Merge branch 'bpf-sock-hashmap'

John Fastabend says:

====================
In the original sockmap implementation we got away with using an
array similar to devmap. However, unlike devmap where an ifindex
has a nice 1:1 function into the map we have found some use cases
with sockets that need to be referenced using longer keys.

This series adds support for a sockhash map reusing as much of
the sockmap code as possible. I made the decision to add sockhash
specific helpers vs trying to generalize the existing helpers
because (a) they have sockmap in the name and (b) the keys are
different types. I prefer to be explicit here rather than play
type games or do something else tricky.

To test this we duplicate all the sockmap testing except swap out
the sockmap with a sockhash.

v2: fix file stats and add v2 tag
v3: move tool updates into test patch, move bpftool updates into
    its own patch, and fixup the test patch stats to catch the
    renamed file and provide only diffs ± on that.
v4: Add documentation to UAPI bpf.h
v5: Add documentation to tools UAPI bpf.h
v6: 'git add' test_sockhash_kern.c which was previously missing
    but was not causing issues because of typo in test script,
    noticed by Daniel. After this the git format-patch -M option
    no longer tracks the rename of the test_sockmap_kern files for
    some reason. I guess the diff has exceeded some threshold.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/linux/bpf.h

@@ -668,6 +668,7 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 
 #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET)
 struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
+struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key);
 int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
 #else
 static inline struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
@@ -675,6 +676,12 @@ static inline struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
 	return NULL;
 }
 
+static inline struct sock  *__sock_hash_lookup_elem(struct bpf_map *map,
+						    void *key)
+{
+	return NULL;
+}
+
 static inline int sock_map_prog(struct bpf_map *map,
 				struct bpf_prog *prog,
 				u32 type)
@@ -724,6 +731,7 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
+extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);

include/linux/bpf_types.h

@@ -47,6 +47,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
 #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_INET)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #if defined(CONFIG_XDP_SOCKETS)

include/linux/filter.h

@@ -515,9 +515,8 @@ struct sk_msg_buff {
 	int sg_end;
 	struct scatterlist sg_data[MAX_SKB_FRAGS];
 	bool sg_copy[MAX_SKB_FRAGS];
-	__u32 key;
 	__u32 flags;
-	struct bpf_map *map;
+	struct sock *sk_redir;
 	struct sk_buff *skb;
 	struct list_head list;
 };

include/net/tcp.h

@@ -814,9 +814,8 @@ struct tcp_skb_cb {
 #endif
 		} header;	/* For incoming skbs */
 		struct {
-			__u32 key;
 			__u32 flags;
-			struct bpf_map *map;
+			struct sock *sk_redir;
 			void *data_end;
 		} bpf;
 	};

include/uapi/linux/bpf.h

@@ -118,6 +118,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_SOCKMAP,
 	BPF_MAP_TYPE_CPUMAP,
 	BPF_MAP_TYPE_XSKMAP,
+	BPF_MAP_TYPE_SOCKHASH,
 };
 
 enum bpf_prog_type {
@@ -1828,7 +1829,6 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- *
  * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
  *	Description
  *		Do FIB lookup in kernel tables using parameters in *params*.
@@ -1855,6 +1855,53 @@ union bpf_attr {
  *             Egress device index on success, 0 if packet needs to continue
  *             up the stack for further processing or a negative error in case
  *             of failure.
+ *
+ * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		Add an entry to, or update a sockhash *map* referencing sockets.
+ *		The *skops* is used as a new value for the entry associated to
+ *		*key*. *flags* is one of:
+ *
+ *		**BPF_NOEXIST**
+ *			The entry for *key* must not exist in the map.
+ *		**BPF_EXIST**
+ *			The entry for *key* must already exist in the map.
+ *		**BPF_ANY**
+ *			No condition on the existence of the entry for *key*.
+ *
+ *		If the *map* has eBPF programs (parser and verdict), those will
+ *		be inherited by the socket being added. If the socket is
+ *		already attached to eBPF programs, this results in an error.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		This helper is used in programs implementing policies at the
+ *		socket level. If the message *msg* is allowed to pass (i.e. if
+ *		the verdict eBPF program returns **SK_PASS**), redirect it to
+ *		the socket referenced by *map* (of type
+ *		**BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ *		egress interfaces can be used for redirection. The
+ *		**BPF_F_INGRESS** value in *flags* is used to make the
+ *		distinction (ingress path is selected if the flag is present,
+ *		egress path otherwise). This is the only flag supported for now.
+ *	Return
+ *		**SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		This helper is used in programs implementing policies at the
+ *		skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
+ *		if the verdeict eBPF program returns **SK_PASS**), redirect it
+ *		to the socket referenced by *map* (of type
+ *		**BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ *		egress interfaces can be used for redirection. The
+ *		**BPF_F_INGRESS** value in *flags* is used to make the
+ *		distinction (ingress path is selected if the flag is present,
+ *		egress otherwise). This is the only flag supported for now.
+ *	Return
+ *		**SK_PASS** on success, or **SK_DROP** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1926,7 +1973,10 @@ union bpf_attr {
 	FN(skb_get_xfrm_state),		\
 	FN(get_stack),			\
 	FN(skb_load_bytes_relative),	\
-	FN(fib_lookup),
+	FN(fib_lookup),			\
+	FN(sock_hash_update),		\
+	FN(msg_redirect_hash),		\
+	FN(sk_redirect_hash),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

kernel/bpf/core.c

@@ -1707,6 +1707,7 @@ const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
 const struct bpf_func_proto bpf_get_current_comm_proto __weak;
 const struct bpf_func_proto bpf_sock_map_update_proto __weak;
+const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {

kernel/bpf/sockmap.c

@@ -48,14 +48,40 @@
 #define SOCK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
-struct bpf_stab {
-	struct bpf_map map;
-	struct sock **sock_map;
+struct bpf_sock_progs {
 	struct bpf_prog *bpf_tx_msg;
 	struct bpf_prog *bpf_parse;
 	struct bpf_prog *bpf_verdict;
 };
 
+struct bpf_stab {
+	struct bpf_map map;
+	struct sock **sock_map;
+	struct bpf_sock_progs progs;
+};
+
+struct bucket {
+	struct hlist_head head;
+	raw_spinlock_t lock;
+};
+
+struct bpf_htab {
+	struct bpf_map map;
+	struct bucket *buckets;
+	atomic_t count;
+	u32 n_buckets;
+	u32 elem_size;
+	struct bpf_sock_progs progs;
+};
+
+struct htab_elem {
+	struct rcu_head rcu;
+	struct hlist_node hash_node;
+	u32 hash;
+	struct sock *sk;
+	char key[0];
+};
+
 enum smap_psock_state {
 	SMAP_TX_RUNNING,
 };
@@ -63,6 +89,8 @@ enum smap_psock_state {
 struct smap_psock_map_entry {
 	struct list_head list;
 	struct sock **entry;
+	struct htab_elem *hash_link;
+	struct bpf_htab *htab;
 };
 
 struct smap_psock {
@@ -191,6 +219,12 @@ static void bpf_tcp_release(struct sock *sk)
 	rcu_read_unlock();
 }
 
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+	atomic_dec(&htab->count);
+	kfree_rcu(l, rcu);
+}
+
 static void bpf_tcp_close(struct sock *sk, long timeout)
 {
 	void (*close_fun)(struct sock *sk, long timeout);
@@ -227,11 +261,17 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 	}
 
 	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+		if (e->entry) {
 			osk = cmpxchg(e->entry, sk, NULL);
 			if (osk == sk) {
 				list_del(&e->list);
 				smap_release_sock(psock, sk);
 			}
+		} else {
+			hlist_del_rcu(&e->hash_link->hash_node);
+			smap_release_sock(psock, e->hash_link->sk);
+			free_htab_elem(e->htab, e->hash_link);
+		}
 	}
 	write_unlock_bh(&sk->sk_callback_lock);
 	rcu_read_unlock();
@@ -461,7 +501,7 @@ static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md)
 static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md)
 {
 	return ((_rc == SK_PASS) ?
-	       (md->map ? __SK_REDIRECT : __SK_PASS) :
+	       (md->sk_redir ? __SK_REDIRECT : __SK_PASS) :
 	       __SK_DROP);
 }
 
@@ -1092,7 +1132,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 	 * when we orphan the skb so that we don't have the possibility
 	 * to reference a stale map.
 	 */
-	TCP_SKB_CB(skb)->bpf.map = NULL;
+	TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
 	skb->sk = psock->sock;
 	bpf_compute_data_pointers(skb);
 	preempt_disable();
@@ -1102,7 +1142,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 
 	/* Moving return codes from UAPI namespace into internal namespace */
 	return rc == SK_PASS ?
-		(TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) :
+		(TCP_SKB_CB(skb)->bpf.sk_redir ? __SK_REDIRECT : __SK_PASS) :
 		__SK_DROP;
 }
 
@@ -1372,7 +1412,6 @@ static int smap_init_sock(struct smap_psock *psock,
 }
 
 static void smap_init_progs(struct smap_psock *psock,
-			    struct bpf_stab *stab,
 			    struct bpf_prog *verdict,
 			    struct bpf_prog *parse)
 {
@@ -1450,14 +1489,13 @@ static void smap_gc_work(struct work_struct *w)
 	kfree(psock);
 }
 
-static struct smap_psock *smap_init_psock(struct sock *sock,
-					  struct bpf_stab *stab)
+static struct smap_psock *smap_init_psock(struct sock *sock, int node)
 {
 	struct smap_psock *psock;
 
 	psock = kzalloc_node(sizeof(struct smap_psock),
 			     GFP_ATOMIC | __GFP_NOWARN,
-			     stab->map.numa_node);
+			     node);
 	if (!psock)
 		return ERR_PTR(-ENOMEM);
 
@@ -1525,12 +1563,14 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	return ERR_PTR(err);
 }
 
-static void smap_list_remove(struct smap_psock *psock, struct sock **entry)
+static void smap_list_remove(struct smap_psock *psock,
+			     struct sock **entry,
+			     struct htab_elem *hash_link)
 {
 	struct smap_psock_map_entry *e, *tmp;
 
 	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
-		if (e->entry == entry) {
+		if (e->entry == entry || e->hash_link == hash_link) {
 			list_del(&e->list);
 			break;
 		}
@@ -1568,7 +1608,7 @@ static void sock_map_free(struct bpf_map *map)
 		 * to be null and queued for garbage collection.
 		 */
 		if (likely(psock)) {
-			smap_list_remove(psock, &stab->sock_map[i]);
+			smap_list_remove(psock, &stab->sock_map[i], NULL);
 			smap_release_sock(psock, sock);
 		}
 		write_unlock_bh(&sock->sk_callback_lock);
@@ -1627,7 +1667,7 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
 
 	if (psock->bpf_parse)
 		smap_stop_sock(psock, sock);
-	smap_list_remove(psock, &stab->sock_map[k]);
+	smap_list_remove(psock, &stab->sock_map[k], NULL);
 	smap_release_sock(psock, sock);
 out:
 	write_unlock_bh(&sock->sk_callback_lock);
@@ -1662,40 +1702,26 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
  *  - sock_map must use READ_ONCE and (cmp)xchg operations
  *  - BPF verdict/parse programs must use READ_ONCE and xchg operations
  */
-static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
-				    struct bpf_map *map,
-				    void *key, u64 flags)
+
+static int __sock_map_ctx_update_elem(struct bpf_map *map,
+				      struct bpf_sock_progs *progs,
+				      struct sock *sock,
+				      struct sock **map_link,
+				      void *key)
 {
-	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
-	struct smap_psock_map_entry *e = NULL;
 	struct bpf_prog *verdict, *parse, *tx_msg;
-	struct sock *osock, *sock;
+	struct smap_psock_map_entry *e = NULL;
 	struct smap_psock *psock;
-	u32 i = *(u32 *)key;
 	bool new = false;
 	int err;
 
-	if (unlikely(flags > BPF_EXIST))
-		return -EINVAL;
-
-	if (unlikely(i >= stab->map.max_entries))
-		return -E2BIG;
-
-	sock = READ_ONCE(stab->sock_map[i]);
-	if (flags == BPF_EXIST && !sock)
-		return -ENOENT;
-	else if (flags == BPF_NOEXIST && sock)
-		return -EEXIST;
-
-	sock = skops->sk;
-
 	/* 1. If sock map has BPF programs those will be inherited by the
 	 * sock being added. If the sock is already attached to BPF programs
 	 * this results in an error.
 	 */
-	verdict = READ_ONCE(stab->bpf_verdict);
-	parse = READ_ONCE(stab->bpf_parse);
-	tx_msg = READ_ONCE(stab->bpf_tx_msg);
+	verdict = READ_ONCE(progs->bpf_verdict);
+	parse = READ_ONCE(progs->bpf_parse);
+	tx_msg = READ_ONCE(progs->bpf_tx_msg);
 
 	if (parse && verdict) {
 		/* bpf prog refcnt may be zero if a concurrent attach operation
@@ -1703,11 +1729,11 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		 * we increment the refcnt. If this is the case abort with an
 		 * error.
 		 */
-		verdict = bpf_prog_inc_not_zero(stab->bpf_verdict);
+		verdict = bpf_prog_inc_not_zero(progs->bpf_verdict);
 		if (IS_ERR(verdict))
 			return PTR_ERR(verdict);
 
-		parse = bpf_prog_inc_not_zero(stab->bpf_parse);
+		parse = bpf_prog_inc_not_zero(progs->bpf_parse);
 		if (IS_ERR(parse)) {
 			bpf_prog_put(verdict);
 			return PTR_ERR(parse);
@@ -1715,7 +1741,7 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	}
 
 	if (tx_msg) {
-		tx_msg = bpf_prog_inc_not_zero(stab->bpf_tx_msg);
+		tx_msg = bpf_prog_inc_not_zero(progs->bpf_tx_msg);
 		if (IS_ERR(tx_msg)) {
 			if (verdict)
 				bpf_prog_put(verdict);
@@ -1748,7 +1774,7 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 			goto out_progs;
 		}
 	} else {
-		psock = smap_init_psock(sock, stab);
+		psock = smap_init_psock(sock, map->numa_node);
 		if (IS_ERR(psock)) {
 			err = PTR_ERR(psock);
 			goto out_progs;
@@ -1758,12 +1784,13 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		new = true;
 	}
 
+	if (map_link) {
 		e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
 		if (!e) {
 			err = -ENOMEM;
 			goto out_progs;
 		}
-	e->entry = &stab->sock_map[i];
+	}
 
 	/* 3. At this point we have a reference to a valid psock that is
 	 * running. Attach any BPF programs needed.
@@ -1780,7 +1807,7 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		err = smap_init_sock(psock, sock);
 		if (err)
 			goto out_free;
-		smap_init_progs(psock, stab, verdict, parse);
+		smap_init_progs(psock, verdict, parse);
 		smap_start_sock(psock, sock);
 	}
 
@@ -1789,20 +1816,14 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	 * it with. Because we can only have a single set of programs if
 	 * old_sock has a strp we can stop it.
 	 */
+	if (map_link) {
+		e->entry = map_link;
 		list_add_tail(&e->list, &psock->maps);
-	write_unlock_bh(&sock->sk_callback_lock);
-
-	osock = xchg(&stab->sock_map[i], sock);
-	if (osock) {
-		struct smap_psock *opsock = smap_psock_sk(osock);
-
-		write_lock_bh(&osock->sk_callback_lock);
-		smap_list_remove(opsock, &stab->sock_map[i]);
-		smap_release_sock(opsock, osock);
-		write_unlock_bh(&osock->sk_callback_lock);
 	}
-	return 0;
+	write_unlock_bh(&sock->sk_callback_lock);
+	return err;
 out_free:
+	kfree(e);
 	smap_release_sock(psock, sock);
 out_progs:
 	if (verdict)
@@ -1816,23 +1837,73 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	return err;
 }
 
-int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
+static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
+				    struct bpf_map *map,
+				    void *key, u64 flags)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+	struct bpf_sock_progs *progs = &stab->progs;
+	struct sock *osock, *sock;
+	u32 i = *(u32 *)key;
+	int err;
+
+	if (unlikely(flags > BPF_EXIST))
+		return -EINVAL;
+
+	if (unlikely(i >= stab->map.max_entries))
+		return -E2BIG;
+
+	sock = READ_ONCE(stab->sock_map[i]);
+	if (flags == BPF_EXIST && !sock)
+		return -ENOENT;
+	else if (flags == BPF_NOEXIST && sock)
+		return -EEXIST;
+
+	sock = skops->sk;
+	err = __sock_map_ctx_update_elem(map, progs, sock, &stab->sock_map[i],
+					 key);
+	if (err)
+		goto out;
+
+	osock = xchg(&stab->sock_map[i], sock);
+	if (osock) {
+		struct smap_psock *opsock = smap_psock_sk(osock);
+
+		write_lock_bh(&osock->sk_callback_lock);
+		smap_list_remove(opsock, &stab->sock_map[i], NULL);
+		smap_release_sock(opsock, osock);
+		write_unlock_bh(&osock->sk_callback_lock);
+	}
+out:
+	return 0;
+}
+
+int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
+{
+	struct bpf_sock_progs *progs;
 	struct bpf_prog *orig;
 
-	if (unlikely(map->map_type != BPF_MAP_TYPE_SOCKMAP))
+	if (map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+		struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+		progs = &stab->progs;
+	} else if (map->map_type == BPF_MAP_TYPE_SOCKHASH) {
+		struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+		progs = &htab->progs;
+	} else {
 		return -EINVAL;
+	}
 
 	switch (type) {
 	case BPF_SK_MSG_VERDICT:
-		orig = xchg(&stab->bpf_tx_msg, prog);
+		orig = xchg(&progs->bpf_tx_msg, prog);
 		break;
 	case BPF_SK_SKB_STREAM_PARSER:
-		orig = xchg(&stab->bpf_parse, prog);
+		orig = xchg(&progs->bpf_parse, prog);
 		break;
 	case BPF_SK_SKB_STREAM_VERDICT:
-		orig = xchg(&stab->bpf_verdict, prog);
+		orig = xchg(&progs->bpf_verdict, prog);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1880,21 +1951,415 @@ static int sock_map_update_elem(struct bpf_map *map,
 
 static void sock_map_release(struct bpf_map *map)
 {
-	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+	struct bpf_sock_progs *progs;
 	struct bpf_prog *orig;
 
-	orig = xchg(&stab->bpf_parse, NULL);
+	if (map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+		struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+		progs = &stab->progs;
+	} else {
+		struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+		progs = &htab->progs;
+	}
+
+	orig = xchg(&progs->bpf_parse, NULL);
 	if (orig)
 		bpf_prog_put(orig);
-	orig = xchg(&stab->bpf_verdict, NULL);
+	orig = xchg(&progs->bpf_verdict, NULL);
 	if (orig)
 		bpf_prog_put(orig);
 
-	orig = xchg(&stab->bpf_tx_msg, NULL);
+	orig = xchg(&progs->bpf_tx_msg, NULL);
 	if (orig)
 		bpf_prog_put(orig);
 }
 
+static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
+{
+	struct bpf_htab *htab;
+	int i, err;
+	u64 cost;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->value_size != 4 ||
+	    attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
+		return ERR_PTR(-EINVAL);
+
+	err = bpf_tcp_ulp_register();
+	if (err && err != -EEXIST)
+		return ERR_PTR(err);
+
+	htab = kzalloc(sizeof(*htab), GFP_USER);
+	if (!htab)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&htab->map, attr);
+
+	htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
+	htab->elem_size = sizeof(struct htab_elem) +
+			  round_up(htab->map.key_size, 8);
+	err = -EINVAL;
+	if (htab->n_buckets == 0 ||
+	    htab->n_buckets > U32_MAX / sizeof(struct bucket))
+		goto free_htab;
+
+	cost = (u64) htab->n_buckets * sizeof(struct bucket) +
+	       (u64) htab->elem_size * htab->map.max_entries;
+
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_htab;
+
+	htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+	err = bpf_map_precharge_memlock(htab->map.pages);
+	if (err)
+		goto free_htab;
+
+	err = -ENOMEM;
+	htab->buckets = bpf_map_area_alloc(
+				htab->n_buckets * sizeof(struct bucket),
+				htab->map.numa_node);
+	if (!htab->buckets)
+		goto free_htab;
+
+	for (i = 0; i < htab->n_buckets; i++) {
+		INIT_HLIST_HEAD(&htab->buckets[i].head);
+		raw_spin_lock_init(&htab->buckets[i].lock);
+	}
+
+	return &htab->map;
+free_htab:
+	kfree(htab);
+	return ERR_PTR(err);
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &__select_bucket(htab, hash)->head;
+}
+
+static void sock_hash_free(struct bpf_map *map)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	int i;
+
+	synchronize_rcu();
+
+	/* At this point no update, lookup or delete operations can happen.
+	 * However, be aware we can still get a socket state event updates,
+	 * and data ready callabacks that reference the psock from sk_user_data
+	 * Also psock worker threads are still in-flight. So smap_release_sock
+	 * will only free the psock after cancel_sync on the worker threads
+	 * and a grace period expire to ensure psock is really safe to remove.
+	 */
+	rcu_read_lock();
+	for (i = 0; i < htab->n_buckets; i++) {
+		struct hlist_head *head = select_bucket(htab, i);
+		struct hlist_node *n;
+		struct htab_elem *l;
+
+		hlist_for_each_entry_safe(l, n, head, hash_node) {
+			struct sock *sock = l->sk;
+			struct smap_psock *psock;
+
+			hlist_del_rcu(&l->hash_node);
+			write_lock_bh(&sock->sk_callback_lock);
+			psock = smap_psock_sk(sock);
+			/* This check handles a racing sock event that can get
+			 * the sk_callback_lock before this case but after xchg
+			 * causing the refcnt to hit zero and sock user data
+			 * (psock) to be null and queued for garbage collection.
+			 */
+			if (likely(psock)) {
+				smap_list_remove(psock, NULL, l);
+				smap_release_sock(psock, sock);
+			}
+			write_unlock_bh(&sock->sk_callback_lock);
+			kfree(l);
+		}
+	}
+	rcu_read_unlock();
+	bpf_map_area_free(htab->buckets);
+	kfree(htab);
+}
+
+static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
+					      void *key, u32 key_size, u32 hash,
+					      struct sock *sk,
+					      struct htab_elem *old_elem)
+{
+	struct htab_elem *l_new;
+
+	if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
+		if (!old_elem) {
+			atomic_dec(&htab->count);
+			return ERR_PTR(-E2BIG);
+		}
+	}
+	l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
+			     htab->map.numa_node);
+	if (!l_new)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(l_new->key, key, key_size);
+	l_new->sk = sk;
+	l_new->hash = hash;
+	return l_new;
+}
+
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+					 u32 hash, void *key, u32 key_size)
+{
+	struct htab_elem *l;
+
+	hlist_for_each_entry_rcu(l, head, hash_node) {
+		if (l->hash == hash && !memcmp(&l->key, key, key_size))
+			return l;
+	}
+
+	return NULL;
+}
+
+static inline u32 htab_map_hash(const void *key, u32 key_len)
+{
+	return jhash(key, key_len, 0);
+}
+
+static int sock_hash_get_next_key(struct bpf_map *map,
+				  void *key, void *next_key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct htab_elem *l, *next_l;
+	struct hlist_head *h;
+	u32 hash, key_size;
+	int i = 0;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	key_size = map->key_size;
+	if (!key)
+		goto find_first_elem;
+	hash = htab_map_hash(key, key_size);
+	h = select_bucket(htab, hash);
+
+	l = lookup_elem_raw(h, hash, key, key_size);
+	if (!l)
+		goto find_first_elem;
+	next_l = hlist_entry_safe(
+		     rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+		     struct htab_elem, hash_node);
+	if (next_l) {
+		memcpy(next_key, next_l->key, key_size);
+		return 0;
+	}
+
+	/* no more elements in this hash list, go to the next bucket */
+	i = hash & (htab->n_buckets - 1);
+	i++;
+
+find_first_elem:
+	/* iterate over buckets */
+	for (; i < htab->n_buckets; i++) {
+		h = select_bucket(htab, i);
+
+		/* pick first element in the bucket */
+		next_l = hlist_entry_safe(
+				rcu_dereference_raw(hlist_first_rcu(h)),
+				struct htab_elem, hash_node);
+		if (next_l) {
+			/* if it's not empty, just return it */
+			memcpy(next_key, next_l->key, key_size);
+			return 0;
+		}
+	}
+
+	/* iterated over all buckets and all elements */
+	return -ENOENT;
+}
+
+static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
+				     struct bpf_map *map,
+				     void *key, u64 map_flags)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct bpf_sock_progs *progs = &htab->progs;
+	struct htab_elem *l_new = NULL, *l_old;
+	struct smap_psock_map_entry *e = NULL;
+	struct hlist_head *head;
+	struct smap_psock *psock;
+	u32 key_size, hash;
+	struct sock *sock;
+	struct bucket *b;
+	int err;
+
+	sock = skops->sk;
+
+	if (sock->sk_type != SOCK_STREAM ||
+	    sock->sk_protocol != IPPROTO_TCP)
+		return -EOPNOTSUPP;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+
+	e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+	if (!e)
+		return -ENOMEM;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	key_size = map->key_size;
+	hash = htab_map_hash(key, key_size);
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	err = __sock_map_ctx_update_elem(map, progs, sock, NULL, key);
+	if (err)
+		goto err;
+
+	/* bpf_map_update_elem() can be called in_irq() */
+	raw_spin_lock_bh(&b->lock);
+	l_old = lookup_elem_raw(head, hash, key, key_size);
+	if (l_old && map_flags == BPF_NOEXIST) {
+		err = -EEXIST;
+		goto bucket_err;
+	}
+	if (!l_old && map_flags == BPF_EXIST) {
+		err = -ENOENT;
+		goto bucket_err;
+	}
+
+	l_new = alloc_sock_hash_elem(htab, key, key_size, hash, sock, l_old);
+	if (IS_ERR(l_new)) {
+		err = PTR_ERR(l_new);
+		goto bucket_err;
+	}
+
+	psock = smap_psock_sk(sock);
+	if (unlikely(!psock)) {
+		err = -EINVAL;
+		goto bucket_err;
+	}
+
+	e->hash_link = l_new;
+	e->htab = container_of(map, struct bpf_htab, map);
+	list_add_tail(&e->list, &psock->maps);
+
+	/* add new element to the head of the list, so that
+	 * concurrent search will find it before old elem
+	 */
+	hlist_add_head_rcu(&l_new->hash_node, head);
+	if (l_old) {
+		psock = smap_psock_sk(l_old->sk);
+
+		hlist_del_rcu(&l_old->hash_node);
+		smap_list_remove(psock, NULL, l_old);
+		smap_release_sock(psock, l_old->sk);
+		free_htab_elem(htab, l_old);
+	}
+	raw_spin_unlock_bh(&b->lock);
+	return 0;
+bucket_err:
+	raw_spin_unlock_bh(&b->lock);
+err:
+	kfree(e);
+	psock = smap_psock_sk(sock);
+	if (psock)
+		smap_release_sock(psock, sock);
+	return err;
+}
+
+static int sock_hash_update_elem(struct bpf_map *map,
+				void *key, void *value, u64 flags)
+{
+	struct bpf_sock_ops_kern skops;
+	u32 fd = *(u32 *)value;
+	struct socket *socket;
+	int err;
+
+	socket = sockfd_lookup(fd, &err);
+	if (!socket)
+		return err;
+
+	skops.sk = socket->sk;
+	if (!skops.sk) {
+		fput(socket->file);
+		return -EINVAL;
+	}
+
+	err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+	fput(socket->file);
+	return err;
+}
+
+static int sock_hash_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_head *head;
+	struct bucket *b;
+	struct htab_elem *l;
+	u32 hash, key_size;
+	int ret = -ENOENT;
+
+	key_size = map->key_size;
+	hash = htab_map_hash(key, key_size);
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	raw_spin_lock_bh(&b->lock);
+	l = lookup_elem_raw(head, hash, key, key_size);
+	if (l) {
+		struct sock *sock = l->sk;
+		struct smap_psock *psock;
+
+		hlist_del_rcu(&l->hash_node);
+		write_lock_bh(&sock->sk_callback_lock);
+		psock = smap_psock_sk(sock);
+		/* This check handles a racing sock event that can get the
+		 * sk_callback_lock before this case but after xchg happens
+		 * causing the refcnt to hit zero and sock user data (psock)
+		 * to be null and queued for garbage collection.
+		 */
+		if (likely(psock)) {
+			smap_list_remove(psock, NULL, l);
+			smap_release_sock(psock, sock);
+		}
+		write_unlock_bh(&sock->sk_callback_lock);
+		free_htab_elem(htab, l);
+		ret = 0;
+	}
+	raw_spin_unlock_bh(&b->lock);
+	return ret;
+}
+
+struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_head *head;
+	struct htab_elem *l;
+	u32 key_size, hash;
+	struct bucket *b;
+	struct sock *sk;
+
+	key_size = map->key_size;
+	hash = htab_map_hash(key, key_size);
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	raw_spin_lock_bh(&b->lock);
+	l = lookup_elem_raw(head, hash, key, key_size);
+	sk = l ? l->sk : NULL;
+	raw_spin_unlock_bh(&b->lock);
+	return sk;
+}
+
 const struct bpf_map_ops sock_map_ops = {
 	.map_alloc = sock_map_alloc,
 	.map_free = sock_map_free,
@@ -1905,6 +2370,15 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_release_uref = sock_map_release,
 };
 
+const struct bpf_map_ops sock_hash_ops = {
+	.map_alloc = sock_hash_alloc,
+	.map_free = sock_hash_free,
+	.map_lookup_elem = sock_map_lookup,
+	.map_get_next_key = sock_hash_get_next_key,
+	.map_update_elem = sock_hash_update_elem,
+	.map_delete_elem = sock_hash_delete_elem,
+};
+
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
@@ -1922,3 +2396,21 @@ const struct bpf_func_proto bpf_sock_map_update_proto = {
 	.arg3_type	= ARG_PTR_TO_MAP_KEY,
 	.arg4_type	= ARG_ANYTHING,
 };
+
+BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock,
+	   struct bpf_map *, map, void *, key, u64, flags)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return sock_hash_ctx_update_elem(bpf_sock, map, key, flags);
+}
+
+const struct bpf_func_proto bpf_sock_hash_update_proto = {
+	.func		= bpf_sock_hash_update,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_PTR_TO_MAP_KEY,
+	.arg4_type	= ARG_ANYTHING,
+};

kernel/bpf/verifier.c

@@ -2093,6 +2093,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_msg_redirect_map)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_SOCKHASH:
+		if (func_id != BPF_FUNC_sk_redirect_hash &&
+		    func_id != BPF_FUNC_sock_hash_update &&
+		    func_id != BPF_FUNC_map_delete_elem &&
+		    func_id != BPF_FUNC_msg_redirect_hash)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -2130,11 +2137,14 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		break;
 	case BPF_FUNC_sk_redirect_map:
 	case BPF_FUNC_msg_redirect_map:
+	case BPF_FUNC_sock_map_update:
 		if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
 			goto error;
 		break;
-	case BPF_FUNC_sock_map_update:
-		if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
+	case BPF_FUNC_sk_redirect_hash:
+	case BPF_FUNC_msg_redirect_hash:
+	case BPF_FUNC_sock_hash_update:
+		if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
 			goto error;
 		break;
 	default:

net/core/filter.c

@@ -2074,6 +2074,33 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb,
+	   struct bpf_map *, map, void *, key, u64, flags)
+{
+	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+
+	/* If user passes invalid input drop the packet. */
+	if (unlikely(flags & ~(BPF_F_INGRESS)))
+		return SK_DROP;
+
+	tcb->bpf.flags = flags;
+	tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key);
+	if (!tcb->bpf.sk_redir)
+		return SK_DROP;
+
+	return SK_PASS;
+}
+
+static const struct bpf_func_proto bpf_sk_redirect_hash_proto = {
+	.func           = bpf_sk_redirect_hash,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_PTR_TO_MAP_KEY,
+	.arg4_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
 	   struct bpf_map *, map, u32, key, u64, flags)
 {
@@ -2083,9 +2110,10 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
 
-	tcb->bpf.key = key;
 	tcb->bpf.flags = flags;
-	tcb->bpf.map = map;
+	tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key);
+	if (!tcb->bpf.sk_redir)
+		return SK_DROP;
 
 	return SK_PASS;
 }
@@ -2093,16 +2121,8 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
 struct sock *do_sk_redirect_map(struct sk_buff *skb)
 {
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
-	struct sock *sk = NULL;
-
-	if (tcb->bpf.map) {
-		sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key);
-
-		tcb->bpf.key = 0;
-		tcb->bpf.map = NULL;
-	}
 
-	return sk;
+	return tcb->bpf.sk_redir;
 }
 
 static const struct bpf_func_proto bpf_sk_redirect_map_proto = {
@@ -2115,32 +2135,49 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = {
 	.arg4_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg,
-	   struct bpf_map *, map, u32, key, u64, flags)
+BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg_buff *, msg,
+	   struct bpf_map *, map, void *, key, u64, flags)
 {
 	/* If user passes invalid input drop the packet. */
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
 
-	msg->key = key;
 	msg->flags = flags;
-	msg->map = map;
+	msg->sk_redir = __sock_hash_lookup_elem(map, key);
+	if (!msg->sk_redir)
+		return SK_DROP;
 
 	return SK_PASS;
 }
 
-struct sock *do_msg_redirect_map(struct sk_msg_buff *msg)
+static const struct bpf_func_proto bpf_msg_redirect_hash_proto = {
+	.func           = bpf_msg_redirect_hash,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_PTR_TO_MAP_KEY,
+	.arg4_type      = ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg,
+	   struct bpf_map *, map, u32, key, u64, flags)
 {
-	struct sock *sk = NULL;
+	/* If user passes invalid input drop the packet. */
+	if (unlikely(flags & ~(BPF_F_INGRESS)))
+		return SK_DROP;
 
-	if (msg->map) {
-		sk = __sock_map_lookup_elem(msg->map, msg->key);
+	msg->flags = flags;
+	msg->sk_redir = __sock_map_lookup_elem(map, key);
+	if (!msg->sk_redir)
+		return SK_DROP;
 
-		msg->key = 0;
-		msg->map = NULL;
-	}
+	return SK_PASS;
+}
 
-	return sk;
+struct sock *do_msg_redirect_map(struct sk_msg_buff *msg)
+{
+	return msg->sk_redir;
 }
 
 static const struct bpf_func_proto bpf_msg_redirect_map_proto = {
@@ -4517,6 +4554,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_ops_cb_flags_set_proto;
 	case BPF_FUNC_sock_map_update:
 		return &bpf_sock_map_update_proto;
+	case BPF_FUNC_sock_hash_update:
+		return &bpf_sock_hash_update_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -4528,6 +4567,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	switch (func_id) {
 	case BPF_FUNC_msg_redirect_map:
 		return &bpf_msg_redirect_map_proto;
+	case BPF_FUNC_msg_redirect_hash:
+		return &bpf_msg_redirect_hash_proto;
 	case BPF_FUNC_msg_apply_bytes:
 		return &bpf_msg_apply_bytes_proto;
 	case BPF_FUNC_msg_cork_bytes:
@@ -4559,6 +4600,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_uid_proto;
 	case BPF_FUNC_sk_redirect_map:
 		return &bpf_sk_redirect_map_proto;
+	case BPF_FUNC_sk_redirect_hash:
+		return &bpf_sk_redirect_hash_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}

tools/bpf/bpftool/map.c

@@ -66,6 +66,7 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_DEVMAP]		= "devmap",
 	[BPF_MAP_TYPE_SOCKMAP]		= "sockmap",
 	[BPF_MAP_TYPE_CPUMAP]		= "cpumap",
+	[BPF_MAP_TYPE_SOCKHASH]		= "sockhash",
 };
 
 static bool map_is_per_cpu(__u32 type)

tools/include/uapi/linux/bpf.h

@@ -118,6 +118,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_SOCKMAP,
 	BPF_MAP_TYPE_CPUMAP,
 	BPF_MAP_TYPE_XSKMAP,
+	BPF_MAP_TYPE_SOCKHASH,
 };
 
 enum bpf_prog_type {
@@ -1828,7 +1829,6 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- *
  * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
  *	Description
  *		Do FIB lookup in kernel tables using parameters in *params*.
@@ -1855,6 +1855,53 @@ union bpf_attr {
  *             Egress device index on success, 0 if packet needs to continue
  *             up the stack for further processing or a negative error in case
  *             of failure.
+ *
+ * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		Add an entry to, or update a sockhash *map* referencing sockets.
+ *		The *skops* is used as a new value for the entry associated to
+ *		*key*. *flags* is one of:
+ *
+ *		**BPF_NOEXIST**
+ *			The entry for *key* must not exist in the map.
+ *		**BPF_EXIST**
+ *			The entry for *key* must already exist in the map.
+ *		**BPF_ANY**
+ *			No condition on the existence of the entry for *key*.
+ *
+ *		If the *map* has eBPF programs (parser and verdict), those will
+ *		be inherited by the socket being added. If the socket is
+ *		already attached to eBPF programs, this results in an error.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		This helper is used in programs implementing policies at the
+ *		socket level. If the message *msg* is allowed to pass (i.e. if
+ *		the verdict eBPF program returns **SK_PASS**), redirect it to
+ *		the socket referenced by *map* (of type
+ *		**BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ *		egress interfaces can be used for redirection. The
+ *		**BPF_F_INGRESS** value in *flags* is used to make the
+ *		distinction (ingress path is selected if the flag is present,
+ *		egress path otherwise). This is the only flag supported for now.
+ *	Return
+ *		**SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		This helper is used in programs implementing policies at the
+ *		skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
+ *		if the verdeict eBPF program returns **SK_PASS**), redirect it
+ *		to the socket referenced by *map* (of type
+ *		**BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ *		egress interfaces can be used for redirection. The
+ *		**BPF_F_INGRESS** value in *flags* is used to make the
+ *		distinction (ingress path is selected if the flag is present,
+ *		egress otherwise). This is the only flag supported for now.
+ *	Return
+ *		**SK_PASS** on success, or **SK_DROP** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1926,7 +1973,10 @@ union bpf_attr {
 	FN(skb_get_xfrm_state),		\
 	FN(get_stack),			\
 	FN(skb_load_bytes_relative),	\
-	FN(fib_lookup),
+	FN(fib_lookup),			\
+	FN(sock_hash_update),		\
+	FN(msg_redirect_hash),		\
+	FN(sk_redirect_hash),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

tools/testing/selftests/bpf/Makefile

@@ -33,7 +33,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
 	sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
-	test_get_stack_rawtp.o
+	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \

tools/testing/selftests/bpf/bpf_helpers.h

@@ -75,9 +75,14 @@ static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) =
 	(void *) BPF_FUNC_sock_ops_cb_flags_set;
 static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_sk_redirect_map;
+static int (*bpf_sk_redirect_hash)(void *ctx, void *map, void *key, int flags) =
+	(void *) BPF_FUNC_sk_redirect_hash;
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,
 				  unsigned long long flags) =
 	(void *) BPF_FUNC_sock_map_update;
+static int (*bpf_sock_hash_update)(void *map, void *key, void *value,
+				   unsigned long long flags) =
+	(void *) BPF_FUNC_sock_hash_update;
 static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
 					void *buf, unsigned int buf_size) =
 	(void *) BPF_FUNC_perf_event_read_value;
@@ -88,6 +93,9 @@ static int (*bpf_override_return)(void *ctx, unsigned long rc) =
 	(void *) BPF_FUNC_override_return;
 static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_msg_redirect_map;
+static int (*bpf_msg_redirect_hash)(void *ctx,
+				    void *map, void *key, int flags) =
+	(void *) BPF_FUNC_msg_redirect_hash;
 static int (*bpf_msg_apply_bytes)(void *ctx, int len) =
 	(void *) BPF_FUNC_msg_apply_bytes;
 static int (*bpf_msg_cork_bytes)(void *ctx, int len) =

tools/testing/selftests/bpf/test_sockhash_kern.c

+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+#undef SOCKMAP
+#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKHASH
+#include "./test_sockmap_kern.h"

tools/testing/selftests/bpf/test_sockmap.c

@@ -47,7 +47,8 @@ static void running_handler(int a);
 #define S1_PORT 10000
 #define S2_PORT 10001
 
-#define BPF_FILENAME "test_sockmap_kern.o"
+#define BPF_SOCKMAP_FILENAME "test_sockmap_kern.o"
+#define BPF_SOCKHASH_FILENAME "test_sockhash_kern.o"
 #define CG_PATH "/sockmap"
 
 /* global sockets */
@@ -1260,9 +1261,8 @@ int prog_type[] = {
 	BPF_PROG_TYPE_SK_MSG,
 };
 
-static int populate_progs(void)
+static int populate_progs(char *bpf_file)
 {
-	char *bpf_file = BPF_FILENAME;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
 	int i = 0;
@@ -1306,11 +1306,11 @@ static int populate_progs(void)
 	return 0;
 }
 
-static int test_suite(void)
+static int __test_suite(char *bpf_file)
 {
 	int cg_fd, err;
 
-	err = populate_progs();
+	err = populate_progs(bpf_file);
 	if (err < 0) {
 		fprintf(stderr, "ERROR: (%i) load bpf failed\n", err);
 		return err;
@@ -1347,17 +1347,30 @@ static int test_suite(void)
 
 out:
 	printf("Summary: %i PASSED %i FAILED\n", passed, failed);
+	cleanup_cgroup_environment();
 	close(cg_fd);
 	return err;
 }
 
+static int test_suite(void)
+{
+	int err;
+
+	err = __test_suite(BPF_SOCKMAP_FILENAME);
+	if (err)
+		goto out;
+	err = __test_suite(BPF_SOCKHASH_FILENAME);
+out:
+	return err;
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
 	int iov_count = 1, length = 1024, rate = 1;
 	struct sockmap_options options = {0};
 	int opt, longindex, err, cg_fd = 0;
-	char *bpf_file = BPF_FILENAME;
+	char *bpf_file = BPF_SOCKMAP_FILENAME;
 	int test = PING_PONG;
 
 	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
@@ -1438,7 +1451,7 @@ int main(int argc, char **argv)
 		return -1;
 	}
 
-	err = populate_progs();
+	err = populate_progs(bpf_file);
 	if (err) {
 		fprintf(stderr, "populate program: (%s) %s\n",
 			bpf_file, strerror(errno));

tools/testing/selftests/bpf/test_sockmap_kern.c

 // SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io
-#include <stddef.h>
-#include <string.h>
-#include <linux/bpf.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/in.h>
-#include <linux/udp.h>
-#include <linux/tcp.h>
-#include <linux/pkt_cls.h>
-#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
-
-/* Sockmap sample program connects a client and a backend together
- * using cgroups.
- *
- *    client:X <---> frontend:80 client:X <---> backend:80
- *
- * For simplicity we hard code values here and bind 1:1. The hard
- * coded values are part of the setup in sockmap.sh script that
- * is associated with this BPF program.
- *
- * The bpf_printk is verbose and prints information as connections
- * are established and verdicts are decided.
- */
-
-#define bpf_printk(fmt, ...)					\
-({								\
-	       char ____fmt[] = fmt;				\
-	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
-				##__VA_ARGS__);			\
-})
-
-struct bpf_map_def SEC("maps") sock_map = {
-	.type = BPF_MAP_TYPE_SOCKMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
-
-struct bpf_map_def SEC("maps") sock_map_txmsg = {
-	.type = BPF_MAP_TYPE_SOCKMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
-
-struct bpf_map_def SEC("maps") sock_map_redir = {
-	.type = BPF_MAP_TYPE_SOCKMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
-
-struct bpf_map_def SEC("maps") sock_apply_bytes = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1
-};
-
-struct bpf_map_def SEC("maps") sock_cork_bytes = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1
-};
-
-struct bpf_map_def SEC("maps") sock_pull_bytes = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 2
-};
-
-struct bpf_map_def SEC("maps") sock_redir_flags = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1
-};
-
-struct bpf_map_def SEC("maps") sock_skb_opts = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1
-};
-
-SEC("sk_skb1")
-int bpf_prog1(struct __sk_buff *skb)
-{
-	return skb->len;
-}
-
-SEC("sk_skb2")
-int bpf_prog2(struct __sk_buff *skb)
-{
-	__u32 lport = skb->local_port;
-	__u32 rport = skb->remote_port;
-	int len, *f, ret, zero = 0;
-	__u64 flags = 0;
-
-	if (lport == 10000)
-		ret = 10;
-	else
-		ret = 1;
-
-	len = (__u32)skb->data_end - (__u32)skb->data;
-	f = bpf_map_lookup_elem(&sock_skb_opts, &zero);
-	if (f && *f) {
-		ret = 3;
-		flags = *f;
-	}
-
-	bpf_printk("sk_skb2: redirect(%iB) flags=%i\n",
-		   len, flags);
-	return bpf_sk_redirect_map(skb, &sock_map, ret, flags);
-}
-
-SEC("sockops")
-int bpf_sockmap(struct bpf_sock_ops *skops)
-{
-	__u32 lport, rport;
-	int op, err = 0, index, key, ret;
-
-
-	op = (int) skops->op;
-
-	switch (op) {
-	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
-		lport = skops->local_port;
-		rport = skops->remote_port;
-
-		if (lport == 10000) {
-			ret = 1;
-			err = bpf_sock_map_update(skops, &sock_map, &ret,
-						  BPF_NOEXIST);
-			bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
-				   lport, bpf_ntohl(rport), err);
-		}
-		break;
-	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
-		lport = skops->local_port;
-		rport = skops->remote_port;
-
-		if (bpf_ntohl(rport) == 10001) {
-			ret = 10;
-			err = bpf_sock_map_update(skops, &sock_map, &ret,
-						  BPF_NOEXIST);
-			bpf_printk("active(%i -> %i) map ctx update err: %d\n",
-				   lport, bpf_ntohl(rport), err);
-		}
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-SEC("sk_msg1")
-int bpf_prog4(struct sk_msg_md *msg)
-{
-	int *bytes, zero = 0, one = 1;
-	int *start, *end;
-
-	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
-	if (bytes)
-		bpf_msg_apply_bytes(msg, *bytes);
-	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
-	if (bytes)
-		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
-	if (start && end)
-		bpf_msg_pull_data(msg, *start, *end, 0);
-	return SK_PASS;
-}
-
-SEC("sk_msg2")
-int bpf_prog5(struct sk_msg_md *msg)
-{
-	int err1 = -1, err2 = -1, zero = 0, one = 1;
-	int *bytes, *start, *end, len1, len2;
-
-	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
-	if (bytes)
-		err1 = bpf_msg_apply_bytes(msg, *bytes);
-	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
-	if (bytes)
-		err2 = bpf_msg_cork_bytes(msg, *bytes);
-	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
-	if (start && end) {
-		int err;
-
-		bpf_printk("sk_msg2: pull(%i:%i)\n",
-			   start ? *start : 0, end ? *end : 0);
-		err = bpf_msg_pull_data(msg, *start, *end, 0);
-		if (err)
-			bpf_printk("sk_msg2: pull_data err %i\n",
-				   err);
-		len2 = (__u64)msg->data_end - (__u64)msg->data;
-		bpf_printk("sk_msg2: length update %i->%i\n",
-			   len1, len2);
-	}
-	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
-		   len1, err1, err2);
-	return SK_PASS;
-}
-
-SEC("sk_msg3")
-int bpf_prog6(struct sk_msg_md *msg)
-{
-	int *bytes, zero = 0, one = 1, key = 0;
-	int *start, *end, *f;
-	__u64 flags = 0;
-
-	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
-	if (bytes)
-		bpf_msg_apply_bytes(msg, *bytes);
-	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
-	if (bytes)
-		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
-	if (start && end)
-		bpf_msg_pull_data(msg, *start, *end, 0);
-	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
-	if (f && *f) {
-		key = 2;
-		flags = *f;
-	}
-	return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
-}
-
-SEC("sk_msg4")
-int bpf_prog7(struct sk_msg_md *msg)
-{
-	int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0;
-	int *f, *bytes, *start, *end, len1, len2;
-	__u64 flags = 0;
-
-		int err;
-	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
-	if (bytes)
-		err1 = bpf_msg_apply_bytes(msg, *bytes);
-	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
-	if (bytes)
-		err2 = bpf_msg_cork_bytes(msg, *bytes);
-	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
-	if (start && end) {
-
-		bpf_printk("sk_msg2: pull(%i:%i)\n",
-			   start ? *start : 0, end ? *end : 0);
-		err = bpf_msg_pull_data(msg, *start, *end, 0);
-		if (err)
-			bpf_printk("sk_msg2: pull_data err %i\n",
-				   err);
-		len2 = (__u64)msg->data_end - (__u64)msg->data;
-		bpf_printk("sk_msg2: length update %i->%i\n",
-			   len1, len2);
-	}
-	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
-	if (f && *f) {
-		key = 2;
-		flags = *f;
-	}
-	bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n",
-		   len1, flags, err1 ? err1 : err2);
-	err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
-	bpf_printk("sk_msg3: err %i\n", err);
-	return err;
-}
-
-SEC("sk_msg5")
-int bpf_prog8(struct sk_msg_md *msg)
-{
-	void *data_end = (void *)(long) msg->data_end;
-	void *data = (void *)(long) msg->data;
-	int ret = 0, *bytes, zero = 0;
-
-	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
-	if (bytes) {
-		ret = bpf_msg_apply_bytes(msg, *bytes);
-		if (ret)
-			return SK_DROP;
-	} else {
-		return SK_DROP;
-	}
-	return SK_PASS;
-}
-SEC("sk_msg6")
-int bpf_prog9(struct sk_msg_md *msg)
-{
-	void *data_end = (void *)(long) msg->data_end;
-	void *data = (void *)(long) msg->data;
-	int ret = 0, *bytes, zero = 0;
-
-	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
-	if (bytes) {
-		if (((__u64)data_end - (__u64)data) >= *bytes)
-			return SK_PASS;
-		ret = bpf_msg_cork_bytes(msg, *bytes);
-		if (ret)
-			return SK_DROP;
-	}
-	return SK_PASS;
-}
-
-SEC("sk_msg7")
-int bpf_prog10(struct sk_msg_md *msg)
-{
-	int *bytes, zero = 0, one = 1;
-	int *start, *end;
-
-	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
-	if (bytes)
-		bpf_msg_apply_bytes(msg, *bytes);
-	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
-	if (bytes)
-		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
-	if (start && end)
-		bpf_msg_pull_data(msg, *start, *end, 0);
-
-	return SK_DROP;
-}
-
-int _version SEC("version") = 1;
-char _license[] SEC("license") = "GPL";
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+#define SOCKMAP
+#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKMAP
+#include "./test_sockmap_kern.h"

tools/testing/selftests/bpf/test_sockmap_kern.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io */
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+/* Sockmap sample program connects a client and a backend together
+ * using cgroups.
+ *
+ *    client:X <---> frontend:80 client:X <---> backend:80
+ *
+ * For simplicity we hard code values here and bind 1:1. The hard
+ * coded values are part of the setup in sockmap.sh script that
+ * is associated with this BPF program.
+ *
+ * The bpf_printk is verbose and prints information as connections
+ * are established and verdicts are decided.
+ */
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+struct bpf_map_def SEC("maps") sock_map = {
+	.type = TEST_MAP_TYPE,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_map_txmsg = {
+	.type = TEST_MAP_TYPE,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_map_redir = {
+	.type = TEST_MAP_TYPE,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_apply_bytes = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 1
+};
+
+struct bpf_map_def SEC("maps") sock_cork_bytes = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 1
+};
+
+struct bpf_map_def SEC("maps") sock_pull_bytes = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 2
+};
+
+struct bpf_map_def SEC("maps") sock_redir_flags = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 1
+};
+
+struct bpf_map_def SEC("maps") sock_skb_opts = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 1
+};
+
+SEC("sk_skb1")
+int bpf_prog1(struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+SEC("sk_skb2")
+int bpf_prog2(struct __sk_buff *skb)
+{
+	__u32 lport = skb->local_port;
+	__u32 rport = skb->remote_port;
+	int len, *f, ret, zero = 0;
+	__u64 flags = 0;
+
+	if (lport == 10000)
+		ret = 10;
+	else
+		ret = 1;
+
+	len = (__u32)skb->data_end - (__u32)skb->data;
+	f = bpf_map_lookup_elem(&sock_skb_opts, &zero);
+	if (f && *f) {
+		ret = 3;
+		flags = *f;
+	}
+
+	bpf_printk("sk_skb2: redirect(%iB) flags=%i\n",
+		   len, flags);
+#ifdef SOCKMAP
+	return bpf_sk_redirect_map(skb, &sock_map, ret, flags);
+#else
+	return bpf_sk_redirect_hash(skb, &sock_map, &ret, flags);
+#endif
+
+}
+
+SEC("sockops")
+int bpf_sockmap(struct bpf_sock_ops *skops)
+{
+	__u32 lport, rport;
+	int op, err = 0, index, key, ret;
+
+
+	op = (int) skops->op;
+
+	switch (op) {
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		lport = skops->local_port;
+		rport = skops->remote_port;
+
+		if (lport == 10000) {
+			ret = 1;
+#ifdef SOCKMAP
+			err = bpf_sock_map_update(skops, &sock_map, &ret,
+						  BPF_NOEXIST);
+#else
+			err = bpf_sock_hash_update(skops, &sock_map, &ret,
+						   BPF_NOEXIST);
+#endif
+			bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
+				   lport, bpf_ntohl(rport), err);
+		}
+		break;
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		lport = skops->local_port;
+		rport = skops->remote_port;
+
+		if (bpf_ntohl(rport) == 10001) {
+			ret = 10;
+#ifdef SOCKMAP
+			err = bpf_sock_map_update(skops, &sock_map, &ret,
+						  BPF_NOEXIST);
+#else
+			err = bpf_sock_hash_update(skops, &sock_map, &ret,
+						   BPF_NOEXIST);
+#endif
+			bpf_printk("active(%i -> %i) map ctx update err: %d\n",
+				   lport, bpf_ntohl(rport), err);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+SEC("sk_msg1")
+int bpf_prog4(struct sk_msg_md *msg)
+{
+	int *bytes, zero = 0, one = 1;
+	int *start, *end;
+
+	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+	if (bytes)
+		bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		bpf_msg_cork_bytes(msg, *bytes);
+	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	if (start && end)
+		bpf_msg_pull_data(msg, *start, *end, 0);
+	return SK_PASS;
+}
+
+SEC("sk_msg2")
+int bpf_prog5(struct sk_msg_md *msg)
+{
+	int err1 = -1, err2 = -1, zero = 0, one = 1;
+	int *bytes, *start, *end, len1, len2;
+
+	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+	if (bytes)
+		err1 = bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		err2 = bpf_msg_cork_bytes(msg, *bytes);
+	len1 = (__u64)msg->data_end - (__u64)msg->data;
+	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	if (start && end) {
+		int err;
+
+		bpf_printk("sk_msg2: pull(%i:%i)\n",
+			   start ? *start : 0, end ? *end : 0);
+		err = bpf_msg_pull_data(msg, *start, *end, 0);
+		if (err)
+			bpf_printk("sk_msg2: pull_data err %i\n",
+				   err);
+		len2 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg2: length update %i->%i\n",
+			   len1, len2);
+	}
+	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
+		   len1, err1, err2);
+	return SK_PASS;
+}
+
+SEC("sk_msg3")
+int bpf_prog6(struct sk_msg_md *msg)
+{
+	int *bytes, zero = 0, one = 1, key = 0;
+	int *start, *end, *f;
+	__u64 flags = 0;
+
+	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+	if (bytes)
+		bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		bpf_msg_cork_bytes(msg, *bytes);
+	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	if (start && end)
+		bpf_msg_pull_data(msg, *start, *end, 0);
+	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
+	if (f && *f) {
+		key = 2;
+		flags = *f;
+	}
+#ifdef SOCKMAP
+	return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
+#else
+	return bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
+#endif
+}
+
+SEC("sk_msg4")
+int bpf_prog7(struct sk_msg_md *msg)
+{
+	int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0;
+	int *f, *bytes, *start, *end, len1, len2;
+	__u64 flags = 0;
+
+		int err;
+	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+	if (bytes)
+		err1 = bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		err2 = bpf_msg_cork_bytes(msg, *bytes);
+	len1 = (__u64)msg->data_end - (__u64)msg->data;
+	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	if (start && end) {
+
+		bpf_printk("sk_msg2: pull(%i:%i)\n",
+			   start ? *start : 0, end ? *end : 0);
+		err = bpf_msg_pull_data(msg, *start, *end, 0);
+		if (err)
+			bpf_printk("sk_msg2: pull_data err %i\n",
+				   err);
+		len2 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg2: length update %i->%i\n",
+			   len1, len2);
+	}
+	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
+	if (f && *f) {
+		key = 2;
+		flags = *f;
+	}
+	bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n",
+		   len1, flags, err1 ? err1 : err2);
+#ifdef SOCKMAP
+	err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
+#else
+	err = bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
+#endif
+	bpf_printk("sk_msg3: err %i\n", err);
+	return err;
+}
+
+SEC("sk_msg5")
+int bpf_prog8(struct sk_msg_md *msg)
+{
+	void *data_end = (void *)(long) msg->data_end;
+	void *data = (void *)(long) msg->data;
+	int ret = 0, *bytes, zero = 0;
+
+	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+	if (bytes) {
+		ret = bpf_msg_apply_bytes(msg, *bytes);
+		if (ret)
+			return SK_DROP;
+	} else {
+		return SK_DROP;
+	}
+	return SK_PASS;
+}
+SEC("sk_msg6")
+int bpf_prog9(struct sk_msg_md *msg)
+{
+	void *data_end = (void *)(long) msg->data_end;
+	void *data = (void *)(long) msg->data;
+	int ret = 0, *bytes, zero = 0;
+
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes) {
+		if (((__u64)data_end - (__u64)data) >= *bytes)
+			return SK_PASS;
+		ret = bpf_msg_cork_bytes(msg, *bytes);
+		if (ret)
+			return SK_DROP;
+	}
+	return SK_PASS;
+}
+
+SEC("sk_msg7")
+int bpf_prog10(struct sk_msg_md *msg)
+{
+	int *bytes, zero = 0, one = 1;
+	int *start, *end;
+
+	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+	if (bytes)
+		bpf_msg_apply_bytes(msg, *bytes);
+	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+	if (bytes)
+		bpf_msg_cork_bytes(msg, *bytes);
+	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	if (start && end)
+		bpf_msg_pull_data(msg, *start, *end, 0);
+
+	return SK_DROP;
+}
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";