tls: Add rx inline crypto offload

This patch completes the generic infrastructure to offload TLS crypto to a
network device. It enables the kernel to skip decryption and
authentication of some skbs marked as decrypted by the NIC. In the fast
path, all packets received are decrypted by the NIC and the performance
is comparable to plain TCP.

This infrastructure doesn't require a TCP offload engine. Instead, the
NIC only decrypts packets that contain the expected TCP sequence number.
Out-Of-Order TCP packets are provided unmodified. As a result, at the
worst case a received TLS record consists of both plaintext and ciphertext
packets. These partially decrypted records must be reencrypted,
only to be decrypted.

The notable differences between SW KTLS Rx and this offload are as
follows:
1. Partial decryption - Software must handle the case of a TLS record
that was only partially decrypted by HW. This can happen due to packet
reordering.
2. Resynchronization - tls_read_size calls the device driver to
resynchronize HW after HW lost track of TLS record framing in
the TCP stream.

Signed-off-by: Boris Pismenny <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: Boris Pismenny

include/net/tls.h

@@ -83,6 +83,16 @@ struct tls_device {
 	void (*unhash)(struct tls_device *device, struct sock *sk);
 };
 
+enum {
+	TLS_BASE,
+	TLS_SW,
+#ifdef CONFIG_TLS_DEVICE
+	TLS_HW,
+#endif
+	TLS_HW_RECORD,
+	TLS_NUM_CONFIG,
+};
+
 struct tls_sw_context_tx {
 	struct crypto_aead *aead_send;
 	struct crypto_wait async_wait;
@@ -197,6 +207,7 @@ struct tls_context {
 	int (*push_pending_record)(struct sock *sk, int flags);
 
 	void (*sk_write_space)(struct sock *sk);
+	void (*sk_destruct)(struct sock *sk);
 	void (*sk_proto_close)(struct sock *sk, long timeout);
 
 	int  (*setsockopt)(struct sock *sk, int level,
@@ -209,13 +220,27 @@ struct tls_context {
 	void (*unhash)(struct sock *sk);
 };
 
+struct tls_offload_context_rx {
+	/* sw must be the first member of tls_offload_context_rx */
+	struct tls_sw_context_rx sw;
+	atomic64_t resync_req;
+	u8 driver_state[];
+	/* The TLS layer reserves room for driver specific state
+	 * Currently the belief is that there is not enough
+	 * driver specific state to justify another layer of indirection
+	 */
+};
+
+#define TLS_OFFLOAD_CONTEXT_SIZE_RX					\
+	(ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \
+	 TLS_DRIVER_STATE_SIZE)
+
 int wait_on_pending_writer(struct sock *sk, long *timeo);
 int tls_sk_query(struct sock *sk, int optname, char __user *optval,
 		int __user *optlen);
 int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
 		  unsigned int optlen);
 
-
 int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
 int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_sw_sendpage(struct sock *sk, struct page *page,
@@ -290,11 +315,19 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx)
 	return tls_ctx->pending_open_record_frags;
 }
 
+struct sk_buff *
+tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
+		      struct sk_buff *skb);
+
 static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
 {
-	return sk_fullsock(sk) &&
-	       /* matches smp_store_release in tls_set_device_offload */
-	       smp_load_acquire(&sk->sk_destruct) == &tls_device_sk_destruct;
+#ifdef CONFIG_SOCK_VALIDATE_XMIT
+	return sk_fullsock(sk) &
+	       (smp_load_acquire(&sk->sk_validate_xmit_skb) ==
+	       &tls_validate_xmit_skb);
+#else
+	return false;
+#endif
 }
 
 static inline void tls_err_abort(struct sock *sk, int err)
@@ -387,10 +420,27 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx)
 	return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx;
 }
 
+static inline struct tls_offload_context_rx *
+tls_offload_ctx_rx(const struct tls_context *tls_ctx)
+{
+	return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx;
+}
+
+/* The TLS context is valid until sk_destruct is called */
+static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
+
+	atomic64_set(&rx_ctx->resync_req, ((((uint64_t)seq) << 32) | 1));
+}
+
+
 int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
 		      unsigned char *record_type);
 void tls_register_device(struct tls_device *device);
 void tls_unregister_device(struct tls_device *device);
+int tls_device_decrypted(struct sock *sk, struct sk_buff *skb);
 int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 		struct scatterlist *sgout);
 
@@ -402,4 +452,9 @@ int tls_sw_fallback_init(struct sock *sk,
 			 struct tls_offload_context_tx *offload_ctx,
 			 struct tls_crypto_info *crypto_info);
 
+int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx);
+
+void tls_device_offload_cleanup_rx(struct sock *sk);
+void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn);
+
 #endif /* _TLS_OFFLOAD_H */