2019-05-27 14:55:01 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2013-10-18 23:43:34 +08:00
|
|
|
/*
|
|
|
|
* drivers/net/bond/bond_options.c - bonding options
|
|
|
|
* Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us>
|
2013-12-13 06:09:55 +08:00
|
|
|
* Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com>
|
2013-10-18 23:43:34 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/if.h>
|
2013-10-18 23:43:35 +08:00
|
|
|
#include <linux/netdevice.h>
|
2014-02-14 15:21:04 +08:00
|
|
|
#include <linux/spinlock.h>
|
2013-10-18 23:43:35 +08:00
|
|
|
#include <linux/rcupdate.h>
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
#include <linux/ctype.h>
|
2014-01-22 21:53:24 +08:00
|
|
|
#include <linux/inet.h>
|
2017-02-03 02:15:33 +08:00
|
|
|
#include <linux/sched/signal.h>
|
|
|
|
|
2014-11-11 02:27:49 +08:00
|
|
|
#include <net/bonding.h>
|
2013-10-18 23:43:34 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_active_slave_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_miimon_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_updelay_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_downdelay_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
static int bond_option_peer_notif_delay_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_use_carrier_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_interval_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target);
|
|
|
|
static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
|
|
|
|
static int bond_option_arp_ip_targets_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2022-02-21 13:54:57 +08:00
|
|
|
static int bond_option_ns_ip6_targets_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_validate_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_all_targets_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2022-06-21 15:49:19 +08:00
|
|
|
static int bond_option_prio_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_primary_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_primary_reselect_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_fail_over_mac_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_xmit_hash_policy_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_resend_igmp_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_num_peer_notif_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_all_slaves_active_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_min_links_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_lp_interval_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_pps_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2021-08-02 11:02:19 +08:00
|
|
|
static int bond_option_lacp_active_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_lacp_rate_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_ad_select_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_queue_id_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_mode_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_slaves_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval);
|
2014-04-23 07:30:22 +08:00
|
|
|
static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2015-05-09 15:01:55 +08:00
|
|
|
static int bond_option_ad_actor_sys_prio_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2015-05-09 15:01:56 +08:00
|
|
|
static int bond_option_ad_actor_system_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2015-05-09 15:01:57 +08:00
|
|
|
static int bond_option_ad_user_port_key_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2021-11-30 12:29:47 +08:00
|
|
|
static int bond_option_missed_max_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval);
|
2014-03-05 08:36:44 +08:00
|
|
|
|
|
|
|
|
|
|
|
static const struct bond_opt_value bond_mode_tbl[] = {
|
2014-01-22 21:53:17 +08:00
|
|
|
{ "balance-rr", BOND_MODE_ROUNDROBIN, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "active-backup", BOND_MODE_ACTIVEBACKUP, 0},
|
|
|
|
{ "balance-xor", BOND_MODE_XOR, 0},
|
|
|
|
{ "broadcast", BOND_MODE_BROADCAST, 0},
|
|
|
|
{ "802.3ad", BOND_MODE_8023AD, 0},
|
|
|
|
{ "balance-tlb", BOND_MODE_TLB, 0},
|
|
|
|
{ "balance-alb", BOND_MODE_ALB, 0},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_pps_tbl[] = {
|
2014-01-22 21:53:18 +08:00
|
|
|
{ "default", 1, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "maxval", USHRT_MAX, BOND_VALFLAG_MAX},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_xmit_hashtype_tbl[] = {
|
bonding: add a vlan+srcmac tx hashing option
This comes from an end-user request, where they're running multiple VMs on
hosts with bonded interfaces connected to some interest switch topologies,
where 802.3ad isn't an option. They're currently running a proprietary
solution that effectively achieves load-balancing of VMs and bandwidth
utilization improvements with a similar form of transmission algorithm.
Basically, each VM has it's own vlan, so it always sends its traffic out
the same interface, unless that interface fails. Traffic gets split
between the interfaces, maintaining a consistent path, with failover still
available if an interface goes down.
Unlike bond_eth_hash(), this hash function is using the full source MAC
address instead of just the last byte, as there are so few components to
the hash, and in the no-vlan case, we would be returning just the last
byte of the source MAC as the hash value. It's entirely possible to have
two NICs in a bond with the same last byte of their MAC, but not the same
MAC, so this adjustment should guarantee distinct hashes in all cases.
This has been rudimetarily tested to provide similar results to the
proprietary solution it is aiming to replace. A patch for iproute2 is also
posted, to properly support the new mode there as well.
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Thomas Davis <tadavis@lbl.gov>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Link: https://lore.kernel.org/r/20210119010927.1191922-1-jarod@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-19 09:09:27 +08:00
|
|
|
{ "layer2", BOND_XMIT_POLICY_LAYER2, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "layer3+4", BOND_XMIT_POLICY_LAYER34, 0},
|
|
|
|
{ "layer2+3", BOND_XMIT_POLICY_LAYER23, 0},
|
|
|
|
{ "encap2+3", BOND_XMIT_POLICY_ENCAP23, 0},
|
|
|
|
{ "encap3+4", BOND_XMIT_POLICY_ENCAP34, 0},
|
|
|
|
{ "vlan+srcmac", BOND_XMIT_POLICY_VLAN_SRCMAC, 0},
|
|
|
|
{ NULL, -1, 0},
|
2014-01-22 21:53:19 +08:00
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_arp_validate_tbl[] = {
|
2014-02-18 14:48:40 +08:00
|
|
|
{ "none", BOND_ARP_VALIDATE_NONE, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "active", BOND_ARP_VALIDATE_ACTIVE, 0},
|
|
|
|
{ "backup", BOND_ARP_VALIDATE_BACKUP, 0},
|
|
|
|
{ "all", BOND_ARP_VALIDATE_ALL, 0},
|
|
|
|
{ "filter", BOND_ARP_FILTER, 0},
|
|
|
|
{ "filter_active", BOND_ARP_FILTER_ACTIVE, 0},
|
|
|
|
{ "filter_backup", BOND_ARP_FILTER_BACKUP, 0},
|
|
|
|
{ NULL, -1, 0},
|
2014-01-22 21:53:20 +08:00
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_arp_all_targets_tbl[] = {
|
2014-01-22 21:53:21 +08:00
|
|
|
{ "any", BOND_ARP_TARGETS_ANY, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "all", BOND_ARP_TARGETS_ALL, 0},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_fail_over_mac_tbl[] = {
|
2014-01-22 21:53:22 +08:00
|
|
|
{ "none", BOND_FOM_NONE, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "active", BOND_FOM_ACTIVE, 0},
|
|
|
|
{ "follow", BOND_FOM_FOLLOW, 0},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_intmax_tbl[] = {
|
2014-01-22 21:53:23 +08:00
|
|
|
{ "off", 0, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "maxval", INT_MAX, BOND_VALFLAG_MAX},
|
2014-05-15 19:35:23 +08:00
|
|
|
{ NULL, -1, 0}
|
2014-01-22 21:53:23 +08:00
|
|
|
};
|
|
|
|
|
2021-08-02 11:02:19 +08:00
|
|
|
static const struct bond_opt_value bond_lacp_active[] = {
|
|
|
|
{ "off", 0, 0},
|
|
|
|
{ "on", 1, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ NULL, -1, 0}
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_lacp_rate_tbl[] = {
|
2014-01-22 21:53:27 +08:00
|
|
|
{ "slow", AD_LACP_SLOW, 0},
|
|
|
|
{ "fast", AD_LACP_FAST, 0},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_ad_select_tbl[] = {
|
2014-01-22 21:53:29 +08:00
|
|
|
{ "stable", BOND_AD_STABLE, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "bandwidth", BOND_AD_BANDWIDTH, 0},
|
|
|
|
{ "count", BOND_AD_COUNT, 0},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_num_peer_notif_tbl[] = {
|
2014-01-22 21:53:30 +08:00
|
|
|
{ "off", 0, 0},
|
|
|
|
{ "maxval", 255, BOND_VALFLAG_MAX},
|
|
|
|
{ "default", 1, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ NULL, -1, 0}
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_primary_reselect_tbl[] = {
|
2014-01-22 21:53:33 +08:00
|
|
|
{ "always", BOND_PRI_RESELECT_ALWAYS, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "better", BOND_PRI_RESELECT_BETTER, 0},
|
|
|
|
{ "failure", BOND_PRI_RESELECT_FAILURE, 0},
|
|
|
|
{ NULL, -1},
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_use_carrier_tbl[] = {
|
2018-05-17 02:02:13 +08:00
|
|
|
{ "off", 0, 0},
|
|
|
|
{ "on", 1, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ NULL, -1, 0}
|
2014-01-22 21:53:34 +08:00
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_all_slaves_active_tbl[] = {
|
2014-01-22 21:53:37 +08:00
|
|
|
{ "off", 0, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "on", 1, 0},
|
|
|
|
{ NULL, -1, 0}
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_resend_igmp_tbl[] = {
|
2014-01-22 21:53:38 +08:00
|
|
|
{ "off", 0, 0},
|
|
|
|
{ "maxval", 255, BOND_VALFLAG_MAX},
|
|
|
|
{ "default", 1, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ NULL, -1, 0}
|
|
|
|
};
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value bond_lp_interval_tbl[] = {
|
2014-01-22 21:53:39 +08:00
|
|
|
{ "minval", 1, BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "maxval", INT_MAX, BOND_VALFLAG_MAX},
|
2014-03-07 05:53:11 +08:00
|
|
|
{ NULL, -1, 0},
|
2014-01-22 21:53:39 +08:00
|
|
|
};
|
|
|
|
|
2014-04-23 07:30:22 +08:00
|
|
|
static const struct bond_opt_value bond_tlb_dynamic_lb_tbl[] = {
|
|
|
|
{ "off", 0, 0},
|
|
|
|
{ "on", 1, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ NULL, -1, 0}
|
|
|
|
};
|
|
|
|
|
2015-05-09 15:01:55 +08:00
|
|
|
static const struct bond_opt_value bond_ad_actor_sys_prio_tbl[] = {
|
|
|
|
{ "minval", 1, BOND_VALFLAG_MIN},
|
|
|
|
{ "maxval", 65535, BOND_VALFLAG_MAX | BOND_VALFLAG_DEFAULT},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2015-05-09 15:01:57 +08:00
|
|
|
static const struct bond_opt_value bond_ad_user_port_key_tbl[] = {
|
|
|
|
{ "minval", 0, BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT},
|
|
|
|
{ "maxval", 1023, BOND_VALFLAG_MAX},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2021-11-30 12:29:47 +08:00
|
|
|
static const struct bond_opt_value bond_missed_max_tbl[] = {
|
|
|
|
{ "minval", 1, BOND_VALFLAG_MIN},
|
|
|
|
{ "maxval", 255, BOND_VALFLAG_MAX},
|
|
|
|
{ "default", 2, BOND_VALFLAG_DEFAULT},
|
|
|
|
{ NULL, -1, 0},
|
|
|
|
};
|
|
|
|
|
2015-01-10 02:31:08 +08:00
|
|
|
static const struct bond_option bond_opts[BOND_OPT_LAST] = {
|
2014-01-22 21:53:17 +08:00
|
|
|
[BOND_OPT_MODE] = {
|
|
|
|
.id = BOND_OPT_MODE,
|
|
|
|
.name = "mode",
|
|
|
|
.desc = "bond device mode",
|
|
|
|
.flags = BOND_OPTFLAG_NOSLAVES | BOND_OPTFLAG_IFDOWN,
|
|
|
|
.values = bond_mode_tbl,
|
|
|
|
.set = bond_option_mode_set
|
|
|
|
},
|
2014-01-22 21:53:18 +08:00
|
|
|
[BOND_OPT_PACKETS_PER_SLAVE] = {
|
|
|
|
.id = BOND_OPT_PACKETS_PER_SLAVE,
|
|
|
|
.name = "packets_per_slave",
|
|
|
|
.desc = "Packets to send per slave in RR mode",
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ROUNDROBIN)),
|
|
|
|
.values = bond_pps_tbl,
|
|
|
|
.set = bond_option_pps_set
|
|
|
|
},
|
2014-01-22 21:53:19 +08:00
|
|
|
[BOND_OPT_XMIT_HASH] = {
|
|
|
|
.id = BOND_OPT_XMIT_HASH,
|
|
|
|
.name = "xmit_hash_policy",
|
2014-04-23 07:30:20 +08:00
|
|
|
.desc = "balance-xor, 802.3ad, and tlb hashing method",
|
2014-01-22 21:53:19 +08:00
|
|
|
.values = bond_xmit_hashtype_tbl,
|
|
|
|
.set = bond_option_xmit_hash_policy_set
|
|
|
|
},
|
2014-01-22 21:53:20 +08:00
|
|
|
[BOND_OPT_ARP_VALIDATE] = {
|
|
|
|
.id = BOND_OPT_ARP_VALIDATE,
|
|
|
|
.name = "arp_validate",
|
|
|
|
.desc = "validate src/dst of ARP probes",
|
2014-02-18 14:48:37 +08:00
|
|
|
.unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) |
|
|
|
|
BIT(BOND_MODE_ALB),
|
2014-01-22 21:53:20 +08:00
|
|
|
.values = bond_arp_validate_tbl,
|
|
|
|
.set = bond_option_arp_validate_set
|
|
|
|
},
|
2014-01-22 21:53:21 +08:00
|
|
|
[BOND_OPT_ARP_ALL_TARGETS] = {
|
|
|
|
.id = BOND_OPT_ARP_ALL_TARGETS,
|
|
|
|
.name = "arp_all_targets",
|
|
|
|
.desc = "fail on any/all arp targets timeout",
|
|
|
|
.values = bond_arp_all_targets_tbl,
|
|
|
|
.set = bond_option_arp_all_targets_set
|
|
|
|
},
|
2014-01-22 21:53:22 +08:00
|
|
|
[BOND_OPT_FAIL_OVER_MAC] = {
|
|
|
|
.id = BOND_OPT_FAIL_OVER_MAC,
|
|
|
|
.name = "fail_over_mac",
|
|
|
|
.desc = "For active-backup, do not set all slaves to the same MAC",
|
|
|
|
.flags = BOND_OPTFLAG_NOSLAVES,
|
|
|
|
.values = bond_fail_over_mac_tbl,
|
|
|
|
.set = bond_option_fail_over_mac_set
|
|
|
|
},
|
2014-01-22 21:53:23 +08:00
|
|
|
[BOND_OPT_ARP_INTERVAL] = {
|
|
|
|
.id = BOND_OPT_ARP_INTERVAL,
|
|
|
|
.name = "arp_interval",
|
|
|
|
.desc = "arp interval in milliseconds",
|
|
|
|
.unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) |
|
|
|
|
BIT(BOND_MODE_ALB),
|
|
|
|
.values = bond_intmax_tbl,
|
|
|
|
.set = bond_option_arp_interval_set
|
|
|
|
},
|
2021-11-30 12:29:47 +08:00
|
|
|
[BOND_OPT_MISSED_MAX] = {
|
|
|
|
.id = BOND_OPT_MISSED_MAX,
|
|
|
|
.name = "arp_missed_max",
|
|
|
|
.desc = "Maximum number of missed ARP interval",
|
|
|
|
.unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) |
|
|
|
|
BIT(BOND_MODE_ALB),
|
|
|
|
.values = bond_missed_max_tbl,
|
|
|
|
.set = bond_option_missed_max_set
|
|
|
|
},
|
2014-01-22 21:53:24 +08:00
|
|
|
[BOND_OPT_ARP_TARGETS] = {
|
|
|
|
.id = BOND_OPT_ARP_TARGETS,
|
|
|
|
.name = "arp_ip_target",
|
|
|
|
.desc = "arp targets in n.n.n.n form",
|
|
|
|
.flags = BOND_OPTFLAG_RAWVAL,
|
|
|
|
.set = bond_option_arp_ip_targets_set
|
|
|
|
},
|
2022-02-21 13:54:57 +08:00
|
|
|
[BOND_OPT_NS_TARGETS] = {
|
|
|
|
.id = BOND_OPT_NS_TARGETS,
|
|
|
|
.name = "ns_ip6_target",
|
|
|
|
.desc = "NS targets in ffff:ffff::ffff:ffff form",
|
|
|
|
.flags = BOND_OPTFLAG_RAWVAL,
|
|
|
|
.set = bond_option_ns_ip6_targets_set
|
|
|
|
},
|
2014-01-22 21:53:25 +08:00
|
|
|
[BOND_OPT_DOWNDELAY] = {
|
|
|
|
.id = BOND_OPT_DOWNDELAY,
|
|
|
|
.name = "downdelay",
|
|
|
|
.desc = "Delay before considering link down, in milliseconds",
|
|
|
|
.values = bond_intmax_tbl,
|
|
|
|
.set = bond_option_downdelay_set
|
|
|
|
},
|
2014-01-22 21:53:26 +08:00
|
|
|
[BOND_OPT_UPDELAY] = {
|
|
|
|
.id = BOND_OPT_UPDELAY,
|
|
|
|
.name = "updelay",
|
|
|
|
.desc = "Delay before considering link up, in milliseconds",
|
|
|
|
.values = bond_intmax_tbl,
|
|
|
|
.set = bond_option_updelay_set
|
|
|
|
},
|
2021-08-02 11:02:19 +08:00
|
|
|
[BOND_OPT_LACP_ACTIVE] = {
|
|
|
|
.id = BOND_OPT_LACP_ACTIVE,
|
|
|
|
.name = "lacp_active",
|
|
|
|
.desc = "Send LACPDU frames with configured lacp rate or acts as speak when spoken to",
|
|
|
|
.flags = BOND_OPTFLAG_IFDOWN,
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
|
|
|
|
.values = bond_lacp_active,
|
|
|
|
.set = bond_option_lacp_active_set
|
|
|
|
},
|
2014-01-22 21:53:27 +08:00
|
|
|
[BOND_OPT_LACP_RATE] = {
|
|
|
|
.id = BOND_OPT_LACP_RATE,
|
|
|
|
.name = "lacp_rate",
|
|
|
|
.desc = "LACPDU tx rate to request from 802.3ad partner",
|
|
|
|
.flags = BOND_OPTFLAG_IFDOWN,
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
|
|
|
|
.values = bond_lacp_rate_tbl,
|
|
|
|
.set = bond_option_lacp_rate_set
|
|
|
|
},
|
2014-01-22 21:53:28 +08:00
|
|
|
[BOND_OPT_MINLINKS] = {
|
|
|
|
.id = BOND_OPT_MINLINKS,
|
|
|
|
.name = "min_links",
|
|
|
|
.desc = "Minimum number of available links before turning on carrier",
|
|
|
|
.values = bond_intmax_tbl,
|
|
|
|
.set = bond_option_min_links_set
|
|
|
|
},
|
2014-01-22 21:53:29 +08:00
|
|
|
[BOND_OPT_AD_SELECT] = {
|
|
|
|
.id = BOND_OPT_AD_SELECT,
|
|
|
|
.name = "ad_select",
|
|
|
|
.desc = "803.ad aggregation selection logic",
|
|
|
|
.flags = BOND_OPTFLAG_IFDOWN,
|
|
|
|
.values = bond_ad_select_tbl,
|
|
|
|
.set = bond_option_ad_select_set
|
|
|
|
},
|
2014-01-22 21:53:30 +08:00
|
|
|
[BOND_OPT_NUM_PEER_NOTIF] = {
|
|
|
|
.id = BOND_OPT_NUM_PEER_NOTIF,
|
|
|
|
.name = "num_unsol_na",
|
|
|
|
.desc = "Number of peer notifications to send on failover event",
|
|
|
|
.values = bond_num_peer_notif_tbl,
|
|
|
|
.set = bond_option_num_peer_notif_set
|
|
|
|
},
|
2014-01-22 21:53:31 +08:00
|
|
|
[BOND_OPT_MIIMON] = {
|
|
|
|
.id = BOND_OPT_MIIMON,
|
|
|
|
.name = "miimon",
|
|
|
|
.desc = "Link check interval in milliseconds",
|
|
|
|
.values = bond_intmax_tbl,
|
|
|
|
.set = bond_option_miimon_set
|
|
|
|
},
|
2022-06-21 15:49:19 +08:00
|
|
|
[BOND_OPT_PRIO] = {
|
|
|
|
.id = BOND_OPT_PRIO,
|
|
|
|
.name = "prio",
|
|
|
|
.desc = "Link priority for failover re-selection",
|
|
|
|
.flags = BOND_OPTFLAG_RAWVAL,
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP) |
|
|
|
|
BIT(BOND_MODE_TLB) |
|
|
|
|
BIT(BOND_MODE_ALB)),
|
|
|
|
.set = bond_option_prio_set
|
|
|
|
},
|
2014-01-22 21:53:32 +08:00
|
|
|
[BOND_OPT_PRIMARY] = {
|
|
|
|
.id = BOND_OPT_PRIMARY,
|
|
|
|
.name = "primary",
|
|
|
|
.desc = "Primary network device to use",
|
|
|
|
.flags = BOND_OPTFLAG_RAWVAL,
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP) |
|
|
|
|
BIT(BOND_MODE_TLB) |
|
|
|
|
BIT(BOND_MODE_ALB)),
|
|
|
|
.set = bond_option_primary_set
|
|
|
|
},
|
2014-01-22 21:53:33 +08:00
|
|
|
[BOND_OPT_PRIMARY_RESELECT] = {
|
|
|
|
.id = BOND_OPT_PRIMARY_RESELECT,
|
|
|
|
.name = "primary_reselect",
|
|
|
|
.desc = "Reselect primary slave once it comes up",
|
|
|
|
.values = bond_primary_reselect_tbl,
|
|
|
|
.set = bond_option_primary_reselect_set
|
|
|
|
},
|
2014-01-22 21:53:34 +08:00
|
|
|
[BOND_OPT_USE_CARRIER] = {
|
|
|
|
.id = BOND_OPT_USE_CARRIER,
|
|
|
|
.name = "use_carrier",
|
|
|
|
.desc = "Use netif_carrier_ok (vs MII ioctls) in miimon",
|
|
|
|
.values = bond_use_carrier_tbl,
|
|
|
|
.set = bond_option_use_carrier_set
|
|
|
|
},
|
2014-01-22 21:53:35 +08:00
|
|
|
[BOND_OPT_ACTIVE_SLAVE] = {
|
|
|
|
.id = BOND_OPT_ACTIVE_SLAVE,
|
|
|
|
.name = "active_slave",
|
|
|
|
.desc = "Currently active slave",
|
|
|
|
.flags = BOND_OPTFLAG_RAWVAL,
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP) |
|
|
|
|
BIT(BOND_MODE_TLB) |
|
|
|
|
BIT(BOND_MODE_ALB)),
|
|
|
|
.set = bond_option_active_slave_set
|
|
|
|
},
|
2014-01-22 21:53:36 +08:00
|
|
|
[BOND_OPT_QUEUE_ID] = {
|
|
|
|
.id = BOND_OPT_QUEUE_ID,
|
|
|
|
.name = "queue_id",
|
|
|
|
.desc = "Set queue id of a slave",
|
|
|
|
.flags = BOND_OPTFLAG_RAWVAL,
|
|
|
|
.set = bond_option_queue_id_set
|
|
|
|
},
|
2014-01-22 21:53:37 +08:00
|
|
|
[BOND_OPT_ALL_SLAVES_ACTIVE] = {
|
|
|
|
.id = BOND_OPT_ALL_SLAVES_ACTIVE,
|
|
|
|
.name = "all_slaves_active",
|
|
|
|
.desc = "Keep all frames received on an interface by setting active flag for all slaves",
|
|
|
|
.values = bond_all_slaves_active_tbl,
|
|
|
|
.set = bond_option_all_slaves_active_set
|
|
|
|
},
|
2014-01-22 21:53:38 +08:00
|
|
|
[BOND_OPT_RESEND_IGMP] = {
|
|
|
|
.id = BOND_OPT_RESEND_IGMP,
|
|
|
|
.name = "resend_igmp",
|
|
|
|
.desc = "Number of IGMP membership reports to send on link failure",
|
|
|
|
.values = bond_resend_igmp_tbl,
|
|
|
|
.set = bond_option_resend_igmp_set
|
|
|
|
},
|
2014-01-22 21:53:39 +08:00
|
|
|
[BOND_OPT_LP_INTERVAL] = {
|
|
|
|
.id = BOND_OPT_LP_INTERVAL,
|
|
|
|
.name = "lp_interval",
|
|
|
|
.desc = "The number of seconds between instances where the bonding driver sends learning packets to each slave's peer switch",
|
|
|
|
.values = bond_lp_interval_tbl,
|
|
|
|
.set = bond_option_lp_interval_set
|
|
|
|
},
|
2014-01-22 21:53:40 +08:00
|
|
|
[BOND_OPT_SLAVES] = {
|
|
|
|
.id = BOND_OPT_SLAVES,
|
|
|
|
.name = "slaves",
|
|
|
|
.desc = "Slave membership management",
|
|
|
|
.flags = BOND_OPTFLAG_RAWVAL,
|
|
|
|
.set = bond_option_slaves_set
|
|
|
|
},
|
2014-04-23 07:30:22 +08:00
|
|
|
[BOND_OPT_TLB_DYNAMIC_LB] = {
|
|
|
|
.id = BOND_OPT_TLB_DYNAMIC_LB,
|
2014-05-08 20:23:54 +08:00
|
|
|
.name = "tlb_dynamic_lb",
|
2014-04-23 07:30:22 +08:00
|
|
|
.desc = "Enable dynamic flow shuffling",
|
2018-05-15 02:48:09 +08:00
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_TLB) | BIT(BOND_MODE_ALB)),
|
2014-04-23 07:30:22 +08:00
|
|
|
.values = bond_tlb_dynamic_lb_tbl,
|
|
|
|
.flags = BOND_OPTFLAG_IFDOWN,
|
|
|
|
.set = bond_option_tlb_dynamic_lb_set,
|
2015-05-09 15:01:55 +08:00
|
|
|
},
|
|
|
|
[BOND_OPT_AD_ACTOR_SYS_PRIO] = {
|
|
|
|
.id = BOND_OPT_AD_ACTOR_SYS_PRIO,
|
|
|
|
.name = "ad_actor_sys_prio",
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
|
|
|
|
.values = bond_ad_actor_sys_prio_tbl,
|
|
|
|
.set = bond_option_ad_actor_sys_prio_set,
|
|
|
|
},
|
2015-05-09 15:01:56 +08:00
|
|
|
[BOND_OPT_AD_ACTOR_SYSTEM] = {
|
|
|
|
.id = BOND_OPT_AD_ACTOR_SYSTEM,
|
|
|
|
.name = "ad_actor_system",
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
|
2016-02-05 00:42:28 +08:00
|
|
|
.flags = BOND_OPTFLAG_RAWVAL,
|
2015-05-09 15:01:56 +08:00
|
|
|
.set = bond_option_ad_actor_system_set,
|
|
|
|
},
|
2015-05-09 15:01:57 +08:00
|
|
|
[BOND_OPT_AD_USER_PORT_KEY] = {
|
|
|
|
.id = BOND_OPT_AD_USER_PORT_KEY,
|
|
|
|
.name = "ad_user_port_key",
|
|
|
|
.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
|
|
|
|
.flags = BOND_OPTFLAG_IFDOWN,
|
|
|
|
.values = bond_ad_user_port_key_tbl,
|
|
|
|
.set = bond_option_ad_user_port_key_set,
|
2015-07-24 21:50:31 +08:00
|
|
|
},
|
|
|
|
[BOND_OPT_NUM_PEER_NOTIF_ALIAS] = {
|
|
|
|
.id = BOND_OPT_NUM_PEER_NOTIF_ALIAS,
|
|
|
|
.name = "num_grat_arp",
|
|
|
|
.desc = "Number of peer notifications to send on failover event",
|
|
|
|
.values = bond_num_peer_notif_tbl,
|
|
|
|
.set = bond_option_num_peer_notif_set
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
},
|
|
|
|
[BOND_OPT_PEER_NOTIF_DELAY] = {
|
|
|
|
.id = BOND_OPT_PEER_NOTIF_DELAY,
|
|
|
|
.name = "peer_notif_delay",
|
|
|
|
.desc = "Delay between each peer notification on failover event, in milliseconds",
|
|
|
|
.values = bond_intmax_tbl,
|
|
|
|
.set = bond_option_peer_notif_delay_set
|
2015-05-09 15:01:57 +08:00
|
|
|
}
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
};
|
|
|
|
|
2014-05-08 20:23:54 +08:00
|
|
|
/* Searches for an option by name */
|
|
|
|
const struct bond_option *bond_opt_get_by_name(const char *name)
|
|
|
|
{
|
|
|
|
const struct bond_option *opt;
|
|
|
|
int option;
|
|
|
|
|
|
|
|
for (option = 0; option < BOND_OPT_LAST; option++) {
|
|
|
|
opt = bond_opt_get(option);
|
|
|
|
if (opt && !strcmp(opt->name, name))
|
|
|
|
return opt;
|
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
/* Searches for a value in opt's values[] table */
|
2014-03-05 08:36:44 +08:00
|
|
|
const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val)
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
{
|
2014-03-05 08:36:44 +08:00
|
|
|
const struct bond_option *opt;
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
int i;
|
|
|
|
|
|
|
|
opt = bond_opt_get(option);
|
|
|
|
if (WARN_ON(!opt))
|
|
|
|
return NULL;
|
|
|
|
for (i = 0; opt->values && opt->values[i].string; i++)
|
|
|
|
if (opt->values[i].value == val)
|
|
|
|
return &opt->values[i];
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Searches for a value in opt's values[] table which matches the flagmask */
|
2014-03-05 08:36:44 +08:00
|
|
|
static const struct bond_opt_value *bond_opt_get_flags(const struct bond_option *opt,
|
2017-06-26 23:49:46 +08:00
|
|
|
u32 flagmask)
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; opt->values && opt->values[i].string; i++)
|
|
|
|
if (opt->values[i].flags & flagmask)
|
|
|
|
return &opt->values[i];
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* If maxval is missing then there's no range to check. In case minval is
|
|
|
|
* missing then it's considered to be 0.
|
|
|
|
*/
|
|
|
|
static bool bond_opt_check_range(const struct bond_option *opt, u64 val)
|
|
|
|
{
|
2014-03-05 08:36:44 +08:00
|
|
|
const struct bond_opt_value *minval, *maxval;
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
|
|
|
|
minval = bond_opt_get_flags(opt, BOND_VALFLAG_MIN);
|
|
|
|
maxval = bond_opt_get_flags(opt, BOND_VALFLAG_MAX);
|
|
|
|
if (!maxval || (minval && val < minval->value) || val > maxval->value)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* bond_opt_parse - parse option value
|
|
|
|
* @opt: the option to parse against
|
|
|
|
* @val: value to parse
|
|
|
|
*
|
|
|
|
* This function tries to extract the value from @val and check if it's
|
|
|
|
* a possible match for the option and returns NULL if a match isn't found,
|
|
|
|
* or the struct_opt_value that matched. It also strips the new line from
|
|
|
|
* @val->string if it's present.
|
|
|
|
*/
|
2014-03-05 08:36:44 +08:00
|
|
|
const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,
|
|
|
|
struct bond_opt_value *val)
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
{
|
|
|
|
char *p, valstr[BOND_OPT_MAX_NAMELEN + 1] = { 0, };
|
2014-03-05 08:36:44 +08:00
|
|
|
const struct bond_opt_value *tbl;
|
|
|
|
const struct bond_opt_value *ret = NULL;
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
bool checkval;
|
|
|
|
int i, rv;
|
|
|
|
|
|
|
|
/* No parsing if the option wants a raw val */
|
|
|
|
if (opt->flags & BOND_OPTFLAG_RAWVAL)
|
|
|
|
return val;
|
|
|
|
|
|
|
|
tbl = opt->values;
|
|
|
|
if (!tbl)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* ULLONG_MAX is used to bypass string processing */
|
|
|
|
checkval = val->value != ULLONG_MAX;
|
|
|
|
if (!checkval) {
|
|
|
|
if (!val->string)
|
|
|
|
goto out;
|
|
|
|
p = strchr(val->string, '\n');
|
|
|
|
if (p)
|
|
|
|
*p = '\0';
|
|
|
|
for (p = val->string; *p; p++)
|
|
|
|
if (!(isdigit(*p) || isspace(*p)))
|
|
|
|
break;
|
|
|
|
/* The following code extracts the string to match or the value
|
|
|
|
* and sets checkval appropriately
|
|
|
|
*/
|
|
|
|
if (*p) {
|
|
|
|
rv = sscanf(val->string, "%32s", valstr);
|
|
|
|
} else {
|
|
|
|
rv = sscanf(val->string, "%llu", &val->value);
|
|
|
|
checkval = true;
|
|
|
|
}
|
|
|
|
if (!rv)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; tbl[i].string; i++) {
|
|
|
|
/* Check for exact match */
|
|
|
|
if (checkval) {
|
|
|
|
if (val->value == tbl[i].value)
|
|
|
|
ret = &tbl[i];
|
|
|
|
} else {
|
|
|
|
if (!strcmp(valstr, "default") &&
|
|
|
|
(tbl[i].flags & BOND_VALFLAG_DEFAULT))
|
|
|
|
ret = &tbl[i];
|
|
|
|
|
|
|
|
if (!strcmp(valstr, tbl[i].string))
|
|
|
|
ret = &tbl[i];
|
|
|
|
}
|
|
|
|
/* Found an exact match */
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
/* Possible range match */
|
|
|
|
if (checkval && bond_opt_check_range(opt, val->value))
|
|
|
|
ret = val;
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Check opt's dependencies against bond mode and currently set options */
|
|
|
|
static int bond_opt_check_deps(struct bonding *bond,
|
|
|
|
const struct bond_option *opt)
|
|
|
|
{
|
|
|
|
struct bond_params *params = &bond->params;
|
|
|
|
|
|
|
|
if (test_bit(params->mode, &opt->unsuppmodes))
|
|
|
|
return -EACCES;
|
|
|
|
if ((opt->flags & BOND_OPTFLAG_NOSLAVES) && bond_has_slaves(bond))
|
|
|
|
return -ENOTEMPTY;
|
|
|
|
if ((opt->flags & BOND_OPTFLAG_IFDOWN) && (bond->dev->flags & IFF_UP))
|
|
|
|
return -EBUSY;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bond_opt_dep_print(struct bonding *bond,
|
2022-06-09 02:14:56 +08:00
|
|
|
const struct bond_option *opt,
|
|
|
|
struct nlattr *bad_attr,
|
|
|
|
struct netlink_ext_ack *extack)
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
{
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *modeval;
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
struct bond_params *params;
|
|
|
|
|
|
|
|
params = &bond->params;
|
2014-01-22 21:53:17 +08:00
|
|
|
modeval = bond_opt_get_val(BOND_OPT_MODE, params->mode);
|
2022-06-09 02:14:56 +08:00
|
|
|
if (test_bit(params->mode, &opt->unsuppmodes)) {
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "option %s: mode dependency failed, not supported in mode %s(%llu)\n",
|
|
|
|
opt->name, modeval->string, modeval->value);
|
2022-06-09 02:14:56 +08:00
|
|
|
NL_SET_ERR_MSG_ATTR(extack, bad_attr,
|
|
|
|
"option not supported in mode");
|
|
|
|
}
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void bond_opt_error_interpret(struct bonding *bond,
|
|
|
|
const struct bond_option *opt,
|
2022-06-09 02:14:56 +08:00
|
|
|
int error, const struct bond_opt_value *val,
|
|
|
|
struct nlattr *bad_attr,
|
|
|
|
struct netlink_ext_ack *extack)
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
{
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *minval, *maxval;
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
char *p;
|
|
|
|
|
|
|
|
switch (error) {
|
|
|
|
case -EINVAL:
|
2022-06-09 02:14:56 +08:00
|
|
|
NL_SET_ERR_MSG_ATTR(extack, bad_attr, "invalid option value");
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
if (val) {
|
|
|
|
if (val->string) {
|
|
|
|
/* sometimes RAWVAL opts may have new lines */
|
|
|
|
p = strchr(val->string, '\n');
|
|
|
|
if (p)
|
|
|
|
*p = '\0';
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "option %s: invalid value (%s)\n",
|
|
|
|
opt->name, val->string);
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
} else {
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "option %s: invalid value (%llu)\n",
|
|
|
|
opt->name, val->value);
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
minval = bond_opt_get_flags(opt, BOND_VALFLAG_MIN);
|
|
|
|
maxval = bond_opt_get_flags(opt, BOND_VALFLAG_MAX);
|
|
|
|
if (!maxval)
|
|
|
|
break;
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "option %s: allowed values %llu - %llu\n",
|
|
|
|
opt->name, minval ? minval->value : 0, maxval->value);
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
break;
|
|
|
|
case -EACCES:
|
2022-06-09 02:14:56 +08:00
|
|
|
bond_opt_dep_print(bond, opt, bad_attr, extack);
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
break;
|
|
|
|
case -ENOTEMPTY:
|
2022-06-09 02:14:56 +08:00
|
|
|
NL_SET_ERR_MSG_ATTR(extack, bad_attr,
|
|
|
|
"unable to set option because the bond device has slaves");
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "option %s: unable to set because the bond device has slaves\n",
|
|
|
|
opt->name);
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
break;
|
|
|
|
case -EBUSY:
|
2022-06-09 02:14:56 +08:00
|
|
|
NL_SET_ERR_MSG_ATTR(extack, bad_attr,
|
|
|
|
"unable to set option because the bond is up");
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "option %s: unable to set because the bond device is up\n",
|
|
|
|
opt->name);
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
break;
|
2021-03-14 22:56:29 +08:00
|
|
|
case -ENODEV:
|
|
|
|
if (val && val->string) {
|
|
|
|
p = strchr(val->string, '\n');
|
|
|
|
if (p)
|
|
|
|
*p = '\0';
|
|
|
|
netdev_err(bond->dev, "option %s: interface %s does not exist!\n",
|
|
|
|
opt->name, val->string);
|
2022-06-09 02:14:56 +08:00
|
|
|
NL_SET_ERR_MSG_ATTR(extack, bad_attr,
|
|
|
|
"interface does not exist");
|
2021-03-14 22:56:29 +08:00
|
|
|
}
|
|
|
|
break;
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* __bond_opt_set - set a bonding option
|
|
|
|
* @bond: target bond device
|
|
|
|
* @option: option to set
|
|
|
|
* @val: value to set it to
|
2022-06-09 02:14:56 +08:00
|
|
|
* @bad_attr: netlink attribue that caused the error
|
|
|
|
* @extack: extended netlink error structure, used when an error message
|
|
|
|
* needs to be returned to the caller via netlink
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
*
|
|
|
|
* This function is used to change the bond's option value, it can be
|
|
|
|
* used for both enabling/changing an option and for disabling it. RTNL lock
|
|
|
|
* must be obtained before calling this function.
|
|
|
|
*/
|
|
|
|
int __bond_opt_set(struct bonding *bond,
|
2022-06-09 02:14:56 +08:00
|
|
|
unsigned int option, struct bond_opt_value *val,
|
|
|
|
struct nlattr *bad_attr, struct netlink_ext_ack *extack)
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
{
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *retval = NULL;
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
const struct bond_option *opt;
|
|
|
|
int ret = -ENOENT;
|
|
|
|
|
|
|
|
ASSERT_RTNL();
|
|
|
|
|
|
|
|
opt = bond_opt_get(option);
|
|
|
|
if (WARN_ON(!val) || WARN_ON(!opt))
|
|
|
|
goto out;
|
|
|
|
ret = bond_opt_check_deps(bond, opt);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
retval = bond_opt_parse(opt, val);
|
|
|
|
if (!retval) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
ret = opt->set(bond, retval);
|
|
|
|
out:
|
|
|
|
if (ret)
|
2022-06-09 02:14:56 +08:00
|
|
|
bond_opt_error_interpret(bond, opt, ret, val, bad_attr, extack);
|
2017-05-27 22:14:35 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
/**
|
|
|
|
* __bond_opt_set_notify - set a bonding option
|
|
|
|
* @bond: target bond device
|
|
|
|
* @option: option to set
|
|
|
|
* @val: value to set it to
|
|
|
|
*
|
|
|
|
* This function is used to change the bond's option value and trigger
|
|
|
|
* a notification to user sapce. It can be used for both enabling/changing
|
|
|
|
* an option and for disabling it. RTNL lock must be obtained before calling
|
|
|
|
* this function.
|
|
|
|
*/
|
|
|
|
int __bond_opt_set_notify(struct bonding *bond,
|
|
|
|
unsigned int option, struct bond_opt_value *val)
|
|
|
|
{
|
2021-06-03 21:19:04 +08:00
|
|
|
int ret;
|
2017-05-27 22:14:35 +08:00
|
|
|
|
|
|
|
ASSERT_RTNL();
|
|
|
|
|
2022-06-09 02:14:56 +08:00
|
|
|
ret = __bond_opt_set(bond, option, val, NULL, NULL);
|
2017-05-27 22:14:35 +08:00
|
|
|
|
|
|
|
if (!ret && (bond->dev->reg_state == NETREG_REGISTERED))
|
2014-08-19 22:02:12 +08:00
|
|
|
call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev);
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* bond_opt_tryset_rtnl - try to acquire rtnl and call __bond_opt_set
|
|
|
|
* @bond: target bond device
|
|
|
|
* @option: option to set
|
|
|
|
* @buf: value to set it to
|
|
|
|
*
|
|
|
|
* This function tries to acquire RTNL without blocking and if successful
|
|
|
|
* calls __bond_opt_set. It is mainly used for sysfs option manipulation.
|
|
|
|
*/
|
|
|
|
int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf)
|
|
|
|
{
|
|
|
|
struct bond_opt_value optval;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!rtnl_trylock())
|
|
|
|
return restart_syscall();
|
|
|
|
bond_opt_initstr(&optval, buf);
|
2017-05-27 22:14:35 +08:00
|
|
|
ret = __bond_opt_set_notify(bond, option, &optval);
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
rtnl_unlock();
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* bond_opt_get - get a pointer to an option
|
|
|
|
* @option: option for which to return a pointer
|
|
|
|
*
|
|
|
|
* This function checks if option is valid and if so returns a pointer
|
|
|
|
* to its entry in the bond_opts[] option array.
|
|
|
|
*/
|
2014-03-05 08:36:44 +08:00
|
|
|
const struct bond_option *bond_opt_get(unsigned int option)
|
bonding: add infrastructure for an option API
This patch adds the necessary basic infrastructure to support
centralized and unified option manipulation API for the bonding. The new
structure bond_option will be used to describe each option with its
dependencies on modes which will be checked automatically thus removing a
lot of duplicated code. Also automatic range checking is added for
some options. Currently the option setting function requires RTNL to
be acquired prior to calling it, since many options already rely on RTNL
it seemed like the best choice to protect all against common race
conditions.
In order to add an option the following steps need to be done:
1. Add an entry BOND_OPT_<option> to bond_options.h so it gets a unique id
and a bit corresponding to the id
2. Add a bond_option entry to the bond_opts[] array in bond_options.c which
describes the option, its dependencies and its manipulation function
3. Add code to export the option through sysfs and/or as a module parameter
(the sysfs export will be made automatically in the future)
The options can have different flags set, currently the following are
supported:
BOND_OPTFLAG_NOSLAVES - require that the bond device has no slaves prior
to setting the option
BOND_OPTFLAG_IFDOWN - require that the bond device is down prior to
setting the option
BOND_OPTFLAG_RAWVAL - don't parse the value but return it raw for the
option to parse
There's a new value structure to describe different types of values
which can have the following flags:
BOND_VALFLAG_DEFAULT - marks the default option (permanent string alias
to this option is "default")
BOND_VALFLAG_MIN - the minimum value that this option can have
BOND_VALFLAG_MAX - the maximum value that this option can have
An example would be nice here, so if we have an option which can have
the values "off"(2), "special"(4, default) and supports a range, say
16 - 32, it should be defined as follows:
"off", 2,
"special", 4, BOND_VALFLAG_DEFAULT,
"rangemin", 16, BOND_VALFLAG_MIN,
"rangemax", 32, BOND_VALFLAG_MAX
So we have the valid intervals: [2, 2], [4, 4], [16, 32]
Also the valid strings: "off" = 2, "special" and "default" = 4
"rangemin" = 16, "rangemax" = 32
BOND_VALFLAG_(MIN|MAX) can be used to specify a valid range for an
option, if MIN is omitted then 0 is considered as a minimum. If an
exact match is found in the values[] table it will be returned,
otherwise the range is tried (if available).
The option parameter passing is done by using a special structure called
bond_opt_value which can take either a string or a value to parse. One
of the bond_opt_init(val|str) macros should be used depending on which
one does the user want to parse (string or value). Then a call to
__bond_opt_set should be done under RTNL.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 21:53:16 +08:00
|
|
|
{
|
|
|
|
if (!BOND_OPT_VALID(option))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
return &bond_opts[option];
|
|
|
|
}
|
|
|
|
|
2021-01-17 22:59:45 +08:00
|
|
|
static bool bond_set_xfrm_features(struct bonding *bond)
|
bonding: fix feature flag setting at init time
Don't try to adjust XFRM support flags if the bond device isn't yet
registered. Bad things can currently happen when netdev_change_features()
is called without having wanted_features fully filled in yet. This code
runs both on post-module-load mode changes, as well as at module init
time, and when run at module init time, it is before register_netdevice()
has been called and filled in wanted_features. The empty wanted_features
led to features also getting emptied out, which was definitely not the
intended behavior, so prevent that from happening.
Originally, I'd hoped to stop adjusting wanted_features at all in the
bonding driver, as it's documented as being something only the network
core should touch, but we actually do need to do this to properly update
both the features and wanted_features fields when changing the bond type,
or we get to a situation where ethtool sees:
esp-hw-offload: off [requested on]
I do think we should be using netdev_update_features instead of
netdev_change_features here though, so we only send notifiers when the
features actually changed.
Fixes: a3b658cfb664 ("bonding: allow xfrm offload setup post-module-load")
Reported-by: Ivan Vecera <ivecera@redhat.com>
Suggested-by: Ivan Vecera <ivecera@redhat.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Link: https://lore.kernel.org/r/20201205172229.576587-1-jarod@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-06 01:22:29 +08:00
|
|
|
{
|
|
|
|
if (!IS_ENABLED(CONFIG_XFRM_OFFLOAD))
|
2021-01-17 22:59:45 +08:00
|
|
|
return false;
|
bonding: fix feature flag setting at init time
Don't try to adjust XFRM support flags if the bond device isn't yet
registered. Bad things can currently happen when netdev_change_features()
is called without having wanted_features fully filled in yet. This code
runs both on post-module-load mode changes, as well as at module init
time, and when run at module init time, it is before register_netdevice()
has been called and filled in wanted_features. The empty wanted_features
led to features also getting emptied out, which was definitely not the
intended behavior, so prevent that from happening.
Originally, I'd hoped to stop adjusting wanted_features at all in the
bonding driver, as it's documented as being something only the network
core should touch, but we actually do need to do this to properly update
both the features and wanted_features fields when changing the bond type,
or we get to a situation where ethtool sees:
esp-hw-offload: off [requested on]
I do think we should be using netdev_update_features instead of
netdev_change_features here though, so we only send notifiers when the
features actually changed.
Fixes: a3b658cfb664 ("bonding: allow xfrm offload setup post-module-load")
Reported-by: Ivan Vecera <ivecera@redhat.com>
Suggested-by: Ivan Vecera <ivecera@redhat.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Link: https://lore.kernel.org/r/20201205172229.576587-1-jarod@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-06 01:22:29 +08:00
|
|
|
|
2021-01-17 22:59:45 +08:00
|
|
|
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
|
|
|
|
bond->dev->wanted_features |= BOND_XFRM_FEATURES;
|
bonding: fix feature flag setting at init time
Don't try to adjust XFRM support flags if the bond device isn't yet
registered. Bad things can currently happen when netdev_change_features()
is called without having wanted_features fully filled in yet. This code
runs both on post-module-load mode changes, as well as at module init
time, and when run at module init time, it is before register_netdevice()
has been called and filled in wanted_features. The empty wanted_features
led to features also getting emptied out, which was definitely not the
intended behavior, so prevent that from happening.
Originally, I'd hoped to stop adjusting wanted_features at all in the
bonding driver, as it's documented as being something only the network
core should touch, but we actually do need to do this to properly update
both the features and wanted_features fields when changing the bond type,
or we get to a situation where ethtool sees:
esp-hw-offload: off [requested on]
I do think we should be using netdev_update_features instead of
netdev_change_features here though, so we only send notifiers when the
features actually changed.
Fixes: a3b658cfb664 ("bonding: allow xfrm offload setup post-module-load")
Reported-by: Ivan Vecera <ivecera@redhat.com>
Suggested-by: Ivan Vecera <ivecera@redhat.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Link: https://lore.kernel.org/r/20201205172229.576587-1-jarod@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-06 01:22:29 +08:00
|
|
|
else
|
2021-01-17 22:59:45 +08:00
|
|
|
bond->dev->wanted_features &= ~BOND_XFRM_FEATURES;
|
bonding: fix feature flag setting at init time
Don't try to adjust XFRM support flags if the bond device isn't yet
registered. Bad things can currently happen when netdev_change_features()
is called without having wanted_features fully filled in yet. This code
runs both on post-module-load mode changes, as well as at module init
time, and when run at module init time, it is before register_netdevice()
has been called and filled in wanted_features. The empty wanted_features
led to features also getting emptied out, which was definitely not the
intended behavior, so prevent that from happening.
Originally, I'd hoped to stop adjusting wanted_features at all in the
bonding driver, as it's documented as being something only the network
core should touch, but we actually do need to do this to properly update
both the features and wanted_features fields when changing the bond type,
or we get to a situation where ethtool sees:
esp-hw-offload: off [requested on]
I do think we should be using netdev_update_features instead of
netdev_change_features here though, so we only send notifiers when the
features actually changed.
Fixes: a3b658cfb664 ("bonding: allow xfrm offload setup post-module-load")
Reported-by: Ivan Vecera <ivecera@redhat.com>
Suggested-by: Ivan Vecera <ivecera@redhat.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Link: https://lore.kernel.org/r/20201205172229.576587-1-jarod@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-06 01:22:29 +08:00
|
|
|
|
2021-01-17 22:59:45 +08:00
|
|
|
return true;
|
bonding: fix feature flag setting at init time
Don't try to adjust XFRM support flags if the bond device isn't yet
registered. Bad things can currently happen when netdev_change_features()
is called without having wanted_features fully filled in yet. This code
runs both on post-module-load mode changes, as well as at module init
time, and when run at module init time, it is before register_netdevice()
has been called and filled in wanted_features. The empty wanted_features
led to features also getting emptied out, which was definitely not the
intended behavior, so prevent that from happening.
Originally, I'd hoped to stop adjusting wanted_features at all in the
bonding driver, as it's documented as being something only the network
core should touch, but we actually do need to do this to properly update
both the features and wanted_features fields when changing the bond type,
or we get to a situation where ethtool sees:
esp-hw-offload: off [requested on]
I do think we should be using netdev_update_features instead of
netdev_change_features here though, so we only send notifiers when the
features actually changed.
Fixes: a3b658cfb664 ("bonding: allow xfrm offload setup post-module-load")
Reported-by: Ivan Vecera <ivecera@redhat.com>
Suggested-by: Ivan Vecera <ivecera@redhat.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Link: https://lore.kernel.org/r/20201205172229.576587-1-jarod@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-06 01:22:29 +08:00
|
|
|
}
|
|
|
|
|
net/bonding: Implement TLS TX device offload
Implement TLS TX device offload for bonding interfaces.
This allows kTLS sockets running on a bond to benefit from the
device offload on capable lower devices.
To allow a simple and fast maintenance of the TLS context in SW and
lower devices, we bind the TLS socket to a specific lower dev.
To achieve a behavior similar to SW kTLS, we support only balance-xor
and 802.3ad modes, with xmit_hash_policy=layer3+4. This is enforced
in bond_sk_check(), done in a previous patch.
For the above configuration, the SW implementation keeps picking the
same exact lower dev for all the socket's SKBs. The device offload
behaves similarly, making the decision once at the connection creation.
Per socket, the TLS module should work directly with the lowest netdev
in chain, to call the tls_dev_ops operations.
As the bond interface is being bypassed by the TLS module, interacting
directly against the lower devs, there is no way for the bond interface
to disable its device offload capabilities, as long as the mode/policy
config allows it.
Hence, the feature flag is not directly controllable, but just reflects
the current offload status based on the logic under bond_sk_check().
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-17 22:59:46 +08:00
|
|
|
static bool bond_set_tls_features(struct bonding *bond)
|
|
|
|
{
|
|
|
|
if (!IS_ENABLED(CONFIG_TLS_DEVICE))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (bond_sk_check(bond))
|
|
|
|
bond->dev->wanted_features |= BOND_TLS_FEATURES;
|
|
|
|
else
|
|
|
|
bond->dev->wanted_features &= ~BOND_TLS_FEATURES;
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2014-07-15 22:08:57 +08:00
|
|
|
static int bond_option_mode_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
2013-10-18 23:43:34 +08:00
|
|
|
{
|
bonding: set default miimon value for non-arp modes if not set
For some time now, if you load the bonding driver and configure bond
parameters via sysfs using minimal config options, such as specifying
nothing but the mode, relying on defaults for everything else, modes
that cannot use arp monitoring (802.3ad, balance-tlb, balance-alb) all
wind up with both arp_interval=0 (as it should be) and miimon=0, which
means the miimon monitor thread never actually runs. This is particularly
problematic for 802.3ad.
For example, from an LNST recipe I've set up:
$ modprobe bonding max_bonds=0"
$ echo "+t_bond0" > /sys/class/net/bonding_masters"
$ ip link set t_bond0 down"
$ echo "802.3ad" > /sys/class/net/t_bond0/bonding/mode"
$ ip link set ens1f1 down"
$ echo "+ens1f1" > /sys/class/net/t_bond0/bonding/slaves"
$ ip link set ens1f0 down"
$ echo "+ens1f0" > /sys/class/net/t_bond0/bonding/slaves"
$ ethtool -i t_bond0"
$ ip link set ens1f1 up"
$ ip link set ens1f0 up"
$ ip link set t_bond0 up"
$ ip addr add 192.168.9.1/24 dev t_bond0"
$ ip addr add 2002::1/64 dev t_bond0"
This bond comes up okay, but things look slightly suspect in
/proc/net/bonding/t_bond0 output:
$ grep -i mii /proc/net/bonding/t_bond0
MII Status: up
MII Polling Interval (ms): 0
MII Status: up
MII Status: up
Now, pull a cable on one of the ports in the bond, then reconnect it, and
you'll see:
Slave Interface: ens1f0
MII Status: down
Speed: 1000 Mbps
Duplex: full
I believe this became a major issue as of commit 4d2c0cda0744, which for
802.3ad bonds, sets slave->link = BOND_LINK_DOWN, with a comment about
relying on link monitoring via miimon to set it correctly, but since the
miimon work queue never runs, the link just stays marked down.
If we simply tweak bond_option_mode_set() slightly, we can check for the
non-arp modes having no miimon value set, and insert BOND_DEFAULT_MIIMON,
which gets things back in full working order. This problem exists as far
back as 4.14, and might be worth fixing in all stable trees since, though
the work-around is to simply specify an miimon value yourself.
Reported-by: Bob Ball <ball@umich.edu>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-19 02:49:36 +08:00
|
|
|
if (!bond_mode_uses_arp(newval->value)) {
|
|
|
|
if (bond->params.arp_interval) {
|
|
|
|
netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
|
|
|
|
newval->string);
|
|
|
|
/* disable arp monitoring */
|
|
|
|
bond->params.arp_interval = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!bond->params.miimon) {
|
|
|
|
/* set miimon to default value */
|
|
|
|
bond->params.miimon = BOND_DEFAULT_MIIMON;
|
|
|
|
netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
|
|
|
|
bond->params.miimon);
|
|
|
|
}
|
2013-10-18 23:43:34 +08:00
|
|
|
}
|
|
|
|
|
net: bonding: Fix transmit load balancing in balance-alb mode if specified by sysfs
Commit cbf5ecb30560 ("net: bonding: Fix transmit load balancing in
balance-alb mode") tried to fix transmit dynamic load balancing in
balance-alb mode, which wasn't working after commit 8b426dc54cf4
("bonding: remove hardcoded value").
It turned out that my previous patch only fixed the case when
balance-alb was specified as bonding module parameter, and not when
balance-alb mode was set using /sys/class/net/*/bonding/mode (the most
common usage). In the latter case, tlb_dynamic_lb was set up according
to the default mode of the bonding interface, which happens to be
balance-rr.
This additional patch addresses this issue by setting up tlb_dynamic_lb
to 1 if "mode" is set to balance-alb through the sysfs interface.
I didn't add code to change tlb_balance_lb back to the default value for
other modes, because "mode" is usually set up only once during
initialization, and it's not worthwhile to change the static variable
bonding_defaults in bond_main.c to a global variable just for this
purpose.
Commit 8b426dc54cf4 also changes the value of tlb_dynamic_lb for
balance-tlb mode if it is set up using the sysfs interface. I didn't
change that behavior, because the value of tlb_balance_lb can be changed
using the sysfs interface for balance-tlb, and I didn't like changing
the default value back and forth for balance-tlb.
As for balance-alb, /sys/class/net/*/bonding/tlb_balance_lb cannot be
written to. However, I think balance-alb with tlb_dynamic_lb set to 0
is not an intended usage, so there is little use making it writable at
this moment.
Fixes: 8b426dc54cf4 ("bonding: remove hardcoded value")
Reported-by: Reinis Rozitis <r@roze.lv>
Signed-off-by: Kosuke Tatsukawa <tatsu@ab.jp.nec.com>
Cc: stable@vger.kernel.org # v4.12+
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-07 06:47:59 +08:00
|
|
|
if (newval->value == BOND_MODE_ALB)
|
|
|
|
bond->params.tlb_dynamic_lb = 1;
|
|
|
|
|
2013-10-18 23:43:34 +08:00
|
|
|
/* don't cache arp_validate between modes */
|
|
|
|
bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
|
2014-01-22 21:53:17 +08:00
|
|
|
bond->params.mode = newval->value;
|
|
|
|
|
net/bonding: Implement TLS TX device offload
Implement TLS TX device offload for bonding interfaces.
This allows kTLS sockets running on a bond to benefit from the
device offload on capable lower devices.
To allow a simple and fast maintenance of the TLS context in SW and
lower devices, we bind the TLS socket to a specific lower dev.
To achieve a behavior similar to SW kTLS, we support only balance-xor
and 802.3ad modes, with xmit_hash_policy=layer3+4. This is enforced
in bond_sk_check(), done in a previous patch.
For the above configuration, the SW implementation keeps picking the
same exact lower dev for all the socket's SKBs. The device offload
behaves similarly, making the decision once at the connection creation.
Per socket, the TLS module should work directly with the lowest netdev
in chain, to call the tls_dev_ops operations.
As the bond interface is being bypassed by the TLS module, interacting
directly against the lower devs, there is no way for the bond interface
to disable its device offload capabilities, as long as the mode/policy
config allows it.
Hence, the feature flag is not directly controllable, but just reflects
the current offload status based on the logic under bond_sk_check().
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-17 22:59:46 +08:00
|
|
|
if (bond->dev->reg_state == NETREG_REGISTERED) {
|
|
|
|
bool update = false;
|
|
|
|
|
|
|
|
update |= bond_set_xfrm_features(bond);
|
|
|
|
update |= bond_set_tls_features(bond);
|
|
|
|
|
|
|
|
if (update)
|
2021-01-17 22:59:45 +08:00
|
|
|
netdev_update_features(bond->dev);
|
net/bonding: Implement TLS TX device offload
Implement TLS TX device offload for bonding interfaces.
This allows kTLS sockets running on a bond to benefit from the
device offload on capable lower devices.
To allow a simple and fast maintenance of the TLS context in SW and
lower devices, we bind the TLS socket to a specific lower dev.
To achieve a behavior similar to SW kTLS, we support only balance-xor
and 802.3ad modes, with xmit_hash_policy=layer3+4. This is enforced
in bond_sk_check(), done in a previous patch.
For the above configuration, the SW implementation keeps picking the
same exact lower dev for all the socket's SKBs. The device offload
behaves similarly, making the decision once at the connection creation.
Per socket, the TLS module should work directly with the lowest netdev
in chain, to call the tls_dev_ops operations.
As the bond interface is being bypassed by the TLS module, interacting
directly against the lower devs, there is no way for the bond interface
to disable its device offload capabilities, as long as the mode/policy
config allows it.
Hence, the feature flag is not directly controllable, but just reflects
the current offload status based on the logic under bond_sk_check().
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-17 22:59:46 +08:00
|
|
|
}
|
2021-01-17 22:59:45 +08:00
|
|
|
|
2013-10-18 23:43:34 +08:00
|
|
|
return 0;
|
|
|
|
}
|
2013-10-18 23:43:35 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_active_slave_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-10-18 23:43:35 +08:00
|
|
|
{
|
2014-01-22 21:53:35 +08:00
|
|
|
char ifname[IFNAMSIZ] = { 0, };
|
|
|
|
struct net_device *slave_dev;
|
2013-10-18 23:43:35 +08:00
|
|
|
int ret = 0;
|
|
|
|
|
2014-01-22 21:53:35 +08:00
|
|
|
sscanf(newval->string, "%15s", ifname); /* IFNAMSIZ */
|
|
|
|
if (!strlen(ifname) || newval->string[0] == '\n') {
|
|
|
|
slave_dev = NULL;
|
|
|
|
} else {
|
|
|
|
slave_dev = __dev_get_by_name(dev_net(bond->dev), ifname);
|
|
|
|
if (!slave_dev)
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
|
2013-10-18 23:43:35 +08:00
|
|
|
if (slave_dev) {
|
|
|
|
if (!netif_is_bond_slave(slave_dev)) {
|
2019-06-07 22:59:32 +08:00
|
|
|
slave_err(bond->dev, slave_dev, "Device is not bonding slave\n");
|
2013-10-18 23:43:35 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (bond->dev != netdev_master_upper_dev_get(slave_dev)) {
|
2019-06-07 22:59:32 +08:00
|
|
|
slave_err(bond->dev, slave_dev, "Device is not our slave\n");
|
2013-10-18 23:43:35 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
block_netpoll_tx();
|
|
|
|
/* check to see if we are clearing active */
|
|
|
|
if (!slave_dev) {
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Clearing current active slave\n");
|
2014-03-24 02:30:17 +08:00
|
|
|
RCU_INIT_POINTER(bond->curr_active_slave, NULL);
|
2013-10-18 23:43:35 +08:00
|
|
|
bond_select_active_slave(bond);
|
|
|
|
} else {
|
2014-09-12 04:49:24 +08:00
|
|
|
struct slave *old_active = rtnl_dereference(bond->curr_active_slave);
|
2013-10-18 23:43:35 +08:00
|
|
|
struct slave *new_active = bond_slave_get_rtnl(slave_dev);
|
|
|
|
|
|
|
|
BUG_ON(!new_active);
|
|
|
|
|
|
|
|
if (new_active == old_active) {
|
|
|
|
/* do nothing */
|
2019-06-07 22:59:32 +08:00
|
|
|
slave_dbg(bond->dev, new_active->dev, "is already the current active slave\n");
|
2013-10-18 23:43:35 +08:00
|
|
|
} else {
|
|
|
|
if (old_active && (new_active->link == BOND_LINK_UP) &&
|
2014-05-16 03:39:57 +08:00
|
|
|
bond_slave_is_up(new_active)) {
|
2019-06-07 22:59:32 +08:00
|
|
|
slave_dbg(bond->dev, new_active->dev, "Setting as active slave\n");
|
2013-10-18 23:43:35 +08:00
|
|
|
bond_change_active_slave(bond, new_active);
|
|
|
|
} else {
|
2019-06-07 22:59:32 +08:00
|
|
|
slave_err(bond->dev, new_active->dev, "Could not set as active slave; either %s is down or the link is down\n",
|
|
|
|
new_active->dev->name);
|
2013-10-18 23:43:35 +08:00
|
|
|
ret = -EINVAL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
unblock_netpoll_tx();
|
2014-01-22 21:53:35 +08:00
|
|
|
|
2013-10-18 23:43:35 +08:00
|
|
|
return ret;
|
|
|
|
}
|
2013-12-13 06:09:55 +08:00
|
|
|
|
2014-05-08 20:23:54 +08:00
|
|
|
/* There are two tricky bits here. First, if MII monitoring is activated, then
|
|
|
|
* we must disable ARP monitoring. Second, if the timer isn't running, we must
|
|
|
|
* start it.
|
|
|
|
*/
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_miimon_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-13 06:09:55 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting MII monitoring interval to %llu\n",
|
|
|
|
newval->value);
|
2014-01-22 21:53:31 +08:00
|
|
|
bond->params.miimon = newval->value;
|
2013-12-13 06:09:55 +08:00
|
|
|
if (bond->params.updelay)
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Note: Updating updelay (to %d) since it is a multiple of the miimon value\n",
|
|
|
|
bond->params.updelay * bond->params.miimon);
|
2013-12-13 06:09:55 +08:00
|
|
|
if (bond->params.downdelay)
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Note: Updating downdelay (to %d) since it is a multiple of the miimon value\n",
|
|
|
|
bond->params.downdelay * bond->params.miimon);
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
if (bond->params.peer_notif_delay)
|
|
|
|
netdev_dbg(bond->dev, "Note: Updating peer_notif_delay (to %d) since it is a multiple of the miimon value\n",
|
|
|
|
bond->params.peer_notif_delay * bond->params.miimon);
|
2014-01-22 21:53:31 +08:00
|
|
|
if (newval->value && bond->params.arp_interval) {
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "MII monitoring cannot be used with ARP monitoring - disabling ARP monitoring...\n");
|
2013-12-13 06:09:55 +08:00
|
|
|
bond->params.arp_interval = 0;
|
|
|
|
if (bond->params.arp_validate)
|
|
|
|
bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
|
|
|
|
}
|
|
|
|
if (bond->dev->flags & IFF_UP) {
|
|
|
|
/* If the interface is up, we may need to fire off
|
|
|
|
* the MII timer. If the interface is down, the
|
|
|
|
* timer will get fired off when the open function
|
|
|
|
* is called.
|
|
|
|
*/
|
2014-01-22 21:53:31 +08:00
|
|
|
if (!newval->value) {
|
2013-12-13 06:09:55 +08:00
|
|
|
cancel_delayed_work_sync(&bond->mii_work);
|
|
|
|
} else {
|
|
|
|
cancel_delayed_work_sync(&bond->arp_work);
|
|
|
|
queue_delayed_work(bond->wq, &bond->mii_work, 0);
|
|
|
|
}
|
|
|
|
}
|
2014-01-22 21:53:31 +08:00
|
|
|
|
2013-12-13 06:09:55 +08:00
|
|
|
return 0;
|
|
|
|
}
|
2013-12-13 06:10:02 +08:00
|
|
|
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
/* Set up, down and peer notification delays. These must be multiples
|
|
|
|
* of the MII monitoring value, and are stored internally as the
|
|
|
|
* multiplier. Thus, we must translate to MS for the real world.
|
2014-05-08 20:23:54 +08:00
|
|
|
*/
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
static int _bond_option_delay_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval,
|
|
|
|
const char *name,
|
|
|
|
int *target)
|
2013-12-13 06:10:02 +08:00
|
|
|
{
|
2014-01-24 06:43:43 +08:00
|
|
|
int value = newval->value;
|
|
|
|
|
2014-01-22 21:53:26 +08:00
|
|
|
if (!bond->params.miimon) {
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
netdev_err(bond->dev, "Unable to set %s as MII monitoring is disabled\n",
|
|
|
|
name);
|
2013-12-13 06:10:02 +08:00
|
|
|
return -EPERM;
|
|
|
|
}
|
2014-01-24 06:43:43 +08:00
|
|
|
if ((value % bond->params.miimon) != 0) {
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
netdev_warn(bond->dev,
|
|
|
|
"%s (%d) is not a multiple of miimon (%d), value rounded to %d ms\n",
|
|
|
|
name,
|
2014-07-16 01:36:08 +08:00
|
|
|
value, bond->params.miimon,
|
|
|
|
(value / bond->params.miimon) *
|
|
|
|
bond->params.miimon);
|
2013-12-13 06:10:02 +08:00
|
|
|
}
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
*target = value / bond->params.miimon;
|
|
|
|
netdev_dbg(bond->dev, "Setting %s to %d\n",
|
|
|
|
name,
|
|
|
|
*target * bond->params.miimon);
|
2013-12-13 06:10:02 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-13 06:10:09 +08:00
|
|
|
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
static int bond_option_updelay_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
|
|
|
return _bond_option_delay_set(bond, newval, "up delay",
|
|
|
|
&bond->params.updelay);
|
|
|
|
}
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_downdelay_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-13 06:10:09 +08:00
|
|
|
{
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
return _bond_option_delay_set(bond, newval, "down delay",
|
|
|
|
&bond->params.downdelay);
|
|
|
|
}
|
2013-12-13 06:10:09 +08:00
|
|
|
|
bonding: add an option to specify a delay between peer notifications
Currently, gratuitous ARP/ND packets are sent every `miimon'
milliseconds. This commit allows a user to specify a custom delay
through a new option, `peer_notif_delay'.
Like for `updelay' and `downdelay', this delay should be a multiple of
`miimon' to avoid managing an additional work queue. The configuration
logic is copied from `updelay' and `downdelay'. However, the default
value cannot be set using a module parameter: Netlink or sysfs should
be used to configure this feature.
When setting `miimon' to 100 and `peer_notif_delay' to 500, we can
observe the 500 ms delay is respected:
20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28
In bond_mii_monitor(), I have tried to keep the lock logic readable.
The change is due to the fact we cannot rely on a notification to
lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is
only triggered once every N times, while we need to decrement the
counter each time.
iproute2 also needs to be updated to be able to specify this new
attribute through `ip link'.
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-03 01:43:54 +08:00
|
|
|
static int bond_option_peer_notif_delay_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
|
|
|
int ret = _bond_option_delay_set(bond, newval,
|
|
|
|
"peer notification delay",
|
|
|
|
&bond->params.peer_notif_delay);
|
|
|
|
return ret;
|
2013-12-13 06:10:09 +08:00
|
|
|
}
|
2013-12-13 06:10:16 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_use_carrier_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-13 06:10:16 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting use_carrier to %llu\n",
|
|
|
|
newval->value);
|
2014-01-22 21:53:34 +08:00
|
|
|
bond->params.use_carrier = newval->value;
|
2013-12-13 06:10:16 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-13 06:10:24 +08:00
|
|
|
|
2014-05-08 20:23:54 +08:00
|
|
|
/* There are two tricky bits here. First, if ARP monitoring is activated, then
|
|
|
|
* we must disable MII monitoring. Second, if the ARP timer isn't running,
|
|
|
|
* we must start it.
|
|
|
|
*/
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_interval_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-13 06:10:24 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting ARP monitoring interval to %llu\n",
|
|
|
|
newval->value);
|
2014-01-22 21:53:23 +08:00
|
|
|
bond->params.arp_interval = newval->value;
|
|
|
|
if (newval->value) {
|
2013-12-13 06:10:24 +08:00
|
|
|
if (bond->params.miimon) {
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "ARP monitoring cannot be used with MII monitoring. Disabling MII monitoring\n");
|
2013-12-13 06:10:24 +08:00
|
|
|
bond->params.miimon = 0;
|
|
|
|
}
|
|
|
|
if (!bond->params.arp_targets[0])
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "ARP monitoring has been set up, but no ARP targets have been specified\n");
|
2013-12-13 06:10:24 +08:00
|
|
|
}
|
|
|
|
if (bond->dev->flags & IFF_UP) {
|
|
|
|
/* If the interface is up, we may need to fire off
|
|
|
|
* the ARP timer. If the interface is down, the
|
|
|
|
* timer will get fired off when the open function
|
|
|
|
* is called.
|
|
|
|
*/
|
2014-01-22 21:53:23 +08:00
|
|
|
if (!newval->value) {
|
2013-12-13 06:10:24 +08:00
|
|
|
if (bond->params.arp_validate)
|
|
|
|
bond->recv_probe = NULL;
|
|
|
|
cancel_delayed_work_sync(&bond->arp_work);
|
|
|
|
} else {
|
|
|
|
/* arp_validate can be set only in active-backup mode */
|
2022-02-21 13:54:56 +08:00
|
|
|
bond->recv_probe = bond_rcv_validate;
|
2013-12-13 06:10:24 +08:00
|
|
|
cancel_delayed_work_sync(&bond->mii_work);
|
|
|
|
queue_delayed_work(bond->wq, &bond->arp_work, 0);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-13 06:10:31 +08:00
|
|
|
|
|
|
|
static void _bond_options_arp_ip_target_set(struct bonding *bond, int slot,
|
|
|
|
__be32 target,
|
|
|
|
unsigned long last_rx)
|
|
|
|
{
|
|
|
|
__be32 *targets = bond->params.arp_targets;
|
|
|
|
struct list_head *iter;
|
|
|
|
struct slave *slave;
|
|
|
|
|
|
|
|
if (slot >= 0 && slot < BOND_MAX_ARP_TARGETS) {
|
|
|
|
bond_for_each_slave(bond, slave, iter)
|
|
|
|
slave->target_last_arp_rx[slot] = last_rx;
|
|
|
|
targets[slot] = target;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int _bond_option_arp_ip_target_add(struct bonding *bond, __be32 target)
|
|
|
|
{
|
|
|
|
__be32 *targets = bond->params.arp_targets;
|
|
|
|
int ind;
|
|
|
|
|
2014-05-16 03:39:56 +08:00
|
|
|
if (!bond_is_ip_target_ok(target)) {
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "invalid ARP target %pI4 specified for addition\n",
|
|
|
|
&target);
|
2013-12-13 06:10:31 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (bond_get_targets_ip(targets, target) != -1) { /* dup */
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "ARP target %pI4 is already present\n",
|
|
|
|
&target);
|
2013-12-13 06:10:31 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
ind = bond_get_targets_ip(targets, 0); /* first free slot */
|
|
|
|
if (ind == -1) {
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "ARP target table is full!\n");
|
2013-12-13 06:10:31 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Adding ARP target %pI4\n", &target);
|
2013-12-13 06:10:31 +08:00
|
|
|
|
|
|
|
_bond_options_arp_ip_target_set(bond, ind, target, jiffies);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target)
|
2013-12-13 06:10:31 +08:00
|
|
|
{
|
2014-09-10 05:17:02 +08:00
|
|
|
return _bond_option_arp_ip_target_add(bond, target);
|
2013-12-13 06:10:31 +08:00
|
|
|
}
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target)
|
2013-12-13 06:10:31 +08:00
|
|
|
{
|
|
|
|
__be32 *targets = bond->params.arp_targets;
|
|
|
|
struct list_head *iter;
|
|
|
|
struct slave *slave;
|
|
|
|
unsigned long *targets_rx;
|
|
|
|
int ind, i;
|
|
|
|
|
2014-05-16 03:39:56 +08:00
|
|
|
if (!bond_is_ip_target_ok(target)) {
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "invalid ARP target %pI4 specified for removal\n",
|
|
|
|
&target);
|
2013-12-13 06:10:31 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
ind = bond_get_targets_ip(targets, target);
|
|
|
|
if (ind == -1) {
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "unable to remove nonexistent ARP target %pI4\n",
|
|
|
|
&target);
|
2013-12-13 06:10:31 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ind == 0 && !targets[1] && bond->params.arp_interval)
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_warn(bond->dev, "Removing last arp target with arp_interval on\n");
|
2013-12-13 06:10:31 +08:00
|
|
|
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Removing ARP target %pI4\n", &target);
|
2013-12-13 06:10:31 +08:00
|
|
|
|
|
|
|
bond_for_each_slave(bond, slave, iter) {
|
|
|
|
targets_rx = slave->target_last_arp_rx;
|
|
|
|
for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
|
|
|
|
targets_rx[i] = targets_rx[i+1];
|
|
|
|
targets_rx[i] = 0;
|
|
|
|
}
|
|
|
|
for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
|
|
|
|
targets[i] = targets[i+1];
|
|
|
|
targets[i] = 0;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-01-22 21:53:24 +08:00
|
|
|
void bond_option_arp_ip_targets_clear(struct bonding *bond)
|
2013-12-13 06:10:31 +08:00
|
|
|
{
|
2014-01-22 21:53:24 +08:00
|
|
|
int i;
|
2013-12-13 06:10:31 +08:00
|
|
|
|
|
|
|
for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
|
|
|
|
_bond_options_arp_ip_target_set(bond, i, 0, 0);
|
2014-01-22 21:53:24 +08:00
|
|
|
}
|
2013-12-13 06:10:31 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_ip_targets_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2014-01-22 21:53:24 +08:00
|
|
|
{
|
|
|
|
int ret = -EPERM;
|
|
|
|
__be32 target;
|
|
|
|
|
|
|
|
if (newval->string) {
|
|
|
|
if (!in4_pton(newval->string+1, -1, (u8 *)&target, -1, NULL)) {
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "invalid ARP target %pI4 specified\n",
|
|
|
|
&target);
|
2014-01-22 21:53:24 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
if (newval->string[0] == '+')
|
|
|
|
ret = bond_option_arp_ip_target_add(bond, target);
|
|
|
|
else if (newval->string[0] == '-')
|
|
|
|
ret = bond_option_arp_ip_target_rem(bond, target);
|
|
|
|
else
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "no command found in arp_ip_targets file - use +<addr> or -<addr>\n");
|
2014-01-22 21:53:24 +08:00
|
|
|
} else {
|
|
|
|
target = newval->value;
|
|
|
|
ret = bond_option_arp_ip_target_add(bond, target);
|
2013-12-13 06:10:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
2013-12-13 06:10:38 +08:00
|
|
|
|
2022-02-21 13:54:57 +08:00
|
|
|
#if IS_ENABLED(CONFIG_IPV6)
|
|
|
|
static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,
|
|
|
|
struct in6_addr *target,
|
|
|
|
unsigned long last_rx)
|
|
|
|
{
|
|
|
|
struct in6_addr *targets = bond->params.ns_targets;
|
|
|
|
struct list_head *iter;
|
|
|
|
struct slave *slave;
|
|
|
|
|
|
|
|
if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) {
|
|
|
|
bond_for_each_slave(bond, slave, iter)
|
|
|
|
slave->target_last_arp_rx[slot] = last_rx;
|
|
|
|
targets[slot] = *target;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void bond_option_ns_ip6_targets_clear(struct bonding *bond)
|
|
|
|
{
|
|
|
|
struct in6_addr addr_any = in6addr_any;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < BOND_MAX_NS_TARGETS; i++)
|
|
|
|
_bond_options_ns_ip6_target_set(bond, i, &addr_any, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int bond_option_ns_ip6_targets_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
|
|
|
struct in6_addr *target = (struct in6_addr *)newval->extra;
|
|
|
|
struct in6_addr *targets = bond->params.ns_targets;
|
|
|
|
struct in6_addr addr_any = in6addr_any;
|
|
|
|
int index;
|
|
|
|
|
|
|
|
if (!bond_is_ip6_target_ok(target)) {
|
|
|
|
netdev_err(bond->dev, "invalid NS target %pI6c specified for addition\n",
|
|
|
|
target);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (bond_get_targets_ip6(targets, target) != -1) { /* dup */
|
|
|
|
netdev_err(bond->dev, "NS target %pI6c is already present\n",
|
|
|
|
target);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
index = bond_get_targets_ip6(targets, &addr_any); /* first free slot */
|
|
|
|
if (index == -1) {
|
|
|
|
netdev_err(bond->dev, "NS target table is full!\n");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
netdev_dbg(bond->dev, "Adding NS target %pI6c\n", target);
|
|
|
|
|
|
|
|
_bond_options_ns_ip6_target_set(bond, index, target, jiffies);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2022-05-31 14:37:27 +08:00
|
|
|
#else
|
|
|
|
static int bond_option_ns_ip6_targets_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
|
|
|
return -EPERM;
|
|
|
|
}
|
2022-02-21 13:54:57 +08:00
|
|
|
#endif
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_validate_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-13 06:10:38 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting arp_validate to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
2014-01-22 21:53:20 +08:00
|
|
|
bond->params.arp_validate = newval->value;
|
2013-12-13 06:10:38 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-13 06:10:45 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_arp_all_targets_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-13 06:10:45 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting arp_all_targets to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
2014-01-22 21:53:21 +08:00
|
|
|
bond->params.arp_all_targets = newval->value;
|
2013-12-13 06:10:45 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-16 08:41:51 +08:00
|
|
|
|
2021-11-30 12:29:47 +08:00
|
|
|
static int bond_option_missed_max_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
|
|
|
netdev_dbg(bond->dev, "Setting missed max to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
|
|
|
bond->params.missed_max = newval->value;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2022-06-21 15:49:19 +08:00
|
|
|
static int bond_option_prio_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
|
|
|
struct slave *slave;
|
|
|
|
|
|
|
|
slave = bond_slave_get_rtnl(newval->slave_dev);
|
|
|
|
if (!slave) {
|
|
|
|
netdev_dbg(newval->slave_dev, "%s called on NULL slave\n", __func__);
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
slave->prio = newval->value;
|
|
|
|
|
|
|
|
if (rtnl_dereference(bond->primary_slave))
|
|
|
|
slave_warn(bond->dev, slave->dev,
|
|
|
|
"prio updated, but will not affect failover re-selection as primary slave have been set\n");
|
|
|
|
else
|
|
|
|
bond_select_active_slave(bond);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_primary_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-16 08:41:51 +08:00
|
|
|
{
|
2014-01-22 21:53:32 +08:00
|
|
|
char *p, *primary = newval->string;
|
2013-12-16 08:41:51 +08:00
|
|
|
struct list_head *iter;
|
|
|
|
struct slave *slave;
|
|
|
|
|
|
|
|
block_netpoll_tx();
|
|
|
|
|
2014-01-22 21:53:32 +08:00
|
|
|
p = strchr(primary, '\n');
|
|
|
|
if (p)
|
|
|
|
*p = '\0';
|
2013-12-16 08:41:51 +08:00
|
|
|
/* check to see if we are clearing primary */
|
|
|
|
if (!strlen(primary)) {
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting primary slave to None\n");
|
2014-09-10 05:17:00 +08:00
|
|
|
RCU_INIT_POINTER(bond->primary_slave, NULL);
|
2013-12-16 08:41:51 +08:00
|
|
|
memset(bond->params.primary, 0, sizeof(bond->params.primary));
|
|
|
|
bond_select_active_slave(bond);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
bond_for_each_slave(bond, slave, iter) {
|
|
|
|
if (strncmp(slave->dev->name, primary, IFNAMSIZ) == 0) {
|
2019-06-07 22:59:32 +08:00
|
|
|
slave_dbg(bond->dev, slave->dev, "Setting as primary slave\n");
|
2014-09-10 05:17:00 +08:00
|
|
|
rcu_assign_pointer(bond->primary_slave, slave);
|
2013-12-16 08:41:51 +08:00
|
|
|
strcpy(bond->params.primary, slave->dev->name);
|
2018-06-07 13:39:59 +08:00
|
|
|
bond->force_primary = true;
|
2013-12-16 08:41:51 +08:00
|
|
|
bond_select_active_slave(bond);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-09-10 05:17:00 +08:00
|
|
|
if (rtnl_dereference(bond->primary_slave)) {
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting primary slave to None\n");
|
2014-09-10 05:17:00 +08:00
|
|
|
RCU_INIT_POINTER(bond->primary_slave, NULL);
|
2014-01-18 16:28:52 +08:00
|
|
|
bond_select_active_slave(bond);
|
|
|
|
}
|
2021-06-03 04:58:20 +08:00
|
|
|
strscpy_pad(bond->params.primary, primary, IFNAMSIZ);
|
2013-12-16 08:41:51 +08:00
|
|
|
|
2019-06-07 22:59:32 +08:00
|
|
|
netdev_dbg(bond->dev, "Recording %s as primary, but it has not been enslaved yet\n",
|
|
|
|
primary);
|
2013-12-16 08:41:51 +08:00
|
|
|
|
|
|
|
out:
|
|
|
|
unblock_netpoll_tx();
|
|
|
|
|
2014-01-22 21:53:32 +08:00
|
|
|
return 0;
|
2013-12-16 08:41:51 +08:00
|
|
|
}
|
2013-12-16 08:41:58 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_primary_reselect_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-16 08:41:58 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting primary_reselect to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
2014-01-22 21:53:33 +08:00
|
|
|
bond->params.primary_reselect = newval->value;
|
2013-12-16 08:41:58 +08:00
|
|
|
|
|
|
|
block_netpoll_tx();
|
|
|
|
bond_select_active_slave(bond);
|
|
|
|
unblock_netpoll_tx();
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-16 08:42:05 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_fail_over_mac_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-16 08:42:05 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting fail_over_mac to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
2014-01-22 21:53:22 +08:00
|
|
|
bond->params.fail_over_mac = newval->value;
|
2013-12-16 08:42:05 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-16 08:42:12 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_xmit_hash_policy_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-16 08:42:12 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting xmit hash policy to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
2014-01-22 21:53:19 +08:00
|
|
|
bond->params.xmit_policy = newval->value;
|
2013-12-16 08:42:12 +08:00
|
|
|
|
net/bonding: Implement TLS TX device offload
Implement TLS TX device offload for bonding interfaces.
This allows kTLS sockets running on a bond to benefit from the
device offload on capable lower devices.
To allow a simple and fast maintenance of the TLS context in SW and
lower devices, we bind the TLS socket to a specific lower dev.
To achieve a behavior similar to SW kTLS, we support only balance-xor
and 802.3ad modes, with xmit_hash_policy=layer3+4. This is enforced
in bond_sk_check(), done in a previous patch.
For the above configuration, the SW implementation keeps picking the
same exact lower dev for all the socket's SKBs. The device offload
behaves similarly, making the decision once at the connection creation.
Per socket, the TLS module should work directly with the lowest netdev
in chain, to call the tls_dev_ops operations.
As the bond interface is being bypassed by the TLS module, interacting
directly against the lower devs, there is no way for the bond interface
to disable its device offload capabilities, as long as the mode/policy
config allows it.
Hence, the feature flag is not directly controllable, but just reflects
the current offload status based on the logic under bond_sk_check().
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-17 22:59:46 +08:00
|
|
|
if (bond->dev->reg_state == NETREG_REGISTERED)
|
|
|
|
if (bond_set_tls_features(bond))
|
|
|
|
netdev_update_features(bond->dev);
|
|
|
|
|
2013-12-16 08:42:12 +08:00
|
|
|
return 0;
|
|
|
|
}
|
2013-12-16 08:42:19 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_resend_igmp_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-16 08:42:19 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting resend_igmp to %llu\n",
|
|
|
|
newval->value);
|
2014-01-22 21:53:38 +08:00
|
|
|
bond->params.resend_igmp = newval->value;
|
2013-12-16 08:42:19 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-18 13:30:09 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_num_peer_notif_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-18 13:30:09 +08:00
|
|
|
{
|
2014-01-22 21:53:30 +08:00
|
|
|
bond->params.num_peer_notif = newval->value;
|
|
|
|
|
2013-12-18 13:30:09 +08:00
|
|
|
return 0;
|
|
|
|
}
|
2013-12-18 13:30:16 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_all_slaves_active_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-18 13:30:16 +08:00
|
|
|
{
|
|
|
|
struct list_head *iter;
|
|
|
|
struct slave *slave;
|
|
|
|
|
2014-01-22 21:53:37 +08:00
|
|
|
if (newval->value == bond->params.all_slaves_active)
|
2013-12-18 13:30:16 +08:00
|
|
|
return 0;
|
2014-01-22 21:53:37 +08:00
|
|
|
bond->params.all_slaves_active = newval->value;
|
2013-12-18 13:30:16 +08:00
|
|
|
bond_for_each_slave(bond, slave, iter) {
|
|
|
|
if (!bond_is_active_slave(slave)) {
|
2014-01-22 21:53:37 +08:00
|
|
|
if (newval->value)
|
2013-12-18 13:30:16 +08:00
|
|
|
slave->inactive = 0;
|
|
|
|
else
|
|
|
|
slave->inactive = 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-18 13:30:23 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_min_links_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-18 13:30:23 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting min links value to %llu\n",
|
|
|
|
newval->value);
|
2014-01-22 21:53:28 +08:00
|
|
|
bond->params.min_links = newval->value;
|
2015-01-26 14:16:57 +08:00
|
|
|
bond_set_carrier(bond);
|
2013-12-18 13:30:23 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-18 13:30:30 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_lp_interval_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-18 13:30:30 +08:00
|
|
|
{
|
2014-01-22 21:53:39 +08:00
|
|
|
bond->params.lp_interval = newval->value;
|
2013-12-18 13:30:30 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-12-18 13:30:37 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_pps_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2013-12-18 13:30:37 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting packets per slave to %llu\n",
|
|
|
|
newval->value);
|
2014-01-22 21:53:18 +08:00
|
|
|
bond->params.packets_per_slave = newval->value;
|
|
|
|
if (newval->value > 0) {
|
reciprocal_divide: update/correction of the algorithm
Jakub Zawadzki noticed that some divisions by reciprocal_divide()
were not correct [1][2], which he could also show with BPF code
after divisions are transformed into reciprocal_value() for runtime
invariance which can be passed to reciprocal_divide() later on;
reverse in BPF dump ended up with a different, off-by-one K in
some situations.
This has been fixed by Eric Dumazet in commit aee636c4809fa5
("bpf: do not use reciprocal divide"). This follow-up patch
improves reciprocal_value() and reciprocal_divide() to work in
all cases by using Granlund and Montgomery method, so that also
future use is safe and without any non-obvious side-effects.
Known problems with the old implementation were that division by 1
always returned 0 and some off-by-ones when the dividend and divisor
where very large. This seemed to not be problematic with its
current users, as far as we can tell. Eric Dumazet checked for
the slab usage, we cannot surely say so in the case of flex_array.
Still, in order to fix that, we propose an extension from the
original implementation from commit 6a2d7a955d8d resp. [3][4],
by using the algorithm proposed in "Division by Invariant Integers
Using Multiplication" [5], Torbjörn Granlund and Peter L.
Montgomery, that is, pseudocode for q = n/d where q, n, d is in
u32 universe:
1) Initialization:
int l = ceil(log_2 d)
uword m' = floor((1<<32)*((1<<l)-d)/d)+1
int sh_1 = min(l,1)
int sh_2 = max(l-1,0)
2) For q = n/d, all uword:
uword t = (n*m')>>32
q = (t+((n-t)>>sh_1))>>sh_2
The assembler implementation from Agner Fog [6] also helped a lot
while implementing. We have tested the implementation on x86_64,
ppc64, i686, s390x; on x86_64/haswell we're still half the latency
compared to normal divide.
Joint work with Daniel Borkmann.
[1] http://www.wireshark.org/~darkjames/reciprocal-buggy.c
[2] http://www.wireshark.org/~darkjames/set-and-dump-filter-k-bug.c
[3] https://gmplib.org/~tege/division-paper.pdf
[4] http://homepage.cs.uiowa.edu/~jones/bcd/divide.html
[5] http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.2556
[6] http://www.agner.org/optimize/asmlib.zip
Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Austin S Hemmelgarn <ahferroin7@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: Jesse Gross <jesse@nicira.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 09:29:41 +08:00
|
|
|
bond->params.reciprocal_packets_per_slave =
|
2014-01-22 21:53:18 +08:00
|
|
|
reciprocal_value(newval->value);
|
reciprocal_divide: update/correction of the algorithm
Jakub Zawadzki noticed that some divisions by reciprocal_divide()
were not correct [1][2], which he could also show with BPF code
after divisions are transformed into reciprocal_value() for runtime
invariance which can be passed to reciprocal_divide() later on;
reverse in BPF dump ended up with a different, off-by-one K in
some situations.
This has been fixed by Eric Dumazet in commit aee636c4809fa5
("bpf: do not use reciprocal divide"). This follow-up patch
improves reciprocal_value() and reciprocal_divide() to work in
all cases by using Granlund and Montgomery method, so that also
future use is safe and without any non-obvious side-effects.
Known problems with the old implementation were that division by 1
always returned 0 and some off-by-ones when the dividend and divisor
where very large. This seemed to not be problematic with its
current users, as far as we can tell. Eric Dumazet checked for
the slab usage, we cannot surely say so in the case of flex_array.
Still, in order to fix that, we propose an extension from the
original implementation from commit 6a2d7a955d8d resp. [3][4],
by using the algorithm proposed in "Division by Invariant Integers
Using Multiplication" [5], Torbjörn Granlund and Peter L.
Montgomery, that is, pseudocode for q = n/d where q, n, d is in
u32 universe:
1) Initialization:
int l = ceil(log_2 d)
uword m' = floor((1<<32)*((1<<l)-d)/d)+1
int sh_1 = min(l,1)
int sh_2 = max(l-1,0)
2) For q = n/d, all uword:
uword t = (n*m')>>32
q = (t+((n-t)>>sh_1))>>sh_2
The assembler implementation from Agner Fog [6] also helped a lot
while implementing. We have tested the implementation on x86_64,
ppc64, i686, s390x; on x86_64/haswell we're still half the latency
compared to normal divide.
Joint work with Daniel Borkmann.
[1] http://www.wireshark.org/~darkjames/reciprocal-buggy.c
[2] http://www.wireshark.org/~darkjames/set-and-dump-filter-k-bug.c
[3] https://gmplib.org/~tege/division-paper.pdf
[4] http://homepage.cs.uiowa.edu/~jones/bcd/divide.html
[5] http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.2556
[6] http://www.agner.org/optimize/asmlib.zip
Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Austin S Hemmelgarn <ahferroin7@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: Jesse Gross <jesse@nicira.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 09:29:41 +08:00
|
|
|
} else {
|
|
|
|
/* reciprocal_packets_per_slave is unused if
|
|
|
|
* packets_per_slave is 0 or 1, just initialize it
|
|
|
|
*/
|
|
|
|
bond->params.reciprocal_packets_per_slave =
|
|
|
|
(struct reciprocal_value) { 0 };
|
|
|
|
}
|
2013-12-18 13:30:37 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2014-01-04 06:18:41 +08:00
|
|
|
|
2021-08-02 11:02:19 +08:00
|
|
|
static int bond_option_lacp_active_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
|
|
|
netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
|
|
|
bond->params.lacp_active = newval->value;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_lacp_rate_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2014-01-04 06:18:41 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting LACP rate to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
2014-01-22 21:53:27 +08:00
|
|
|
bond->params.lacp_fast = newval->value;
|
2014-01-04 06:28:18 +08:00
|
|
|
bond_3ad_update_lacp_rate(bond);
|
2014-01-04 06:18:41 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2014-01-04 06:18:49 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_ad_select_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2014-01-04 06:18:49 +08:00
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting ad_select to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
2014-01-22 21:53:29 +08:00
|
|
|
bond->params.ad_select = newval->value;
|
2014-01-04 06:18:49 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2014-01-22 21:53:36 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_queue_id_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2014-01-22 21:53:36 +08:00
|
|
|
{
|
|
|
|
struct slave *slave, *update_slave;
|
|
|
|
struct net_device *sdev;
|
|
|
|
struct list_head *iter;
|
|
|
|
char *delim;
|
|
|
|
int ret = 0;
|
|
|
|
u16 qid;
|
|
|
|
|
|
|
|
/* delim will point to queue id if successful */
|
|
|
|
delim = strchr(newval->string, ':');
|
|
|
|
if (!delim)
|
|
|
|
goto err_no_cmd;
|
|
|
|
|
|
|
|
/* Terminate string that points to device name and bump it
|
|
|
|
* up one, so we can read the queue id there.
|
|
|
|
*/
|
|
|
|
*delim = '\0';
|
|
|
|
if (sscanf(++delim, "%hd\n", &qid) != 1)
|
|
|
|
goto err_no_cmd;
|
|
|
|
|
|
|
|
/* Check buffer length, valid ifname and queue id */
|
2014-02-12 14:58:50 +08:00
|
|
|
if (!dev_valid_name(newval->string) ||
|
2014-01-22 21:53:36 +08:00
|
|
|
qid > bond->dev->real_num_tx_queues)
|
|
|
|
goto err_no_cmd;
|
|
|
|
|
|
|
|
/* Get the pointer to that interface if it exists */
|
|
|
|
sdev = __dev_get_by_name(dev_net(bond->dev), newval->string);
|
|
|
|
if (!sdev)
|
|
|
|
goto err_no_cmd;
|
|
|
|
|
|
|
|
/* Search for thes slave and check for duplicate qids */
|
|
|
|
update_slave = NULL;
|
|
|
|
bond_for_each_slave(bond, slave, iter) {
|
|
|
|
if (sdev == slave->dev)
|
|
|
|
/* We don't need to check the matching
|
|
|
|
* slave for dups, since we're overwriting it
|
|
|
|
*/
|
|
|
|
update_slave = slave;
|
|
|
|
else if (qid && qid == slave->queue_id) {
|
|
|
|
goto err_no_cmd;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!update_slave)
|
|
|
|
goto err_no_cmd;
|
|
|
|
|
|
|
|
/* Actually set the qids for the slave */
|
|
|
|
update_slave->queue_id = qid;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
err_no_cmd:
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "invalid input for queue_id set\n");
|
2014-01-22 21:53:36 +08:00
|
|
|
ret = -EPERM;
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
}
|
2014-01-22 21:53:40 +08:00
|
|
|
|
2014-03-05 08:36:44 +08:00
|
|
|
static int bond_option_slaves_set(struct bonding *bond,
|
2014-03-07 06:20:17 +08:00
|
|
|
const struct bond_opt_value *newval)
|
2014-01-22 21:53:40 +08:00
|
|
|
{
|
|
|
|
char command[IFNAMSIZ + 1] = { 0, };
|
|
|
|
struct net_device *dev;
|
|
|
|
char *ifname;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
sscanf(newval->string, "%16s", command); /* IFNAMSIZ*/
|
|
|
|
ifname = command + 1;
|
|
|
|
if ((strlen(command) <= 1) ||
|
2019-02-12 02:49:48 +08:00
|
|
|
(command[0] != '+' && command[0] != '-') ||
|
2014-01-22 21:53:40 +08:00
|
|
|
!dev_valid_name(ifname))
|
|
|
|
goto err_no_cmd;
|
|
|
|
|
|
|
|
dev = __dev_get_by_name(dev_net(bond->dev), ifname);
|
|
|
|
if (!dev) {
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "interface %s does not exist!\n",
|
|
|
|
ifname);
|
2014-01-22 21:53:40 +08:00
|
|
|
ret = -ENODEV;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (command[0]) {
|
|
|
|
case '+':
|
2019-06-07 22:59:32 +08:00
|
|
|
slave_dbg(bond->dev, dev, "Enslaving interface\n");
|
2017-10-05 08:48:46 +08:00
|
|
|
ret = bond_enslave(bond->dev, dev, NULL);
|
2014-01-22 21:53:40 +08:00
|
|
|
break;
|
|
|
|
|
|
|
|
case '-':
|
2019-06-07 22:59:32 +08:00
|
|
|
slave_dbg(bond->dev, dev, "Releasing interface\n");
|
2014-01-22 21:53:40 +08:00
|
|
|
ret = bond_release(bond->dev, dev);
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
2019-02-12 02:49:48 +08:00
|
|
|
/* should not run here. */
|
2014-01-22 21:53:40 +08:00
|
|
|
goto err_no_cmd;
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
err_no_cmd:
|
2014-07-16 01:36:08 +08:00
|
|
|
netdev_err(bond->dev, "no command found in slaves file - use +ifname or -ifname\n");
|
2014-01-22 21:53:40 +08:00
|
|
|
ret = -EPERM;
|
|
|
|
goto out;
|
|
|
|
}
|
2014-04-23 07:30:22 +08:00
|
|
|
|
|
|
|
static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting dynamic-lb to %s (%llu)\n",
|
|
|
|
newval->string, newval->value);
|
2014-04-23 07:30:22 +08:00
|
|
|
bond->params.tlb_dynamic_lb = newval->value;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2015-05-09 15:01:55 +08:00
|
|
|
|
|
|
|
static int bond_option_ad_actor_sys_prio_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting ad_actor_sys_prio to %llu\n",
|
|
|
|
newval->value);
|
2015-05-09 15:01:55 +08:00
|
|
|
|
|
|
|
bond->params.ad_actor_sys_prio = newval->value;
|
2016-02-03 20:17:01 +08:00
|
|
|
bond_3ad_update_ad_actor_settings(bond);
|
|
|
|
|
2015-05-09 15:01:55 +08:00
|
|
|
return 0;
|
|
|
|
}
|
2015-05-09 15:01:56 +08:00
|
|
|
|
|
|
|
static int bond_option_ad_actor_system_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
|
|
|
u8 macaddr[ETH_ALEN];
|
2015-05-09 15:01:58 +08:00
|
|
|
u8 *mac;
|
2015-05-09 15:01:56 +08:00
|
|
|
|
2015-05-09 15:01:58 +08:00
|
|
|
if (newval->string) {
|
2017-12-20 02:20:44 +08:00
|
|
|
if (!mac_pton(newval->string, macaddr))
|
2015-05-09 15:01:58 +08:00
|
|
|
goto err;
|
|
|
|
mac = macaddr;
|
|
|
|
} else {
|
|
|
|
mac = (u8 *)&newval->value;
|
2015-05-09 15:01:56 +08:00
|
|
|
}
|
|
|
|
|
2021-12-21 19:13:45 +08:00
|
|
|
if (is_multicast_ether_addr(mac))
|
2015-05-09 15:01:58 +08:00
|
|
|
goto err;
|
|
|
|
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting ad_actor_system to %pM\n", mac);
|
2015-05-09 15:01:58 +08:00
|
|
|
ether_addr_copy(bond->params.ad_actor_system, mac);
|
2016-02-03 20:17:01 +08:00
|
|
|
bond_3ad_update_ad_actor_settings(bond);
|
|
|
|
|
2015-05-09 15:01:56 +08:00
|
|
|
return 0;
|
2015-05-09 15:01:58 +08:00
|
|
|
|
|
|
|
err:
|
2019-06-07 22:59:32 +08:00
|
|
|
netdev_err(bond->dev, "Invalid ad_actor_system MAC address.\n");
|
2015-05-09 15:01:58 +08:00
|
|
|
return -EINVAL;
|
2015-05-09 15:01:56 +08:00
|
|
|
}
|
2015-05-09 15:01:57 +08:00
|
|
|
|
|
|
|
static int bond_option_ad_user_port_key_set(struct bonding *bond,
|
|
|
|
const struct bond_opt_value *newval)
|
|
|
|
{
|
2017-06-26 23:49:46 +08:00
|
|
|
netdev_dbg(bond->dev, "Setting ad_user_port_key to %llu\n",
|
|
|
|
newval->value);
|
2015-05-09 15:01:57 +08:00
|
|
|
|
|
|
|
bond->params.ad_user_port_key = newval->value;
|
|
|
|
return 0;
|
|
|
|
}
|