diff options
Diffstat (limited to 'drivers/infiniband/core/addr.c')
| -rw-r--r-- | drivers/infiniband/core/addr.c | 213 |
1 files changed, 161 insertions, 52 deletions
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 8aba0ba57de..8172d37f9ad 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -37,6 +37,7 @@ #include <linux/inetdevice.h> #include <linux/slab.h> #include <linux/workqueue.h> +#include <linux/module.h> #include <net/arp.h> #include <net/neighbour.h> #include <net/route.h> @@ -44,6 +45,7 @@ #include <net/addrconf.h> #include <net/ip6_route.h> #include <rdma/ib_addr.h> +#include <rdma/ib.h> MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("IB Address Translation"); @@ -69,6 +71,23 @@ static LIST_HEAD(req_list); static DECLARE_DELAYED_WORK(work, process_req); static struct workqueue_struct *addr_wq; +int rdma_addr_size(struct sockaddr *addr) +{ + switch (addr->sa_family) { + case AF_INET: + return sizeof(struct sockaddr_in); + case AF_INET6: + return sizeof(struct sockaddr_in6); + case AF_IB: + return sizeof(struct sockaddr_ib); + default: + return 0; + } +} +EXPORT_SYMBOL(rdma_addr_size); + +static struct rdma_addr_client self; + void rdma_addr_register_client(struct rdma_addr_client *client) { atomic_set(&client->refcount, 1); @@ -102,7 +121,8 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev, } EXPORT_SYMBOL(rdma_copy_addr); -int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) +int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr, + u16 *vlan_id) { struct net_device *dev; int ret = -EADDRNOTAVAIL; @@ -125,10 +145,12 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) return ret; ret = rdma_copy_addr(dev_addr, dev, NULL); + if (vlan_id) + *vlan_id = rdma_vlan_dev_vlan_id(dev); dev_put(dev); break; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { @@ -136,6 +158,8 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) &((struct sockaddr_in6 *) addr)->sin6_addr, dev, 1)) { ret = rdma_copy_addr(dev_addr, dev, NULL); + if (vlan_id) + *vlan_id = rdma_vlan_dev_vlan_id(dev); break; } } @@ -151,13 +175,11 @@ static void set_timeout(unsigned long time) { unsigned long delay; - cancel_delayed_work(&work); - delay = time - jiffies; if ((long)delay <= 0) delay = 1; - queue_delayed_work(addr_wq, &work, delay); + mod_delayed_work(addr_wq, &work, delay); } static void queue_req(struct addr_req *req) @@ -177,31 +199,53 @@ static void queue_req(struct addr_req *req) mutex_unlock(&lock); } +static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr, void *daddr) +{ + struct neighbour *n; + int ret; + + n = dst_neigh_lookup(dst, daddr); + + rcu_read_lock(); + if (!n || !(n->nud_state & NUD_VALID)) { + if (n) + neigh_event_send(n, NULL); + ret = -ENODATA; + } else { + ret = rdma_copy_addr(dev_addr, dst->dev, n->ha); + } + rcu_read_unlock(); + + if (n) + neigh_release(n); + + return ret; +} + static int addr4_resolve(struct sockaddr_in *src_in, struct sockaddr_in *dst_in, struct rdma_dev_addr *addr) { __be32 src_ip = src_in->sin_addr.s_addr; __be32 dst_ip = dst_in->sin_addr.s_addr; - struct flowi fl; struct rtable *rt; - struct neighbour *neigh; + struct flowi4 fl4; int ret; - memset(&fl, 0, sizeof fl); - fl.nl_u.ip4_u.daddr = dst_ip; - fl.nl_u.ip4_u.saddr = src_ip; - fl.oif = addr->bound_dev_if; - - ret = ip_route_output_key(&init_net, &rt, &fl); - if (ret) + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = dst_ip; + fl4.saddr = src_ip; + fl4.flowi4_oif = addr->bound_dev_if; + rt = ip_route_output_key(&init_net, &fl4); + if (IS_ERR(rt)) { + ret = PTR_ERR(rt); goto out; - + } src_in->sin_family = AF_INET; - src_in->sin_addr.s_addr = rt->rt_src; + src_in->sin_addr.s_addr = fl4.saddr; if (rt->dst.dev->flags & IFF_LOOPBACK) { - ret = rdma_translate_ip((struct sockaddr *) dst_in, addr); + ret = rdma_translate_ip((struct sockaddr *)dst_in, addr, NULL); if (!ret) memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN); goto put; @@ -209,59 +253,47 @@ static int addr4_resolve(struct sockaddr_in *src_in, /* If the device does ARP internally, return 'done' */ if (rt->dst.dev->flags & IFF_NOARP) { - rdma_copy_addr(addr, rt->dst.dev, NULL); - goto put; - } - - neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->dst.dev); - if (!neigh || !(neigh->nud_state & NUD_VALID)) { - neigh_event_send(rt->dst.neighbour, NULL); - ret = -ENODATA; - if (neigh) - goto release; + ret = rdma_copy_addr(addr, rt->dst.dev, NULL); goto put; } - ret = rdma_copy_addr(addr, neigh->dev, neigh->ha); -release: - neigh_release(neigh); + ret = dst_fetch_ha(&rt->dst, addr, &fl4.daddr); put: ip_rt_put(rt); out: return ret; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static int addr6_resolve(struct sockaddr_in6 *src_in, struct sockaddr_in6 *dst_in, struct rdma_dev_addr *addr) { - struct flowi fl; - struct neighbour *neigh; + struct flowi6 fl6; struct dst_entry *dst; int ret; - memset(&fl, 0, sizeof fl); - ipv6_addr_copy(&fl.fl6_dst, &dst_in->sin6_addr); - ipv6_addr_copy(&fl.fl6_src, &src_in->sin6_addr); - fl.oif = addr->bound_dev_if; + memset(&fl6, 0, sizeof fl6); + fl6.daddr = dst_in->sin6_addr; + fl6.saddr = src_in->sin6_addr; + fl6.flowi6_oif = addr->bound_dev_if; - dst = ip6_route_output(&init_net, NULL, &fl); + dst = ip6_route_output(&init_net, NULL, &fl6); if ((ret = dst->error)) goto put; - if (ipv6_addr_any(&fl.fl6_src)) { + if (ipv6_addr_any(&fl6.saddr)) { ret = ipv6_dev_get_saddr(&init_net, ip6_dst_idev(dst)->dev, - &fl.fl6_dst, 0, &fl.fl6_src); + &fl6.daddr, 0, &fl6.saddr); if (ret) goto put; src_in->sin6_family = AF_INET6; - ipv6_addr_copy(&src_in->sin6_addr, &fl.fl6_src); + src_in->sin6_addr = fl6.saddr; } if (dst->dev->flags & IFF_LOOPBACK) { - ret = rdma_translate_ip((struct sockaddr *) dst_in, addr); + ret = rdma_translate_ip((struct sockaddr *)dst_in, addr, NULL); if (!ret) memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN); goto put; @@ -273,14 +305,7 @@ static int addr6_resolve(struct sockaddr_in6 *src_in, goto put; } - neigh = dst->neighbour; - if (!neigh || !(neigh->nud_state & NUD_VALID)) { - neigh_event_send(dst->neighbour, NULL); - ret = -ENODATA; - goto put; - } - - ret = rdma_copy_addr(addr, dst->dev, neigh->ha); + ret = dst_fetch_ha(dst, addr, &fl6.daddr); put: dst_release(dst); return ret; @@ -367,12 +392,12 @@ int rdma_resolve_ip(struct rdma_addr_client *client, goto err; } - memcpy(src_in, src_addr, ip_addr_size(src_addr)); + memcpy(src_in, src_addr, rdma_addr_size(src_addr)); } else { src_in->sa_family = dst_addr->sa_family; } - memcpy(dst_in, dst_addr, ip_addr_size(dst_addr)); + memcpy(dst_in, dst_addr, rdma_addr_size(dst_addr)); req->addr = addr; req->callback = callback; req->context = context; @@ -419,6 +444,88 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr) } EXPORT_SYMBOL(rdma_addr_cancel); +struct resolve_cb_context { + struct rdma_dev_addr *addr; + struct completion comp; +}; + +static void resolve_cb(int status, struct sockaddr *src_addr, + struct rdma_dev_addr *addr, void *context) +{ + memcpy(((struct resolve_cb_context *)context)->addr, addr, sizeof(struct + rdma_dev_addr)); + complete(&((struct resolve_cb_context *)context)->comp); +} + +int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac, + u16 *vlan_id) +{ + int ret = 0; + struct rdma_dev_addr dev_addr; + struct resolve_cb_context ctx; + struct net_device *dev; + + union { + struct sockaddr _sockaddr; + struct sockaddr_in _sockaddr_in; + struct sockaddr_in6 _sockaddr_in6; + } sgid_addr, dgid_addr; + + + ret = rdma_gid2ip(&sgid_addr._sockaddr, sgid); + if (ret) + return ret; + + ret = rdma_gid2ip(&dgid_addr._sockaddr, dgid); + if (ret) + return ret; + + memset(&dev_addr, 0, sizeof(dev_addr)); + + ctx.addr = &dev_addr; + init_completion(&ctx.comp); + ret = rdma_resolve_ip(&self, &sgid_addr._sockaddr, &dgid_addr._sockaddr, + &dev_addr, 1000, resolve_cb, &ctx); + if (ret) + return ret; + + wait_for_completion(&ctx.comp); + + memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN); + dev = dev_get_by_index(&init_net, dev_addr.bound_dev_if); + if (!dev) + return -ENODEV; + if (vlan_id) + *vlan_id = rdma_vlan_dev_vlan_id(dev); + dev_put(dev); + return ret; +} +EXPORT_SYMBOL(rdma_addr_find_dmac_by_grh); + +int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id) +{ + int ret = 0; + struct rdma_dev_addr dev_addr; + union { + struct sockaddr _sockaddr; + struct sockaddr_in _sockaddr_in; + struct sockaddr_in6 _sockaddr_in6; + } gid_addr; + + ret = rdma_gid2ip(&gid_addr._sockaddr, sgid); + + if (ret) + return ret; + memset(&dev_addr, 0, sizeof(dev_addr)); + ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id); + if (ret) + return ret; + + memcpy(smac, dev_addr.src_dev_addr, ETH_ALEN); + return ret; +} +EXPORT_SYMBOL(rdma_addr_find_smac_by_sgid); + static int netevent_callback(struct notifier_block *self, unsigned long event, void *ctx) { @@ -443,11 +550,13 @@ static int __init addr_init(void) return -ENOMEM; register_netevent_notifier(&nb); + rdma_addr_register_client(&self); return 0; } static void __exit addr_cleanup(void) { + rdma_addr_unregister_client(&self); unregister_netevent_notifier(&nb); destroy_workqueue(addr_wq); } |