From 5e8d90497d65f528c54015644095ace6e330fd8e Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:15 -0800 Subject: switchdev: add IPv4 fib ndo ops wrappers Add IPv4 fib ndo wrapper funcs and stub them out for now. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- net/switchdev/switchdev.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'net/switchdev/switchdev.c') diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8c1e558db118..3c090f8d071b 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -14,6 +14,7 @@ #include #include #include +#include #include /** @@ -225,3 +226,41 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, return ret; } EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink); + +/** + * netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch + * + * @dst: route's IPv4 destination address + * @dst_len: destination address length (prefix length) + * @fi: route FIB info structure + * @tos: route TOS + * @type: route type + * @tb_id: route table ID + * + * Add IPv4 route entry to switch device. + */ +int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) +{ + return 0; +} +EXPORT_SYMBOL(netdev_switch_fib_ipv4_add); + +/** + * netdev_switch_fib_ipv4_del - Delete IPv4 route entry from switch + * + * @dst: route's IPv4 destination address + * @dst_len: destination address length (prefix length) + * @fi: route FIB info structure + * @tos: route TOS + * @type: route type + * @tb_id: route table ID + * + * Delete IPv4 route entry from switch device. + */ +int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) +{ + return 0; +} +EXPORT_SYMBOL(netdev_switch_fib_ipv4_del); -- cgit v1.2.3 From 104616e74e0b464d449fdd2ee2f547d2fad71610 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:16 -0800 Subject: switchdev: don't support custom ip rules, for now Keep switchdev FIB offload model simple for now and don't allow custom ip rules. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 ++ net/ipv4/fib_frontend.c | 13 ++++++++++ net/ipv4/fib_rules.c | 3 +++ net/ipv4/fib_trie.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++ net/switchdev/switchdev.c | 4 ++++ 5 files changed, 83 insertions(+) (limited to 'net/switchdev/switchdev.c') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 825cb2800908..1657604c5dd3 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -196,6 +196,7 @@ int fib_table_delete(struct fib_table *, struct fib_config *); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct fib_table *table); +void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); @@ -308,6 +309,7 @@ static inline int fib_num_tclassid_users(struct net *net) return 0; } #endif +void fib_flush_external(struct net *net); /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 220c4b4af4cf..e067770235bf 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -144,6 +144,19 @@ static void fib_flush(struct net *net) rt_cache_flush(net); } +void fib_flush_external(struct net *net) +{ + struct fib_table *tb; + struct hlist_head *head; + unsigned int h; + + for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + head = &net->ipv4.fib_table_hash[h]; + hlist_for_each_entry(tb, head, tb_hlist) + fib_table_flush_external(tb); + } +} + /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index d3db718be51d..190d0d00d744 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -209,6 +209,8 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->tos = frh->tos; net->ipv4.fib_has_custom_rules = true; + fib_flush_external(rule->fr_net); + err = 0; errout: return err; @@ -224,6 +226,7 @@ static void fib4_rule_delete(struct fib_rule *rule) net->ipv4.fib_num_tclassid_users--; #endif net->ipv4.fib_has_custom_rules = true; + fib_flush_external(rule->fr_net); } static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index fae34ad4bb1a..2de43956c9d0 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1536,6 +1536,67 @@ found: return n; } +/* Caller must hold RTNL */ +void fib_table_flush_external(struct fib_table *tb) +{ + struct trie *t = (struct trie *)tb->tb_data; + struct fib_alias *fa; + struct tnode *n, *pn; + unsigned long cindex; + unsigned char slen; + int found = 0; + + n = rcu_dereference(t->trie); + if (!n) + return; + + pn = NULL; + cindex = 0; + + while (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; +backtrace: + /* walk trie in reverse order */ + do { + while (!(cindex--)) { + t_key pkey = pn->key; + + n = pn; + pn = node_parent(n); + + /* resize completed node */ + resize(t, n); + + /* if we got the root we are done */ + if (!pn) + return; + + cindex = get_index(pkey, pn); + } + + /* grab the next available node */ + n = tnode_get_child(pn, cindex); + } while (!n); + } + + hlist_for_each_entry(fa, &n->leaf, fa_list) { + struct fib_info *fi = fa->fa_info; + + if (fi && (fi->fib_flags & RTNH_F_EXTERNAL)) { + netdev_switch_fib_ipv4_del(n->key, + KEYLENGTH - fa->fa_slen, + fi, fa->fa_tos, + fa->fa_type, tb->tb_id); + } + } + + /* if trie is leaf only loop is completed */ + if (pn) + goto backtrace; +} + /* Caller must hold RTNL. */ int fib_table_flush(struct fib_table *tb) { diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 3c090f8d071b..81c4c0274b9b 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -242,6 +242,10 @@ EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink); int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { + /* Don't offload route if using custom ip rules */ + if (fi->fib_net->ipv4.fib_has_custom_rules) + return 0; + return 0; } EXPORT_SYMBOL(netdev_switch_fib_ipv4_add); -- cgit v1.2.3 From b5d6fbdeede861b52d67b9a4ea3fdfcc6e6865cd Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:17 -0800 Subject: switchdev: implement IPv4 fib ndo wrappers Flesh out ndo wrappers to call into device driver. To call into device driver, the wrapper must interate over route's nexthops to ensure all nexthop devs belong to the same switch device. Currently, there is no support for route's nexthops spanning offloaded and non-offloaded devices, or spanning ports of multiple offload devices. Since switch device ports may be stacked under virtual interfaces (bonds and/or bridges), and the route's nexthop may be on the virtual interface, the wrapper will traverse the nexthop dev down to the base dev. It's the base dev that's passed to the switchdev driver's ndo ops. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- net/switchdev/switchdev.c | 98 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 96 insertions(+), 2 deletions(-) (limited to 'net/switchdev/switchdev.c') diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 81c4c0274b9b..99907d829419 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -227,6 +227,65 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, } EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink); +static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct net_device *lower_dev; + struct net_device *port_dev; + struct list_head *iter; + + /* Recusively search down until we find a sw port dev. + * (A sw port dev supports ndo_switch_parent_id_get). + */ + + if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD && + ops->ndo_switch_parent_id_get) + return dev; + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + port_dev = netdev_switch_get_lowest_dev(lower_dev); + if (port_dev) + return port_dev; + } + + return NULL; +} + +static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) +{ + struct netdev_phys_item_id psid; + struct netdev_phys_item_id prev_psid; + struct net_device *dev = NULL; + int nhsel; + + /* For this route, all nexthop devs must be on the same switch. */ + + for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { + const struct fib_nh *nh = &fi->fib_nh[nhsel]; + + if (!nh->nh_dev) + return NULL; + + dev = netdev_switch_get_lowest_dev(nh->nh_dev); + if (!dev) + return NULL; + + if (netdev_switch_parent_id_get(dev, &psid)) + return NULL; + + if (nhsel > 0) { + if (prev_psid.id_len != psid.id_len) + return NULL; + if (memcmp(prev_psid.id, psid.id, psid.id_len)) + return NULL; + } + + prev_psid = psid; + } + + return dev; +} + /** * netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch * @@ -242,11 +301,27 @@ EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink); int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { + struct net_device *dev; + const struct net_device_ops *ops; + int err = 0; + /* Don't offload route if using custom ip rules */ if (fi->fib_net->ipv4.fib_has_custom_rules) return 0; - return 0; + dev = netdev_switch_get_dev_by_nhs(fi); + if (!dev) + return 0; + ops = dev->netdev_ops; + + if (ops->ndo_switch_fib_ipv4_add) { + err = ops->ndo_switch_fib_ipv4_add(dev, htonl(dst), dst_len, + fi, tos, type, tb_id); + if (!err) + fi->fib_flags |= RTNH_F_EXTERNAL; + } + + return err; } EXPORT_SYMBOL(netdev_switch_fib_ipv4_add); @@ -265,6 +340,25 @@ EXPORT_SYMBOL(netdev_switch_fib_ipv4_add); int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { - return 0; + struct net_device *dev; + const struct net_device_ops *ops; + int err = 0; + + if (!(fi->fib_flags & RTNH_F_EXTERNAL)) + return 0; + + dev = netdev_switch_get_dev_by_nhs(fi); + if (!dev) + return 0; + ops = dev->netdev_ops; + + if (ops->ndo_switch_fib_ipv4_del) { + err = ops->ndo_switch_fib_ipv4_del(dev, htonl(dst), dst_len, + fi, tos, type, tb_id); + if (!err) + fi->fib_flags &= ~RTNH_F_EXTERNAL; + } + + return err; } EXPORT_SYMBOL(netdev_switch_fib_ipv4_del); -- cgit v1.2.3 From 8e05fd7166c6123334b7a739a697d677747aa462 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:19 -0800 Subject: fib: hook IPv4 fib for hardware offload Call into the switchdev driver any time an IPv4 fib entry is added/modified/deleted from the kernel's FIB. The switchdev driver may or may not install the route to the offload device. In the case where the driver tries to install the route and something goes wrong (device's routing table is full, etc), then all of the offloaded routes will be flushed from the device, route forwarding falls back to the kernel, and no more routes are offloading. We can refine this logic later. For now, use the simplist model of offloading routes up to the point of failure, and then on failure, undo everything and mark IPv4 offloading disabled. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/net/switchdev.h | 5 +++++ net/ipv4/fib_trie.c | 31 ++++++++++++++++++++++++++++++- net/switchdev/switchdev.c | 28 ++++++++++++++++++++++++++-- 3 files changed, 61 insertions(+), 3 deletions(-) (limited to 'net/switchdev/switchdev.c') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 8d2ac663325a..dc0a5cc7c2c5 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -55,6 +55,7 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id); int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id); +void netdev_switch_fib_ipv4_abort(struct fib_info *fi); #else @@ -128,6 +129,10 @@ static inline int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, return 0; } +void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +{ +} + #endif #endif /* _LINUX_SWITCHDEV_H_ */ diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2de43956c9d0..6544f1a0cfa1 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -79,6 +79,7 @@ #include #include #include +#include #include "fib_lookup.h" #define MAX_STAT_DEPTH 32 @@ -1135,7 +1136,18 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; + err = netdev_switch_fib_ipv4_add(key, plen, fi, + new_fa->fa_tos, + cfg->fc_type, + tb->tb_id); + if (err) { + netdev_switch_fib_ipv4_abort(fi); + kmem_cache_free(fn_alias_kmem, new_fa); + goto out; + } + hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); + alias_free_mem_rcu(fa); fib_release_info(fi_drop); @@ -1171,10 +1183,18 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = 0; new_fa->fa_slen = slen; + /* (Optionally) offload fib entry to switch hardware. */ + err = netdev_switch_fib_ipv4_add(key, plen, fi, tos, + cfg->fc_type, tb->tb_id); + if (err) { + netdev_switch_fib_ipv4_abort(fi); + goto out_free_new_fa; + } + /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) - goto out_free_new_fa; + goto out_sw_fib_del; if (!plen) tb->tb_num_default++; @@ -1185,6 +1205,8 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) succeeded: return 0; +out_sw_fib_del: + netdev_switch_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: @@ -1456,6 +1478,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if (!fa_to_delete) return -ESRCH; + netdev_switch_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos, + cfg->fc_type, tb->tb_id); + rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -1650,6 +1675,10 @@ backtrace: struct fib_info *fi = fa->fa_info; if (fi && (fi->fib_flags & RTNH_F_DEAD)) { + netdev_switch_fib_ipv4_del(n->key, + KEYLENGTH - fa->fa_slen, + fi, fa->fa_tos, + fa->fa_type, tb->tb_id); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 99907d829419..f4fd575aa2a3 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -305,8 +305,12 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, const struct net_device_ops *ops; int err = 0; - /* Don't offload route if using custom ip rules */ - if (fi->fib_net->ipv4.fib_has_custom_rules) + /* Don't offload route if using custom ip rules or if + * IPv4 FIB offloading has been disabled completely. + */ + + if (fi->fib_net->ipv4.fib_has_custom_rules | + fi->fib_net->ipv4.fib_offload_disabled) return 0; dev = netdev_switch_get_dev_by_nhs(fi); @@ -362,3 +366,23 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, return err; } EXPORT_SYMBOL(netdev_switch_fib_ipv4_del); + +/** + * netdev_switch_fib_ipv4_abort - Abort an IPv4 FIB operation + * + * @fi: route FIB info structure + */ +void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +{ + /* There was a problem installing this route to the offload + * device. For now, until we come up with more refined + * policy handling, abruptly end IPv4 fib offloading for + * for entire net by flushing offload device(s) of all + * IPv4 routes, and mark IPv4 fib offloading broken from + * this point forward. + */ + + fib_flush_external(fi->fib_net); + fi->fib_net->ipv4.fib_offload_disabled = true; +} +EXPORT_SYMBOL(netdev_switch_fib_ipv4_abort); -- cgit v1.2.3