1
linux/net/l3mdev/l3mdev.c

302 lines
6.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/l3mdev/l3mdev.c - L3 master device implementation
* Copyright (c) 2015 Cumulus Networks
* Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com>
*/
#include <linux/netdevice.h>
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 10:55:39 -07:00
#include <net/fib_rules.h>
#include <net/l3mdev.h>
static DEFINE_SPINLOCK(l3mdev_lock);
struct l3mdev_handler {
lookup_by_table_id_t dev_lookup;
};
static struct l3mdev_handler l3mdev_handlers[L3MDEV_TYPE_MAX + 1];
static int l3mdev_check_type(enum l3mdev_type l3type)
{
if (l3type <= L3MDEV_TYPE_UNSPEC || l3type > L3MDEV_TYPE_MAX)
return -EINVAL;
return 0;
}
int l3mdev_table_lookup_register(enum l3mdev_type l3type,
lookup_by_table_id_t fn)
{
struct l3mdev_handler *hdlr;
int res;
res = l3mdev_check_type(l3type);
if (res)
return res;
hdlr = &l3mdev_handlers[l3type];
spin_lock(&l3mdev_lock);
if (hdlr->dev_lookup) {
res = -EBUSY;
goto unlock;
}
hdlr->dev_lookup = fn;
res = 0;
unlock:
spin_unlock(&l3mdev_lock);
return res;
}
EXPORT_SYMBOL_GPL(l3mdev_table_lookup_register);
void l3mdev_table_lookup_unregister(enum l3mdev_type l3type,
lookup_by_table_id_t fn)
{
struct l3mdev_handler *hdlr;
if (l3mdev_check_type(l3type))
return;
hdlr = &l3mdev_handlers[l3type];
spin_lock(&l3mdev_lock);
if (hdlr->dev_lookup == fn)
hdlr->dev_lookup = NULL;
spin_unlock(&l3mdev_lock);
}
EXPORT_SYMBOL_GPL(l3mdev_table_lookup_unregister);
int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type,
struct net *net, u32 table_id)
{
lookup_by_table_id_t lookup;
struct l3mdev_handler *hdlr;
int ifindex = -EINVAL;
int res;
res = l3mdev_check_type(l3type);
if (res)
return res;
hdlr = &l3mdev_handlers[l3type];
spin_lock(&l3mdev_lock);
lookup = hdlr->dev_lookup;
if (!lookup)
goto unlock;
ifindex = lookup(net, table_id);
unlock:
spin_unlock(&l3mdev_lock);
return ifindex;
}
EXPORT_SYMBOL_GPL(l3mdev_ifindex_lookup_by_table_id);
/**
* l3mdev_master_ifindex_rcu - get index of L3 master device
* @dev: targeted interface
*/
net: l3mdev: address selection should only consider devices in L3 domain David Lamparter noted a use case where the source address selection fails to pick an address from a VRF interface - unnumbered interfaces. Relevant commands from his script: ip addr add 9.9.9.9/32 dev lo ip link set lo up ip link add name vrf0 type vrf table 101 ip rule add oif vrf0 table 101 ip rule add iif vrf0 table 101 ip link set vrf0 up ip addr add 10.0.0.3/32 dev vrf0 ip link add name dummy2 type dummy ip link set dummy2 master vrf0 up --> note dummy2 has no address - unnumbered device ip route add 10.2.2.2/32 dev dummy2 table 101 ip neigh add 10.2.2.2 dev dummy2 lladdr 02:00:00:00:00:02 tcpdump -ni dummy2 & And using ping instead of his socat example: $ ping -I vrf0 -c1 10.2.2.2 ping: Warning: source address might be selected on device other than vrf0. PING 10.2.2.2 (10.2.2.2) from 9.9.9.9 vrf0: 56(84) bytes of data. >From tcpdump: 12:57:29.449128 IP 9.9.9.9 > 10.2.2.2: ICMP echo request, id 2491, seq 1, length 64 Note the source address is from lo and is not a VRF local address. With this patch: $ ping -I vrf0 -c1 10.2.2.2 PING 10.2.2.2 (10.2.2.2) from 10.0.0.3 vrf0: 56(84) bytes of data. >From tcpdump: 12:59:25.096426 IP 10.0.0.3 > 10.2.2.2: ICMP echo request, id 2113, seq 1, length 64 Now the source address comes from vrf0. The ipv4 function for selecting source address takes a const argument. Removing the const requires touching a lot of places, so instead l3mdev_master_ifindex_rcu is changed to take a const argument and then do the typecast to non-const as required by netdev_master_upper_dev_get_rcu. This is similar to what l3mdev_fib_table_rcu does. IPv6 for unnumbered interfaces appears to be selecting the addresses properly. Cc: David Lamparter <david@opensourcerouting.org> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-24 12:47:02 -07:00
int l3mdev_master_ifindex_rcu(const struct net_device *dev)
{
int ifindex = 0;
if (!dev)
return 0;
if (netif_is_l3_master(dev)) {
ifindex = dev->ifindex;
} else if (netif_is_l3_slave(dev)) {
struct net_device *master;
net: l3mdev: address selection should only consider devices in L3 domain David Lamparter noted a use case where the source address selection fails to pick an address from a VRF interface - unnumbered interfaces. Relevant commands from his script: ip addr add 9.9.9.9/32 dev lo ip link set lo up ip link add name vrf0 type vrf table 101 ip rule add oif vrf0 table 101 ip rule add iif vrf0 table 101 ip link set vrf0 up ip addr add 10.0.0.3/32 dev vrf0 ip link add name dummy2 type dummy ip link set dummy2 master vrf0 up --> note dummy2 has no address - unnumbered device ip route add 10.2.2.2/32 dev dummy2 table 101 ip neigh add 10.2.2.2 dev dummy2 lladdr 02:00:00:00:00:02 tcpdump -ni dummy2 & And using ping instead of his socat example: $ ping -I vrf0 -c1 10.2.2.2 ping: Warning: source address might be selected on device other than vrf0. PING 10.2.2.2 (10.2.2.2) from 9.9.9.9 vrf0: 56(84) bytes of data. >From tcpdump: 12:57:29.449128 IP 9.9.9.9 > 10.2.2.2: ICMP echo request, id 2491, seq 1, length 64 Note the source address is from lo and is not a VRF local address. With this patch: $ ping -I vrf0 -c1 10.2.2.2 PING 10.2.2.2 (10.2.2.2) from 10.0.0.3 vrf0: 56(84) bytes of data. >From tcpdump: 12:59:25.096426 IP 10.0.0.3 > 10.2.2.2: ICMP echo request, id 2113, seq 1, length 64 Now the source address comes from vrf0. The ipv4 function for selecting source address takes a const argument. Removing the const requires touching a lot of places, so instead l3mdev_master_ifindex_rcu is changed to take a const argument and then do the typecast to non-const as required by netdev_master_upper_dev_get_rcu. This is similar to what l3mdev_fib_table_rcu does. IPv6 for unnumbered interfaces appears to be selecting the addresses properly. Cc: David Lamparter <david@opensourcerouting.org> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-24 12:47:02 -07:00
struct net_device *_dev = (struct net_device *)dev;
/* netdev_master_upper_dev_get_rcu calls
* list_first_or_null_rcu to walk the upper dev list.
* list_first_or_null_rcu does not handle a const arg. We aren't
* making changes, just want the master device from that list so
* typecast to remove the const
*/
master = netdev_master_upper_dev_get_rcu(_dev);
if (master)
ifindex = master->ifindex;
}
return ifindex;
}
EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu);
/**
* l3mdev_master_upper_ifindex_by_index_rcu - get index of upper l3 master
* device
* @net: network namespace for device index lookup
* @ifindex: targeted interface
*/
int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
{
struct net_device *dev;
dev = dev_get_by_index_rcu(net, ifindex);
while (dev && !netif_is_l3_master(dev))
l3mdev: l3mdev_master_upper_ifindex_by_index_rcu should be using netdev_master_upper_dev_get_rcu Next patch uses l3mdev_master_upper_ifindex_by_index_rcu which throws a splat with debug kernels: [13783.087570] ------------[ cut here ]------------ [13783.093974] RTNL: assertion failed at net/core/dev.c (6702) [13783.100761] WARNING: CPU: 3 PID: 51132 at net/core/dev.c:6702 netdev_master_upper_dev_get+0x16a/0x1a0 [13783.184226] CPU: 3 PID: 51132 Comm: kworker/3:3 Not tainted 5.17.0-custom-100090-g6f963aafb1cc #682 [13783.194788] Hardware name: Mellanox Technologies Ltd. MSN2010/SA002610, BIOS 5.6.5 08/24/2017 [13783.204755] Workqueue: mld mld_ifc_work [ipv6] [13783.210338] RIP: 0010:netdev_master_upper_dev_get+0x16a/0x1a0 [13783.217209] Code: 0f 85 e3 fe ff ff e8 65 ac ec fe ba 2e 1a 00 00 48 c7 c6 60 6f 38 83 48 c7 c7 c0 70 38 83 c6 05 5e b5 d7 01 01 e8 c6 29 52 00 <0f> 0b e9 b8 fe ff ff e8 5a 6c 35 ff e9 1c ff ff ff 48 89 ef e8 7d [13783.238659] RSP: 0018:ffffc9000b37f5a8 EFLAGS: 00010286 [13783.244995] RAX: 0000000000000000 RBX: ffff88812ee5c000 RCX: 0000000000000000 [13783.253379] RDX: ffff88811ce09d40 RSI: ffffffff812d0fcd RDI: fffff5200166fea7 [13783.261769] RBP: 0000000000000000 R08: 0000000000000001 R09: ffff8882375f4287 [13783.270138] R10: ffffed1046ebe850 R11: 0000000000000001 R12: dffffc0000000000 [13783.278510] R13: 0000000000000275 R14: ffffc9000b37f688 R15: ffff8881273b4af8 [13783.286870] FS: 0000000000000000(0000) GS:ffff888237400000(0000) knlGS:0000000000000000 [13783.296352] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [13783.303177] CR2: 00007ff25fc9b2e8 CR3: 0000000174d23000 CR4: 00000000001006e0 [13783.311546] Call Trace: [13783.314660] <TASK> [13783.317553] l3mdev_master_upper_ifindex_by_index_rcu+0x43/0xe0 ... Change l3mdev_master_upper_ifindex_by_index_rcu to use netdev_master_upper_dev_get_rcu. Fixes: 6a6d6681ac1a ("l3mdev: add function to retreive upper master") Signed-off-by: Ido Schimmel <idosch@idosch.org> Signed-off-by: David Ahern <dsahern@kernel.org> Cc: Alexis Bauvin <abauvin@scaleway.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-04-13 10:43:19 -07:00
dev = netdev_master_upper_dev_get_rcu(dev);
return dev ? dev->ifindex : 0;
}
EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu);
/**
* l3mdev_fib_table_rcu - get FIB table id associated with an L3
* master interface
* @dev: targeted interface
*/
u32 l3mdev_fib_table_rcu(const struct net_device *dev)
{
u32 tb_id = 0;
if (!dev)
return 0;
if (netif_is_l3_master(dev)) {
if (dev->l3mdev_ops->l3mdev_fib_table)
tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev);
} else if (netif_is_l3_slave(dev)) {
/* Users of netdev_master_upper_dev_get_rcu need non-const,
* but current inet_*type functions take a const
*/
struct net_device *_dev = (struct net_device *) dev;
const struct net_device *master;
master = netdev_master_upper_dev_get_rcu(_dev);
if (master &&
master->l3mdev_ops->l3mdev_fib_table)
tb_id = master->l3mdev_ops->l3mdev_fib_table(master);
}
return tb_id;
}
EXPORT_SYMBOL_GPL(l3mdev_fib_table_rcu);
u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
u32 tb_id = 0;
if (!ifindex)
return 0;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
tb_id = l3mdev_fib_table_rcu(dev);
rcu_read_unlock();
return tb_id;
}
EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index);
/**
* l3mdev_link_scope_lookup - IPv6 route lookup based on flow for link
* local and multicast addresses
* @net: network namespace for device index lookup
* @fl6: IPv6 flow struct for lookup
* This function does not hold refcnt on the returned dst.
* Caller must hold rcu_read_lock().
*/
struct dst_entry *l3mdev_link_scope_lookup(struct net *net,
struct flowi6 *fl6)
{
struct dst_entry *dst = NULL;
struct net_device *dev;
WARN_ON_ONCE(!rcu_read_lock_held());
if (fl6->flowi6_oif) {
dev = dev_get_by_index_rcu(net, fl6->flowi6_oif);
if (dev && netif_is_l3_slave(dev))
dev = netdev_master_upper_dev_get_rcu(dev);
if (dev && netif_is_l3_master(dev) &&
dev->l3mdev_ops->l3mdev_link_scope_lookup)
dst = dev->l3mdev_ops->l3mdev_link_scope_lookup(dev, fl6);
}
return dst;
}
EXPORT_SYMBOL_GPL(l3mdev_link_scope_lookup);
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 10:55:39 -07:00
/**
* l3mdev_fib_rule_match - Determine if flowi references an
* L3 master device
* @net: network namespace for device index lookup
* @fl: flow struct
* @arg: store the table the rule matched with here
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 10:55:39 -07:00
*/
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
struct fib_lookup_arg *arg)
{
struct net_device *dev;
int rc = 0;
net: Add l3mdev index to flow struct and avoid oif reset for port devices The fundamental premise of VRF and l3mdev core code is binding a socket to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope. Legacy code resets flowi_oif to the l3mdev losing any original port device binding. Ben (among others) has demonstrated use cases where the original port device binding is important and needs to be retained. This patch handles that by adding a new entry to the common flow struct that can indicate the l3mdev index for later rule and table matching avoiding the need to reset flowi_oif. In addition to allowing more use cases that require port device binds, this patch brings a few datapath simplications: 1. l3mdev_fib_rule_match is only called when walking fib rules and always after l3mdev_update_flow. That allows an optimization to bail early for non-VRF type uses cases when flowi_l3mdev is not set. Also, only that index needs to be checked for the FIB table id. 2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev (e.g., VRF) device. By resetting flowi_oif only for this case the FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed, removing several checks in the datapath. The flowi_iif path can be simplified to only be called if the it is not loopback (loopback can not be assigned to an L3 domain) and the l3mdev index is not already set. 3. Avoid another device lookup in the output path when the fib lookup returns a reject failure. Note: 2 functional tests for local traffic with reject fib rules are updated to reflect the new direct failure at FIB lookup time for ping rather than the failure on packet path. The current code fails like this: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: Warning: source address might be selected on device other than: eth1 PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data. --- 172.16.3.1 ping statistics --- 1 packets transmitted, 0 received, 100% packet loss, time 0ms where the test now directly fails: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: connect: No route to host Signed-off-by: David Ahern <dsahern@kernel.org> Tested-by: Ben Greear <greearb@candelatech.com> Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-03-14 13:45:51 -07:00
/* update flow ensures flowi_l3mdev is set when relevant */
if (!fl->flowi_l3mdev)
return 0;
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 10:55:39 -07:00
net: Add l3mdev index to flow struct and avoid oif reset for port devices The fundamental premise of VRF and l3mdev core code is binding a socket to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope. Legacy code resets flowi_oif to the l3mdev losing any original port device binding. Ben (among others) has demonstrated use cases where the original port device binding is important and needs to be retained. This patch handles that by adding a new entry to the common flow struct that can indicate the l3mdev index for later rule and table matching avoiding the need to reset flowi_oif. In addition to allowing more use cases that require port device binds, this patch brings a few datapath simplications: 1. l3mdev_fib_rule_match is only called when walking fib rules and always after l3mdev_update_flow. That allows an optimization to bail early for non-VRF type uses cases when flowi_l3mdev is not set. Also, only that index needs to be checked for the FIB table id. 2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev (e.g., VRF) device. By resetting flowi_oif only for this case the FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed, removing several checks in the datapath. The flowi_iif path can be simplified to only be called if the it is not loopback (loopback can not be assigned to an L3 domain) and the l3mdev index is not already set. 3. Avoid another device lookup in the output path when the fib lookup returns a reject failure. Note: 2 functional tests for local traffic with reject fib rules are updated to reflect the new direct failure at FIB lookup time for ping rather than the failure on packet path. The current code fails like this: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: Warning: source address might be selected on device other than: eth1 PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data. --- 172.16.3.1 ping statistics --- 1 packets transmitted, 0 received, 100% packet loss, time 0ms where the test now directly fails: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: connect: No route to host Signed-off-by: David Ahern <dsahern@kernel.org> Tested-by: Ben Greear <greearb@candelatech.com> Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-03-14 13:45:51 -07:00
rcu_read_lock();
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 10:55:39 -07:00
net: Add l3mdev index to flow struct and avoid oif reset for port devices The fundamental premise of VRF and l3mdev core code is binding a socket to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope. Legacy code resets flowi_oif to the l3mdev losing any original port device binding. Ben (among others) has demonstrated use cases where the original port device binding is important and needs to be retained. This patch handles that by adding a new entry to the common flow struct that can indicate the l3mdev index for later rule and table matching avoiding the need to reset flowi_oif. In addition to allowing more use cases that require port device binds, this patch brings a few datapath simplications: 1. l3mdev_fib_rule_match is only called when walking fib rules and always after l3mdev_update_flow. That allows an optimization to bail early for non-VRF type uses cases when flowi_l3mdev is not set. Also, only that index needs to be checked for the FIB table id. 2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev (e.g., VRF) device. By resetting flowi_oif only for this case the FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed, removing several checks in the datapath. The flowi_iif path can be simplified to only be called if the it is not loopback (loopback can not be assigned to an L3 domain) and the l3mdev index is not already set. 3. Avoid another device lookup in the output path when the fib lookup returns a reject failure. Note: 2 functional tests for local traffic with reject fib rules are updated to reflect the new direct failure at FIB lookup time for ping rather than the failure on packet path. The current code fails like this: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: Warning: source address might be selected on device other than: eth1 PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data. --- 172.16.3.1 ping statistics --- 1 packets transmitted, 0 received, 100% packet loss, time 0ms where the test now directly fails: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: connect: No route to host Signed-off-by: David Ahern <dsahern@kernel.org> Tested-by: Ben Greear <greearb@candelatech.com> Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-03-14 13:45:51 -07:00
dev = dev_get_by_index_rcu(net, fl->flowi_l3mdev);
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 10:55:39 -07:00
if (dev && netif_is_l3_master(dev) &&
dev->l3mdev_ops->l3mdev_fib_table) {
arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev);
rc = 1;
}
rcu_read_unlock();
return rc;
}
void l3mdev_update_flow(struct net *net, struct flowi *fl)
{
struct net_device *dev;
rcu_read_lock();
if (fl->flowi_oif) {
dev = dev_get_by_index_rcu(net, fl->flowi_oif);
if (dev) {
net: Add l3mdev index to flow struct and avoid oif reset for port devices The fundamental premise of VRF and l3mdev core code is binding a socket to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope. Legacy code resets flowi_oif to the l3mdev losing any original port device binding. Ben (among others) has demonstrated use cases where the original port device binding is important and needs to be retained. This patch handles that by adding a new entry to the common flow struct that can indicate the l3mdev index for later rule and table matching avoiding the need to reset flowi_oif. In addition to allowing more use cases that require port device binds, this patch brings a few datapath simplications: 1. l3mdev_fib_rule_match is only called when walking fib rules and always after l3mdev_update_flow. That allows an optimization to bail early for non-VRF type uses cases when flowi_l3mdev is not set. Also, only that index needs to be checked for the FIB table id. 2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev (e.g., VRF) device. By resetting flowi_oif only for this case the FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed, removing several checks in the datapath. The flowi_iif path can be simplified to only be called if the it is not loopback (loopback can not be assigned to an L3 domain) and the l3mdev index is not already set. 3. Avoid another device lookup in the output path when the fib lookup returns a reject failure. Note: 2 functional tests for local traffic with reject fib rules are updated to reflect the new direct failure at FIB lookup time for ping rather than the failure on packet path. The current code fails like this: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: Warning: source address might be selected on device other than: eth1 PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data. --- 172.16.3.1 ping statistics --- 1 packets transmitted, 0 received, 100% packet loss, time 0ms where the test now directly fails: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: connect: No route to host Signed-off-by: David Ahern <dsahern@kernel.org> Tested-by: Ben Greear <greearb@candelatech.com> Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-03-14 13:45:51 -07:00
if (!fl->flowi_l3mdev)
fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev);
/* oif set to L3mdev directs lookup to its table;
* reset to avoid oif match in fib_lookup
*/
if (netif_is_l3_master(dev))
fl->flowi_oif = 0;
goto out;
}
}
net: Add l3mdev index to flow struct and avoid oif reset for port devices The fundamental premise of VRF and l3mdev core code is binding a socket to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope. Legacy code resets flowi_oif to the l3mdev losing any original port device binding. Ben (among others) has demonstrated use cases where the original port device binding is important and needs to be retained. This patch handles that by adding a new entry to the common flow struct that can indicate the l3mdev index for later rule and table matching avoiding the need to reset flowi_oif. In addition to allowing more use cases that require port device binds, this patch brings a few datapath simplications: 1. l3mdev_fib_rule_match is only called when walking fib rules and always after l3mdev_update_flow. That allows an optimization to bail early for non-VRF type uses cases when flowi_l3mdev is not set. Also, only that index needs to be checked for the FIB table id. 2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev (e.g., VRF) device. By resetting flowi_oif only for this case the FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed, removing several checks in the datapath. The flowi_iif path can be simplified to only be called if the it is not loopback (loopback can not be assigned to an L3 domain) and the l3mdev index is not already set. 3. Avoid another device lookup in the output path when the fib lookup returns a reject failure. Note: 2 functional tests for local traffic with reject fib rules are updated to reflect the new direct failure at FIB lookup time for ping rather than the failure on packet path. The current code fails like this: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: Warning: source address might be selected on device other than: eth1 PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data. --- 172.16.3.1 ping statistics --- 1 packets transmitted, 0 received, 100% packet loss, time 0ms where the test now directly fails: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: connect: No route to host Signed-off-by: David Ahern <dsahern@kernel.org> Tested-by: Ben Greear <greearb@candelatech.com> Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-03-14 13:45:51 -07:00
if (fl->flowi_iif > LOOPBACK_IFINDEX && !fl->flowi_l3mdev) {
dev = dev_get_by_index_rcu(net, fl->flowi_iif);
net: Add l3mdev index to flow struct and avoid oif reset for port devices The fundamental premise of VRF and l3mdev core code is binding a socket to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope. Legacy code resets flowi_oif to the l3mdev losing any original port device binding. Ben (among others) has demonstrated use cases where the original port device binding is important and needs to be retained. This patch handles that by adding a new entry to the common flow struct that can indicate the l3mdev index for later rule and table matching avoiding the need to reset flowi_oif. In addition to allowing more use cases that require port device binds, this patch brings a few datapath simplications: 1. l3mdev_fib_rule_match is only called when walking fib rules and always after l3mdev_update_flow. That allows an optimization to bail early for non-VRF type uses cases when flowi_l3mdev is not set. Also, only that index needs to be checked for the FIB table id. 2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev (e.g., VRF) device. By resetting flowi_oif only for this case the FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed, removing several checks in the datapath. The flowi_iif path can be simplified to only be called if the it is not loopback (loopback can not be assigned to an L3 domain) and the l3mdev index is not already set. 3. Avoid another device lookup in the output path when the fib lookup returns a reject failure. Note: 2 functional tests for local traffic with reject fib rules are updated to reflect the new direct failure at FIB lookup time for ping rather than the failure on packet path. The current code fails like this: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: Warning: source address might be selected on device other than: eth1 PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data. --- 172.16.3.1 ping statistics --- 1 packets transmitted, 0 received, 100% packet loss, time 0ms where the test now directly fails: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: connect: No route to host Signed-off-by: David Ahern <dsahern@kernel.org> Tested-by: Ben Greear <greearb@candelatech.com> Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-03-14 13:45:51 -07:00
if (dev)
fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev);
}
out:
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(l3mdev_update_flow);