mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-05-18 13:31:45 -04:00
Code Issues Packages Projects Releases Wiki Activity
Files
3faf0ce6e499dfd32e596bcb5bca2c44d64f4cc1
linux/include/net/netns/ipv4.h
Fernando Fernandez Mancera 7da62262ec inet: add ip_local_port_step_width sysctl to improve port usage distribution 
With the current port selection algorithm, ports after a reserved port
range or long time used port are used more often than others [1]. This
causes an uneven port usage distribution. This combines with cloud
environments blocking connections between the application server and the
database server if there was a previous connection with the same source
port, leading to connectivity problems between applications on cloud
environments.

The real issue here is that these firewalls cannot cope with
standards-compliant port reuse. This is a workaround for such situations
and an improvement on the distribution of ports selected.

The proposed solution is to implement a variant of RFC 6056 Algorithm 5.
The step size is selected randomly on every connect() call ensuring it
is a coprime with respect to the size of the range of ports we want to
scan. This way, we can ensure that all ports within the range are
scanned before returning an error. To enable this algorithm, the user
must configure the new sysctl option "net.ipv4.ip_local_port_step_width".

In addition, on graphs generated we can observe that the distribution of
source ports is more even with the proposed approach. [2]

[1] https://0xffsoftware.com/port_graph_current_alg.html

[2] https://0xffsoftware.com/port_graph_random_step_alg.html

Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Link: https://patch.msgid.link/20260309023946.5473-2-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-03-10 18:59:39 -07:00

304 lines
7.8 KiB
C
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* ipv4 in net namespaces
*/
#ifndef __NETNS_IPV4_H__
#define __NETNS_IPV4_H__
#include <linux/uidgid.h>
#include <net/inet_frag.h>
#include <linux/rcupdate.h>
#include <linux/seqlock.h>
#include <linux/siphash.h>
struct ctl_table_header;
struct ipv4_devconf;
struct fib_rules_ops;
struct hlist_head;
struct fib_table;
struct sock;
struct local_ports {
u32 range; /* high << 16 | low */
bool warned;
};
struct ping_group_range {
seqlock_t lock;
kgid_t range[2];
};
struct inet_hashinfo;
struct inet_timewait_death_row {
refcount_t tw_refcount;
/* Padding to avoid false sharing, tw_refcount can be often written */
struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp;
int sysctl_max_tw_buckets;
};
struct tcp_fastopen_context;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
struct sysctl_fib_multipath_hash_seed {
u32 user_seed;
u32 mp_seed;
};
#endif
struct udp_tunnel_gro {
struct sock __rcu *sk;
struct hlist_head list;
};
struct netns_ipv4 {
/* Cacheline organization can be found documented in
* Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst.
* Please update the document when adding new fields.
*/
/* TX readonly hotpath cache lines */
__cacheline_group_begin(netns_ipv4_read_tx);
u8 sysctl_tcp_early_retrans;
u8 sysctl_tcp_tso_win_divisor;
u8 sysctl_tcp_tso_rtt_log;
u8 sysctl_tcp_autocorking;
int sysctl_tcp_min_snd_mss;
unsigned int sysctl_tcp_notsent_lowat;
int sysctl_tcp_limit_output_bytes;
int sysctl_tcp_min_rtt_wlen;
int sysctl_tcp_wmem[3];
u8 sysctl_ip_fwd_use_pmtu;
__cacheline_group_end(netns_ipv4_read_tx);
/* TXRX readonly hotpath cache lines */
__cacheline_group_begin(netns_ipv4_read_txrx);
u8 sysctl_tcp_shrink_window;
__cacheline_group_end(netns_ipv4_read_txrx);
/* RX readonly hotpath cache line */
__cacheline_group_begin(netns_ipv4_read_rx);
u8 sysctl_tcp_moderate_rcvbuf;
u8 sysctl_ip_early_demux;
u8 sysctl_tcp_early_demux;
u8 sysctl_tcp_l3mdev_accept;
/* 3 bytes hole, try to pack */
int sysctl_tcp_reordering;
int sysctl_tcp_rmem[3];
int sysctl_tcp_rcvbuf_low_rtt;
__cacheline_group_end(netns_ipv4_read_rx);
/* ICMP rate limiter hot cache line. */
__cacheline_group_begin_aligned(icmp);
atomic_t icmp_global_credit;
u32 icmp_global_stamp;
__cacheline_group_end_aligned(icmp);
struct inet_timewait_death_row tcp_death_row;
struct udp_table *udp_table;
#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
/* Not in a pernet subsys because need to be available at GRO stage */
struct udp_tunnel_gro udp_tunnel_gro[2];
#endif
#ifdef CONFIG_SYSCTL
struct ctl_table_header *forw_hdr;
struct ctl_table_header *frags_hdr;
struct ctl_table_header *ipv4_hdr;
struct ctl_table_header *route_hdr;
struct ctl_table_header *xfrm4_hdr;
#endif
struct ipv4_devconf *devconf_all;
struct ipv4_devconf *devconf_dflt;
struct ip_ra_chain __rcu *ra_chain;
struct mutex ra_mutex;
#ifdef CONFIG_IP_MULTIPLE_TABLES
struct fib_rules_ops *rules_ops;
struct fib_table __rcu *fib_main;
struct fib_table __rcu *fib_default;
unsigned int fib_rules_require_fldissect;
bool fib_has_custom_rules;
#endif
bool fib_has_custom_local_routes;
bool fib_offload_disabled;
#ifdef CONFIG_IP_ROUTE_CLASSID
atomic_t fib_num_tclassid_users;
#endif
struct hlist_head *fib_table_hash;
struct sock *fibnl;
struct hlist_head *fib_info_hash;
unsigned int fib_info_hash_bits;
unsigned int fib_info_cnt;
struct sock *mc_autojoin_sk;
struct inet_peer_base *peers;
struct fqdir *fqdir;
u8 sysctl_icmp_echo_ignore_all;
u8 sysctl_icmp_echo_enable_probe;
u8 sysctl_icmp_echo_ignore_broadcasts;
u8 sysctl_icmp_ignore_bogus_error_responses;
u8 sysctl_icmp_errors_use_inbound_ifaddr;
u8 sysctl_icmp_errors_extension_mask;
int sysctl_icmp_ratelimit;
int sysctl_icmp_ratemask;
int sysctl_icmp_msgs_per_sec;
int sysctl_icmp_msgs_burst;
u32 ip_rt_min_pmtu;
int ip_rt_mtu_expires;
int ip_rt_min_advmss;
struct local_ports ip_local_ports;
u8 sysctl_tcp_ecn;
u8 sysctl_tcp_ecn_option;
u8 sysctl_tcp_ecn_option_beacon;
u8 sysctl_tcp_ecn_fallback;
u8 sysctl_ip_default_ttl;
u8 sysctl_ip_no_pmtu_disc;
u8 sysctl_ip_fwd_update_priority;
u8 sysctl_ip_nonlocal_bind;
u8 sysctl_ip_autobind_reuse;
/* Shall we try to damage output packets if routing dev changes? */
u8 sysctl_ip_dynaddr;
u32 sysctl_ip_local_port_step_width;
#ifdef CONFIG_NET_L3_MASTER_DEV
u8 sysctl_raw_l3mdev_accept;
#endif
u8 sysctl_udp_early_demux;
u8 sysctl_nexthop_compat_mode;
u8 sysctl_fwmark_reflect;
u8 sysctl_tcp_fwmark_accept;
u8 sysctl_tcp_mtu_probing;
int sysctl_tcp_mtu_probe_floor;
int sysctl_tcp_base_mss;
int sysctl_tcp_probe_threshold;
u32 sysctl_tcp_probe_interval;
int sysctl_tcp_keepalive_time;
int sysctl_tcp_keepalive_intvl;
u8 sysctl_tcp_keepalive_probes;
u8 sysctl_tcp_syn_retries;
u8 sysctl_tcp_synack_retries;
u8 sysctl_tcp_syncookies;
u8 sysctl_tcp_migrate_req;
u8 sysctl_tcp_comp_sack_nr;
u8 sysctl_tcp_backlog_ack_defer;
u8 sysctl_tcp_pingpong_thresh;
u8 sysctl_tcp_retries1;
u8 sysctl_tcp_retries2;
u8 sysctl_tcp_orphan_retries;
u8 sysctl_tcp_tw_reuse;
unsigned int sysctl_tcp_tw_reuse_delay;
int sysctl_tcp_fin_timeout;
u8 sysctl_tcp_sack;
u8 sysctl_tcp_window_scaling;
u8 sysctl_tcp_timestamps;
int sysctl_tcp_rto_min_us;
int sysctl_tcp_rto_max_ms;
u8 sysctl_tcp_recovery;
u8 sysctl_tcp_thin_linear_timeouts;
u8 sysctl_tcp_slow_start_after_idle;
u8 sysctl_tcp_retrans_collapse;
u8 sysctl_tcp_stdurg;
u8 sysctl_tcp_rfc1337;
u8 sysctl_tcp_abort_on_overflow;
u8 sysctl_tcp_fack; /* obsolete */
int sysctl_tcp_max_reordering;
int sysctl_tcp_adv_win_scale; /* obsolete */
u8 sysctl_tcp_dsack;
u8 sysctl_tcp_app_win;
u8 sysctl_tcp_frto;
u8 sysctl_tcp_nometrics_save;
u8 sysctl_tcp_no_ssthresh_metrics_save;
u8 sysctl_tcp_workaround_signed_windows;
int sysctl_tcp_challenge_ack_limit;
u8 sysctl_tcp_min_tso_segs;
u8 sysctl_tcp_reflect_tos;
int sysctl_tcp_invalid_ratelimit;
int sysctl_tcp_pacing_ss_ratio;
int sysctl_tcp_pacing_ca_ratio;
unsigned int sysctl_tcp_child_ehash_entries;
int sysctl_tcp_comp_sack_rtt_percent;
unsigned long sysctl_tcp_comp_sack_delay_ns;
unsigned long sysctl_tcp_comp_sack_slack_ns;
int sysctl_max_syn_backlog;
int sysctl_tcp_fastopen;
const struct tcp_congestion_ops __rcu *tcp_congestion_control;
struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
unsigned int sysctl_tcp_fastopen_blackhole_timeout;
atomic_t tfo_active_disable_times;
unsigned long tfo_active_disable_stamp;
u32 tcp_challenge_timestamp;
u32 tcp_challenge_count;
u8 sysctl_tcp_plb_enabled;
u8 sysctl_tcp_plb_idle_rehash_rounds;
u8 sysctl_tcp_plb_rehash_rounds;
u8 sysctl_tcp_plb_suspend_rto_sec;
int sysctl_tcp_plb_cong_thresh;
int sysctl_udp_wmem_min;
int sysctl_udp_rmem_min;
u8 sysctl_fib_notify_on_flag_change;
u8 sysctl_tcp_syn_linear_timeouts;
#ifdef CONFIG_NET_L3_MASTER_DEV
u8 sysctl_udp_l3mdev_accept;
#endif
u8 sysctl_igmp_llm_reports;
int sysctl_igmp_max_memberships;
int sysctl_igmp_max_msf;
int sysctl_igmp_qrv;
struct ping_group_range ping_group_range;
u16 ping_port_rover;
atomic_t dev_addr_genid;
unsigned int sysctl_udp_child_hash_entries;
#ifdef CONFIG_SYSCTL
unsigned long *sysctl_local_reserved_ports;
int sysctl_ip_prot_sock;
#endif
#ifdef CONFIG_IP_MROUTE
#ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES
struct mr_table *mrt;
#else
struct list_head mr_tables;
struct fib_rules_ops *mr_rules_ops;
#endif
struct fib_notifier_ops *ipmr_notifier_ops;
atomic_t ipmr_seq;
struct mutex mfc_mutex;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
struct sysctl_fib_multipath_hash_seed sysctl_fib_multipath_hash_seed;
u32 sysctl_fib_multipath_hash_fields;
u8 sysctl_fib_multipath_use_neigh;
u8 sysctl_fib_multipath_hash_policy;
#endif
struct fib_notifier_ops *notifier_ops;
unsigned int fib_seq; /* writes protected by rtnl_mutex */
atomic_t rt_genid;
siphash_key_t ip_id_key;
struct hlist_head *inet_addr_lst;
struct delayed_work addr_chk_work;
};
#endif
Reference in New Issue View Git Blame Copy Permalink