Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-07-20

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add sharing of BPF objects within one ASIC: this allows for reuse of
   the same program on multiple ports of a device, and therefore gains
   better code store utilization. On top of that, this now also enables
   sharing of maps between programs attached to different ports of a
   device, from Jakub.

2) Cleanup in libbpf and bpftool's Makefile to reduce unneeded feature
   detections and unused variable exports, also from Jakub.

3) First batch of RCU annotation fixes in prog array handling, i.e.
   there are several __rcu markers which are not correct as well as
   some of the RCU handling, from Roman.

4) Two fixes in BPF sample files related to checking of the prog_cnt
   upper limit from sample loader, from Dan.

5) Minor cleanup in sockmap to remove a set but not used variable,
   from Colin.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/bpf/cgroup.c

@@ -95,7 +95,7 @@ static int compute_effective_progs(struct cgroup *cgrp,
 				   enum bpf_attach_type type,
 				   struct bpf_prog_array __rcu **array)
 {
-	struct bpf_prog_array __rcu *progs;
+	struct bpf_prog_array *progs;
 	struct bpf_prog_list *pl;
 	struct cgroup *p = cgrp;
 	int cnt = 0;
@@ -120,13 +120,12 @@ static int compute_effective_progs(struct cgroup *cgrp,
 					    &p->bpf.progs[type], node) {
 				if (!pl->prog)
 					continue;
-				rcu_dereference_protected(progs, 1)->
-					progs[cnt++] = pl->prog;
+				progs->progs[cnt++] = pl->prog;
 			}
 		p = cgroup_parent(p);
 	} while (p);
 
-	*array = progs;
+	rcu_assign_pointer(*array, progs);
 	return 0;
 }
 

kernel/bpf/core.c

@@ -1538,7 +1538,7 @@ static struct {
 	.null_prog = NULL,
 };
 
-struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
 {
 	if (prog_cnt)
 		return kzalloc(sizeof(struct bpf_prog_array) +

kernel/bpf/offload.c

@@ -18,19 +18,43 @@
 #include <linux/bug.h>
 #include <linux/kdev_t.h>
 #include <linux/list.h>
+#include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/printk.h>
 #include <linux/proc_ns.h>
+#include <linux/rhashtable.h>
 #include <linux/rtnetlink.h>
 #include <linux/rwsem.h>
 
-/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members
+/* Protects offdevs, members of bpf_offload_netdev and offload members
  * of all progs.
  * RTNL lock cannot be taken when holding this lock.
  */
 static DECLARE_RWSEM(bpf_devs_lock);
-static LIST_HEAD(bpf_prog_offload_devs);
-static LIST_HEAD(bpf_map_offload_devs);
+
+struct bpf_offload_dev {
+	struct list_head netdevs;
+};
+
+struct bpf_offload_netdev {
+	struct rhash_head l;
+	struct net_device *netdev;
+	struct bpf_offload_dev *offdev;
+	struct list_head progs;
+	struct list_head maps;
+	struct list_head offdev_netdevs;
+};
+
+static const struct rhashtable_params offdevs_params = {
+	.nelem_hint		= 4,
+	.key_len		= sizeof(struct net_device *),
+	.key_offset		= offsetof(struct bpf_offload_netdev, netdev),
+	.head_offset		= offsetof(struct bpf_offload_netdev, l),
+	.automatic_shrinking	= true,
+};
+
+static struct rhashtable offdevs;
+static bool offdevs_inited;
 
 static int bpf_dev_offload_check(struct net_device *netdev)
 {
@@ -41,8 +65,19 @@ static int bpf_dev_offload_check(struct net_device *netdev)
 	return 0;
 }
 
+static struct bpf_offload_netdev *
+bpf_offload_find_netdev(struct net_device *netdev)
+{
+	lockdep_assert_held(&bpf_devs_lock);
+
+	if (!offdevs_inited)
+		return NULL;
+	return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+}
+
 int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 {
+	struct bpf_offload_netdev *ondev;
 	struct bpf_prog_offload *offload;
 	int err;
 
@@ -66,12 +101,13 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 		goto err_maybe_put;
 
 	down_write(&bpf_devs_lock);
-	if (offload->netdev->reg_state != NETREG_REGISTERED) {
+	ondev = bpf_offload_find_netdev(offload->netdev);
+	if (!ondev) {
 		err = -EINVAL;
 		goto err_unlock;
 	}
 	prog->aux->offload = offload;
-	list_add_tail(&offload->offloads, &bpf_prog_offload_devs);
+	list_add_tail(&offload->offloads, &ondev->progs);
 	dev_put(offload->netdev);
 	up_write(&bpf_devs_lock);
 
@@ -294,6 +330,7 @@ static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 {
 	struct net *net = current->nsproxy->net_ns;
+	struct bpf_offload_netdev *ondev;
 	struct bpf_offloaded_map *offmap;
 	int err;
 
@@ -316,11 +353,17 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 	if (err)
 		goto err_unlock;
 
+	ondev = bpf_offload_find_netdev(offmap->netdev);
+	if (!ondev) {
+		err = -EINVAL;
+		goto err_unlock;
+	}
+
 	err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC);
 	if (err)
 		goto err_unlock;
 
-	list_add_tail(&offmap->offloads, &bpf_map_offload_devs);
+	list_add_tail(&offmap->offloads, &ondev->maps);
 	up_write(&bpf_devs_lock);
 	rtnl_unlock();
 
@@ -468,77 +511,159 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map)
 	return 0;
 }
 
-bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map)
+static bool __bpf_offload_dev_match(struct bpf_prog *prog,
+				    struct net_device *netdev)
 {
-	struct bpf_offloaded_map *offmap;
+	struct bpf_offload_netdev *ondev1, *ondev2;
 	struct bpf_prog_offload *offload;
-	bool ret;
 
 	if (!bpf_prog_is_dev_bound(prog->aux))
 		return false;
-	if (!bpf_map_is_dev_bound(map))
-		return bpf_map_offload_neutral(map);
+
+	offload = prog->aux->offload;
+	if (!offload)
+		return false;
+	if (offload->netdev == netdev)
+		return true;
+
+	ondev1 = bpf_offload_find_netdev(offload->netdev);
+	ondev2 = bpf_offload_find_netdev(netdev);
+
+	return ondev1 && ondev2 && ondev1->offdev == ondev2->offdev;
+}
+
+bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev)
+{
+	bool ret;
 
 	down_read(&bpf_devs_lock);
-	offload = prog->aux->offload;
+	ret = __bpf_offload_dev_match(prog, netdev);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_match);
+
+bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
+{
+	struct bpf_offloaded_map *offmap;
+	bool ret;
+
+	if (!bpf_map_is_dev_bound(map))
+		return bpf_map_offload_neutral(map);
 	offmap = map_to_offmap(map);
 
-	ret = offload && offload->netdev == offmap->netdev;
+	down_read(&bpf_devs_lock);
+	ret = __bpf_offload_dev_match(prog, offmap->netdev);
 	up_read(&bpf_devs_lock);
 
 	return ret;
 }
 
-static void bpf_offload_orphan_all_progs(struct net_device *netdev)
+int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
+				    struct net_device *netdev)
 {
-	struct bpf_prog_offload *offload, *tmp;
+	struct bpf_offload_netdev *ondev;
+	int err;
 
-	list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads)
-		if (offload->netdev == netdev)
-			__bpf_prog_offload_destroy(offload->prog);
+	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
+	if (!ondev)
+		return -ENOMEM;
+
+	ondev->netdev = netdev;
+	ondev->offdev = offdev;
+	INIT_LIST_HEAD(&ondev->progs);
+	INIT_LIST_HEAD(&ondev->maps);
+
+	down_write(&bpf_devs_lock);
+	err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
+	if (err) {
+		netdev_warn(netdev, "failed to register for BPF offload\n");
+		goto err_unlock_free;
+	}
+
+	list_add(&ondev->offdev_netdevs, &offdev->netdevs);
+	up_write(&bpf_devs_lock);
+	return 0;
+
+err_unlock_free:
+	up_write(&bpf_devs_lock);
+	kfree(ondev);
+	return err;
 }
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
 
-static void bpf_offload_orphan_all_maps(struct net_device *netdev)
+void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
+				       struct net_device *netdev)
 {
-	struct bpf_offloaded_map *offmap, *tmp;
-
-	list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads)
-		if (offmap->netdev == netdev)
-			__bpf_map_offload_destroy(offmap);
-}
-
-static int bpf_offload_notification(struct notifier_block *notifier,
-				    ulong event, void *ptr)
-{
-	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct bpf_offload_netdev *ondev, *altdev;
+	struct bpf_offloaded_map *offmap, *mtmp;
+	struct bpf_prog_offload *offload, *ptmp;
 
 	ASSERT_RTNL();
 
-	switch (event) {
-	case NETDEV_UNREGISTER:
-		/* ignore namespace changes */
-		if (netdev->reg_state != NETREG_UNREGISTERING)
-			break;
+	down_write(&bpf_devs_lock);
+	ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+	if (WARN_ON(!ondev))
+		goto unlock;
 
-		down_write(&bpf_devs_lock);
-		bpf_offload_orphan_all_progs(netdev);
-		bpf_offload_orphan_all_maps(netdev);
-		up_write(&bpf_devs_lock);
-		break;
-	default:
-		break;
+	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
+	list_del(&ondev->offdev_netdevs);
+
+	/* Try to move the objects to another netdev of the device */
+	altdev = list_first_entry_or_null(&offdev->netdevs,
+					  struct bpf_offload_netdev,
+					  offdev_netdevs);
+	if (altdev) {
+		list_for_each_entry(offload, &ondev->progs, offloads)
+			offload->netdev = altdev->netdev;
+		list_splice_init(&ondev->progs, &altdev->progs);
+
+		list_for_each_entry(offmap, &ondev->maps, offloads)
+			offmap->netdev = altdev->netdev;
+		list_splice_init(&ondev->maps, &altdev->maps);
+	} else {
+		list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
+			__bpf_prog_offload_destroy(offload->prog);
+		list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
+			__bpf_map_offload_destroy(offmap);
 	}
-	return NOTIFY_OK;
+
+	WARN_ON(!list_empty(&ondev->progs));
+	WARN_ON(!list_empty(&ondev->maps));
+	kfree(ondev);
+unlock:
+	up_write(&bpf_devs_lock);
 }
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
 
-static struct notifier_block bpf_offload_notifier = {
-	.notifier_call = bpf_offload_notification,
-};
-
-static int __init bpf_offload_init(void)
+struct bpf_offload_dev *bpf_offload_dev_create(void)
 {
-	register_netdevice_notifier(&bpf_offload_notifier);
-	return 0;
-}
+	struct bpf_offload_dev *offdev;
+	int err;
 
-subsys_initcall(bpf_offload_init);
+	down_write(&bpf_devs_lock);
+	if (!offdevs_inited) {
+		err = rhashtable_init(&offdevs, &offdevs_params);
+		if (err)
+			return ERR_PTR(err);
+		offdevs_inited = true;
+	}
+	up_write(&bpf_devs_lock);
+
+	offdev = kzalloc(sizeof(*offdev), GFP_KERNEL);
+	if (!offdev)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&offdev->netdevs);
+
+	return offdev;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_create);
+
+void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev)
+{
+	WARN_ON(!list_empty(&offdev->netdevs));
+	kfree(offdev);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy);

kernel/bpf/sockmap.c

@@ -725,11 +725,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 {
 	bool ingress = !!(md->flags & BPF_F_INGRESS);
 	struct smap_psock *psock;
-	struct scatterlist *sg;
 	int err = 0;
 
-	sg = md->sg_data;
-
 	rcu_read_lock();
 	psock = smap_psock_sk(sk);
 	if (unlikely(!psock))

kernel/bpf/verifier.c

@@ -5054,7 +5054,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 	}
 
 	if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
-	    !bpf_offload_dev_match(prog, map)) {
+	    !bpf_offload_prog_map_match(prog, map)) {
 		verbose(env, "offload device mismatch between prog and map\n");
 		return -EINVAL;
 	}