[PATCH net-next 1/6] tls: Generalize zerocopy_from_iter

[PATCH net-next 1/6] tls: Generalize zerocopy_from_iter

[Dave Watson]

Refactor zerocopy_from_iter to take arguments for pages and size,
such that it can be used for both tx and rx. RX will also support
zerocopy direct to output iter, as long as the full message can
be copied at once (a large enough userspace buffer was provided).

Signed-off-by: Dave Watson <davejwatson@fb.com>
---
 net/tls/tls_sw.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f26376e..d58f675 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -281,23 +281,24 @@ static int tls_sw_push_pending_record(struct sock *sk, int flags)
 }
 
 static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
-			      int length)
+			      int length, int *pages_used,
+			      unsigned int *size_used,
+			      struct scatterlist *to, int to_max_pages,
+			      bool charge)
 {
-	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
 	struct page *pages[MAX_SKB_FRAGS];
 
 	size_t offset;
 	ssize_t copied, use;
 	int i = 0;
-	unsigned int size = ctx->sg_plaintext_size;
-	int num_elem = ctx->sg_plaintext_num_elem;
+	unsigned int size = *size_used;
+	int num_elem = *pages_used;
 	int rc = 0;
 	int maxpages;
 
 	while (length > 0) {
 		i = 0;
-		maxpages = ARRAY_SIZE(ctx->sg_plaintext_data) - num_elem;
+		maxpages = to_max_pages - num_elem;
 		if (maxpages == 0) {
 			rc = -EFAULT;
 			goto out;
@@ -317,10 +318,11 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 		while (copied) {
 			use = min_t(int, copied, PAGE_SIZE - offset);
 
-			sg_set_page(&ctx->sg_plaintext_data[num_elem],
+			sg_set_page(&to[num_elem],
 				    pages[i], use, offset);
-			sg_unmark_end(&ctx->sg_plaintext_data[num_elem]);
-			sk_mem_charge(sk, use);
+			sg_unmark_end(&to[num_elem]);
+			if (charge)
+				sk_mem_charge(sk, use);
 
 			offset = 0;
 			copied -= use;
@@ -331,8 +333,9 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 	}
 
 out:
-	ctx->sg_plaintext_size = size;
-	ctx->sg_plaintext_num_elem = num_elem;
+	*size_used = size;
+	*pages_used = num_elem;
+
 	return rc;
 }
 
@@ -429,7 +432,11 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 		if (full_record || eor) {
 			ret = zerocopy_from_iter(sk, &msg->msg_iter,
-						 try_to_copy);
+				try_to_copy, &ctx->sg_plaintext_num_elem,
+				&ctx->sg_plaintext_size,
+				ctx->sg_plaintext_data,
+				ARRAY_SIZE(ctx->sg_plaintext_data),
+				true);
 			if (ret)
 				goto fallback_to_reg_send;
 
-- 
2.9.5

[PATCH net-next 2/6] tls: Move cipher info to a separate struct

[Dave Watson]

Separate tx crypto parameters to a separate cipher_context struct.
The same parameters will be used for rx using the same struct.

tls_advance_record_sn is modified to only take the cipher info.

Signed-off-by: Dave Watson <davejwatson@fb.com>
---
 include/net/tls.h  | 26 +++++++++++++-----------
 net/tls/tls_main.c |  8 ++++----
 net/tls/tls_sw.c   | 58 ++++++++++++++++++++++++++++--------------------------
 3 files changed, 49 insertions(+), 43 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 4913430..019e52d 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -81,6 +81,16 @@ enum {
 	TLS_PENDING_CLOSED_RECORD
 };
 
+struct cipher_context {
+	u16 prepend_size;
+	u16 tag_size;
+	u16 overhead_size;
+	u16 iv_size;
+	char *iv;
+	u16 rec_seq_size;
+	char *rec_seq;
+};
+
 struct tls_context {
 	union {
 		struct tls_crypto_info crypto_send;
@@ -91,13 +101,7 @@ struct tls_context {
 
 	u8 tx_conf:2;
 
-	u16 prepend_size;
-	u16 tag_size;
-	u16 overhead_size;
-	u16 iv_size;
-	char *iv;
-	u16 rec_seq_size;
-	char *rec_seq;
+	struct cipher_context tx;
 
 	struct scatterlist *partially_sent_record;
 	u16 partially_sent_offset;
@@ -190,7 +194,7 @@ static inline bool tls_bigint_increment(unsigned char *seq, int len)
 }
 
 static inline void tls_advance_record_sn(struct sock *sk,
-					 struct tls_context *ctx)
+					 struct cipher_context *ctx)
 {
 	if (tls_bigint_increment(ctx->rec_seq, ctx->rec_seq_size))
 		tls_err_abort(sk);
@@ -203,9 +207,9 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
 			     size_t plaintext_len,
 			     unsigned char record_type)
 {
-	size_t pkt_len, iv_size = ctx->iv_size;
+	size_t pkt_len, iv_size = ctx->tx.iv_size;
 
-	pkt_len = plaintext_len + iv_size + ctx->tag_size;
+	pkt_len = plaintext_len + iv_size + ctx->tx.tag_size;
 
 	/* we cover nonce explicit here as well, so buf should be of
 	 * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE
@@ -217,7 +221,7 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
 	buf[3] = pkt_len >> 8;
 	buf[4] = pkt_len & 0xFF;
 	memcpy(buf + TLS_NONCE_OFFSET,
-	       ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size);
+	       ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size);
 }
 
 static inline void tls_make_aad(char *buf,
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index d824d54..c671560 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -259,8 +259,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		}
 	}
 
-	kfree(ctx->rec_seq);
-	kfree(ctx->iv);
+	kfree(ctx->tx.rec_seq);
+	kfree(ctx->tx.iv);
 
 	if (ctx->tx_conf == TLS_SW_TX)
 		tls_sw_free_tx_resources(sk);
@@ -319,9 +319,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
 		}
 		lock_sock(sk);
 		memcpy(crypto_info_aes_gcm_128->iv,
-		       ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+		       ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
 		       TLS_CIPHER_AES_GCM_128_IV_SIZE);
-		memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->rec_seq,
+		memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->tx.rec_seq,
 		       TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE);
 		release_sock(sk);
 		if (copy_to_user(optval,
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d58f675..dd4441d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -79,7 +79,7 @@ static void trim_both_sgl(struct sock *sk, int target_size)
 		target_size);
 
 	if (target_size > 0)
-		target_size += tls_ctx->overhead_size;
+		target_size += tls_ctx->tx.overhead_size;
 
 	trim_sg(sk, ctx->sg_encrypted_data,
 		&ctx->sg_encrypted_num_elem,
@@ -207,21 +207,21 @@ static int tls_do_encryption(struct tls_context *tls_ctx,
 	if (!aead_req)
 		return -ENOMEM;
 
-	ctx->sg_encrypted_data[0].offset += tls_ctx->prepend_size;
-	ctx->sg_encrypted_data[0].length -= tls_ctx->prepend_size;
+	ctx->sg_encrypted_data[0].offset += tls_ctx->tx.prepend_size;
+	ctx->sg_encrypted_data[0].length -= tls_ctx->tx.prepend_size;
 
 	aead_request_set_tfm(aead_req, ctx->aead_send);
 	aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
 	aead_request_set_crypt(aead_req, ctx->sg_aead_in, ctx->sg_aead_out,
-			       data_len, tls_ctx->iv);
+			       data_len, tls_ctx->tx.iv);
 
 	aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				  crypto_req_done, &ctx->async_wait);
 
 	rc = crypto_wait_req(crypto_aead_encrypt(aead_req), &ctx->async_wait);
 
-	ctx->sg_encrypted_data[0].offset -= tls_ctx->prepend_size;
-	ctx->sg_encrypted_data[0].length += tls_ctx->prepend_size;
+	ctx->sg_encrypted_data[0].offset -= tls_ctx->tx.prepend_size;
+	ctx->sg_encrypted_data[0].length += tls_ctx->tx.prepend_size;
 
 	kfree(aead_req);
 	return rc;
@@ -238,7 +238,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1);
 
 	tls_make_aad(ctx->aad_space, ctx->sg_plaintext_size,
-		     tls_ctx->rec_seq, tls_ctx->rec_seq_size,
+		     tls_ctx->tx.rec_seq, tls_ctx->tx.rec_seq_size,
 		     record_type);
 
 	tls_fill_prepend(tls_ctx,
@@ -271,7 +271,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	if (rc < 0 && rc != -EAGAIN)
 		tls_err_abort(sk);
 
-	tls_advance_record_sn(sk, tls_ctx);
+	tls_advance_record_sn(sk, &tls_ctx->tx);
 	return rc;
 }
 
@@ -412,7 +412,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		}
 
 		required_size = ctx->sg_plaintext_size + try_to_copy +
-				tls_ctx->overhead_size;
+				tls_ctx->tx.overhead_size;
 
 		if (!sk_stream_memory_free(sk))
 			goto wait_for_sndbuf;
@@ -475,7 +475,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 				&ctx->sg_encrypted_num_elem,
 				&ctx->sg_encrypted_size,
 				ctx->sg_plaintext_size +
-				tls_ctx->overhead_size);
+				tls_ctx->tx.overhead_size);
 		}
 
 		ret = memcopy_from_iter(sk, &msg->msg_iter, try_to_copy);
@@ -567,7 +567,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 			full_record = true;
 		}
 		required_size = ctx->sg_plaintext_size + copy +
-			      tls_ctx->overhead_size;
+			      tls_ctx->tx.overhead_size;
 
 		if (!sk_stream_memory_free(sk))
 			goto wait_for_sndbuf;
@@ -699,24 +699,26 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 		goto free_priv;
 	}
 
-	ctx->prepend_size = TLS_HEADER_SIZE + nonce_size;
-	ctx->tag_size = tag_size;
-	ctx->overhead_size = ctx->prepend_size + ctx->tag_size;
-	ctx->iv_size = iv_size;
-	ctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, GFP_KERNEL);
-	if (!ctx->iv) {
+	ctx->tx.prepend_size = TLS_HEADER_SIZE + nonce_size;
+	ctx->tx.tag_size = tag_size;
+	ctx->tx.overhead_size = ctx->tx.prepend_size + ctx->tx.tag_size;
+	ctx->tx.iv_size = iv_size;
+	ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+			     GFP_KERNEL);
+	if (!ctx->tx.iv) {
 		rc = -ENOMEM;
 		goto free_priv;
 	}
-	memcpy(ctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
-	memcpy(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
-	ctx->rec_seq_size = rec_seq_size;
-	ctx->rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
-	if (!ctx->rec_seq) {
+	memcpy(ctx->tx.iv, gcm_128_info->salt,
+	       TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+	memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
+	ctx->tx.rec_seq_size = rec_seq_size;
+	ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
+	if (!ctx->tx.rec_seq) {
 		rc = -ENOMEM;
 		goto free_iv;
 	}
-	memcpy(ctx->rec_seq, rec_seq, rec_seq_size);
+	memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size);
 
 	sg_init_table(sw_ctx->sg_encrypted_data,
 		      ARRAY_SIZE(sw_ctx->sg_encrypted_data));
@@ -752,7 +754,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 	if (rc)
 		goto free_aead;
 
-	rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tag_size);
+	rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tx.tag_size);
 	if (!rc)
 		return 0;
 
@@ -760,11 +762,11 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 	crypto_free_aead(sw_ctx->aead_send);
 	sw_ctx->aead_send = NULL;
 free_rec_seq:
-	kfree(ctx->rec_seq);
-	ctx->rec_seq = NULL;
+	kfree(ctx->tx.rec_seq);
+	ctx->tx.rec_seq = NULL;
 free_iv:
-	kfree(ctx->iv);
-	ctx->iv = NULL;
+	kfree(ctx->tx.iv);
+	ctx->tx.iv = NULL;
 free_priv:
 	kfree(ctx->priv_ctx);
 	ctx->priv_ctx = NULL;
-- 
2.9.5

[PATCH net-next 3/6] tls: Pass error code explicitly to tls_err_abort

[Dave Watson]

Pass EBADMSG explicitly to tls_err_abort.  Receive path will
pass additional codes - EMSGSIZE if framing is larger than max
TLS record size, EINVAL if TLS version mismatch.

Signed-off-by: Dave Watson <davejwatson@fb.com>
---
 include/net/tls.h | 6 +++---
 net/tls/tls_sw.c  | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 019e52d..6b44875 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -174,9 +174,9 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx)
 	return tls_ctx->pending_open_record_frags;
 }
 
-static inline void tls_err_abort(struct sock *sk)
+static inline void tls_err_abort(struct sock *sk, int err)
 {
-	sk->sk_err = EBADMSG;
+	sk->sk_err = err;
 	sk->sk_error_report(sk);
 }
 
@@ -197,7 +197,7 @@ static inline void tls_advance_record_sn(struct sock *sk,
 					 struct cipher_context *ctx)
 {
 	if (tls_bigint_increment(ctx->rec_seq, ctx->rec_seq_size))
-		tls_err_abort(sk);
+		tls_err_abort(sk, EBADMSG);
 	tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
 			     ctx->iv_size);
 }
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index dd4441d..6a0a669 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -269,7 +269,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	/* Only pass through MSG_DONTWAIT and MSG_NOSIGNAL flags */
 	rc = tls_push_sg(sk, tls_ctx, ctx->sg_encrypted_data, 0, flags);
 	if (rc < 0 && rc != -EAGAIN)
-		tls_err_abort(sk);
+		tls_err_abort(sk, EBADMSG);
 
 	tls_advance_record_sn(sk, &tls_ctx->tx);
 	return rc;
-- 
2.9.5

[PATCH net-next 4/6] tls: Refactor variable names

[Dave Watson]

Several config variables are prefixed with tx, drop the prefix
since these will be used for both tx and rx.

Signed-off-by: Dave Watson <davejwatson@fb.com>
---
 include/net/tls.h  |  2 +-
 net/tls/tls_main.c | 26 +++++++++++++-------------
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 6b44875..095b722 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -99,7 +99,7 @@ struct tls_context {
 
 	void *priv_ctx;
 
-	u8 tx_conf:2;
+	u8 conf:2;
 
 	struct cipher_context tx;
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index c671560..c405bee 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -52,7 +52,7 @@ enum {
 };
 
 enum {
-	TLS_BASE_TX,
+	TLS_BASE,
 	TLS_SW_TX,
 	TLS_NUM_CONFIG,
 };
@@ -65,7 +65,7 @@ static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx)
 {
 	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
 
-	sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf];
+	sk->sk_prot = &tls_prots[ip_ver][ctx->conf];
 }
 
 int wait_on_pending_writer(struct sock *sk, long *timeo)
@@ -238,7 +238,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	lock_sock(sk);
 	sk_proto_close = ctx->sk_proto_close;
 
-	if (ctx->tx_conf == TLS_BASE_TX) {
+	if (ctx->conf == TLS_BASE) {
 		kfree(ctx);
 		goto skip_tx_cleanup;
 	}
@@ -262,7 +262,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	kfree(ctx->tx.rec_seq);
 	kfree(ctx->tx.iv);
 
-	if (ctx->tx_conf == TLS_SW_TX)
+	if (ctx->conf == TLS_SW_TX)
 		tls_sw_free_tx_resources(sk);
 
 skip_tx_cleanup:
@@ -371,7 +371,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	struct tls_crypto_info *crypto_info;
 	struct tls_context *ctx = tls_get_ctx(sk);
 	int rc = 0;
-	int tx_conf;
+	int conf;
 
 	if (!optval || (optlen < sizeof(*crypto_info))) {
 		rc = -EINVAL;
@@ -418,11 +418,11 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 
 	/* currently SW is default, we will have ethtool in future */
 	rc = tls_set_sw_offload(sk, ctx);
-	tx_conf = TLS_SW_TX;
+	conf = TLS_SW_TX;
 	if (rc)
 		goto err_crypto_info;
 
-	ctx->tx_conf = tx_conf;
+	ctx->conf = conf;
 	update_sk_prot(sk, ctx);
 	ctx->sk_write_space = sk->sk_write_space;
 	sk->sk_write_space = tls_write_space;
@@ -465,12 +465,12 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
 
 static void build_protos(struct proto *prot, struct proto *base)
 {
-	prot[TLS_BASE_TX] = *base;
-	prot[TLS_BASE_TX].setsockopt	= tls_setsockopt;
-	prot[TLS_BASE_TX].getsockopt	= tls_getsockopt;
-	prot[TLS_BASE_TX].close		= tls_sk_proto_close;
+	prot[TLS_BASE] = *base;
+	prot[TLS_BASE].setsockopt	= tls_setsockopt;
+	prot[TLS_BASE].getsockopt	= tls_getsockopt;
+	prot[TLS_BASE].close		= tls_sk_proto_close;
 
-	prot[TLS_SW_TX] = prot[TLS_BASE_TX];
+	prot[TLS_SW_TX] = prot[TLS_BASE];
 	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
 	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
 }
@@ -513,7 +513,7 @@ static int tls_init(struct sock *sk)
 		mutex_unlock(&tcpv6_prot_mutex);
 	}
 
-	ctx->tx_conf = TLS_BASE_TX;
+	ctx->conf = TLS_BASE;
 	update_sk_prot(sk, ctx);
 out:
 	return rc;
-- 
2.9.5

[PATCH net-next 5/6] tls: RX path for ktls

[Dave Watson]

Add rx path for tls software implementation.

recvmsg, splice_read, and poll implemented.

An additional sockopt TLS_RX is added, with the same interface as
TLS_TX.  Either TLX_RX or TLX_TX may be provided separately, or
together (with two different setsockopt calls with appropriate keys).

Control messages are passed via CMSG in a similar way to transmit.
If no cmsg buffer is passed, then only application data records
will be passed to userspace, and EIO is returned for other types of
alerts.

EBADMSG is passed for decryption errors, and EMSGSIZE is passed for
framing errors (either framing too big *or* too small with crypto
overhead). EINVAL is returned for TLS versions that do not match the
original setsockopt call.  All are unrecoverable.

strparser is used to parse TLS framing.   Decryption is done directly
in to userspace buffers if they are large enough to support it, otherwise
sk_cow_data is called (similar to ipsec), and buffers are decrypted in
place and copied.  splice_read always decrypts in place, since no
buffers are provided to decrypt in to.

sk_poll is overridden, and only returns POLLIN if a full TLS message is
received.  Otherwise we wait for strparser to finish reading a full frame.
Actual decryption is only done during recvmsg or splice_read calls.

Signed-off-by: Dave Watson <davejwatson@fb.com>
---
 include/net/tls.h        |  27 ++-
 include/uapi/linux/tls.h |   2 +
 net/tls/Kconfig          |   1 +
 net/tls/tls_main.c       |  62 ++++-
 net/tls/tls_sw.c         | 587 ++++++++++++++++++++++++++++++++++++++++++-----
 5 files changed, 609 insertions(+), 70 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 095b722..437a746 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -40,6 +40,7 @@
 #include <linux/socket.h>
 #include <linux/tcp.h>
 #include <net/tcp.h>
+#include <net/strparser.h>
 
 #include <uapi/linux/tls.h>
 
@@ -58,8 +59,18 @@
 
 struct tls_sw_context {
 	struct crypto_aead *aead_send;
+	struct crypto_aead *aead_recv;
 	struct crypto_wait async_wait;
 
+	/* Receive context */
+	struct strparser strp;
+	void (*saved_data_ready)(struct sock *sk);
+	unsigned int (*sk_poll)(struct file *file, struct socket *sock,
+				struct poll_table_struct *wait);
+	struct sk_buff *recv_pkt;
+	u8 control;
+	bool decrypted;
+
 	/* Sending context */
 	char aad_space[TLS_AAD_SPACE_SIZE];
 
@@ -96,12 +107,17 @@ struct tls_context {
 		struct tls_crypto_info crypto_send;
 		struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128;
 	};
+	union {
+		struct tls_crypto_info crypto_recv;
+		struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128;
+	};
 
 	void *priv_ctx;
 
 	u8 conf:2;
 
 	struct cipher_context tx;
+	struct cipher_context rx;
 
 	struct scatterlist *partially_sent_record;
 	u16 partially_sent_offset;
@@ -128,12 +144,19 @@ 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 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,
 		    int offset, size_t size, int flags);
 void tls_sw_close(struct sock *sk, long timeout);
-void tls_sw_free_tx_resources(struct sock *sk);
+void tls_sw_free_resources(struct sock *sk);
+int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		   int nonblock, int flags, int *addr_len);
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+			 struct poll_table_struct *wait);
+ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
+			   struct pipe_inode_info *pipe,
+			   size_t len, unsigned int flags);
 
 void tls_sk_destruct(struct sock *sk, struct tls_context *ctx);
 void tls_icsk_clean_acked(struct sock *sk);
diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h
index 293b2cd..c6633e9 100644
--- a/include/uapi/linux/tls.h
+++ b/include/uapi/linux/tls.h
@@ -38,6 +38,7 @@
 
 /* TLS socket options */
 #define TLS_TX			1	/* Set transmit parameters */
+#define TLS_RX			2	/* Set receive parameters */
 
 /* Supported versions */
 #define TLS_VERSION_MINOR(ver)	((ver) & 0xFF)
@@ -59,6 +60,7 @@
 #define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE		8
 
 #define TLS_SET_RECORD_TYPE	1
+#define TLS_GET_RECORD_TYPE	2
 
 struct tls_crypto_info {
 	__u16 version;
diff --git a/net/tls/Kconfig b/net/tls/Kconfig
index eb58303..89b8745a 100644
--- a/net/tls/Kconfig
+++ b/net/tls/Kconfig
@@ -7,6 +7,7 @@ config TLS
 	select CRYPTO
 	select CRYPTO_AES
 	select CRYPTO_GCM
+	select STREAM_PARSER
 	default n
 	---help---
 	Enable kernel support for TLS protocol. This allows symmetric
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index c405bee..6f5c114 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -54,12 +54,15 @@ enum {
 enum {
 	TLS_BASE,
 	TLS_SW_TX,
+	TLS_SW_RX,
+	TLS_SW_RXTX,
 	TLS_NUM_CONFIG,
 };
 
 static struct proto *saved_tcpv6_prot;
 static DEFINE_MUTEX(tcpv6_prot_mutex);
 static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG];
+static struct proto_ops tls_sw_proto_ops;
 
 static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx)
 {
@@ -261,9 +264,14 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 
 	kfree(ctx->tx.rec_seq);
 	kfree(ctx->tx.iv);
+	kfree(ctx->rx.rec_seq);
+	kfree(ctx->rx.iv);
 
-	if (ctx->conf == TLS_SW_TX)
-		tls_sw_free_tx_resources(sk);
+	if (ctx->conf == TLS_SW_TX ||
+	    ctx->conf == TLS_SW_RX ||
+	    ctx->conf == TLS_SW_RXTX) {
+		tls_sw_free_resources(sk);
+	}
 
 skip_tx_cleanup:
 	release_sock(sk);
@@ -365,8 +373,8 @@ static int tls_getsockopt(struct sock *sk, int level, int optname,
 	return do_tls_getsockopt(sk, optname, optval, optlen);
 }
 
-static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
-				unsigned int optlen)
+static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
+				  unsigned int optlen, int tx)
 {
 	struct tls_crypto_info *crypto_info;
 	struct tls_context *ctx = tls_get_ctx(sk);
@@ -378,7 +386,11 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 		goto out;
 	}
 
-	crypto_info = &ctx->crypto_send;
+	if (tx)
+		crypto_info = &ctx->crypto_send;
+	else
+		crypto_info = &ctx->crypto_recv;
+
 	/* Currently we don't support set crypto info more than one time */
 	if (TLS_CRYPTO_INFO_READY(crypto_info)) {
 		rc = -EBUSY;
@@ -417,15 +429,31 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	}
 
 	/* currently SW is default, we will have ethtool in future */
-	rc = tls_set_sw_offload(sk, ctx);
-	conf = TLS_SW_TX;
+	if (tx) {
+		rc = tls_set_sw_offload(sk, ctx, 1);
+		if (ctx->conf == TLS_SW_RX)
+			conf = TLS_SW_RXTX;
+		else
+			conf = TLS_SW_TX;
+	} else {
+		rc = tls_set_sw_offload(sk, ctx, 0);
+		if (ctx->conf == TLS_SW_TX)
+			conf = TLS_SW_RXTX;
+		else
+			conf = TLS_SW_RX;
+	}
+
 	if (rc)
 		goto err_crypto_info;
 
 	ctx->conf = conf;
 	update_sk_prot(sk, ctx);
-	ctx->sk_write_space = sk->sk_write_space;
-	sk->sk_write_space = tls_write_space;
+	if (tx) {
+		ctx->sk_write_space = sk->sk_write_space;
+		sk->sk_write_space = tls_write_space;
+	} else {
+		sk->sk_socket->ops = &tls_sw_proto_ops;
+	}
 	goto out;
 
 err_crypto_info:
@@ -441,8 +469,10 @@ static int do_tls_setsockopt(struct sock *sk, int optname,
 
 	switch (optname) {
 	case TLS_TX:
+	case TLS_RX:
 		lock_sock(sk);
-		rc = do_tls_setsockopt_tx(sk, optval, optlen);
+		rc = do_tls_setsockopt_conf(sk, optval, optlen,
+					    optname == TLS_TX);
 		release_sock(sk);
 		break;
 	default:
@@ -473,6 +503,14 @@ static void build_protos(struct proto *prot, struct proto *base)
 	prot[TLS_SW_TX] = prot[TLS_BASE];
 	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
 	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
+
+	prot[TLS_SW_RX] = prot[TLS_BASE];
+	prot[TLS_SW_RX].recvmsg		= tls_sw_recvmsg;
+	prot[TLS_SW_RX].close		= tls_sk_proto_close;
+
+	prot[TLS_SW_RXTX] = prot[TLS_SW_TX];
+	prot[TLS_SW_RXTX].recvmsg	= tls_sw_recvmsg;
+	prot[TLS_SW_RXTX].close		= tls_sk_proto_close;
 }
 
 static int tls_init(struct sock *sk)
@@ -531,6 +569,10 @@ static int __init tls_register(void)
 {
 	build_protos(tls_prots[TLSV4], &tcp_prot);
 
+	tls_sw_proto_ops = inet_stream_ops;
+	tls_sw_proto_ops.poll = tls_sw_poll;
+	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
+
 	tcp_register_ulp(&tcp_tls_ulp_ops);
 
 	return 0;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 6a0a669..474408f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -34,11 +34,60 @@
  * SOFTWARE.
  */
 
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <crypto/aead.h>
 
+#include <net/strparser.h>
 #include <net/tls.h>
 
+static int tls_do_decryption(struct sock *sk,
+			     struct scatterlist *sgin,
+			     struct scatterlist *sgout,
+			     char *iv_recv,
+			     size_t data_len,
+			     struct sk_buff *skb,
+			     gfp_t flags)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct strp_msg *rxm = strp_msg(skb);
+	struct aead_request *aead_req;
+
+	int ret;
+	unsigned int req_size = sizeof(struct aead_request) +
+		crypto_aead_reqsize(ctx->aead_recv);
+
+	aead_req = kzalloc(req_size, flags);
+	if (!aead_req)
+		return -ENOMEM;
+
+	aead_request_set_tfm(aead_req, ctx->aead_recv);
+	aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
+	aead_request_set_crypt(aead_req, sgin, sgout,
+			       data_len + tls_ctx->rx.tag_size,
+			       (u8 *)iv_recv);
+	aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				  crypto_req_done, &ctx->async_wait);
+
+	ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait);
+
+	if (ret < 0)
+		goto out;
+
+	rxm->offset += tls_ctx->rx.prepend_size;
+	rxm->full_len -= tls_ctx->rx.overhead_size;
+	tls_advance_record_sn(sk, &tls_ctx->rx);
+
+	ctx->decrypted = true;
+
+	ctx->saved_data_ready(sk);
+
+out:
+	kfree(aead_req);
+	return ret;
+}
+
 static void trim_sg(struct sock *sk, struct scatterlist *sg,
 		    int *sg_num_elem, unsigned int *sg_size, int target_size)
 {
@@ -636,13 +685,404 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 	return ret;
 }
 
-void tls_sw_free_tx_resources(struct sock *sk)
+static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
+				     long timeo, int *err)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct sk_buff *skb;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	while (!(skb = ctx->recv_pkt)) {
+		if (sk->sk_err) {
+			*err = sock_error(sk);
+			return NULL;
+		}
+
+		if (sock_flag(sk, SOCK_DONE))
+			return NULL;
+
+		if ((flags & MSG_DONTWAIT) || !timeo) {
+			*err = -EAGAIN;
+			return NULL;
+		}
+
+		add_wait_queue(sk_sleep(sk), &wait);
+		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+		sk_wait_event(sk, &timeo, ctx->recv_pkt != skb, &wait);
+		sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+		remove_wait_queue(sk_sleep(sk), &wait);
+
+		/* Handle signals */
+		if (signal_pending(current)) {
+			*err = sock_intr_errno(timeo);
+			return NULL;
+		}
+	}
+
+	return skb;
+}
+
+static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
+		       struct scatterlist *sgout)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + tls_ctx->rx.iv_size];
+	struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2];
+	struct scatterlist *sgin = &sgin_arr[0];
+	struct strp_msg *rxm = strp_msg(skb);
+	int ret, nsg = ARRAY_SIZE(sgin_arr);
+	char aad_recv[TLS_AAD_SPACE_SIZE];
+	struct sk_buff *unused;
+
+	ret = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
+			    iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+			    tls_ctx->rx.iv_size);
+	if (ret < 0)
+		return ret;
+
+	memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+	if (!sgout) {
+		nsg = skb_cow_data(skb, 0, &unused) + 1;
+		sgin = kmalloc_array(nsg, sizeof(*sgin), sk->sk_allocation);
+		if (!sgout)
+			sgout = sgin;
+	}
+
+	sg_init_table(sgin, nsg);
+	sg_set_buf(&sgin[0], aad_recv, sizeof(aad_recv));
+
+	nsg = skb_to_sgvec(skb, &sgin[1],
+			   rxm->offset + tls_ctx->rx.prepend_size,
+			   rxm->full_len - tls_ctx->rx.prepend_size);
+
+	tls_make_aad(aad_recv,
+		     rxm->full_len - tls_ctx->rx.overhead_size,
+		     tls_ctx->rx.rec_seq,
+		     tls_ctx->rx.rec_seq_size,
+		     ctx->control);
+
+	ret = tls_do_decryption(sk, sgin, sgout, iv,
+				rxm->full_len - tls_ctx->rx.overhead_size,
+				skb, sk->sk_allocation);
+
+	if (sgin != &sgin_arr[0])
+		kfree(sgin);
+
+	return ret;
+}
+
+static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb,
+			       unsigned int len)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct strp_msg *rxm = strp_msg(skb);
+
+	if (len < rxm->full_len) {
+		rxm->offset += len;
+		rxm->full_len -= len;
+
+		return false;
+	}
+
+	/* Finished with message */
+	ctx->recv_pkt = NULL;
+	kfree_skb(skb);
+	strp_unpause(&ctx->strp);
+
+	return true;
+}
+
+int tls_sw_recvmsg(struct sock *sk,
+		   struct msghdr *msg,
+		   size_t len,
+		   int nonblock,
+		   int flags,
+		   int *addr_len)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	unsigned char control;
+	struct strp_msg *rxm;
+	struct sk_buff *skb;
+	ssize_t copied = 0;
+	bool cmsg = false;
+	int err = 0;
+	long timeo;
+
+	flags |= nonblock;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR);
+
+	lock_sock(sk);
+
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+	do {
+		bool zc = false;
+		int chunk = 0;
+
+		skb = tls_wait_data(sk, flags, timeo, &err);
+		if (!skb)
+			goto recv_end;
+
+		rxm = strp_msg(skb);
+		if (!cmsg) {
+			int cerr;
+
+			cerr = put_cmsg(msg, SOL_TLS, TLS_GET_RECORD_TYPE,
+					sizeof(ctx->control), &ctx->control);
+			cmsg = true;
+			control = ctx->control;
+			if (ctx->control != TLS_RECORD_TYPE_DATA) {
+				if (cerr || msg->msg_flags & MSG_CTRUNC) {
+					err = -EIO;
+					goto recv_end;
+				}
+			}
+		} else if (control != ctx->control) {
+			goto recv_end;
+		}
+
+		if (!ctx->decrypted) {
+			int page_count;
+			int to_copy;
+
+			page_count = iov_iter_npages(&msg->msg_iter,
+						     MAX_SKB_FRAGS);
+			to_copy = rxm->full_len - tls_ctx->rx.overhead_size;
+			if (to_copy <= len && page_count < MAX_SKB_FRAGS &&
+			    likely(!(flags & MSG_PEEK)))  {
+				struct scatterlist sgin[MAX_SKB_FRAGS + 1];
+				char unused[21];
+				int pages = 0;
+
+				zc = true;
+				sg_init_table(sgin, MAX_SKB_FRAGS + 1);
+				sg_set_buf(&sgin[0], unused, 13);
+
+				err = zerocopy_from_iter(sk, &msg->msg_iter,
+							 to_copy, &pages,
+							 &chunk, &sgin[1],
+							 MAX_SKB_FRAGS,	false);
+				if (err < 0)
+					goto fallback_to_reg_recv;
+
+				err = decrypt_skb(sk, skb, sgin);
+				for (; pages > 0; pages--)
+					put_page(sg_page(&sgin[pages]));
+				if (err < 0) {
+					tls_err_abort(sk, EBADMSG);
+					goto recv_end;
+				}
+			} else {
+fallback_to_reg_recv:
+				err = decrypt_skb(sk, skb, NULL);
+				if (err < 0) {
+					tls_err_abort(sk, EBADMSG);
+					goto recv_end;
+				}
+			}
+			ctx->decrypted = true;
+		}
+
+		if (!zc) {
+			chunk = min_t(unsigned int, rxm->full_len, len);
+			err = skb_copy_datagram_msg(skb, rxm->offset, msg,
+						    chunk);
+			if (err < 0)
+				goto recv_end;
+		}
+
+		copied += chunk;
+		len -= chunk;
+		if (likely(!(flags & MSG_PEEK))) {
+			u8 control = ctx->control;
+
+			if (tls_sw_advance_skb(sk, skb, chunk)) {
+				/* Return full control message to
+				 * userspace before trying to parse
+				 * another message type
+				 */
+				msg->msg_flags |= MSG_EOR;
+				if (control != TLS_RECORD_TYPE_DATA)
+					goto recv_end;
+			}
+		}
+	} while (len);
+
+recv_end:
+	release_sock(sk);
+	return copied ? : err;
+}
+
+ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
+			   struct pipe_inode_info *pipe,
+			   size_t len, unsigned int flags)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sock->sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct strp_msg *rxm = NULL;
+	struct sock *sk = sock->sk;
+	struct sk_buff *skb;
+	ssize_t copied = 0;
+	int err = 0;
+	long timeo;
+	int chunk;
+
+	lock_sock(sk);
+
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+
+	skb = tls_wait_data(sk, flags, timeo, &err);
+	if (!skb)
+		goto splice_read_end;
+
+	/* splice does not support reading control messages */
+	if (ctx->control != TLS_RECORD_TYPE_DATA) {
+		err = -ENOTSUPP;
+		goto splice_read_end;
+	}
+
+	if (!ctx->decrypted) {
+		err = decrypt_skb(sk, skb, NULL);
+
+		if (err < 0) {
+			tls_err_abort(sk, EBADMSG);
+			goto splice_read_end;
+		}
+		ctx->decrypted = true;
+	}
+	rxm = strp_msg(skb);
+
+	chunk = min_t(unsigned int, rxm->full_len, len);
+	copied = skb_splice_bits(skb, sk, rxm->offset, pipe, chunk, flags);
+	if (copied < 0)
+		goto splice_read_end;
+
+	if (likely(!(flags & MSG_PEEK)))
+		tls_sw_advance_skb(sk, skb, copied);
+
+splice_read_end:
+	release_sock(sk);
+	return copied ? : err;
+}
+
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+			 struct poll_table_struct *wait)
+{
+	unsigned int ret;
+	struct sock *sk = sock->sk;
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+
+	/* Grab POLLOUT and POLLHUP from the underlying socket */
+	ret = ctx->sk_poll(file, sock, wait);
+
+	/* Clear POLLIN bits, and set based on recv_pkt */
+	ret &= ~(POLLIN | POLLRDNORM);
+	if (ctx->recv_pkt)
+		ret |= POLLIN | POLLRDNORM;
+
+	return ret;
+}
+
+static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	char header[tls_ctx->rx.prepend_size];
+	struct strp_msg *rxm = strp_msg(skb);
+	size_t cipher_overhead;
+	size_t data_len = 0;
+	int ret;
+
+	/* Verify that we have a full TLS header, or wait for more data */
+	if (rxm->offset + tls_ctx->rx.prepend_size > skb->len)
+		return 0;
+
+	/* Linearize header to local buffer */
+	ret = skb_copy_bits(skb, rxm->offset, header, tls_ctx->rx.prepend_size);
+
+	if (ret < 0)
+		goto read_failure;
+
+	ctx->control = header[0];
+
+	data_len = ((header[4] & 0xFF) | (header[3] << 8));
+
+	cipher_overhead = tls_ctx->rx.tag_size + tls_ctx->rx.iv_size;
+
+	if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead) {
+		ret = -EMSGSIZE;
+		goto read_failure;
+	}
+	if (data_len < cipher_overhead) {
+		ret = -EMSGSIZE;
+		goto read_failure;
+	}
+
+	if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) ||
+	    header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) {
+		ret = -EINVAL;
+		goto read_failure;
+	}
+
+	return data_len + TLS_HEADER_SIZE;
+
+read_failure:
+	tls_err_abort(strp->sk, ret);
+
+	return ret;
+}
+
+static void tls_queue(struct strparser *strp, struct sk_buff *skb)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct strp_msg *rxm;
+
+	rxm = strp_msg(skb);
+
+	ctx->decrypted = false;
+
+	ctx->recv_pkt = skb;
+	strp_pause(strp);
+
+	strp->sk->sk_state_change(strp->sk);
+}
+
+static void tls_data_ready(struct sock *sk)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+
+	strp_data_ready(&ctx->strp);
+}
+
+void tls_sw_free_resources(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
 
 	if (ctx->aead_send)
 		crypto_free_aead(ctx->aead_send);
+	if (ctx->aead_recv) {
+		if (ctx->recv_pkt) {
+			kfree_skb(ctx->recv_pkt);
+			ctx->recv_pkt = NULL;
+		}
+		crypto_free_aead(ctx->aead_recv);
+		strp_stop(&ctx->strp);
+		write_lock_bh(&sk->sk_callback_lock);
+		sk->sk_data_ready = ctx->saved_data_ready;
+		write_unlock_bh(&sk->sk_callback_lock);
+		release_sock(sk);
+		strp_done(&ctx->strp);
+		lock_sock(sk);
+	}
 
 	tls_free_both_sg(sk);
 
@@ -650,12 +1090,15 @@ void tls_sw_free_tx_resources(struct sock *sk)
 	kfree(tls_ctx);
 }
 
-int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
+int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 {
 	char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
 	struct tls_crypto_info *crypto_info;
 	struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
 	struct tls_sw_context *sw_ctx;
+	struct cipher_context *cctx;
+	struct crypto_aead **aead;
+	struct strp_callbacks cb;
 	u16 nonce_size, tag_size, iv_size, rec_seq_size;
 	char *iv, *rec_seq;
 	int rc = 0;
@@ -665,22 +1108,29 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 		goto out;
 	}
 
-	if (ctx->priv_ctx) {
-		rc = -EEXIST;
-		goto out;
-	}
-
-	sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL);
-	if (!sw_ctx) {
-		rc = -ENOMEM;
-		goto out;
+	if (!ctx->priv_ctx) {
+		sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL);
+		if (!sw_ctx) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		crypto_init_wait(&sw_ctx->async_wait);
+	} else {
+		sw_ctx = ctx->priv_ctx;
 	}
 
-	crypto_init_wait(&sw_ctx->async_wait);
-
 	ctx->priv_ctx = (struct tls_offload_context *)sw_ctx;
 
-	crypto_info = &ctx->crypto_send;
+	if (tx) {
+		crypto_info = &ctx->crypto_send;
+		cctx = &ctx->tx;
+		aead = &sw_ctx->aead_send;
+	} else {
+		crypto_info = &ctx->crypto_recv;
+		cctx = &ctx->rx;
+		aead = &sw_ctx->aead_recv;
+	}
+
 	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128: {
 		nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
@@ -699,48 +1149,49 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 		goto free_priv;
 	}
 
-	ctx->tx.prepend_size = TLS_HEADER_SIZE + nonce_size;
-	ctx->tx.tag_size = tag_size;
-	ctx->tx.overhead_size = ctx->tx.prepend_size + ctx->tx.tag_size;
-	ctx->tx.iv_size = iv_size;
-	ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
-			     GFP_KERNEL);
-	if (!ctx->tx.iv) {
+	cctx->prepend_size = TLS_HEADER_SIZE + nonce_size;
+	cctx->tag_size = tag_size;
+	cctx->overhead_size = cctx->prepend_size + cctx->tag_size;
+	cctx->iv_size = iv_size;
+	cctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+			   GFP_KERNEL);
+	if (!cctx->iv) {
 		rc = -ENOMEM;
 		goto free_priv;
 	}
-	memcpy(ctx->tx.iv, gcm_128_info->salt,
-	       TLS_CIPHER_AES_GCM_128_SALT_SIZE);
-	memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
-	ctx->tx.rec_seq_size = rec_seq_size;
-	ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
-	if (!ctx->tx.rec_seq) {
+	memcpy(cctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+	memcpy(cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
+	cctx->rec_seq_size = rec_seq_size;
+	cctx->rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
+	if (!cctx->rec_seq) {
 		rc = -ENOMEM;
 		goto free_iv;
 	}
-	memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size);
-
-	sg_init_table(sw_ctx->sg_encrypted_data,
-		      ARRAY_SIZE(sw_ctx->sg_encrypted_data));
-	sg_init_table(sw_ctx->sg_plaintext_data,
-		      ARRAY_SIZE(sw_ctx->sg_plaintext_data));
-
-	sg_init_table(sw_ctx->sg_aead_in, 2);
-	sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space,
-		   sizeof(sw_ctx->aad_space));
-	sg_unmark_end(&sw_ctx->sg_aead_in[1]);
-	sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data);
-	sg_init_table(sw_ctx->sg_aead_out, 2);
-	sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space,
-		   sizeof(sw_ctx->aad_space));
-	sg_unmark_end(&sw_ctx->sg_aead_out[1]);
-	sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data);
-
-	if (!sw_ctx->aead_send) {
-		sw_ctx->aead_send = crypto_alloc_aead("gcm(aes)", 0, 0);
-		if (IS_ERR(sw_ctx->aead_send)) {
-			rc = PTR_ERR(sw_ctx->aead_send);
-			sw_ctx->aead_send = NULL;
+	memcpy(cctx->rec_seq, rec_seq, rec_seq_size);
+
+	if (tx) {
+		sg_init_table(sw_ctx->sg_encrypted_data,
+			      ARRAY_SIZE(sw_ctx->sg_encrypted_data));
+		sg_init_table(sw_ctx->sg_plaintext_data,
+			      ARRAY_SIZE(sw_ctx->sg_plaintext_data));
+
+		sg_init_table(sw_ctx->sg_aead_in, 2);
+		sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space,
+			   sizeof(sw_ctx->aad_space));
+		sg_unmark_end(&sw_ctx->sg_aead_in[1]);
+		sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data);
+		sg_init_table(sw_ctx->sg_aead_out, 2);
+		sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space,
+			   sizeof(sw_ctx->aad_space));
+		sg_unmark_end(&sw_ctx->sg_aead_out[1]);
+		sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data);
+	}
+
+	if (!*aead) {
+		*aead = crypto_alloc_aead("gcm(aes)", 0, 0);
+		if (IS_ERR(*aead)) {
+			rc = PTR_ERR(*aead);
+			*aead = NULL;
 			goto free_rec_seq;
 		}
 	}
@@ -749,21 +1200,41 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 
 	memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
 
-	rc = crypto_aead_setkey(sw_ctx->aead_send, keyval,
+	rc = crypto_aead_setkey(*aead, keyval,
 				TLS_CIPHER_AES_GCM_128_KEY_SIZE);
 	if (rc)
 		goto free_aead;
 
-	rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tx.tag_size);
-	if (!rc)
-		return 0;
+	rc = crypto_aead_setauthsize(*aead, cctx->tag_size);
+	if (rc)
+		goto free_aead;
+
+	if (!tx) {
+		/* Set up strparser */
+		memset(&cb, 0, sizeof(cb));
+		cb.rcv_msg = tls_queue;
+		cb.parse_msg = tls_read_size;
+
+		strp_init(&sw_ctx->strp, sk, &cb);
+
+		write_lock_bh(&sk->sk_callback_lock);
+		sw_ctx->saved_data_ready = sk->sk_data_ready;
+		sk->sk_data_ready = tls_data_ready;
+		write_unlock_bh(&sk->sk_callback_lock);
+
+		sw_ctx->sk_poll = sk->sk_socket->ops->poll;
+
+		strp_check_rcv(&sw_ctx->strp);
+	}
+
+	goto out;
 
 free_aead:
-	crypto_free_aead(sw_ctx->aead_send);
-	sw_ctx->aead_send = NULL;
+	crypto_free_aead(*aead);
+	*aead = NULL;
 free_rec_seq:
-	kfree(ctx->tx.rec_seq);
-	ctx->tx.rec_seq = NULL;
+	kfree(cctx->rec_seq);
+	cctx->rec_seq = NULL;
 free_iv:
 	kfree(ctx->tx.iv);
 	ctx->tx.iv = NULL;
-- 
2.9.5

Re: [PATCH net-next 5/6] tls: RX path for ktls

[Boris Pismenny]

On 3/20/2018 7:54 PM, Dave Watson wrote:
> Add rx path for tls software implementation.
> 
> recvmsg, splice_read, and poll implemented.
> 
> An additional sockopt TLS_RX is added, with the same interface as
> TLS_TX.  Either TLX_RX or TLX_TX may be provided separately, or
> together (with two different setsockopt calls with appropriate keys).
> 
> Control messages are passed via CMSG in a similar way to transmit.
> If no cmsg buffer is passed, then only application data records
> will be passed to userspace, and EIO is returned for other types of
> alerts.
> 
> EBADMSG is passed for decryption errors, and EMSGSIZE is passed for
> framing errors (either framing too big *or* too small with crypto
> overhead). EINVAL is returned for TLS versions that do not match the
> original setsockopt call.  All are unrecoverable.
> 
> strparser is used to parse TLS framing.   Decryption is done directly
> in to userspace buffers if they are large enough to support it, otherwise
> sk_cow_data is called (similar to ipsec), and buffers are decrypted in
> place and copied.  splice_read always decrypts in place, since no
> buffers are provided to decrypt in to.
> 
> sk_poll is overridden, and only returns POLLIN if a full TLS message is
> received.  Otherwise we wait for strparser to finish reading a full frame.
> Actual decryption is only done during recvmsg or splice_read calls.
> 
> Signed-off-by: Dave Watson <davejwatson@fb.com>
> ---
...
> +
> +static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
> +{
> +	struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
> +	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
> +	char header[tls_ctx->rx.prepend_size];
> +	struct strp_msg *rxm = strp_msg(skb);
> +	size_t cipher_overhead;
> +	size_t data_len = 0;
> +	int ret;
> +
> +	/* Verify that we have a full TLS header, or wait for more data */
> +	if (rxm->offset + tls_ctx->rx.prepend_size > skb->len)
> +		return 0;
> +
> +	/* Linearize header to local buffer */
> +	ret = skb_copy_bits(skb, rxm->offset, header, tls_ctx->rx.prepend_size);
> +
> +	if (ret < 0)
> +		goto read_failure;
> +
> +	ctx->control = header[0];
> +
> +	data_len = ((header[4] & 0xFF) | (header[3] << 8));
> +
> +	cipher_overhead = tls_ctx->rx.tag_size + tls_ctx->rx.iv_size;
> +
> +	if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead) {
> +		ret = -EMSGSIZE;
> +		goto read_failure;
> +	}
> +	if (data_len < cipher_overhead) {
> +		ret = -EMSGSIZE;

I think this should be considered EBADMSG, because this error is cipher 
dependent. At least, that's what happens within OpenSSL. Also, EMSGSIZE 
is usually used only for too long messages.

> +		goto read_failure;
> +	}
> +
> +	if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) ||
> +	    header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) {
> +		ret = -EINVAL;
> +		goto read_failure;
> +	}
> +
> +	return data_len + TLS_HEADER_SIZE;
> +
> +read_failure:
> +	tls_err_abort(strp->sk, ret);
> +
> +	return ret;
> +}
> +
...

Re: [PATCH net-next 5/6] tls: RX path for ktls

[Dave Watson]

On 03/21/18 07:20 AM, Boris Pismenny wrote:
> 
> 
> On 3/20/2018 7:54 PM, Dave Watson wrote:
> > +	ctx->control = header[0];
> > +
> > +	data_len = ((header[4] & 0xFF) | (header[3] << 8));
> > +
> > +	cipher_overhead = tls_ctx->rx.tag_size + tls_ctx->rx.iv_size;
> > +
> > +	if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead) {
> > +		ret = -EMSGSIZE;
> > +		goto read_failure;
> > +	}
> > +	if (data_len < cipher_overhead) {
> > +		ret = -EMSGSIZE;
> 
> I think this should be considered EBADMSG, because this error is cipher
> dependent. At least, that's what happens within OpenSSL. Also, EMSGSIZE is
> usually used only for too long messages.

Ah, indeed.  Thanks, will send v2.

[PATCH net-next 6/6] tls: Add receive path documentation

[Dave Watson]

Add documentation on rx path setup and cmsg interface.

Signed-off-by: Dave Watson <davejwatson@fb.com>
---
 Documentation/networking/tls.txt | 67 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 65 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/tls.txt b/Documentation/networking/tls.txt
index 77ed006..6c39505 100644
--- a/Documentation/networking/tls.txt
+++ b/Documentation/networking/tls.txt
@@ -48,6 +48,9 @@ the transmit and the receive into the kernel.
 
   setsockopt(sock, SOL_TLS, TLS_TX, &crypto_info, sizeof(crypto_info));
 
+Transmit and receive are set separately, but the setup is the same, using either
+TLS_TX or TLS_RX.
+
 Sending TLS application data
 ----------------------------
 
@@ -79,6 +82,29 @@ for memory), or the encryption will always succeed.  If send() returns
 -ENOMEM and some data was left on the socket buffer from a previous
 call using MSG_MORE, the MSG_MORE data is left on the socket buffer.
 
+Receiving TLS application data
+------------------------------
+
+After setting the TLS_RX socket option, all recv family socket calls
+are decrypted using TLS parameters provided.  A full TLS record must
+be received before decryption can happen.
+
+  char buffer[16384];
+  recv(sock, buffer, 16384);
+
+Received data is decrypted directly in to the user buffer if it is
+large enough, and no additional allocations occur.  If the userspace
+buffer is too small, data is decrypted in the kernel and copied to
+userspace.
+
+EINVAL is returned if the TLS version in the received message does not
+match the version passed in setsockopt.
+
+EMSGSIZE is returned if the received message is too big, or too small
+when crypto overheads are included.
+
+EBADMSG is returned if decryption failed for any other reason.
+
 Send TLS control messages
 -------------------------
 
@@ -118,6 +144,43 @@ using a record of type @record_type.
 Control message data should be provided unencrypted, and will be
 encrypted by the kernel.
 
+Receiving TLS control messages
+------------------------------
+
+TLS control messages are passed in the userspace buffer, with message
+type passed via cmsg.  If no cmsg buffer is provided, an error is
+returned if a control message is received.  Data messages may be
+received without a cmsg buffer set.
+
+  char buffer[16384];
+  char cmsg[CMSG_SPACE(sizeof(unsigned char))];
+  struct msghdr msg = {0};
+  msg.msg_control = cmsg;
+  msg.msg_controllen = sizeof(cmsg);
+
+  struct iovec msg_iov;
+  msg_iov.iov_base = buffer;
+  msg_iov.iov_len = 16384;
+
+  msg.msg_iov = &msg_iov;
+  msg.msg_iovlen = 1;
+
+  int ret = recvmsg(sock, &msg, 0 /* flags */);
+
+  struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+  if (cmsg->cmsg_level == SOL_TLS &&
+      cmsg->cmsg_type == TLS_GET_RECORD_TYPE) {
+      int record_type = *((unsigned char *)CMSG_DATA(cmsg));
+      // Do something with record_type, and control message data in
+      // buffer.
+      //
+      // Note that record_type may be == to application data (23).
+  } else {
+      // Buffer contains application data.
+  }
+
+recv will never return data from mixed types of TLS records.
+
 Integrating in to userspace TLS library
 ---------------------------------------
 
@@ -126,10 +189,10 @@ layer of a userspace TLS library.
 
 A patchset to OpenSSL to use ktls as the record layer is here:
 
-https://github.com/Mellanox/tls-openssl
+https://github.com/Mellanox/openssl/commits/tls_rx2
 
 An example of calling send directly after a handshake using
 gnutls.  Since it doesn't implement a full record layer, control
 messages are not supported:
 
-https://github.com/Mellanox/tls-af_ktls_tool
+https://github.com/ktls/af_ktls-tool/commits/RX
-- 
2.9.5