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. 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 v14: - Moved the call to nat_inbound() to a much more sensible place in netlink.c, as suggested by David. v15: - Changes according to feedback from David and Stefano - Removed 'blocker' entry for guest_gw. - Let blocker entry for ctx->map_guest_addr use our_mac_addr - We let fwd_neigh_mac_get() do a secondary lookup in the table, using the guest_gw address, when the primary lookup fails. This way, we always return the correct gateway MAC address if there happens to be a real host presenting that address. --- fwd.c | 202 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ fwd.h | 7 ++ netlink.c | 12 +++- passt.c | 1 + 4 files changed, 220 insertions(+), 2 deletions(-) diff --git a/fwd.c b/fwd.c index 250cf56..93d83e3 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 +34,207 @@ 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; + ssize_t slot; + + /* MAC address might change sometimes */ + e = fwd_neigh_table_find(c, addr); + 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, addr); + e->next = t->slots[slot]; + t->slots[slot] = e; + + memcpy(&e->addr, addr, sizeof(*addr)); + 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) { + union inany_addr ggw; + + if (inany_v4(addr)) + ggw = inany_from_v4(c->ip4.guest_gw); + else + ggw.a6 = c->ip6.guest_gw; + + e = fwd_neigh_table_find(c, &ggw); + } + + 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); + 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); + + if (!inany_is_unspecified4(&mga)) + fwd_neigh_table_update(c, &mga, c->our_tap_mac, true); + + mhl = *(union inany_addr *)&c->ip6.map_host_loopback; + mga = *(union inany_addr *)&c->ip6.map_guest_addr; + + if (!inany_is_unspecified6(&mhl)) + fwd_neigh_table_update(c, &mhl, c->our_tap_mac, true); + + if (!inany_is_unspecified6(&mga)) + fwd_neigh_table_update(c, &mga, c->our_tap_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 2896e23..ee7466a 100644 --- a/netlink.c +++ b/netlink.c @@ -1123,9 +1123,9 @@ static void nl_neigh_msg_read(const struct ctx *c, struct nlmsghdr *nh) char ip_str[INET6_ADDRSTRLEN]; char mac_str[ETH_ADDRSTRLEN]; const uint8_t *lladdr = NULL; + union inany_addr addr, daddr; const void *dst = NULL; size_t lladdr_len = 0; - union inany_addr addr; size_t dstlen = 0; if (nh->nlmsg_type == NLMSG_DONE) @@ -1172,16 +1172,23 @@ static void nl_neigh_msg_read(const struct ctx *c, struct nlmsghdr *nh) warn("netlink: wrong address length in AF_INET6 notification"); return; } + + /* We only handle guest-side visible addresses */ inany_from_af(&addr, ndm->ndm_family, dst); - inany_ntop(&addr, ip_str, sizeof(ip_str)); + if (!nat_inbound(c, &addr, &daddr)) + return; + + inany_ntop(&daddr, ip_str, sizeof(ip_str)); if (nh->nlmsg_type == RTM_DELNEIGH) { trace("neighbour notifier delete: %s", ip_str); + fwd_neigh_table_free(c, &daddr); return; } if (!(ndm->ndm_state & NUD_VALID)) { trace("neighbour notifier: %s unreachable, state: 0x%02x", ip_str, ndm->ndm_state); + fwd_neigh_table_free(c, &daddr); return; } if (!lladdr) { @@ -1193,6 +1200,7 @@ static void nl_neigh_msg_read(const struct ctx *c, struct nlmsghdr *nh) eth_ntop(lladdr, mac_str, sizeof(mac_str)); trace("neighbour notifier update: %s / %s", ip_str, mac_str); + fwd_neigh_table_update(c, &daddr, lladdr, false); } /** diff --git a/passt.c b/passt.c index a10e469..24e4348 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