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 <[email protected]>

include/linux/bpf.h

@@ -668,13 +668,20 @@ 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)
 {
 	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)
 {