Commit 05f43db7 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'allow-configuration-of-multipath-hash-seed' 

Petr Machata says:

====================
Allow configuration of multipath hash seed

Let me just quote the commit message of patch #2 here to inform the
motivation and some of the implementation:

    When calculating hashes for the purpose of multipath forwarding,
    both IPv4 and IPv6 code currently fall back on
    flow_hash_from_keys(). That uses a randomly-generated seed. That's a
    fine choice by default, but unfortunately some deployments may need
    a tighter control over the seed used.

    In this patchset, make the seed configurable by adding a new sysctl
    key, net.ipv4.fib_multipath_hash_seed to control the seed. This seed
    is used specifically for multipath forwarding and not for the other
    concerns that flow_hash_from_keys() is used for, such as queue
    selection. Expose the knob as sysctl because other such settings,
    such as headers to hash, are also handled that way.

    Despite being placed in the net.ipv4 namespace, the multipath seed
    sysctl is used for both IPv4 and IPv6, similarly to e.g. a number of
    TCP variables. Like those, the multipath hash seed is a per-netns
    variable.

    The seed used by flow_hash_from_keys() is a 128-bit quantity.
    However it seems that usually the seed is a much more modest value.
    32 bits seem typical (Cisco, Cumulus), some systems go even lower.
    For that reason, and to decouple the user interface from
    implementation details, go with a 32-bit quantity, which is then
    quadruplicated to form the siphash key.

One example of use of this interface is avoiding hash polarization,
where two ECMP routers, one behind the other, happen to make consistent
hashing decisions, and as a result, part of the ECMP space of the latter
router is never used. Another is a load balancer where several machines
forward traffic to one of a number of leaves, and the forwarding
decisions need to be made consistently. (This is a case of a desired
hash polarization, mentioned e.g. in chapter 6.3 of [0].)

There has already been a proposal to include a hash seed control
interface in the past[1].

- Patches #1-#2 contain the substance of the work
- Patch #3 is an mlxsw offload
- Patches #4 and #5 are a selftest

[0] https://www.usenix.org/system/files/conference/nsdi18/nsdi18-araujo.pdf
[1] https://lore.kernel.org/netdev/YIlVpYMCn%2F8WfE1P@rnd/
====================

Link: https://lore.kernel.org/r/20240607151357.421181-1-petrm@nvidia.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 32b06603 5f90d93b

Documentation/networking/ip-sysctl.rst

+14 −0
Original line number Diff line number Diff line
@@ -131,6 +131,20 @@ fib_multipath_hash_fields - UNSIGNED INTEGER 


	Default: 0x0007 (source IP, destination IP and IP protocol)



fib_multipath_hash_seed - UNSIGNED INTEGER

	The seed value used when calculating hash for multipath routes. Applies

	to both IPv4 and IPv6 datapath. Only present for kernels built with

	CONFIG_IP_ROUTE_MULTIPATH enabled.



	When set to 0, the seed value used for multipath routing defaults to an

	internal random-generated one.



	The actual hashing algorithm is not specified -- there is no guarantee

	that a next hop distribution effected by a given seed will keep stable

	across kernel versions.



	Default: 0 (random)



fib_sync_mem - UNSIGNED INTEGER

	Amount of dirty memory from fib entries that can be backlogged before

	synchronize_rcu is forced.

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

+5 −1
Original line number Diff line number Diff line
@@ -11450,12 +11450,16 @@ static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) 
{

	bool old_inc_parsing_depth, new_inc_parsing_depth;

	struct mlxsw_sp_mp_hash_config config = {};

	struct net *net = mlxsw_sp_net(mlxsw_sp);

	char recr2_pl[MLXSW_REG_RECR2_LEN];

	unsigned long bit;

	u32 seed;

	int err;



	seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).user_seed;

	if (!seed)

		seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0);



	mlxsw_reg_recr2_pack(recr2_pl, seed);

	mlxsw_sp_mp4_hash_init(mlxsw_sp, &config);

	mlxsw_sp_mp6_hash_init(mlxsw_sp, &config);

include/net/flow_dissector.h

+2 −0
Original line number Diff line number Diff line
@@ -442,6 +442,8 @@ static inline bool flow_keys_have_l4(const struct flow_keys *keys) 
}



u32 flow_hash_from_keys(struct flow_keys *keys);

u32 flow_hash_from_keys_seed(struct flow_keys *keys,

			     const siphash_key_t *keyval);

void skb_flow_get_icmp_tci(const struct sk_buff *skb,

			   struct flow_dissector_key_icmp *key_icmp,

			   const void *data, int thoff, int hlen);

include/net/ip_fib.h

+28 −0
Original line number Diff line number Diff line
@@ -520,7 +520,35 @@ void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); 
#ifdef CONFIG_IP_ROUTE_MULTIPATH

int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,

		       const struct sk_buff *skb, struct flow_keys *flkeys);



static void

fib_multipath_hash_construct_key(siphash_key_t *key, u32 mp_seed)

{

	u64 mp_seed_64 = mp_seed;



	key->key[0] = (mp_seed_64 << 32) | mp_seed_64;

	key->key[1] = key->key[0];

}



static inline u32 fib_multipath_hash_from_keys(const struct net *net,

					       struct flow_keys *keys)

{

	siphash_aligned_key_t hash_key;

	u32 mp_seed;



	mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed;

	fib_multipath_hash_construct_key(&hash_key, mp_seed);



	return flow_hash_from_keys_seed(keys, &hash_key);

}

#else

static inline u32 fib_multipath_hash_from_keys(const struct net *net,

					       struct flow_keys *keys)

{

	return flow_hash_from_keys(keys);

}

#endif



int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,

		 struct netlink_ext_ack *extack);

void fib_select_multipath(struct fib_result *res, int hash);

include/net/netns/ipv4.h

+8 −0
Original line number Diff line number Diff line
@@ -40,6 +40,13 @@ struct inet_timewait_death_row { 


struct tcp_fastopen_context;



#ifdef CONFIG_IP_ROUTE_MULTIPATH

struct sysctl_fib_multipath_hash_seed {

	u32 user_seed;

	u32 mp_seed;

};

#endif



struct netns_ipv4 {

	/* Cacheline organization can be found documented in

	 * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst.
@@ -246,6 +253,7 @@ struct netns_ipv4 { 
#endif

#endif

#ifdef CONFIG_IP_ROUTE_MULTIPATH

	struct sysctl_fib_multipath_hash_seed sysctl_fib_multipath_hash_seed;

	u32 sysctl_fib_multipath_hash_fields;

	u8 sysctl_fib_multipath_use_neigh;

	u8 sysctl_fib_multipath_hash_policy;