1 files changed, 69 insertions, 55 deletions

diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 1dc7208c71ba..afa457506274 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -4,39 +4,26 @@
  */
 
 #include <linux/bpf.h>
-#include <linux/capability.h>
+#include <linux/filter.h>
 #include <net/xdp_sock.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/btf_ids.h>
 
 #include "xsk.h"
 
-int xsk_map_inc(struct xsk_map *map)
-{
-	bpf_map_inc(&map->map);
-	return 0;
-}
-
-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 xdp_sock __rcu **map_entry)
 {
 	struct xsk_map_node *node;
-	int err;
 
-	node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN);
+	node = bpf_map_kzalloc(&map->map, sizeof(*node),
+			       GFP_ATOMIC | __GFP_NOWARN);
 	if (!node)
 		return ERR_PTR(-ENOMEM);
 
-	err = xsk_map_inc(map);
-	if (err) {
-		kfree(node);
-		return ERR_PTR(err);
-	}
+	bpf_map_inc(&map->map);
+	atomic_inc(&map->count);
 
 	node->map = map;
 	node->map_entry = map_entry;
@@ -45,8 +32,11 @@ static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
 
 static void xsk_map_node_free(struct xsk_map_node *node)
 {
-	xsk_map_put(node->map);
+	struct xsk_map *map = node->map;
+
+	bpf_map_put(&node->map->map);
 	kfree(node);
+	atomic_dec(&map->count);
 }
 
 static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
@@ -57,7 +47,7 @@ static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
 }
 
 static void xsk_map_sock_delete(struct xdp_sock *xs,
-				struct xdp_sock **map_entry)
+				struct xdp_sock __rcu **map_entry)
 {
 	struct xsk_map_node *n, *tmp;
 
@@ -73,14 +63,10 @@ static void xsk_map_sock_delete(struct xdp_sock *xs,
 
 static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 {
-	struct bpf_map_memory mem;
-	int err, numa_node;
 	struct xsk_map *m;
+	int numa_node;
 	u64 size;
 
-	if (!capable(CAP_NET_ADMIN))
-		return ERR_PTR(-EPERM);
-
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size != 4 ||
 	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
@@ -89,28 +75,28 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 	numa_node = bpf_map_attr_numa_node(attr);
 	size = struct_size(m, xsk_map, attr->max_entries);
 
-	err = bpf_map_charge_init(&mem, size);
-	if (err < 0)
-		return ERR_PTR(err);
-
 	m = bpf_map_area_alloc(size, numa_node);
-	if (!m) {
-		bpf_map_charge_finish(&mem);
+	if (!m)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	bpf_map_init_from_attr(&m->map, attr);
-	bpf_map_charge_move(&m->map.memory, &mem);
 	spin_lock_init(&m->lock);
 
 	return &m->map;
 }
 
+static u64 xsk_map_mem_usage(const struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+
+	return struct_size(m, xsk_map, map->max_entries) +
+		   (u64)atomic_read(&m->count) * sizeof(struct xsk_map_node);
+}
+
 static void xsk_map_free(struct bpf_map *map)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
 
-	bpf_clear_redirect_map(map);
 	synchronize_net();
 	bpf_map_area_free(m);
 }
@@ -132,7 +118,7 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
 	const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
 	struct bpf_insn *insn = insn_buf;
@@ -148,9 +134,22 @@ static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	return insn - insn_buf;
 }
 
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
+static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	return rcu_dereference_check(m->xsk_map[key], rcu_read_lock_bh_held());
+}
+
 static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held());
 	return __xsk_map_lookup_elem(map, *(u32 *)key);
 }
 
@@ -159,11 +158,12 @@ static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
-			       u64 map_flags)
+static long 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;
+	struct xdp_sock __rcu **map_entry;
+	struct xdp_sock *xs, *old_xs;
 	u32 i = *(u32 *)key, fd = *(u32 *)value;
 	struct xsk_map_node *node;
 	struct socket *sock;
@@ -185,11 +185,6 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 
 	xs = (struct xdp_sock *)sock->sk;
 
-	if (!xsk_is_setup_for_bpf_map(xs)) {
-		sockfd_put(sock);
-		return -EOPNOTSUPP;
-	}
-
 	map_entry = &m->xsk_map[i];
 	node = xsk_map_node_alloc(m, map_entry);
 	if (IS_ERR(node)) {
@@ -198,7 +193,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 	}
 
 	spin_lock_bh(&m->lock);
-	old_xs = READ_ONCE(*map_entry);
+	old_xs = rcu_dereference_protected(*map_entry, lockdep_is_held(&m->lock));
 	if (old_xs == xs) {
 		err = 0;
 		goto out;
@@ -210,7 +205,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 		goto out;
 	}
 	xsk_map_sock_add(xs, node);
-	WRITE_ONCE(*map_entry, xs);
+	rcu_assign_pointer(*map_entry, xs);
 	if (old_xs)
 		xsk_map_sock_delete(old_xs, map_entry);
 	spin_unlock_bh(&m->lock);
@@ -224,18 +219,19 @@ out:
 	return err;
 }
 
-static int xsk_map_delete_elem(struct bpf_map *map, void *key)
+static long 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, **map_entry;
-	int k = *(u32 *)key;
+	struct xdp_sock __rcu **map_entry;
+	struct xdp_sock *old_xs;
+	u32 k = *(u32 *)key;
 
 	if (k >= map->max_entries)
 		return -EINVAL;
 
 	spin_lock_bh(&m->lock);
 	map_entry = &m->xsk_map[k];
-	old_xs = xchg(map_entry, NULL);
+	old_xs = unrcu_pointer(xchg(map_entry, NULL));
 	if (old_xs)
 		xsk_map_sock_delete(old_xs, map_entry);
 	spin_unlock_bh(&m->lock);
@@ -243,18 +239,33 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 	return 0;
 }
 
+static long xsk_map_redirect(struct bpf_map *map, u64 index, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, index, flags, 0,
+				      __xsk_map_lookup_elem);
+}
+
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
-			     struct xdp_sock **map_entry)
+			     struct xdp_sock __rcu **map_entry)
 {
 	spin_lock_bh(&map->lock);
-	if (READ_ONCE(*map_entry) == xs) {
-		WRITE_ONCE(*map_entry, NULL);
+	if (rcu_access_pointer(*map_entry) == xs) {
+		rcu_assign_pointer(*map_entry, NULL);
 		xsk_map_sock_delete(xs, map_entry);
 	}
 	spin_unlock_bh(&map->lock);
 }
 
+static bool xsk_map_meta_equal(const struct bpf_map *meta0,
+			       const struct bpf_map *meta1)
+{
+	return meta0->max_entries == meta1->max_entries &&
+		bpf_map_meta_equal(meta0, meta1);
+}
+
+BTF_ID_LIST_SINGLE(xsk_map_btf_ids, struct, xsk_map)
 const struct bpf_map_ops xsk_map_ops = {
+	.map_meta_equal = xsk_map_meta_equal,
 	.map_alloc = xsk_map_alloc,
 	.map_free = xsk_map_free,
 	.map_get_next_key = xsk_map_get_next_key,
@@ -264,4 +275,7 @@ const struct bpf_map_ops xsk_map_ops = {
 	.map_update_elem = xsk_map_update_elem,
 	.map_delete_elem = xsk_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = xsk_map_mem_usage,
+	.map_btf_id = &xsk_map_btf_ids[0],
+	.map_redirect = xsk_map_redirect,
 };