1 files changed, 227 insertions, 196 deletions

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 5be1bd4fc7e..8172d37f9ad 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -35,8 +35,9 @@
 
 #include <linux/mutex.h>
 #include <linux/inetdevice.h>
+#include <linux/slab.h>
 #include <linux/workqueue.h>
-#include <linux/if_arp.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);
@@ -92,31 +111,31 @@ EXPORT_SYMBOL(rdma_addr_unregister_client);
 int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
 		     const unsigned char *dst_dev_addr)
 {
-	switch (dev->type) {
-	case ARPHRD_INFINIBAND:
-		dev_addr->dev_type = RDMA_NODE_IB_CA;
-		break;
-	case ARPHRD_ETHER:
-		dev_addr->dev_type = RDMA_NODE_RNIC;
-		break;
-	default:
-		return -EADDRNOTAVAIL;
-	}
-
+	dev_addr->dev_type = dev->type;
 	memcpy(dev_addr->src_dev_addr, dev->dev_addr, MAX_ADDR_LEN);
 	memcpy(dev_addr->broadcast, dev->broadcast, MAX_ADDR_LEN);
 	if (dst_dev_addr)
 		memcpy(dev_addr->dst_dev_addr, dst_dev_addr, MAX_ADDR_LEN);
-	dev_addr->src_dev = dev;
+	dev_addr->bound_dev_if = dev->ifindex;
 	return 0;
 }
 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;
 
+	if (dev_addr->bound_dev_if) {
+		dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+		if (!dev)
+			return -ENODEV;
+		ret = rdma_copy_addr(dev_addr, dev, NULL);
+		dev_put(dev);
+		return ret;
+	}
+
 	switch (addr->sa_family) {
 	case AF_INET:
 		dev = ip_dev_find(&init_net,
@@ -126,19 +145,25 @@ 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:
-		for_each_netdev(&init_net, dev) {
+		rcu_read_lock();
+		for_each_netdev_rcu(&init_net, dev) {
 			if (ipv6_chk_addr(&init_net,
 					  &((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;
 			}
 		}
+		rcu_read_unlock();
 		break;
 #endif
 	}
@@ -150,13 +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)
@@ -176,141 +199,135 @@ static void queue_req(struct addr_req *req)
 	mutex_unlock(&lock);
 }
 
-static void addr_send_arp(struct sockaddr *dst_in)
+static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr, void *daddr)
 {
-	struct rtable *rt;
-	struct flowi fl;
-
-	memset(&fl, 0, sizeof fl);
-
-	switch (dst_in->sa_family) {
-	case AF_INET:
-		fl.nl_u.ip4_u.daddr =
-			((struct sockaddr_in *) dst_in)->sin_addr.s_addr;
-
-		if (ip_route_output_key(&init_net, &rt, &fl))
-			return;
-
-		neigh_event_send(rt->u.dst.neighbour, NULL);
-		ip_rt_put(rt);
-		break;
+	struct neighbour *n;
+	int ret;
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-	case AF_INET6:
-	{
-		struct dst_entry *dst;
+	n = dst_neigh_lookup(dst, daddr);
 
-		fl.nl_u.ip6_u.daddr =
-			((struct sockaddr_in6 *) dst_in)->sin6_addr;
+	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();
 
-		dst = ip6_route_output(&init_net, NULL, &fl);
-		if (!dst)
-			return;
+	if (n)
+		neigh_release(n);
 
-		neigh_event_send(dst->neighbour, NULL);
-		dst_release(dst);
-		break;
-	}
-#endif
-	}
+	return ret;
 }
 
-static int addr4_resolve_remote(struct sockaddr_in *src_in,
-			       struct sockaddr_in *dst_in,
-			       struct rdma_dev_addr *addr)
+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;
-	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;
-
-	/* If the device does ARP internally, return 'done' */
-	if (rt->idev->dev->flags & IFF_NOARP) {
-		rdma_copy_addr(addr, rt->idev->dev, NULL);
-		goto put;
 	}
+	src_in->sin_family = AF_INET;
+	src_in->sin_addr.s_addr = fl4.saddr;
 
-	neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->idev->dev);
-	if (!neigh) {
-		ret = -ENODATA;
+	if (rt->dst.dev->flags & IFF_LOOPBACK) {
+		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;
 	}
 
-	if (!(neigh->nud_state & NUD_VALID)) {
-		ret = -ENODATA;
-		goto release;
-	}
-
-	if (!src_ip) {
-		src_in->sin_family = dst_in->sin_family;
-		src_in->sin_addr.s_addr = rt->rt_src;
+	/* If the device does ARP internally, return 'done' */
+	if (rt->dst.dev->flags & IFF_NOARP) {
+		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)
-static int addr6_resolve_remote(struct sockaddr_in6 *src_in,
-			       struct sockaddr_in6 *dst_in,
-			       struct rdma_dev_addr *addr)
+#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 = -ENODATA;
+	int ret;
 
-	memset(&fl, 0, sizeof fl);
-	fl.nl_u.ip6_u.daddr = dst_in->sin6_addr;
-	fl.nl_u.ip6_u.saddr = src_in->sin6_addr;
+	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);
-	if (!dst)
-		return ret;
+	dst = ip6_route_output(&init_net, NULL, &fl6);
+	if ((ret = dst->error))
+		goto put;
+
+	if (ipv6_addr_any(&fl6.saddr)) {
+		ret = ipv6_dev_get_saddr(&init_net, ip6_dst_idev(dst)->dev,
+					 &fl6.daddr, 0, &fl6.saddr);
+		if (ret)
+			goto put;
+
+		src_in->sin6_family = AF_INET6;
+		src_in->sin6_addr = fl6.saddr;
+	}
+
+	if (dst->dev->flags & IFF_LOOPBACK) {
+		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;
+	}
 
+	/* If the device does ARP internally, return 'done' */
 	if (dst->dev->flags & IFF_NOARP) {
 		ret = rdma_copy_addr(addr, dst->dev, NULL);
-	} else {
-		neigh = dst->neighbour;
-		if (neigh && (neigh->nud_state & NUD_VALID))
-			ret = rdma_copy_addr(addr, neigh->dev, neigh->ha);
+		goto put;
 	}
 
+	ret = dst_fetch_ha(dst, addr, &fl6.daddr);
+put:
 	dst_release(dst);
 	return ret;
 }
 #else
-static int addr6_resolve_remote(struct sockaddr_in6 *src_in,
-			       struct sockaddr_in6 *dst_in,
-			       struct rdma_dev_addr *addr)
+static int addr6_resolve(struct sockaddr_in6 *src_in,
+			 struct sockaddr_in6 *dst_in,
+			 struct rdma_dev_addr *addr)
 {
 	return -EADDRNOTAVAIL;
 }
 #endif
 
-static int addr_resolve_remote(struct sockaddr *src_in,
-				struct sockaddr *dst_in,
-				struct rdma_dev_addr *addr)
+static int addr_resolve(struct sockaddr *src_in,
+			struct sockaddr *dst_in,
+			struct rdma_dev_addr *addr)
 {
 	if (src_in->sa_family == AF_INET) {
-		return addr4_resolve_remote((struct sockaddr_in *) src_in,
+		return addr4_resolve((struct sockaddr_in *) src_in,
 			(struct sockaddr_in *) dst_in, addr);
 	} else
-		return addr6_resolve_remote((struct sockaddr_in6 *) src_in,
+		return addr6_resolve((struct sockaddr_in6 *) src_in,
 			(struct sockaddr_in6 *) dst_in, addr);
 }
 
@@ -327,8 +344,7 @@ static void process_req(struct work_struct *work)
 		if (req->status == -ENODATA) {
 			src_in = (struct sockaddr *) &req->src_addr;
 			dst_in = (struct sockaddr *) &req->dst_addr;
-			req->status = addr_resolve_remote(src_in, dst_in,
-							  req->addr);
+			req->status = addr_resolve(src_in, dst_in, req->addr);
 			if (req->status && time_after_eq(jiffies, req->timeout))
 				req->status = -ETIMEDOUT;
 			else if (req->status == -ENODATA)
@@ -352,82 +368,6 @@ static void process_req(struct work_struct *work)
 	}
 }
 
-static int addr_resolve_local(struct sockaddr *src_in,
-			      struct sockaddr *dst_in,
-			      struct rdma_dev_addr *addr)
-{
-	struct net_device *dev;
-	int ret;
-
-	switch (dst_in->sa_family) {
-	case AF_INET:
-	{
-		__be32 src_ip = ((struct sockaddr_in *) src_in)->sin_addr.s_addr;
-		__be32 dst_ip = ((struct sockaddr_in *) dst_in)->sin_addr.s_addr;
-
-		dev = ip_dev_find(&init_net, dst_ip);
-		if (!dev)
-			return -EADDRNOTAVAIL;
-
-		if (ipv4_is_zeronet(src_ip)) {
-			src_in->sa_family = dst_in->sa_family;
-			((struct sockaddr_in *) src_in)->sin_addr.s_addr = dst_ip;
-			ret = rdma_copy_addr(addr, dev, dev->dev_addr);
-		} else if (ipv4_is_loopback(src_ip)) {
-			ret = rdma_translate_ip(dst_in, addr);
-			if (!ret)
-				memcpy(addr->dst_dev_addr, dev->dev_addr, MAX_ADDR_LEN);
-		} else {
-			ret = rdma_translate_ip(src_in, addr);
-			if (!ret)
-				memcpy(addr->dst_dev_addr, dev->dev_addr, MAX_ADDR_LEN);
-		}
-		dev_put(dev);
-		break;
-	}
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-	case AF_INET6:
-	{
-		struct in6_addr *a;
-
-		for_each_netdev(&init_net, dev)
-			if (ipv6_chk_addr(&init_net,
-					  &((struct sockaddr_in6 *) addr)->sin6_addr,
-					  dev, 1))
-				break;
-
-		if (!dev)
-			return -EADDRNOTAVAIL;
-
-		a = &((struct sockaddr_in6 *) src_in)->sin6_addr;
-
-		if (ipv6_addr_any(a)) {
-			src_in->sa_family = dst_in->sa_family;
-			((struct sockaddr_in6 *) src_in)->sin6_addr =
-				((struct sockaddr_in6 *) dst_in)->sin6_addr;
-			ret = rdma_copy_addr(addr, dev, dev->dev_addr);
-		} else if (ipv6_addr_loopback(a)) {
-			ret = rdma_translate_ip(dst_in, addr);
-			if (!ret)
-				memcpy(addr->dst_dev_addr, dev->dev_addr, MAX_ADDR_LEN);
-		} else  {
-			ret = rdma_translate_ip(src_in, addr);
-			if (!ret)
-				memcpy(addr->dst_dev_addr, dev->dev_addr, MAX_ADDR_LEN);
-		}
-		break;
-	}
-#endif
-
-	default:
-		ret = -EADDRNOTAVAIL;
-		break;
-	}
-
-	return ret;
-}
-
 int rdma_resolve_ip(struct rdma_addr_client *client,
 		    struct sockaddr *src_addr, struct sockaddr *dst_addr,
 		    struct rdma_dev_addr *addr, int timeout_ms,
@@ -443,22 +383,28 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
 	if (!req)
 		return -ENOMEM;
 
-	if (src_addr)
-		memcpy(&req->src_addr, src_addr, ip_addr_size(src_addr));
-	memcpy(&req->dst_addr, dst_addr, ip_addr_size(dst_addr));
+	src_in = (struct sockaddr *) &req->src_addr;
+	dst_in = (struct sockaddr *) &req->dst_addr;
+
+	if (src_addr) {
+		if (src_addr->sa_family != dst_addr->sa_family) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		memcpy(src_in, src_addr, rdma_addr_size(src_addr));
+	} else {
+		src_in->sa_family = dst_addr->sa_family;
+	}
+
+	memcpy(dst_in, dst_addr, rdma_addr_size(dst_addr));
 	req->addr = addr;
 	req->callback = callback;
 	req->context = context;
 	req->client = client;
 	atomic_inc(&client->refcount);
 
-	src_in = (struct sockaddr *) &req->src_addr;
-	dst_in = (struct sockaddr *) &req->dst_addr;
-
-	req->status = addr_resolve_local(src_in, dst_in, addr);
-	if (req->status == -EADDRNOTAVAIL)
-		req->status = addr_resolve_remote(src_in, dst_in, addr);
-
+	req->status = addr_resolve(src_in, dst_in, addr);
 	switch (req->status) {
 	case 0:
 		req->timeout = jiffies;
@@ -467,15 +413,16 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
 	case -ENODATA:
 		req->timeout = msecs_to_jiffies(timeout_ms) + jiffies;
 		queue_req(req);
-		addr_send_arp(dst_in);
 		break;
 	default:
 		ret = req->status;
 		atomic_dec(&client->refcount);
-		kfree(req);
-		break;
+		goto err;
 	}
 	return ret;
+err:
+	kfree(req);
+	return ret;
 }
 EXPORT_SYMBOL(rdma_resolve_ip);
 
@@ -497,6 +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)
 {
@@ -521,11 +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);
 }