1 files changed, 168 insertions, 48 deletions

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index bbf26cc4f6ee..9937d4c810f2 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags)
 
 tx_err:
 	if (rc < 0 && rc != -EAGAIN)
-		tls_err_abort(sk, -EBADMSG);
+		tls_err_abort(sk, rc);
 
 	return rc;
 }
@@ -872,6 +872,19 @@ more_data:
 		delta = msg->sg.size;
 		psock->eval = sk_psock_msg_verdict(sk, psock, msg);
 		delta -= msg->sg.size;
+
+		if ((s32)delta > 0) {
+			/* It indicates that we executed bpf_msg_pop_data(),
+			 * causing the plaintext data size to decrease.
+			 * Therefore the encrypted data size also needs to
+			 * correspondingly decrease. We only need to subtract
+			 * delta to calculate the new ciphertext length since
+			 * ktls does not support block encryption.
+			 */
+			struct sk_msg *enc = &ctx->open_rec->msg_encrypted;
+
+			sk_msg_trim(sk, enc, enc->sg.size - delta);
+		}
 	}
 	if (msg->cork_bytes && msg->cork_bytes > msg->sg.size &&
 	    !enospc && !full_record) {
@@ -908,6 +921,13 @@ more_data:
 					    &msg_redir, send, flags);
 		lock_sock(sk);
 		if (err < 0) {
+			/* Regardless of whether the data represented by
+			 * msg_redir is sent successfully, we have already
+			 * uncharged it via sk_msg_return_zero(). The
+			 * msg->sg.size represents the remaining unprocessed
+			 * data, which needs to be uncharged here.
+			 */
+			sk_mem_uncharge(sk, msg->sg.size);
 			*copied -= sk_msg_free_nocharge(sk, &msg_redir);
 			msg->sg.size = 0;
 		}
@@ -1034,7 +1054,7 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 			if (ret == -EINPROGRESS)
 				num_async++;
 			else if (ret != -EAGAIN)
-				goto send_end;
+				goto end;
 		}
 	}
 
@@ -1059,7 +1079,7 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 		orig_size = msg_pl->sg.size;
 		full_record = false;
 		try_to_copy = msg_data_left(msg);
-		record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size;
+		record_room = tls_ctx->tx_max_payload_len - msg_pl->sg.size;
 		if (try_to_copy >= record_room) {
 			try_to_copy = record_room;
 			full_record = true;
@@ -1092,8 +1112,11 @@ alloc_encrypted:
 				goto send_end;
 			tls_ctx->pending_open_record_frags = true;
 
-			if (sk_msg_full(msg_pl))
+			if (sk_msg_full(msg_pl)) {
 				full_record = true;
+				sk_msg_trim(sk, msg_en,
+					    msg_pl->sg.size + prot->overhead_size);
+			}
 
 			if (full_record || eor)
 				goto copied;
@@ -1120,11 +1143,22 @@ alloc_encrypted:
 					num_async++;
 				else if (ret == -ENOMEM)
 					goto wait_for_memory;
-				else if (ctx->open_rec && ret == -ENOSPC)
+				else if (ctx->open_rec && ret == -ENOSPC) {
+					if (msg_pl->cork_bytes) {
+						ret = 0;
+						goto send_end;
+					}
 					goto rollback_iter;
-				else if (ret != -EAGAIN)
+				} else if (ret != -EAGAIN)
 					goto send_end;
 			}
+
+			/* Transmit if any encryptions have completed */
+			if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+				cancel_delayed_work(&ctx->tx_work.work);
+				tls_tx_records(sk, msg->msg_flags);
+			}
+
 			continue;
 rollback_iter:
 			copied -= try_to_copy;
@@ -1180,6 +1214,12 @@ copied:
 					goto send_end;
 				}
 			}
+
+			/* Transmit if any encryptions have completed */
+			if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+				cancel_delayed_work(&ctx->tx_work.work);
+				tls_tx_records(sk, msg->msg_flags);
+			}
 		}
 
 		continue;
@@ -1199,8 +1239,9 @@ trim_sgl:
 			goto alloc_encrypted;
 	}
 
+send_end:
 	if (!num_async) {
-		goto send_end;
+		goto end;
 	} else if (num_zc || eor) {
 		int err;
 
@@ -1218,7 +1259,7 @@ trim_sgl:
 		tls_tx_records(sk, msg->msg_flags);
 	}
 
-send_end:
+end:
 	ret = sk_stream_error(sk, msg->msg_flags, ret);
 	return copied > 0 ? copied : ret;
 }
@@ -1314,6 +1355,10 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
 	int ret = 0;
 	long timeo;
 
+	/* a rekey is pending, let userspace deal with it */
+	if (unlikely(ctx->key_update_pending))
+		return -EKEYEXPIRED;
+
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	while (!tls_strp_msg_ready(ctx)) {
@@ -1356,7 +1401,8 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
 			return sock_intr_errno(timeo);
 	}
 
-	tls_strp_msg_load(&ctx->strp, released);
+	if (unlikely(!tls_strp_msg_load(&ctx->strp, released)))
+		return tls_rx_rec_wait(sk, psock, nonblock, false);
 
 	return 1;
 }
@@ -1608,8 +1654,10 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
 
 	if (unlikely(darg->async)) {
 		err = tls_strp_msg_hold(&ctx->strp, &ctx->async_hold);
-		if (err)
-			__skb_queue_tail(&ctx->async_hold, darg->skb);
+		if (err) {
+			err = tls_decrypt_async_wait(ctx);
+			darg->async = false;
+		}
 		return err;
 	}
 
@@ -1720,6 +1768,36 @@ tls_decrypt_device(struct sock *sk, struct msghdr *msg,
 	return 1;
 }
 
+static int tls_check_pending_rekey(struct sock *sk, struct tls_context *ctx,
+				   struct sk_buff *skb)
+{
+	const struct strp_msg *rxm = strp_msg(skb);
+	const struct tls_msg *tlm = tls_msg(skb);
+	char hs_type;
+	int err;
+
+	if (likely(tlm->control != TLS_RECORD_TYPE_HANDSHAKE))
+		return 0;
+
+	if (rxm->full_len < 1)
+		return 0;
+
+	err = skb_copy_bits(skb, rxm->offset, &hs_type, 1);
+	if (err < 0) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		return err;
+	}
+
+	if (hs_type == TLS_HANDSHAKE_KEYUPDATE) {
+		struct tls_sw_context_rx *rx_ctx = ctx->priv_ctx_rx;
+
+		WRITE_ONCE(rx_ctx->key_update_pending, true);
+		TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXREKEYRECEIVED);
+	}
+
+	return 0;
+}
+
 static int tls_rx_one_record(struct sock *sk, struct msghdr *msg,
 			     struct tls_decrypt_arg *darg)
 {
@@ -1739,7 +1817,7 @@ static int tls_rx_one_record(struct sock *sk, struct msghdr *msg,
 	rxm->full_len -= prot->overhead_size;
 	tls_advance_record_sn(sk, prot, &tls_ctx->rx);
 
-	return 0;
+	return tls_check_pending_rekey(sk, tls_ctx, darg->skb);
 }
 
 int decrypt_skb(struct sock *sk, struct scatterlist *sgout)
@@ -1749,6 +1827,9 @@ int decrypt_skb(struct sock *sk, struct scatterlist *sgout)
 	return tls_decrypt_sg(sk, NULL, sgout, &darg);
 }
 
+/* All records returned from a recvmsg() call must have the same type.
+ * 0 is not a valid content type. Use it as "no type reported, yet".
+ */
 static int tls_record_content_type(struct msghdr *msg, struct tls_msg *tlm,
 				   u8 *control)
 {
@@ -1992,8 +2073,10 @@ int tls_sw_recvmsg(struct sock *sk,
 	if (err < 0)
 		goto end;
 
+	/* process_rx_list() will set @control if it processed any records */
 	copied = err;
-	if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more)
+	if (len <= copied || rx_more ||
+	    (control && control != TLS_RECORD_TYPE_DATA))
 		goto end;
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
@@ -2410,8 +2493,7 @@ int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb)
 	return data_len + TLS_HEADER_SIZE;
 
 read_failure:
-	tls_err_abort(strp->sk, ret);
-
+	tls_strp_abort_strp(strp, ret);
 	return ret;
 }
 
@@ -2684,12 +2766,22 @@ int init_prot_info(struct tls_prot_info *prot,
 	return 0;
 }
 
-int tls_set_sw_offload(struct sock *sk, int tx)
+static void tls_finish_key_update(struct sock *sk, struct tls_context *tls_ctx)
+{
+	struct tls_sw_context_rx *ctx = tls_ctx->priv_ctx_rx;
+
+	WRITE_ONCE(ctx->key_update_pending, false);
+	/* wake-up pre-existing poll() */
+	ctx->saved_data_ready(sk);
+}
+
+int tls_set_sw_offload(struct sock *sk, int tx,
+		       struct tls_crypto_info *new_crypto_info)
 {
+	struct tls_crypto_info *crypto_info, *src_crypto_info;
 	struct tls_sw_context_tx *sw_ctx_tx = NULL;
 	struct tls_sw_context_rx *sw_ctx_rx = NULL;
 	const struct tls_cipher_desc *cipher_desc;
-	struct tls_crypto_info *crypto_info;
 	char *iv, *rec_seq, *key, *salt;
 	struct cipher_context *cctx;
 	struct tls_prot_info *prot;
@@ -2701,44 +2793,47 @@ int tls_set_sw_offload(struct sock *sk, int tx)
 	ctx = tls_get_ctx(sk);
 	prot = &ctx->prot_info;
 
-	if (tx) {
-		ctx->priv_ctx_tx = init_ctx_tx(ctx, sk);
-		if (!ctx->priv_ctx_tx)
-			return -ENOMEM;
+	/* new_crypto_info != NULL means rekey */
+	if (!new_crypto_info) {
+		if (tx) {
+			ctx->priv_ctx_tx = init_ctx_tx(ctx, sk);
+			if (!ctx->priv_ctx_tx)
+				return -ENOMEM;
+		} else {
+			ctx->priv_ctx_rx = init_ctx_rx(ctx);
+			if (!ctx->priv_ctx_rx)
+				return -ENOMEM;
+		}
+	}
 
+	if (tx) {
 		sw_ctx_tx = ctx->priv_ctx_tx;
 		crypto_info = &ctx->crypto_send.info;
 		cctx = &ctx->tx;
 		aead = &sw_ctx_tx->aead_send;
 	} else {
-		ctx->priv_ctx_rx = init_ctx_rx(ctx);
-		if (!ctx->priv_ctx_rx)
-			return -ENOMEM;
-
 		sw_ctx_rx = ctx->priv_ctx_rx;
 		crypto_info = &ctx->crypto_recv.info;
 		cctx = &ctx->rx;
 		aead = &sw_ctx_rx->aead_recv;
 	}
 
-	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
+	src_crypto_info = new_crypto_info ?: crypto_info;
+
+	cipher_desc = get_cipher_desc(src_crypto_info->cipher_type);
 	if (!cipher_desc) {
 		rc = -EINVAL;
 		goto free_priv;
 	}
 
-	rc = init_prot_info(prot, crypto_info, cipher_desc);
+	rc = init_prot_info(prot, src_crypto_info, cipher_desc);
 	if (rc)
 		goto free_priv;
 
-	iv = crypto_info_iv(crypto_info, cipher_desc);
-	key = crypto_info_key(crypto_info, cipher_desc);
-	salt = crypto_info_salt(crypto_info, cipher_desc);
-	rec_seq = crypto_info_rec_seq(crypto_info, cipher_desc);
-
-	memcpy(cctx->iv, salt, cipher_desc->salt);
-	memcpy(cctx->iv + cipher_desc->salt, iv, cipher_desc->iv);
-	memcpy(cctx->rec_seq, rec_seq, cipher_desc->rec_seq);
+	iv = crypto_info_iv(src_crypto_info, cipher_desc);
+	key = crypto_info_key(src_crypto_info, cipher_desc);
+	salt = crypto_info_salt(src_crypto_info, cipher_desc);
+	rec_seq = crypto_info_rec_seq(src_crypto_info, cipher_desc);
 
 	if (!*aead) {
 		*aead = crypto_alloc_aead(cipher_desc->cipher_name, 0, 0);
@@ -2751,20 +2846,30 @@ int tls_set_sw_offload(struct sock *sk, int tx)
 
 	ctx->push_pending_record = tls_sw_push_pending_record;
 
+	/* setkey is the last operation that could fail during a
+	 * rekey. if it succeeds, we can start modifying the
+	 * context.
+	 */
 	rc = crypto_aead_setkey(*aead, key, cipher_desc->key);
-	if (rc)
-		goto free_aead;
+	if (rc) {
+		if (new_crypto_info)
+			goto out;
+		else
+			goto free_aead;
+	}
 
-	rc = crypto_aead_setauthsize(*aead, prot->tag_size);
-	if (rc)
-		goto free_aead;
+	if (!new_crypto_info) {
+		rc = crypto_aead_setauthsize(*aead, prot->tag_size);
+		if (rc)
+			goto free_aead;
+	}
 
-	if (sw_ctx_rx) {
+	if (!tx && !new_crypto_info) {
 		tfm = crypto_aead_tfm(sw_ctx_rx->aead_recv);
 
 		tls_update_rx_zc_capable(ctx);
 		sw_ctx_rx->async_capable =
-			crypto_info->version != TLS_1_3_VERSION &&
+			src_crypto_info->version != TLS_1_3_VERSION &&
 			!!(tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC);
 
 		rc = tls_strp_init(&sw_ctx_rx->strp, sk);
@@ -2772,18 +2877,33 @@ int tls_set_sw_offload(struct sock *sk, int tx)
 			goto free_aead;
 	}
 
+	memcpy(cctx->iv, salt, cipher_desc->salt);
+	memcpy(cctx->iv + cipher_desc->salt, iv, cipher_desc->iv);
+	memcpy(cctx->rec_seq, rec_seq, cipher_desc->rec_seq);
+
+	if (new_crypto_info) {
+		unsafe_memcpy(crypto_info, new_crypto_info,
+			      cipher_desc->crypto_info,
+			      /* size was checked in do_tls_setsockopt_conf */);
+		memzero_explicit(new_crypto_info, cipher_desc->crypto_info);
+		if (!tx)
+			tls_finish_key_update(sk, ctx);
+	}
+
 	goto out;
 
 free_aead:
 	crypto_free_aead(*aead);
 	*aead = NULL;
 free_priv:
-	if (tx) {
-		kfree(ctx->priv_ctx_tx);
-		ctx->priv_ctx_tx = NULL;
-	} else {
-		kfree(ctx->priv_ctx_rx);
-		ctx->priv_ctx_rx = NULL;
+	if (!new_crypto_info) {
+		if (tx) {
+			kfree(ctx->priv_ctx_tx);
+			ctx->priv_ctx_tx = NULL;
+		} else {
+			kfree(ctx->priv_ctx_rx);
+			ctx->priv_ctx_rx = NULL;
+		}
 	}
 out:
 	return rc;