On Sun, Oct 12, 2025 at 03:33:30PM -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.
Last sentence only really makes sense in the context of earlier versions of this series, which won't be in the final commit log.
Signed-off-by: Jon Maloy
--- 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 v12: - Changes according to feedback from David and Stefano - Added dummy entries for loopback and default GW addresses v13: - Changes according to feedback and discussions with David and Stefano --- fwd.c | 222 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ fwd.h | 7 ++ netlink.c | 3 + passt.c | 1 + 4 files changed, 233 insertions(+)
diff --git a/fwd.c b/fwd.c index 250cf56..d062ebc 100644 --- a/fwd.c +++ b/fwd.c @@ -26,6 +26,7 @@ #include "passt.h" #include "lineread.h" #include "flow_table.h" +#include "netlink.h"
/* Empheral port range: values from RFC 6335 */ static in_port_t fwd_ephemeral_min = (1 << 15) + (1 << 14); @@ -33,6 +34,227 @@ 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 +#define NEIGH_TABLE_SIZE (NEIGH_TABLE_SLOTS / 2) +static_assert((NEIGH_TABLE_SLOTS & (NEIGH_TABLE_SLOTS - 1)) == 0, + "NEIGH_TABLE_SLOTS must be a power of two"); + +/** + * struct 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 + * @permanent: Entry cannot be altered or freed by notification + */ +struct neigh_table_entry { + struct neigh_table_entry *next; + union inany_addr addr; + uint8_t mac[ETH_ALEN]; + bool permanent; +}; + +/** + * struct 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]; + 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 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 matching entry, if found. 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 or update neighbour table entry + * @c: Execution context + * @addr: IP address used to determine insertion slot and store in entry + * @mac: The MAC address associated with the neighbour address + * @permanent: Created entry cannot be altered or freed + */ +void fwd_neigh_table_update(const struct ctx *c, const union inany_addr *addr, + const uint8_t *mac, bool permanent) +{ + struct neigh_table *t = &neigh_table; + struct neigh_table_entry *e; + union inany_addr daddr; + ssize_t slot; + + /* We only add guest-side visible addresses */ + if (!nat_inbound(c, addr, &daddr)) + return;
To me, it makes more sense to have the nat_inbound() in the caller. That way the hash table is just a hash table, with no specific knowledge of what the contents mean. The caller is the thing which knows it has a host side address, and wants to update a corresponding entry in a table indexed by guest side address. It also means that the fwd_neigh_table_*() functions will consistently take guest side addresses.
+ /* MAC address might change sometimes */ + e = fwd_neigh_table_find(c, &daddr); + if (e) { + if (!e->permanent) + memcpy(e->mac, mac, ETH_ALEN); + return; + } + + e = t->free; + if (!e) { + debug("Failed to allocate neighbour table entry"); + return; + } + t->free = e->next; + slot = neigh_table_slot(c, &daddr); + e->next = t->slots[slot]; + t->slots[slot] = e; + + memcpy(&e->addr, &daddr, sizeof(daddr)); + memcpy(e->mac, mac, ETH_ALEN); + e->permanent = permanent; +} + +/** + * fwd_neigh_table_free() - Remove an entry from a slot and add it to free list + * @c: Execution context + * @addr: IP 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 || e->permanent) + 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() - Look up MAC address in the ARP/NDP table + * @c: Execution context + * @addr: Neighbour IP address used as lookup key + * @mac: Buffer for returned MAC address + */ +void fwd_neigh_mac_get(const struct ctx *c, const union inany_addr *addr, + uint8_t *mac) +{ + const 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); +} + +/** + * fwd_neigh_table_init() - Initialize the neighbour table + * @c: Execution context + */ +void fwd_neigh_table_init(const struct ctx *c) +{ + union inany_addr mhl = inany_from_v4(c->ip4.map_host_loopback); + union inany_addr mga = inany_from_v4(c->ip4.map_guest_addr); + union inany_addr ggw = inany_from_v4(c->ip4.guest_gw); + struct neigh_table *t = &neigh_table; + struct neigh_table_entry *e; + int i; + + memset(t, 0, sizeof(*t)); + + for (i = 0; i < NEIGH_TABLE_SIZE; i++) { + e = &t->entries[i]; + e->next = t->free; + t->free = e; + } + + /* Blocker entries to stop events from hosts using these addresses */ + if (!inany_is_unspecified4(&mhl)) + fwd_neigh_table_update(c, &mhl, c->our_tap_mac, true);
Here mhl is already a guest side address - and may not have a corresponding address host side - so we definitely don't want the nat_inbound() inside fwd_neigh_table_update().
+ if (!inany_is_unspecified4(&ggw) && !c->no_map_gw) + fwd_neigh_table_update(c, &ggw, c->our_tap_mac, true);
Same here.
+ if (!inany_is_unspecified4(&mga) && !inany_equals(&mhl, &mga)) { + uint8_t mac[ETH_ALEN]; + int rc; + + rc = nl_link_get_mac(nl_sock, c->ifi4, mac); + if (rc < 0) { + debug("Couldn't get ip4 MAC addr: %s", strerror_(-rc)); + memcpy(mac, c->our_tap_mac, ETH_ALEN); + } + fwd_neigh_table_update(c, &mga, mac, true);
And here.
+ } + + mhl = *(union inany_addr *)&c->ip6.map_host_loopback; + mga = *(union inany_addr *)&c->ip4.map_guest_addr; + ggw = *(union inany_addr *)&c->ip4.guest_gw; + + if (!inany_is_unspecified6(&mhl)) + fwd_neigh_table_update(c, &mhl, c->our_tap_mac, true);
..and so forth.
+ if (!inany_is_unspecified6(&ggw) && !c->no_map_gw) + fwd_neigh_table_update(c, &ggw, c->our_tap_mac, true); + + if (!inany_is_unspecified6(&mga) && !inany_equals(&mhl, &mga)) { + uint8_t mac[ETH_ALEN]; + int rc; + + rc = nl_link_get_mac(nl_sock, c->ifi6, mac); + if (rc < 0) { + debug("Couldn't get ip6 MAC addr: %s", strerror_(-rc)); + memcpy(mac, c->our_tap_mac, ETH_ALEN); + } + fwd_neigh_table_update(c, &mga, mac, true); + } +} + /** 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..352f3b5 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, + const uint8_t *mac, bool permanent); +void fwd_neigh_table_free(const struct ctx *c, + const union inany_addr *addr); +void fwd_neigh_mac_get(const struct ctx *c, const union inany_addr *addr, + uint8_t *mac); +void fwd_neigh_table_init(const struct ctx *c);
#endif /* FWD_H */ diff --git a/netlink.c b/netlink.c index 99dcb72..61796fb 100644 --- a/netlink.c +++ b/netlink.c @@ -1186,10 +1186,12 @@ static void nl_neigh_msg_read(const struct ctx *c, struct nlmsghdr *nh)
if (nh->nlmsg_type == RTM_DELNEIGH) { trace("neigh table delete: %s", ip_str); + fwd_neigh_table_free(c, &addr);
You'll need a nat_inbound() on the delete side as well. Again, I think it makes more sense here than in fwd_neigh_table_free(), but at the moment it's in neither.
return; } if (!(ndm->ndm_state & NUD_VALID)) { trace("neigh table: invalid state for %s", ip_str); + fwd_neigh_table_free(c, &addr); return; } if (nh->nlmsg_type != RTM_NEWNEIGH || !lladdr) { @@ -1202,6 +1204,7 @@ static void nl_neigh_msg_read(const struct ctx *c, struct nlmsghdr *nh) memcpy(mac, lladdr, ETH_ALEN); eth_ntop(mac, mac_str, sizeof(mac_str)); trace("neigh table update: %s / %s", ip_str, mac_str); + fwd_neigh_table_update(c, &addr, mac, false); }
/** diff --git a/passt.c b/passt.c index e21d6ba..98fc430 100644 --- a/passt.c +++ b/passt.c @@ -324,6 +324,7 @@ int main(int argc, char **argv)
pcap_init(&c);
+ fwd_neigh_table_init(&c); nl_neigh_notify_init(&c);
if (!c.foreground) { -- 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