On Sat, Sep 27, 2025 at 03:25:15PM -0400, Jon Maloy wrote:
We add a cache table to keep track of the contents of the kernel ARP and NDP tables. The table is fed from the just introduced netlink based neigbour subscription function. The new table eliminates the need for explicit netlink calls to find a host's MAC address.
Signed-off-by: Jon Maloy
A few comments below, but they're all pretty minor, so
Reviewed-by: David Gibson
--- v5: - Moved to earlier in series to reduce rebase conflicts v6: - Sqashed the hash list commit and the FIFO/LRU queue commit - Removed hash lookup. We now only use linear lookup in a linked list - Eliminated dynamic memory allocation. - Ensured there is only one call to clock_gettime() - Using MAC_ZERO instead of the previously dedicated definitions v7: - NOW using MAC_ZERO where needed - I am still using linear back-off for empty cache entries. Even an incoming, flow-creating packet from a local host gives no guarantee that its MAC address is in the ARP table, so we must allow for a few new attempts at first possible occasions. Only after several failed lookups can we conclude that we probably never will succeed. Hence the back-off. - Fixed a bug that David inadvertently made me aware of: I only intended to set the initial expiry value to MAC_CACHE_RENEWAL when an ARP/NDP table lookup was successful. - Improved struct and function description comments. v8: - Total re-design of table, adapting to the new, subscription based way of updating it. v9: - Catering for MAC address change for an existing host. v10: - Changes according to feedback from David Gibson --- conf.c | 1 + fwd.c | 164 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ fwd.h | 7 +++ netlink.c | 2 + 4 files changed, 174 insertions(+)
diff --git a/conf.c b/conf.c index 66b9e63..cfd8590 100644 --- a/conf.c +++ b/conf.c @@ -2133,6 +2133,7 @@ void conf(struct ctx *c, int argc, char **argv) c->udp.fwd_out.mode = fwd_default;
fwd_scan_ports_init(c); + fwd_neigh_table_init();
if (!c->quiet) conf_print(c); diff --git a/fwd.c b/fwd.c index 250cf56..2fd6cee 100644 --- a/fwd.c +++ b/fwd.c @@ -33,6 +33,170 @@ static in_port_t fwd_ephemeral_max = NUM_PORTS - 1;
#define PORT_RANGE_SYSCTL "/proc/sys/net/ipv4/ip_local_port_range"
+#define NEIGH_TABLE_SLOTS 1024 /* Must be power of two */
A comment is better than nothing, but a static_assert() is better still. IMO, not having the restriction at all is even better, since it's pretty easy to do so in this case.
+#define NEIGH_TABLE_SIZE (NEIGH_TABLE_SLOTS / 2) + +/** + * neigh_table_entry - Entry in the ARP/NDP table + * @next: Next entry in slot or free list + * @addr: IP address of represented host + * @mac: MAC address of represented host + */ +struct neigh_table_entry { + struct neigh_table_entry *next; + union inany_addr addr; + uint8_t mac[ETH_ALEN]; +}; + +/** + * neigh_table - Cache of ARP/NDP table contents + * @entries: Entries to be plugged into the hash slots when allocated + * @slots: Hash table slots + * @free: Linked list of unused entries + */ +struct neigh_table { + struct neigh_table_entry entries[NEIGH_TABLE_SIZE]; + struct neigh_table_entry *slots[NEIGH_TABLE_SLOTS];
Given that we have bucket chains, I don't think it's particularly required for this to be bigger than SIZE (unlike the flow table, where linear probing means it's absolutely vital we have more hash buckets than the maximum number of entries).
+ struct neigh_table_entry *free; +}; + +static struct neigh_table neigh_table; + +/** + * neigh_table_slot() - Hash key to a number within the table range + * @c: Execution context + * @key: The key to be used for the hash + * + * Return: The resulting hash value + */ +static inline size_t neigh_table_slot(const struct ctx *c, + const union inany_addr *key) +{ + struct siphash_state st = SIPHASH_INIT(c->hash_secret); + uint32_t i; + + inany_siphash_feed(&st, key); + i = siphash_final(&st, sizeof(*key), 0); + + return ((size_t)i) & (NEIGH_TABLE_SIZE - 1); +} + +/** + * fwd_neigh_table_find() - Find a MAC table entry + * @c: Execution context + * @addr: Neighbour address to be used as key for the lookup + * + * Return: The found entry, if any. Otherwise NULL. + */ +static struct neigh_table_entry *fwd_neigh_table_find(const struct ctx *c, + const union inany_addr *addr) +{ + size_t slot = neigh_table_slot(c, addr); + struct neigh_table_entry *e = neigh_table.slots[slot]; + + while (e && !inany_equals(&e->addr, addr)) + e = e->next; + + return e; +} + +/** + * fwd_neigh_table_update() - Allocate a neigbour table entry from the free list
I like the change to the name, but now the one line description is misleading.
+ * @c: Execution context + * @addr: Address used to determine insertion slot and store in entry + * @mac: The MAC address associated with the neighbour address + */ +void fwd_neigh_table_update(const struct ctx *c, + const union inany_addr *addr, uint8_t *mac) +{ + struct neigh_table *t = &neigh_table; + struct neigh_table_entry *e; + ssize_t slot; + + /* MAC address might change sometimes */ + e = fwd_neigh_table_find(c, addr); + if (e) { + memcpy(e->mac, mac, ETH_ALEN); + return; + } + + e = t->free; + if (!e) + return; + t->free = e->next; + + slot = neigh_table_slot(c, addr); + e->next = t->slots[slot]; + t->slots[slot] = e; + + memcpy(&e->addr, addr, sizeof(*addr)); + memcpy(e->mac, mac, ETH_ALEN); +} + +/** + * fwd_neigh_table_free() - Remove an entry from a slot and add it to free list + * @c: Execution context + * @addr: Neighbour address used to find the slot for the entry + */ +void fwd_neigh_table_free(const struct ctx *c, const union inany_addr *addr) +{ + ssize_t slot = neigh_table_slot(c, addr); + struct neigh_table *t = &neigh_table; + struct neigh_table_entry *e, **prev; + + prev = &t->slots[slot]; + e = t->slots[slot]; + while (e && !inany_equals(&e->addr, addr)) { + prev = &e->next; + e = e->next; + } + if (!e) + return; + + *prev = e->next; + e->next = t->free; + t->free = e; + memset(&e->addr, 0, sizeof(*addr)); + memset(e->mac, 0, ETH_ALEN); +} + +/** + * fwd_neigh_mac_get() - Lookup MAC address in the ARP/NDP table + * @c: Execution context + * @addr: Neighbour address used as lookup key + * @mac: Buffer for Ethernet MAC to return, found or default value. + * + * Return: true if real MAC found, false if not found or if failure + */ +bool fwd_neigh_mac_get(const struct ctx *c, const union inany_addr *addr, + uint8_t *mac) +{ + struct neigh_table_entry *e = fwd_neigh_table_find(c, addr); + + if (e) + memcpy(mac, e->mac, ETH_ALEN); + else + memcpy(mac, c->our_tap_mac, ETH_ALEN); + + return !!e; +} + +/** + * fwd_neigh_table_init() - Initialize the neighbor table + */ +void fwd_neigh_table_init(void) +{ + struct neigh_table *t = &neigh_table; + struct neigh_table_entry *e; + + memset(t, 0, sizeof(*t)); + for (int i = 0; i < NEIGH_TABLE_SIZE; i++) { + e = &t->entries[i]; + e->next = t->free; + t->free = e; + } +} + /** fwd_probe_ephemeral() - Determine what ports this host considers ephemeral * * Work out what ports the host thinks are emphemeral and record it for later diff --git a/fwd.h b/fwd.h index 65c7c96..5464349 100644 --- a/fwd.h +++ b/fwd.h @@ -56,5 +56,12 @@ uint8_t fwd_nat_from_splice(const struct ctx *c, uint8_t proto, const struct flowside *ini, struct flowside *tgt); uint8_t fwd_nat_from_host(const struct ctx *c, uint8_t proto, const struct flowside *ini, struct flowside *tgt); +void fwd_neigh_table_update(const struct ctx *c, + const union inany_addr *addr, uint8_t *mac); +void fwd_neigh_table_free(const struct ctx *c, + const union inany_addr *addr); +bool fwd_neigh_mac_get(const struct ctx *c, const union inany_addr *addr, + uint8_t *mac); +void fwd_neigh_table_init(void);
#endif /* FWD_H */ diff --git a/netlink.c b/netlink.c index 0dc4e9d..da9e1d5 100644 --- a/netlink.c +++ b/netlink.c @@ -1189,8 +1189,10 @@ static void nl_neigh_msg_read(const struct ctx *c, struct nlmsghdr *nh) if (nh->nlmsg_type == RTM_NEWNEIGH && ndm->ndm_state & NUD_VALID) { trace("neigh table update: %s / %s", ip_str, mac_str); + fwd_neigh_table_update(c, &addr, mac); } else { trace("neigh table delete: %s / %s", ip_str, mac_str); + fwd_neigh_table_free(c, &addr); } }
-- 2.50.1
-- David Gibson (he or they) | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you, not the other way | around. http://www.ozlabs.org/~dgibson