low, high;



	bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);

	if (!bind_list)

		return -ENOMEM;



retry:

	/* FIXME: add proper port randomization per like inet_csk_get_port */

	do {

		ret = idr_get_new_above(ps, bind_list, next_port, &port);

	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
@@ -1880,18 +1881,19 @@ static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv) 
	if (ret)

		goto err1;



	if (port > sysctl_local_port_range[1]) {

		if (next_port != sysctl_local_port_range[0]) {

	inet_get_local_port_range(&low, &high);

	if (port > high) {

		if (next_port != low) {

			idr_remove(ps, port);

			next_port = sysctl_local_port_range[0];

			next_port = low;

			goto retry;

		}

		ret = -EADDRNOTAVAIL;

		goto err2;

	}



	if (port == sysctl_local_port_range[1])

		next_port = sysctl_local_port_range[0];

	if (port == high)

		next_port = low;

	else

		next_port = port + 1;
@@ -2769,12 +2771,12 @@ static void cma_remove_one(struct ib_device *device) 


static int cma_init(void)

{

	int ret;

	int ret, low, high;



	get_random_bytes(&next_port, sizeof next_port);

	next_port = ((unsigned int) next_port %

		    (sysctl_local_port_range[1] - sysctl_local_port_range[0])) +

		    sysctl_local_port_range[0];

	inet_get_local_port_range(&low, &high);

	next_port = ((unsigned int) next_port % (high - low)) + low;



	cma_wq = create_singlethread_workqueue("rdma_cm");

	if (!cma_wq)

		return -ENOMEM;

include/net/ip.h

+2 −1
Original line number Diff line number Diff line
@@ -171,7 +171,8 @@ extern unsigned long snmp_fold_field(void *mib[], int offt); 
extern int snmp_mib_init(void *ptr[2], size_t mibsize, size_t mibalign);

extern void snmp_mib_free(void *ptr[2]);



extern int sysctl_local_port_range[2];

extern void inet_get_local_port_range(int *low, int *high);



extern int sysctl_ip_default_ttl;

extern int sysctl_ip_nonlocal_bind;

net/ipv4/inet_connection_sock.c

+18 −4
Original line number Diff line number Diff line
@@ -33,6 +33,19 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg); 
 * This array holds the first and last local port number.

 */

int sysctl_local_port_range[2] = { 32768, 61000 };

DEFINE_SEQLOCK(sysctl_port_range_lock);



void inet_get_local_port_range(int *low, int *high)

{

	unsigned seq;

	do {

		seq = read_seqbegin(&sysctl_port_range_lock);



		*low = sysctl_local_port_range[0];

		*high = sysctl_local_port_range[1];

	} while (read_seqretry(&sysctl_port_range_lock, seq));

}

EXPORT_SYMBOL(inet_get_local_port_range);



int inet_csk_bind_conflict(const struct sock *sk,

			   const struct inet_bind_bucket *tb)
@@ -77,10 +90,11 @@ int inet_csk_get_port(struct inet_hashinfo *hashinfo, 


	local_bh_disable();

	if (!snum) {

		int low = sysctl_local_port_range[0];

		int high = sysctl_local_port_range[1];

		int remaining = (high - low) + 1;

		int rover = net_random() % (high - low) + low;

		int remaining, rover, low, high;



		inet_get_local_port_range(&low, &high);

		remaining = high - low;

		rover = net_random() % remaining + low;



		do {

			head = &hashinfo->bhash[inet_bhashfn(rover, hashinfo->bhash_size)];

net/ipv4/inet_hashtables.c

+6 −7
Original line number Diff line number Diff line
@@ -279,19 +279,18 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row, 
	int ret;



	if (!snum) {

		int low = sysctl_local_port_range[0];

		int high = sysctl_local_port_range[1];

		int range = high - low;

		int i;

		int port;

		int i, remaining, low, high, port;

		static u32 hint;

		u32 offset = hint + inet_sk_port_offset(sk);

		struct hlist_node *node;

		struct inet_timewait_sock *tw = NULL;



		inet_get_local_port_range(&low, &high);

		remaining = high - low;



		local_bh_disable();

		for (i = 1; i <= range; i++) {

			port = low + (i + offset) % range;

		for (i = 1; i <= remaining; i++) {

			port = low + (i + offset) % remaining;

			head = &hinfo->bhash[inet_bhashfn(port, hinfo->bhash_size)];

			spin_lock(&head->lock);

net/ipv4/sysctl_net_ipv4.c

+71 −4
Original line number Diff line number Diff line
@@ -12,6 +12,7 @@ 
#include <linux/sysctl.h>

#include <linux/igmp.h>

#include <linux/inetdevice.h>

#include <linux/seqlock.h>

#include <net/snmp.h>

#include <net/icmp.h>

#include <net/ip.h>
@@ -89,6 +90,74 @@ static int ipv4_sysctl_forward_strategy(ctl_table *table, 
	return 1;

}



extern seqlock_t sysctl_port_range_lock;

extern int sysctl_local_port_range[2];



/* Update system visible IP port range */

static void set_local_port_range(int range[2])

{

	write_seqlock(&sysctl_port_range_lock);

	sysctl_local_port_range[0] = range[0];

	sysctl_local_port_range[1] = range[1];

	write_sequnlock(&sysctl_port_range_lock);

}



/* Validate changes from /proc interface. */

static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp,

				 void __user *buffer,

				 size_t *lenp, loff_t *ppos)

{

	int ret;

	int range[2] = { sysctl_local_port_range[0],

			 sysctl_local_port_range[1] };

	ctl_table tmp = {

		.data = &range,

		.maxlen = sizeof(range),

		.mode = table->mode,

		.extra1 = &ip_local_port_range_min,

		.extra2 = &ip_local_port_range_max,

	};



	ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos);



	if (write && ret == 0) {

		if (range[1] <= range[0])

			ret = -EINVAL;

		else

			set_local_port_range(range);

	}



	return ret;

}



/* Validate changes from sysctl interface. */

static int ipv4_sysctl_local_port_range(ctl_table *table, int __user *name,

					 int nlen, void __user *oldval,

					 size_t __user *oldlenp,

					void __user *newval, size_t newlen)

{

	int ret;

	int range[2] = { sysctl_local_port_range[0],

			 sysctl_local_port_range[1] };

	ctl_table tmp = {

		.data = &range,

		.maxlen = sizeof(range),

		.mode = table->mode,

		.extra1 = &ip_local_port_range_min,

		.extra2 = &ip_local_port_range_max,

	};



	ret = sysctl_intvec(&tmp, name, nlen, oldval, oldlenp, newval, newlen);

	if (ret == 0 && newval && newlen) {

		if (range[1] <= range[0])

			ret = -EINVAL;

		else

			set_local_port_range(range);

	}

	return ret;

}





static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * filp,

				       void __user *buffer, size_t *lenp, loff_t *ppos)

{
@@ -427,10 +496,8 @@ ctl_table ipv4_table[] = { 
		.data		= &sysctl_local_port_range,

		.maxlen		= sizeof(sysctl_local_port_range),

		.mode		= 0644,

		.proc_handler	= &proc_dointvec_minmax,

		.strategy	= &sysctl_intvec,

		.extra1		= ip_local_port_range_min,

		.extra2		= ip_local_port_range_max

		.proc_handler	= &ipv4_local_port_range,

		.strategy	= &ipv4_sysctl_local_port_range,

	},

	{

		.ctl_name	= NET_IPV4_ICMP_ECHO_IGNORE_ALL,