bpf, sockmap: convert to generic sk_msg interface

Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.

This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.

Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.

The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.

Joint work with John.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

5 files changed, 410 insertions, 44 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9b558713447f..e60fff48288b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -737,33 +737,18 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 }
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
-#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);
-int sockmap_get_from_fd(const union bpf_attr *attr, int type,
-			struct bpf_prog *prog);
+#if defined(CONFIG_BPF_STREAM_PARSER)
+int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which);
+int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
 #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)
+static inline int sock_map_prog_update(struct bpf_map *map,
+				       struct bpf_prog *prog, u32 which)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type,
-				      struct bpf_prog *prog)
+static inline int sock_map_get_from_fd(const union bpf_attr *attr,
+				       struct bpf_prog *prog)
 {
 	return -EINVAL;
 }
@@ -839,6 +824,10 @@ 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;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
+extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
+extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
+extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;
+extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
 
 extern const struct bpf_func_proto bpf_get_local_storage_proto;
 
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 5432f4c9f50e..fa48343a5ea1 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -57,7 +57,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
 #ifdef CONFIG_NET
 BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
-#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_INET)
+#if defined(CONFIG_BPF_STREAM_PARSER)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
 #endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6791a0ac0139..5771874bc01e 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -520,24 +520,6 @@ struct bpf_skb_data_end {
 	void *data_end;
 };
 
-struct sk_msg_buff {
-	void *data;
-	void *data_end;
-	__u32 apply_bytes;
-	__u32 cork_bytes;
-	int sg_copybreak;
-	int sg_start;
-	int sg_curr;
-	int sg_end;
-	struct scatterlist sg_data[MAX_SKB_FRAGS];
-	bool sg_copy[MAX_SKB_FRAGS];
-	__u32 flags;
-	struct sock *sk_redir;
-	struct sock *sk;
-	struct sk_buff *skb;
-	struct list_head list;
-};
-
 struct bpf_redirect_info {
 	u32 ifindex;
 	u32 flags;
@@ -833,9 +815,6 @@ void xdp_do_flush_map(void);
 
 void bpf_warn_invalid_xdp_action(u32 act);
 
-struct sock *do_sk_redirect_map(struct sk_buff *skb);
-struct sock *do_msg_redirect_map(struct sk_msg_buff *md);
-
 #ifdef CONFIG_INET
 struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 				  struct bpf_prog *prog, struct sk_buff *skb,
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
new file mode 100644
index 000000000000..95678103c4a0
--- /dev/null
+++ b/include/linux/skmsg.h
@@ -0,0 +1,371 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */
+
+#ifndef _LINUX_SKMSG_H
+#define _LINUX_SKMSG_H
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/scatterlist.h>
+#include <linux/skbuff.h>
+
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <net/strparser.h>
+
+#define MAX_MSG_FRAGS			MAX_SKB_FRAGS
+
+enum __sk_action {
+	__SK_DROP = 0,
+	__SK_PASS,
+	__SK_REDIRECT,
+	__SK_NONE,
+};
+
+struct sk_msg_sg {
+	u32				start;
+	u32				curr;
+	u32				end;
+	u32				size;
+	u32				copybreak;
+	bool				copy[MAX_MSG_FRAGS];
+	struct scatterlist		data[MAX_MSG_FRAGS];
+};
+
+struct sk_msg {
+	struct sk_msg_sg		sg;
+	void				*data;
+	void				*data_end;
+	u32				apply_bytes;
+	u32				cork_bytes;
+	u32				flags;
+	struct sk_buff			*skb;
+	struct sock			*sk_redir;
+	struct sock			*sk;
+	struct list_head		list;
+};
+
+struct sk_psock_progs {
+	struct bpf_prog			*msg_parser;
+	struct bpf_prog			*skb_parser;
+	struct bpf_prog			*skb_verdict;
+};
+
+enum sk_psock_state_bits {
+	SK_PSOCK_TX_ENABLED,
+};
+
+struct sk_psock_link {
+	struct list_head		list;
+	struct bpf_map			*map;
+	void				*link_raw;
+};
+
+struct sk_psock_parser {
+	struct strparser		strp;
+	bool				enabled;
+	void (*saved_data_ready)(struct sock *sk);
+};
+
+struct sk_psock_work_state {
+	struct sk_buff			*skb;
+	u32				len;
+	u32				off;
+};
+
+struct sk_psock {
+	struct sock			*sk;
+	struct sock			*sk_redir;
+	u32				apply_bytes;
+	u32				cork_bytes;
+	u32				eval;
+	struct sk_msg			*cork;
+	struct sk_psock_progs		progs;
+	struct sk_psock_parser		parser;
+	struct sk_buff_head		ingress_skb;
+	struct list_head		ingress_msg;
+	unsigned long			state;
+	struct list_head		link;
+	spinlock_t			link_lock;
+	refcount_t			refcnt;
+	void (*saved_unhash)(struct sock *sk);
+	void (*saved_close)(struct sock *sk, long timeout);
+	void (*saved_write_space)(struct sock *sk);
+	struct proto			*sk_proto;
+	struct sk_psock_work_state	work_state;
+	struct work_struct		work;
+	union {
+		struct rcu_head		rcu;
+		struct work_struct	gc;
+	};
+};
+
+int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
+		 int elem_first_coalesce);
+void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len);
+int sk_msg_free(struct sock *sk, struct sk_msg *msg);
+int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg);
+void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes);
+void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg,
+				  u32 bytes);
+
+void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes);
+
+int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
+			      struct sk_msg *msg, u32 bytes);
+int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
+			     struct sk_msg *msg, u32 bytes);
+
+static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
+{
+	WARN_ON(i == msg->sg.end && bytes);
+}
+
+static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes)
+{
+	if (psock->apply_bytes) {
+		if (psock->apply_bytes < bytes)
+			psock->apply_bytes = 0;
+		else
+			psock->apply_bytes -= bytes;
+	}
+}
+
+#define sk_msg_iter_var_prev(var)			\
+	do {						\
+		if (var == 0)				\
+			var = MAX_MSG_FRAGS - 1;	\
+		else					\
+			var--;				\
+	} while (0)
+
+#define sk_msg_iter_var_next(var)			\
+	do {						\
+		var++;					\
+		if (var == MAX_MSG_FRAGS)		\
+			var = 0;			\
+	} while (0)
+
+#define sk_msg_iter_prev(msg, which)			\
+	sk_msg_iter_var_prev(msg->sg.which)
+
+#define sk_msg_iter_next(msg, which)			\
+	sk_msg_iter_var_next(msg->sg.which)
+
+static inline void sk_msg_clear_meta(struct sk_msg *msg)
+{
+	memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy));
+}
+
+static inline void sk_msg_init(struct sk_msg *msg)
+{
+	memset(msg, 0, sizeof(*msg));
+	sg_init_marker(msg->sg.data, ARRAY_SIZE(msg->sg.data));
+}
+
+static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
+			       int which, u32 size)
+{
+	dst->sg.data[which] = src->sg.data[which];
+	dst->sg.data[which].length  = size;
+	src->sg.data[which].length -= size;
+	src->sg.data[which].offset += size;
+}
+
+static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
+{
+	return msg->sg.end >= msg->sg.start ?
+		msg->sg.end - msg->sg.start :
+		msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start);
+}
+
+static inline bool sk_msg_full(const struct sk_msg *msg)
+{
+	return (msg->sg.end == msg->sg.start) && msg->sg.size;
+}
+
+static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
+{
+	return &msg->sg.data[which];
+}
+
+static inline struct page *sk_msg_page(struct sk_msg *msg, int which)
+{
+	return sg_page(sk_msg_elem(msg, which));
+}
+
+static inline bool sk_msg_to_ingress(const struct sk_msg *msg)
+{
+	return msg->flags & BPF_F_INGRESS;
+}
+
+static inline void sk_msg_compute_data_pointers(struct sk_msg *msg)
+{
+	struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start);
+
+	if (msg->sg.copy[msg->sg.start]) {
+		msg->data = NULL;
+		msg->data_end = NULL;
+	} else {
+		msg->data = sg_virt(sge);
+		msg->data_end = msg->data + sge->length;
+	}
+}
+
+static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page,
+				   u32 len, u32 offset)
+{
+	struct scatterlist *sge;
+
+	get_page(page);
+	sge = sk_msg_elem(msg, msg->sg.end);
+	sg_set_page(sge, page, len, offset);
+	sg_unmark_end(sge);
+
+	msg->sg.copy[msg->sg.end] = true;
+	msg->sg.size += len;
+	sk_msg_iter_next(msg, end);
+}
+
+static inline struct sk_psock *sk_psock(const struct sock *sk)
+{
+	return rcu_dereference_sk_user_data(sk);
+}
+
+static inline bool sk_has_psock(struct sock *sk)
+{
+	return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg;
+}
+
+static inline void sk_psock_queue_msg(struct sk_psock *psock,
+				      struct sk_msg *msg)
+{
+	list_add_tail(&msg->list, &psock->ingress_msg);
+}
+
+static inline void sk_psock_report_error(struct sk_psock *psock, int err)
+{
+	struct sock *sk = psock->sk;
+
+	sk->sk_err = err;
+	sk->sk_error_report(sk);
+}
+
+struct sk_psock *sk_psock_init(struct sock *sk, int node);
+
+int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock);
+void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock);
+void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock);
+
+int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
+			 struct sk_msg *msg);
+
+static inline struct sk_psock_link *sk_psock_init_link(void)
+{
+	return kzalloc(sizeof(struct sk_psock_link),
+		       GFP_ATOMIC | __GFP_NOWARN);
+}
+
+static inline void sk_psock_free_link(struct sk_psock_link *link)
+{
+	kfree(link);
+}
+
+struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock);
+#if defined(CONFIG_BPF_STREAM_PARSER)
+void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link);
+#else
+static inline void sk_psock_unlink(struct sock *sk,
+				   struct sk_psock_link *link)
+{
+}
+#endif
+
+void __sk_psock_purge_ingress_msg(struct sk_psock *psock);
+
+static inline void sk_psock_cork_free(struct sk_psock *psock)
+{
+	if (psock->cork) {
+		sk_msg_free(psock->sk, psock->cork);
+		kfree(psock->cork);
+		psock->cork = NULL;
+	}
+}
+
+static inline void sk_psock_update_proto(struct sock *sk,
+					 struct sk_psock *psock,
+					 struct proto *ops)
+{
+	psock->saved_unhash = sk->sk_prot->unhash;
+	psock->saved_close = sk->sk_prot->close;
+	psock->saved_write_space = sk->sk_write_space;
+
+	psock->sk_proto = sk->sk_prot;
+	sk->sk_prot = ops;
+}
+
+static inline void sk_psock_restore_proto(struct sock *sk,
+					  struct sk_psock *psock)
+{
+	if (psock->sk_proto) {
+		sk->sk_prot = psock->sk_proto;
+		psock->sk_proto = NULL;
+	}
+}
+
+static inline void sk_psock_set_state(struct sk_psock *psock,
+				      enum sk_psock_state_bits bit)
+{
+	set_bit(bit, &psock->state);
+}
+
+static inline void sk_psock_clear_state(struct sk_psock *psock,
+					enum sk_psock_state_bits bit)
+{
+	clear_bit(bit, &psock->state);
+}
+
+static inline bool sk_psock_test_state(const struct sk_psock *psock,
+				       enum sk_psock_state_bits bit)
+{
+	return test_bit(bit, &psock->state);
+}
+
+static inline struct sk_psock *sk_psock_get(struct sock *sk)
+{
+	struct sk_psock *psock;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (psock && !refcount_inc_not_zero(&psock->refcnt))
+		psock = NULL;
+	rcu_read_unlock();
+	return psock;
+}
+
+void sk_psock_stop(struct sock *sk, struct sk_psock *psock);
+void sk_psock_destroy(struct rcu_head *rcu);
+void sk_psock_drop(struct sock *sk, struct sk_psock *psock);
+
+static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
+{
+	if (refcount_dec_and_test(&psock->refcnt))
+		sk_psock_drop(sk, psock);
+}
+
+static inline void psock_set_prog(struct bpf_prog **pprog,
+				  struct bpf_prog *prog)
+{
+	prog = xchg(pprog, prog);
+	if (prog)
+		bpf_prog_put(prog);
+}
+
+static inline void psock_progs_drop(struct sk_psock_progs *progs)
+{
+	psock_set_prog(&progs->msg_parser, NULL);
+	psock_set_prog(&progs->skb_parser, NULL);
+	psock_set_prog(&progs->skb_verdict, NULL);
+}
+
+#endif /* _LINUX_SKMSG_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8f5cef67fd35..3600ae0f25c3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -858,6 +858,21 @@ static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
 }
 
+static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS;
+}
+
+static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->bpf.sk_redir;
+}
+
+static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb)
+{
+	TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 /* This is the variant of inet6_iif() that must be used by TCP,
  * as TCP moves IP6CB into a different location in skb->cb[]
@@ -2064,6 +2079,18 @@ void tcp_cleanup_ulp(struct sock *sk);
 	__MODULE_INFO(alias, alias_userspace, name);		\
 	__MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name)
 
+struct sk_msg;
+struct sk_psock;
+
+int tcp_bpf_init(struct sock *sk);
+void tcp_bpf_reinit(struct sock *sk);
+int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes,
+			  int flags);
+int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		    int nonblock, int flags, int *addr_len);
+int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
+		      struct msghdr *msg, int len);
+
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF
  * program does not support the chosen operation or there is no BPF