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

Daniel Borkmann says:

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

The main changes are:

1) Add the ability to use unaligned chunks in the AF_XDP umem. By
   relaxing where the chunks can be placed, it allows to use an
   arbitrary buffer size and place whenever there is a free
   address in the umem. Helps more seamless DPDK AF_XDP driver
   integration. Support for i40e, ixgbe and mlx5e, from Kevin and
   Maxim.

2) Addition of a wakeup flag for AF_XDP tx and fill rings so the
   application can wake up the kernel for rx/tx processing which
   avoids busy-spinning of the latter, useful when app and driver
   is located on the same core. Support for i40e, ixgbe and mlx5e,
   from Magnus and Maxim.

3) bpftool fixes for printf()-like functions so compiler can actually
   enforce checks, bpftool build system improvements for custom output
   directories, and addition of 'bpftool map freeze' command, from Quentin.

4) Support attaching/detaching XDP programs from 'bpftool net' command,
   from Daniel.

5) Automatic xskmap cleanup when AF_XDP socket is released, and several
   barrier/{read,write}_once fixes in AF_XDP code, from Björn.

6) Relicense of bpf_helpers.h/bpf_endian.h for future libbpf
   inclusion as well as libbpf versioning improvements, from Andrii.

7) Several new BPF kselftests for verifier precision tracking, from Alexei.

8) Several BPF kselftest fixes wrt endianess to run on s390x, from Ilya.

9) And more BPF kselftest improvements all over the place, from Stanislav.

10) Add simple BPF map op cache for nfp driver to batch dumps, from Jakub.

11) AF_XDP socket umem mapping improvements for 32bit archs, from Ivan.

12) Add BPF-to-BPF call and BTF line info support for s390x JIT, from Yauheni.

13) Small optimization in arm64 JIT to spare 1 insns for BPF_MOD, from Jerin.

14) Fix an error check in bpf_tcp_gen_syncookie() helper, from Petar.

15) Various minor fixes and cleanups, from Nathan, Masahiro, Masanari,
    Peter, Wei, Yue.
====================

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

1 files changed, 111 insertions, 22 deletions

diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index 9bb96ace9fa1..942c662e2eed 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -13,8 +13,71 @@ struct xsk_map {
 	struct bpf_map map;
 	struct xdp_sock **xsk_map;
 	struct list_head __percpu *flush_list;
+	spinlock_t lock; /* Synchronize map updates */
 };
 
+int xsk_map_inc(struct xsk_map *map)
+{
+	struct bpf_map *m = &map->map;
+
+	m = bpf_map_inc(m, false);
+	return PTR_ERR_OR_ZERO(m);
+}
+
+void xsk_map_put(struct xsk_map *map)
+{
+	bpf_map_put(&map->map);
+}
+
+static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
+					       struct xdp_sock **map_entry)
+{
+	struct xsk_map_node *node;
+	int err;
+
+	node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN);
+	if (!node)
+		return NULL;
+
+	err = xsk_map_inc(map);
+	if (err) {
+		kfree(node);
+		return ERR_PTR(err);
+	}
+
+	node->map = map;
+	node->map_entry = map_entry;
+	return node;
+}
+
+static void xsk_map_node_free(struct xsk_map_node *node)
+{
+	xsk_map_put(node->map);
+	kfree(node);
+}
+
+static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
+{
+	spin_lock_bh(&xs->map_list_lock);
+	list_add_tail(&node->node, &xs->map_list);
+	spin_unlock_bh(&xs->map_list_lock);
+}
+
+static void xsk_map_sock_delete(struct xdp_sock *xs,
+				struct xdp_sock **map_entry)
+{
+	struct xsk_map_node *n, *tmp;
+
+	spin_lock_bh(&xs->map_list_lock);
+	list_for_each_entry_safe(n, tmp, &xs->map_list, node) {
+		if (map_entry == n->map_entry) {
+			list_del(&n->node);
+			xsk_map_node_free(n);
+		}
+	}
+	spin_unlock_bh(&xs->map_list_lock);
+}
+
 static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 {
 	struct xsk_map *m;
@@ -34,6 +97,7 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&m->map, attr);
+	spin_lock_init(&m->lock);
 
 	cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
 	cost += sizeof(struct list_head) * num_possible_cpus();
@@ -71,21 +135,9 @@ free_m:
 static void xsk_map_free(struct bpf_map *map)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	int i;
 
 	bpf_clear_redirect_map(map);
 	synchronize_net();
-
-	for (i = 0; i < map->max_entries; i++) {
-		struct xdp_sock *xs;
-
-		xs = m->xsk_map[i];
-		if (!xs)
-			continue;
-
-		sock_put((struct sock *)xs);
-	}
-
 	free_percpu(m->flush_list);
 	bpf_map_area_free(m->xsk_map);
 	kfree(m);
@@ -164,8 +216,9 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 			       u64 map_flags)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock *xs, *old_xs, **map_entry;
 	u32 i = *(u32 *)key, fd = *(u32 *)value;
-	struct xdp_sock *xs, *old_xs;
+	struct xsk_map_node *node;
 	struct socket *sock;
 	int err;
 
@@ -173,8 +226,6 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EINVAL;
 	if (unlikely(i >= m->map.max_entries))
 		return -E2BIG;
-	if (unlikely(map_flags == BPF_NOEXIST))
-		return -EEXIST;
 
 	sock = sockfd_lookup(fd, &err);
 	if (!sock)
@@ -192,32 +243,70 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EOPNOTSUPP;
 	}
 
-	sock_hold(sock->sk);
+	map_entry = &m->xsk_map[i];
+	node = xsk_map_node_alloc(m, map_entry);
+	if (IS_ERR(node)) {
+		sockfd_put(sock);
+		return PTR_ERR(node);
+	}
 
-	old_xs = xchg(&m->xsk_map[i], xs);
+	spin_lock_bh(&m->lock);
+	old_xs = READ_ONCE(*map_entry);
+	if (old_xs == xs) {
+		err = 0;
+		goto out;
+	} else if (old_xs && map_flags == BPF_NOEXIST) {
+		err = -EEXIST;
+		goto out;
+	} else if (!old_xs && map_flags == BPF_EXIST) {
+		err = -ENOENT;
+		goto out;
+	}
+	xsk_map_sock_add(xs, node);
+	WRITE_ONCE(*map_entry, xs);
 	if (old_xs)
-		sock_put((struct sock *)old_xs);
-
+		xsk_map_sock_delete(old_xs, map_entry);
+	spin_unlock_bh(&m->lock);
 	sockfd_put(sock);
 	return 0;
+
+out:
+	spin_unlock_bh(&m->lock);
+	sockfd_put(sock);
+	xsk_map_node_free(node);
+	return err;
 }
 
 static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *old_xs;
+	struct xdp_sock *old_xs, **map_entry;
 	int k = *(u32 *)key;
 
 	if (k >= map->max_entries)
 		return -EINVAL;
 
-	old_xs = xchg(&m->xsk_map[k], NULL);
+	spin_lock_bh(&m->lock);
+	map_entry = &m->xsk_map[k];
+	old_xs = xchg(map_entry, NULL);
 	if (old_xs)
-		sock_put((struct sock *)old_xs);
+		xsk_map_sock_delete(old_xs, map_entry);
+	spin_unlock_bh(&m->lock);
 
 	return 0;
 }
 
+void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
+			     struct xdp_sock **map_entry)
+{
+	spin_lock_bh(&map->lock);
+	if (READ_ONCE(*map_entry) == xs) {
+		WRITE_ONCE(*map_entry, NULL);
+		xsk_map_sock_delete(xs, map_entry);
+	}
+	spin_unlock_bh(&map->lock);
+}
+
 const struct bpf_map_ops xsk_map_ops = {
 	.map_alloc = xsk_map_alloc,
 	.map_free = xsk_map_free,