linux/include/net/ip_fib.h

558 lines
14 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the Forwarding Information Base.
*
* Authors: A.N.Kuznetsov, <kuznet@ms2.inr.ac.ru>
*/
#ifndef _NET_IP_FIB_H
#define _NET_IP_FIB_H
#include <net/flow.h>
#include <linux/seq_file.h>
#include <linux/rcupdate.h>
#include <net/fib_notifier.h>
#include <net/fib_rules.h>
#include <net/inetpeer.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/refcount.h>
struct fib_config {
u8 fc_dst_len;
u8 fc_tos;
u8 fc_protocol;
u8 fc_scope;
u8 fc_type;
u8 fc_gw_family;
/* 2 bytes unused */
u32 fc_table;
__be32 fc_dst;
union {
__be32 fc_gw4;
struct in6_addr fc_gw6;
};
int fc_oif;
u32 fc_flags;
u32 fc_priority;
__be32 fc_prefsrc;
u32 fc_nh_id;
struct nlattr *fc_mx;
struct rtnexthop *fc_mp;
int fc_mx_len;
int fc_mp_len;
u32 fc_flow;
u32 fc_nlflags;
struct nl_info fc_nlinfo;
struct nlattr *fc_encap;
u16 fc_encap_type;
};
struct fib_info;
struct rtable;
struct fib_nh_exception {
struct fib_nh_exception __rcu *fnhe_next;
int fnhe_genid;
__be32 fnhe_daddr;
u32 fnhe_pmtu;
bool fnhe_mtu_locked;
__be32 fnhe_gw;
unsigned long fnhe_expires;
struct rtable __rcu *fnhe_rth_input;
struct rtable __rcu *fnhe_rth_output;
unsigned long fnhe_stamp;
struct rcu_head rcu;
};
struct fnhe_hash_bucket {
struct fib_nh_exception __rcu *chain;
};
#define FNHE_HASH_SHIFT 11
#define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT)
#define FNHE_RECLAIM_DEPTH 5
struct fib_nh_common {
struct net_device *nhc_dev;
int nhc_oif;
unsigned char nhc_scope;
u8 nhc_family;
u8 nhc_gw_family;
unsigned char nhc_flags;
struct lwtunnel_state *nhc_lwtstate;
union {
__be32 ipv4;
struct in6_addr ipv6;
} nhc_gw;
int nhc_weight;
atomic_t nhc_upper_bound;
/* v4 specific, but allows fib6_nh with v4 routes */
struct rtable __rcu * __percpu *nhc_pcpu_rth_output;
struct rtable __rcu *nhc_rth_input;
struct fnhe_hash_bucket __rcu *nhc_exceptions;
};
struct fib_nh {
struct fib_nh_common nh_common;
struct hlist_node nh_hash;
struct fib_info *nh_parent;
#ifdef CONFIG_IP_ROUTE_CLASSID
__u32 nh_tclassid;
#endif
__be32 nh_saddr;
int nh_saddr_genid;
#define fib_nh_family nh_common.nhc_family
#define fib_nh_dev nh_common.nhc_dev
#define fib_nh_oif nh_common.nhc_oif
#define fib_nh_flags nh_common.nhc_flags
#define fib_nh_lws nh_common.nhc_lwtstate
#define fib_nh_scope nh_common.nhc_scope
#define fib_nh_gw_family nh_common.nhc_gw_family
#define fib_nh_gw4 nh_common.nhc_gw.ipv4
#define fib_nh_gw6 nh_common.nhc_gw.ipv6
#define fib_nh_weight nh_common.nhc_weight
#define fib_nh_upper_bound nh_common.nhc_upper_bound
};
/*
* This structure contains data shared by many of routes.
*/
ipv4: Plumb support for nexthop object in a fib_info Add 'struct nexthop' and nh_list list_head to fib_info. nh_list is the fib_info side of the nexthop <-> fib_info relationship. Add fi_list list_head to 'struct nexthop' to track fib_info entries using a nexthop instance. Add __remove_nexthop_fib and add it to __remove_nexthop to walk the new list_head and mark those fib entries as dead when the nexthop is deleted. Add a few nexthop helpers for use when a nexthop is added to fib_info: - nexthop_cmp to determine if 2 nexthops are the same - nexthop_path_fib_result to select a path for a multipath 'struct nexthop' - nexthop_fib_nhc to select a specific fib_nh_common within a multipath 'struct nexthop' Update existing fib_info_nhc to use nexthop_fib_nhc if a fib_info uses a 'struct nexthop', and mark fib_info_nh as only used for the non-nexthop case. Update the fib_info functions to check for fi->nh and take a different path as needed: - free_fib_info_rcu - put the nexthop object reference - fib_release_info - remove the fib_info from the nexthop's fi_list - nh_comp - use nexthop_cmp when either fib_info references a nexthop object - fib_info_hashfn - use the nexthop id for the hashing vs the oif of each fib_nh in a fib_info - fib_nlmsg_size - add space for the RTA_NH_ID attribute - fib_create_info - verify nexthop reference can be taken, verify nexthop spec is valid for fib entry, and add fib_info to fi_list for a nexthop - fib_select_multipath - use the new nexthop_path_fib_result to select a path when nexthop objects are used - fib_table_lookup - if the 'struct nexthop' is a blackhole nexthop, treat it the same as a fib entry using 'blackhole' The bulk of the changes are in fib_semantics.c and most of that is moving the existing change_nexthops into an else branch. Update the nexthop code to walk fi_list on a nexthop deleted to remove fib entries referencing it. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-04 03:19:51 +00:00
struct nexthop;
struct fib_info {
struct hlist_node fib_hash;
struct hlist_node fib_lhash;
ipv4: Plumb support for nexthop object in a fib_info Add 'struct nexthop' and nh_list list_head to fib_info. nh_list is the fib_info side of the nexthop <-> fib_info relationship. Add fi_list list_head to 'struct nexthop' to track fib_info entries using a nexthop instance. Add __remove_nexthop_fib and add it to __remove_nexthop to walk the new list_head and mark those fib entries as dead when the nexthop is deleted. Add a few nexthop helpers for use when a nexthop is added to fib_info: - nexthop_cmp to determine if 2 nexthops are the same - nexthop_path_fib_result to select a path for a multipath 'struct nexthop' - nexthop_fib_nhc to select a specific fib_nh_common within a multipath 'struct nexthop' Update existing fib_info_nhc to use nexthop_fib_nhc if a fib_info uses a 'struct nexthop', and mark fib_info_nh as only used for the non-nexthop case. Update the fib_info functions to check for fi->nh and take a different path as needed: - free_fib_info_rcu - put the nexthop object reference - fib_release_info - remove the fib_info from the nexthop's fi_list - nh_comp - use nexthop_cmp when either fib_info references a nexthop object - fib_info_hashfn - use the nexthop id for the hashing vs the oif of each fib_nh in a fib_info - fib_nlmsg_size - add space for the RTA_NH_ID attribute - fib_create_info - verify nexthop reference can be taken, verify nexthop spec is valid for fib entry, and add fib_info to fi_list for a nexthop - fib_select_multipath - use the new nexthop_path_fib_result to select a path when nexthop objects are used - fib_table_lookup - if the 'struct nexthop' is a blackhole nexthop, treat it the same as a fib entry using 'blackhole' The bulk of the changes are in fib_semantics.c and most of that is moving the existing change_nexthops into an else branch. Update the nexthop code to walk fi_list on a nexthop deleted to remove fib entries referencing it. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-04 03:19:51 +00:00
struct list_head nh_list;
struct net *fib_net;
int fib_treeref;
refcount_t fib_clntref;
unsigned int fib_flags;
unsigned char fib_dead;
unsigned char fib_protocol;
unsigned char fib_scope;
ipv4: add a fib_type to fib_info commit d2d68ba9fe8 (ipv4: Cache input routes in fib_info nexthops.) introduced a regression for forwarding. This was hard to reproduce but the symptom was that packets were delivered to local host instead of being forwarded. David suggested to add fib_type to fib_info so that we dont inadvertently share same fib_info for different purposes. With help from Julian Anastasov who provided very helpful hints, reproduced here : <quote> Can it be a problem related to fib_info reuse from different routes. For example, when local IP address is created for subnet we have: broadcast 192.168.0.255 dev DEV proto kernel scope link src 192.168.0.1 192.168.0.0/24 dev DEV proto kernel scope link src 192.168.0.1 local 192.168.0.1 dev DEV proto kernel scope host src 192.168.0.1 The "dev DEV proto kernel scope link src 192.168.0.1" is a reused fib_info structure where we put cached routes. The result can be same fib_info for 192.168.0.255 and 192.168.0.0/24. RTN_BROADCAST is cached only for input routes. Incoming broadcast to 192.168.0.255 can be cached and can cause problems for traffic forwarded to 192.168.0.0/24. So, this patch should solve the problem because it separates the broadcast from unicast traffic. And the ip_route_input_slow caching will work for local and broadcast input routes (above routes 1 and 3) just because they differ in scope and use different fib_info. </quote> Many thanks to Chris Clayton for his patience and help. Reported-by: Chris Clayton <chris2553@googlemail.com> Bisected-by: Chris Clayton <chris2553@googlemail.com> Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Tested-by: Chris Clayton <chris2553@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-04 01:25:26 +00:00
unsigned char fib_type;
__be32 fib_prefsrc;
u32 fib_tb_id;
u32 fib_priority;
struct dst_metrics *fib_metrics;
#define fib_mtu fib_metrics->metrics[RTAX_MTU-1]
#define fib_window fib_metrics->metrics[RTAX_WINDOW-1]
#define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
int fib_nhs;
bool fib_nh_is_v6;
bool nh_updated;
ipv4: Plumb support for nexthop object in a fib_info Add 'struct nexthop' and nh_list list_head to fib_info. nh_list is the fib_info side of the nexthop <-> fib_info relationship. Add fi_list list_head to 'struct nexthop' to track fib_info entries using a nexthop instance. Add __remove_nexthop_fib and add it to __remove_nexthop to walk the new list_head and mark those fib entries as dead when the nexthop is deleted. Add a few nexthop helpers for use when a nexthop is added to fib_info: - nexthop_cmp to determine if 2 nexthops are the same - nexthop_path_fib_result to select a path for a multipath 'struct nexthop' - nexthop_fib_nhc to select a specific fib_nh_common within a multipath 'struct nexthop' Update existing fib_info_nhc to use nexthop_fib_nhc if a fib_info uses a 'struct nexthop', and mark fib_info_nh as only used for the non-nexthop case. Update the fib_info functions to check for fi->nh and take a different path as needed: - free_fib_info_rcu - put the nexthop object reference - fib_release_info - remove the fib_info from the nexthop's fi_list - nh_comp - use nexthop_cmp when either fib_info references a nexthop object - fib_info_hashfn - use the nexthop id for the hashing vs the oif of each fib_nh in a fib_info - fib_nlmsg_size - add space for the RTA_NH_ID attribute - fib_create_info - verify nexthop reference can be taken, verify nexthop spec is valid for fib entry, and add fib_info to fi_list for a nexthop - fib_select_multipath - use the new nexthop_path_fib_result to select a path when nexthop objects are used - fib_table_lookup - if the 'struct nexthop' is a blackhole nexthop, treat it the same as a fib entry using 'blackhole' The bulk of the changes are in fib_semantics.c and most of that is moving the existing change_nexthops into an else branch. Update the nexthop code to walk fi_list on a nexthop deleted to remove fib entries referencing it. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-04 03:19:51 +00:00
struct nexthop *nh;
fib: RCU conversion of fib_lookup() fib_lookup() converted to be called in RCU protected context, no reference taken and released on a contended cache line (fib_clntref) fib_table_lookup() and fib_semantic_match() get an additional parameter. struct fib_info gets an rcu_head field, and is freed after an rcu grace period. Stress test : (Sending 160.000.000 UDP frames on same neighbour, IP route cache disabled, dual E5540 @2.53GHz, 32bit kernel, FIB_HASH) (about same results for FIB_TRIE) Before patch : real 1m31.199s user 0m13.761s sys 23m24.780s After patch: real 1m5.375s user 0m14.997s sys 15m50.115s Before patch Profile : 13044.00 15.4% __ip_route_output_key vmlinux 8438.00 10.0% dst_destroy vmlinux 5983.00 7.1% fib_semantic_match vmlinux 5410.00 6.4% fib_rules_lookup vmlinux 4803.00 5.7% neigh_lookup vmlinux 4420.00 5.2% _raw_spin_lock vmlinux 3883.00 4.6% rt_set_nexthop vmlinux 3261.00 3.9% _raw_read_lock vmlinux 2794.00 3.3% fib_table_lookup vmlinux 2374.00 2.8% neigh_resolve_output vmlinux 2153.00 2.5% dst_alloc vmlinux 1502.00 1.8% _raw_read_lock_bh vmlinux 1484.00 1.8% kmem_cache_alloc vmlinux 1407.00 1.7% eth_header vmlinux 1406.00 1.7% ipv4_dst_destroy vmlinux 1298.00 1.5% __copy_from_user_ll vmlinux 1174.00 1.4% dev_queue_xmit vmlinux 1000.00 1.2% ip_output vmlinux After patch Profile : 13712.00 15.8% dst_destroy vmlinux 8548.00 9.9% __ip_route_output_key vmlinux 7017.00 8.1% neigh_lookup vmlinux 4554.00 5.3% fib_semantic_match vmlinux 4067.00 4.7% _raw_read_lock vmlinux 3491.00 4.0% dst_alloc vmlinux 3186.00 3.7% neigh_resolve_output vmlinux 3103.00 3.6% fib_table_lookup vmlinux 2098.00 2.4% _raw_read_lock_bh vmlinux 2081.00 2.4% kmem_cache_alloc vmlinux 2013.00 2.3% _raw_spin_lock vmlinux 1763.00 2.0% __copy_from_user_ll vmlinux 1763.00 2.0% ip_output vmlinux 1761.00 2.0% ipv4_dst_destroy vmlinux 1631.00 1.9% eth_header vmlinux 1440.00 1.7% _raw_read_unlock_bh vmlinux Reference results, if IP route cache is enabled : real 0m29.718s user 0m10.845s sys 7m37.341s 25213.00 29.5% __ip_route_output_key vmlinux 9011.00 10.5% dst_release vmlinux 4817.00 5.6% ip_push_pending_frames vmlinux 4232.00 5.0% ip_finish_output vmlinux 3940.00 4.6% udp_sendmsg vmlinux 3730.00 4.4% __copy_from_user_ll vmlinux 3716.00 4.4% ip_route_output_flow vmlinux 2451.00 2.9% __xfrm_lookup vmlinux 2221.00 2.6% ip_append_data vmlinux 1718.00 2.0% _raw_spin_lock_bh vmlinux 1655.00 1.9% __alloc_skb vmlinux 1572.00 1.8% sock_wfree vmlinux 1345.00 1.6% kfree vmlinux Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-05 10:41:36 +00:00
struct rcu_head rcu;
struct fib_nh fib_nh[];
};
#ifdef CONFIG_IP_MULTIPLE_TABLES
struct fib_rule;
#endif
struct fib_table;
struct fib_result {
__be32 prefix;
unsigned char prefixlen;
unsigned char nh_sel;
unsigned char type;
unsigned char scope;
u32 tclassid;
struct fib_nh_common *nhc;
struct fib_info *fi;
struct fib_table *table;
struct hlist_head *fa_head;
};
struct fib_result_nl {
__be32 fl_addr; /* To be looked up*/
u32 fl_mark;
unsigned char fl_tos;
unsigned char fl_scope;
unsigned char tb_id_in;
unsigned char tb_id; /* Results */
unsigned char prefixlen;
unsigned char nh_sel;
unsigned char type;
unsigned char scope;
int err;
};
#ifdef CONFIG_IP_MULTIPLE_TABLES
#define FIB_TABLE_HASHSZ 256
#else
#define FIB_TABLE_HASHSZ 2
#endif
__be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
unsigned char scope);
__be32 fib_result_prefsrc(struct net *net, struct fib_result *res);
#define FIB_RES_NHC(res) ((res).nhc)
#define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev)
#define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif)
struct fib_rt_info {
struct fib_info *fi;
u32 tb_id;
__be32 dst;
int dst_len;
u8 tos;
u8 type;
ipv4: Add "offload" and "trap" indications to routes When performing L3 offload, routes and nexthops are usually programmed into two different tables in the underlying device. Therefore, the fact that a nexthop resides in hardware does not necessarily mean that all the associated routes also reside in hardware and vice-versa. While the kernel can signal to user space the presence of a nexthop in hardware (via 'RTNH_F_OFFLOAD'), it does not have a corresponding flag for routes. In addition, the fact that a route resides in hardware does not necessarily mean that the traffic is offloaded. For example, unreachable routes (i.e., 'RTN_UNREACHABLE') are programmed to trap packets to the CPU so that the kernel will be able to generate the appropriate ICMP error packet. This patch adds an "offload" and "trap" indications to IPv4 routes, so that users will have better visibility into the offload process. 'struct fib_alias' is extended with two new fields that indicate if the route resides in hardware or not and if it is offloading traffic from the kernel or trapping packets to it. Note that the new fields are added in the 6 bytes hole and therefore the struct still fits in a single cache line [1]. Capable drivers are expected to invoke fib_alias_hw_flags_set() with the route's key in order to set the flags. The indications are dumped to user space via a new flags (i.e., 'RTM_F_OFFLOAD' and 'RTM_F_TRAP') in the 'rtm_flags' field in the ancillary header. v2: * Make use of 'struct fib_rt_info' in fib_alias_hw_flags_set() [1] struct fib_alias { struct hlist_node fa_list; /* 0 16 */ struct fib_info * fa_info; /* 16 8 */ u8 fa_tos; /* 24 1 */ u8 fa_type; /* 25 1 */ u8 fa_state; /* 26 1 */ u8 fa_slen; /* 27 1 */ u32 tb_id; /* 28 4 */ s16 fa_default; /* 32 2 */ u8 offload:1; /* 34: 0 1 */ u8 trap:1; /* 34: 1 1 */ u8 unused:6; /* 34: 2 1 */ /* XXX 5 bytes hole, try to pack */ struct callback_head rcu __attribute__((__aligned__(8))); /* 40 16 */ /* size: 56, cachelines: 1, members: 12 */ /* sum members: 50, holes: 1, sum holes: 5 */ /* sum bitfield members: 8 bits (1 bytes) */ /* forced alignments: 1, forced holes: 1, sum forced holes: 5 */ /* last cacheline: 56 bytes */ } __attribute__((__aligned__(8))); Signed-off-by: Ido Schimmel <idosch@mellanox.com> Reviewed-by: David Ahern <dsahern@gmail.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-01-14 11:23:11 +00:00
u8 offload:1,
trap:1,
unused:6;
};
struct fib_entry_notifier_info {
struct fib_notifier_info info; /* must be first */
u32 dst;
int dst_len;
struct fib_info *fi;
u8 tos;
u8 type;
u32 tb_id;
};
struct fib_nh_notifier_info {
struct fib_notifier_info info; /* must be first */
struct fib_nh *fib_nh;
};
int call_fib4_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_notifier_info *info);
int call_fib4_notifiers(struct net *net, enum fib_event_type event_type,
struct fib_notifier_info *info);
int __net_init fib4_notifier_init(struct net *net);
void __net_exit fib4_notifier_exit(struct net *net);
void fib_info_notify_update(struct net *net, struct nl_info *info);
int fib_notify(struct net *net, struct notifier_block *nb,
struct netlink_ext_ack *extack);
struct fib_table {
struct hlist_node tb_hlist;
u32 tb_id;
int tb_num_default;
struct rcu_head rcu;
unsigned long *tb_data;
unsigned long __data[];
};
struct fib_dump_filter {
u32 table_id;
/* filter_set is an optimization that an entry is set */
bool filter_set;
fib_frontend, ip6_fib: Select routes or exceptions dump from RTM_F_CLONED The following patches add back the ability to dump IPv4 and IPv6 exception routes, and we need to allow selection of regular routes or exceptions. Use RTM_F_CLONED as filter to decide whether to dump routes or exceptions: iproute2 passes it in dump requests (except for IPv6 cache flush requests, this will be fixed in iproute2) and this used to work as long as exceptions were stored directly in the FIB, for both IPv4 and IPv6. Caveat: if strict checking is not requested (that is, if the dump request doesn't go through ip_valid_fib_dump_req()), we can't filter on protocol, tables or route types. In this case, filtering on RTM_F_CLONED would be inconsistent: we would fix 'ip route list cache' by returning exception routes and at the same time introduce another bug in case another selector is present, e.g. on 'ip route list cache table main' we would return all exception routes, without filtering on tables. Keep this consistent by applying no filters at all, and dumping both routes and exceptions, if strict checking is not requested. iproute2 currently filters results anyway, and no unwanted results will be presented to the user. The kernel will just dump more data than needed. v7: No changes v6: Rebase onto net-next, no changes v5: New patch: add dump_routes and dump_exceptions flags in filter and simply clear the unwanted one if strict checking is enabled, don't ignore NLM_F_MATCH and don't set filter_set if NLM_F_MATCH is set. Skip filtering altogether if no strict checking is requested: selecting routes or exceptions only would be inconsistent with the fact we can't filter on tables. Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-21 15:45:20 +00:00
bool dump_routes;
bool dump_exceptions;
unsigned char protocol;
unsigned char rt_type;
unsigned int flags;
struct net_device *dev;
};
int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
struct fib_result *res, int fib_flags);
int fib_table_insert(struct net *, struct fib_table *, struct fib_config *,
struct netlink_ext_ack *extack);
int fib_table_delete(struct net *, struct fib_table *, struct fib_config *,
struct netlink_ext_ack *extack);
int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
struct netlink_callback *cb, struct fib_dump_filter *filter);
net: ipv4: Fix memory leak in network namespace dismantle IPv4 routing tables are flushed in two cases: 1. In response to events in the netdev and inetaddr notification chains 2. When a network namespace is being dismantled In both cases only routes associated with a dead nexthop group are flushed. However, a nexthop group will only be marked as dead in case it is populated with actual nexthops using a nexthop device. This is not the case when the route in question is an error route (e.g., 'blackhole', 'unreachable'). Therefore, when a network namespace is being dismantled such routes are not flushed and leaked [1]. To reproduce: # ip netns add blue # ip -n blue route add unreachable 192.0.2.0/24 # ip netns del blue Fix this by not skipping error routes that are not marked with RTNH_F_DEAD when flushing the routing tables. To prevent the flushing of such routes in case #1, add a parameter to fib_table_flush() that indicates if the table is flushed as part of namespace dismantle or not. Note that this problem does not exist in IPv6 since error routes are associated with the loopback device. [1] unreferenced object 0xffff888066650338 (size 56): comm "ip", pid 1206, jiffies 4294786063 (age 26.235s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 b0 1c 62 61 80 88 ff ff ..........ba.... e8 8b a1 64 80 88 ff ff 00 07 00 08 fe 00 00 00 ...d............ backtrace: [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220 [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20 [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380 [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690 [<0000000014f62875>] netlink_sendmsg+0x929/0xe10 [<00000000bac9d967>] sock_sendmsg+0xc8/0x110 [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0 [<000000002e94f880>] __sys_sendmsg+0xf7/0x250 [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610 [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000003a8b605b>] 0xffffffffffffffff unreferenced object 0xffff888061621c88 (size 48): comm "ip", pid 1206, jiffies 4294786063 (age 26.235s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b d8 8e 26 5f 80 88 ff ff kkkkkkkk..&_.... backtrace: [<00000000733609e3>] fib_table_insert+0x978/0x1500 [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220 [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20 [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380 [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690 [<0000000014f62875>] netlink_sendmsg+0x929/0xe10 [<00000000bac9d967>] sock_sendmsg+0xc8/0x110 [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0 [<000000002e94f880>] __sys_sendmsg+0xf7/0x250 [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610 [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000003a8b605b>] 0xffffffffffffffff Fixes: 8cced9eff1d4 ("[NETNS]: Enable routing configuration in non-initial namespace.") Signed-off-by: Ido Schimmel <idosch@mellanox.com> Reviewed-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-09 09:57:39 +00:00
int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all);
struct fib_table *fib_trie_unmerge(struct fib_table *main_tb);
void fib_table_flush_external(struct fib_table *table);
void fib_free_table(struct fib_table *tb);
#ifndef CONFIG_IP_MULTIPLE_TABLES
fib_trie: Fix /proc/net/fib_trie when CONFIG_IP_MULTIPLE_TABLES is not defined In recent testing I had disabled CONFIG_IP_MULTIPLE_TABLES and as a result when I ran "cat /proc/net/fib_trie" the main trie was displayed multiple times. I found that the problem line of code was in the function fib_trie_seq_next. Specifically the line below caused the indexes to go in the opposite direction of our traversal: h = tb->tb_id & (FIB_TABLE_HASHSZ - 1); This issue was that the RT tables are defined such that RT_TABLE_LOCAL is ID 255, while it is located at TABLE_LOCAL_INDEX of 0, and RT_TABLE_MAIN is 254 with a TABLE_MAIN_INDEX of 1. This means that the above line will return 1 for the local table and 0 for main. The result is that fib_trie_seq_next will return NULL at the end of the local table, fib_trie_seq_start will return the start of the main table, and then fib_trie_seq_next will loop on main forever as h will always return 0. The fix for this is to reverse the ordering of the two tables. It has the advantage of making it so that the tables now print in the same order regardless of if multiple tables are enabled or not. In order to make the definition consistent with the multiple tables case I simply masked the to RT_TABLE_XXX values by (FIB_TABLE_HASHSZ - 1). This way the two table layouts should always stay consistent. Fixes: 93456b6 ("[IPV4]: Unify access to the routing tables") Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-02 18:58:21 +00:00
#define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1))
#define TABLE_MAIN_INDEX (RT_TABLE_MAIN & (FIB_TABLE_HASHSZ - 1))
static inline struct fib_table *fib_get_table(struct net *net, u32 id)
{
struct hlist_node *tb_hlist;
struct hlist_head *ptr;
ptr = id == RT_TABLE_LOCAL ?
&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] :
&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX];
tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr));
return hlist_entry(tb_hlist, struct fib_table, tb_hlist);
}
static inline struct fib_table *fib_new_table(struct net *net, u32 id)
{
return fib_get_table(net, id);
}
static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 17:45:37 +00:00
struct fib_result *res, unsigned int flags)
{
struct fib_table *tb;
int err = -ENETUNREACH;
rcu_read_lock();
tb = fib_get_table(net, RT_TABLE_MAIN);
if (tb)
err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF);
if (err == -EAGAIN)
err = -ENETUNREACH;
rcu_read_unlock();
return err;
}
static inline bool fib4_has_custom_rules(const struct net *net)
{
return false;
}
ipv4: fib_rules: Check if rule is a default rule Currently, when non-default (custom) FIB rules are used, devices capable of layer 3 offloading flush their tables and let the kernel do the forwarding instead. When these devices' drivers are loaded they register to the FIB notification chain, which lets them know about the existence of any custom FIB rules. This is done by sending a RULE_ADD notification based on the value of 'net->ipv4.fib_has_custom_rules'. This approach is problematic when VRF offload is taken into account, as upon the creation of the first VRF netdev, a l3mdev rule is programmed to direct skbs to the VRF's table. Instead of merely reading the above value and sending a single RULE_ADD notification, we should iterate over all the FIB rules and send a detailed notification for each, thereby allowing offloading drivers to sanitize the rules they don't support and potentially flush their tables. While l3mdev rules are uniquely marked, the default rules are not. Therefore, when they are being notified they might invoke offloading drivers to unnecessarily flush their tables. Solve this by adding an helper to check if a FIB rule is a default rule. Namely, its selector should match all packets and its action should point to the local, main or default tables. As noted by David Ahern, uniquely marking the default rules is insufficient. When using VRFs, it's common to avoid false hits by moving the rule for the local table to just before the main table: Default configuration: $ ip rule show 0: from all lookup local 32766: from all lookup main 32767: from all lookup default Common configuration with VRFs: $ ip rule show 1000: from all lookup [l3mdev-table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-16 08:08:12 +00:00
static inline bool fib4_rule_default(const struct fib_rule *rule)
{
return true;
}
static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb,
struct netlink_ext_ack *extack)
{
return 0;
}
static inline unsigned int fib4_rules_seq_read(struct net *net)
{
return 0;
}
static inline bool fib4_rules_early_flow_dissect(struct net *net,
struct sk_buff *skb,
struct flowi4 *fl4,
struct flow_keys *flkeys)
{
return false;
}
#else /* CONFIG_IP_MULTIPLE_TABLES */
int __net_init fib4_rules_init(struct net *net);
void __net_exit fib4_rules_exit(struct net *net);
struct fib_table *fib_new_table(struct net *net, u32 id);
struct fib_table *fib_get_table(struct net *net, u32 id);
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 17:45:37 +00:00
int __fib_lookup(struct net *net, struct flowi4 *flp,
struct fib_result *res, unsigned int flags);
static inline int fib_lookup(struct net *net, struct flowi4 *flp,
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 17:45:37 +00:00
struct fib_result *res, unsigned int flags)
{
struct fib_table *tb;
int err = -ENETUNREACH;
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 17:45:37 +00:00
flags |= FIB_LOOKUP_NOREF;
if (net->ipv4.fib_has_custom_rules)
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 17:45:37 +00:00
return __fib_lookup(net, flp, res, flags);
rcu_read_lock();
res->tclassid = 0;
tb = rcu_dereference_rtnl(net->ipv4.fib_main);
if (tb)
err = fib_table_lookup(tb, flp, res, flags);
if (!err)
goto out;
tb = rcu_dereference_rtnl(net->ipv4.fib_default);
if (tb)
err = fib_table_lookup(tb, flp, res, flags);
out:
if (err == -EAGAIN)
err = -ENETUNREACH;
rcu_read_unlock();
return err;
}
static inline bool fib4_has_custom_rules(const struct net *net)
{
return net->ipv4.fib_has_custom_rules;
}
ipv4: fib_rules: Check if rule is a default rule Currently, when non-default (custom) FIB rules are used, devices capable of layer 3 offloading flush their tables and let the kernel do the forwarding instead. When these devices' drivers are loaded they register to the FIB notification chain, which lets them know about the existence of any custom FIB rules. This is done by sending a RULE_ADD notification based on the value of 'net->ipv4.fib_has_custom_rules'. This approach is problematic when VRF offload is taken into account, as upon the creation of the first VRF netdev, a l3mdev rule is programmed to direct skbs to the VRF's table. Instead of merely reading the above value and sending a single RULE_ADD notification, we should iterate over all the FIB rules and send a detailed notification for each, thereby allowing offloading drivers to sanitize the rules they don't support and potentially flush their tables. While l3mdev rules are uniquely marked, the default rules are not. Therefore, when they are being notified they might invoke offloading drivers to unnecessarily flush their tables. Solve this by adding an helper to check if a FIB rule is a default rule. Namely, its selector should match all packets and its action should point to the local, main or default tables. As noted by David Ahern, uniquely marking the default rules is insufficient. When using VRFs, it's common to avoid false hits by moving the rule for the local table to just before the main table: Default configuration: $ ip rule show 0: from all lookup local 32766: from all lookup main 32767: from all lookup default Common configuration with VRFs: $ ip rule show 1000: from all lookup [l3mdev-table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-16 08:08:12 +00:00
bool fib4_rule_default(const struct fib_rule *rule);
int fib4_rules_dump(struct net *net, struct notifier_block *nb,
struct netlink_ext_ack *extack);
unsigned int fib4_rules_seq_read(struct net *net);
ipv4: fib_rules: Check if rule is a default rule Currently, when non-default (custom) FIB rules are used, devices capable of layer 3 offloading flush their tables and let the kernel do the forwarding instead. When these devices' drivers are loaded they register to the FIB notification chain, which lets them know about the existence of any custom FIB rules. This is done by sending a RULE_ADD notification based on the value of 'net->ipv4.fib_has_custom_rules'. This approach is problematic when VRF offload is taken into account, as upon the creation of the first VRF netdev, a l3mdev rule is programmed to direct skbs to the VRF's table. Instead of merely reading the above value and sending a single RULE_ADD notification, we should iterate over all the FIB rules and send a detailed notification for each, thereby allowing offloading drivers to sanitize the rules they don't support and potentially flush their tables. While l3mdev rules are uniquely marked, the default rules are not. Therefore, when they are being notified they might invoke offloading drivers to unnecessarily flush their tables. Solve this by adding an helper to check if a FIB rule is a default rule. Namely, its selector should match all packets and its action should point to the local, main or default tables. As noted by David Ahern, uniquely marking the default rules is insufficient. When using VRFs, it's common to avoid false hits by moving the rule for the local table to just before the main table: Default configuration: $ ip rule show 0: from all lookup local 32766: from all lookup main 32767: from all lookup default Common configuration with VRFs: $ ip rule show 1000: from all lookup [l3mdev-table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-16 08:08:12 +00:00
static inline bool fib4_rules_early_flow_dissect(struct net *net,
struct sk_buff *skb,
struct flowi4 *fl4,
struct flow_keys *flkeys)
{
unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
if (!net->ipv4.fib_rules_require_fldissect)
return false;
skb_flow_dissect_flow_keys(skb, flkeys, flag);
fl4->fl4_sport = flkeys->ports.src;
fl4->fl4_dport = flkeys->ports.dst;
fl4->flowi4_proto = flkeys->basic.ip_proto;
return true;
}
#endif /* CONFIG_IP_MULTIPLE_TABLES */
/* Exported by fib_frontend.c */
extern const struct nla_policy rtm_ipv4_policy[];
void ip_fib_init(void);
int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
struct netlink_ext_ack *extack);
__be32 fib_compute_spec_dst(struct sk_buff *skb);
bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev);
int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
struct in_device *idev, u32 *itag);
#ifdef CONFIG_IP_ROUTE_CLASSID
static inline int fib_num_tclassid_users(struct net *net)
{
return net->ipv4.fib_num_tclassid_users;
}
#else
static inline int fib_num_tclassid_users(struct net *net)
{
return 0;
}
#endif
int fib_unmerge(struct net *net);
static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc,
const struct net_device *dev)
{
if (nhc->nhc_dev == dev ||
l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex)
return true;
return false;
}
/* Exported by fib_semantics.c */
int ip_fib_check_default(__be32 gw, struct net_device *dev);
int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
int fib_sync_down_addr(struct net_device *dev, __be32 local);
int fib_sync_up(struct net_device *dev, unsigned char nh_flags);
2018-10-09 15:48:14 +00:00
void fib_sync_mtu(struct net_device *dev, u32 orig_mtu);
void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
const struct sk_buff *skb, struct flow_keys *flkeys);
#endif
int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
struct netlink_ext_ack *extack);
void fib_select_multipath(struct fib_result *res, int hash);
void fib_select_path(struct net *net, struct fib_result *res,
struct flowi4 *fl4, const struct sk_buff *skb);
int fib_nh_init(struct net *net, struct fib_nh *fib_nh,
struct fib_config *cfg, int nh_weight,
struct netlink_ext_ack *extack);
void fib_nh_release(struct net *net, struct fib_nh *fib_nh);
int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc,
struct nlattr *fc_encap, u16 fc_encap_type,
void *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
void fib_nh_common_release(struct fib_nh_common *nhc);
/* Exported by fib_trie.c */
ipv4: Add "offload" and "trap" indications to routes When performing L3 offload, routes and nexthops are usually programmed into two different tables in the underlying device. Therefore, the fact that a nexthop resides in hardware does not necessarily mean that all the associated routes also reside in hardware and vice-versa. While the kernel can signal to user space the presence of a nexthop in hardware (via 'RTNH_F_OFFLOAD'), it does not have a corresponding flag for routes. In addition, the fact that a route resides in hardware does not necessarily mean that the traffic is offloaded. For example, unreachable routes (i.e., 'RTN_UNREACHABLE') are programmed to trap packets to the CPU so that the kernel will be able to generate the appropriate ICMP error packet. This patch adds an "offload" and "trap" indications to IPv4 routes, so that users will have better visibility into the offload process. 'struct fib_alias' is extended with two new fields that indicate if the route resides in hardware or not and if it is offloading traffic from the kernel or trapping packets to it. Note that the new fields are added in the 6 bytes hole and therefore the struct still fits in a single cache line [1]. Capable drivers are expected to invoke fib_alias_hw_flags_set() with the route's key in order to set the flags. The indications are dumped to user space via a new flags (i.e., 'RTM_F_OFFLOAD' and 'RTM_F_TRAP') in the 'rtm_flags' field in the ancillary header. v2: * Make use of 'struct fib_rt_info' in fib_alias_hw_flags_set() [1] struct fib_alias { struct hlist_node fa_list; /* 0 16 */ struct fib_info * fa_info; /* 16 8 */ u8 fa_tos; /* 24 1 */ u8 fa_type; /* 25 1 */ u8 fa_state; /* 26 1 */ u8 fa_slen; /* 27 1 */ u32 tb_id; /* 28 4 */ s16 fa_default; /* 32 2 */ u8 offload:1; /* 34: 0 1 */ u8 trap:1; /* 34: 1 1 */ u8 unused:6; /* 34: 2 1 */ /* XXX 5 bytes hole, try to pack */ struct callback_head rcu __attribute__((__aligned__(8))); /* 40 16 */ /* size: 56, cachelines: 1, members: 12 */ /* sum members: 50, holes: 1, sum holes: 5 */ /* sum bitfield members: 8 bits (1 bytes) */ /* forced alignments: 1, forced holes: 1, sum forced holes: 5 */ /* last cacheline: 56 bytes */ } __attribute__((__aligned__(8))); Signed-off-by: Ido Schimmel <idosch@mellanox.com> Reviewed-by: David Ahern <dsahern@gmail.com> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-01-14 11:23:11 +00:00
void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri);
void fib_trie_init(void);
struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags,
const struct flowi4 *flp);
static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
{
#ifdef CONFIG_IP_ROUTE_CLASSID
struct fib_nh_common *nhc = res->nhc;
#ifdef CONFIG_IP_MULTIPLE_TABLES
u32 rtag;
#endif
if (nhc->nhc_family == AF_INET) {
struct fib_nh *nh;
nh = container_of(nhc, struct fib_nh, nh_common);
*itag = nh->nh_tclassid << 16;
} else {
*itag = 0;
}
#ifdef CONFIG_IP_MULTIPLE_TABLES
rtag = res->tclassid;
if (*itag == 0)
*itag = (rtag<<16);
*itag |= (rtag>>16);
#endif
#endif
}
void fib_flush(struct net *net);
void free_fib_info(struct fib_info *fi);
static inline void fib_info_hold(struct fib_info *fi)
{
refcount_inc(&fi->fib_clntref);
}
static inline void fib_info_put(struct fib_info *fi)
{
if (refcount_dec_and_test(&fi->fib_clntref))
free_fib_info(fi);
}
#ifdef CONFIG_PROC_FS
int __net_init fib_proc_init(struct net *net);
void __net_exit fib_proc_exit(struct net *net);
#else
static inline int fib_proc_init(struct net *net)
{
return 0;
}
static inline void fib_proc_exit(struct net *net)
{
}
#endif
u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr);
int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
struct fib_dump_filter *filter,
struct netlink_callback *cb);
int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh,
u8 rt_family, unsigned char *flags, bool skip_oif);
int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh,
int nh_weight, u8 rt_family);
#endif /* _NET_FIB_H */