Merge branch 'tls1.3-key-updates'

Sabrina Dubroca says:

====================
tls: implement key updates for TLS1.3

This adds support for receiving KeyUpdate messages (RFC 8446, 4.6.3
[1]). A sender transmits a KeyUpdate message and then changes its TX
key. The receiver should react by updating its RX key before
processing the next message.

This patchset implements key updates by:
 1. pausing decryption when a KeyUpdate message is received, to avoid
    attempting to use the old key to decrypt a record encrypted with
    the new key
 2. returning -EKEYEXPIRED to syscalls that cannot receive the
    KeyUpdate message, until the rekey has been performed by userspace
 3. passing the KeyUpdate message to userspace as a control message
 4. allowing updates of the crypto_info via the TLS_TX/TLS_RX
    setsockopts

This API has been tested with gnutls to make sure that it allows
userspace libraries to implement key updates [2]. Thanks to Frantisek
Krenzelok <fkrenzel@redhat.com> for providing the implementation in
gnutls and testing the kernel patches.

=======================================================================
Discussions around v2 of this patchset focused on how HW offload would
interact with rekey.

RX
 - The existing SW path will handle all records between the KeyUpdate
   message signaling the change of key and the new key becoming known
   to the kernel -- those will be queued encrypted, and decrypted in
   SW as they are read by userspace (once the key is provided, ie same
   as this patchset)
 - Call ->tls_dev_del + ->tls_dev_add immediately during
   setsockopt(TLS_RX)

TX
 - After setsockopt(TLS_TX), switch to the existing SW path (not the
   current device_fallback) until we're able to re-enable HW offload
   - tls_device_sendmsg will call into tls_sw_sendmsg under lock_sock
     to avoid changing socket ops during the rekey while another
     thread might be waiting on the lock
 - We only re-enable HW offload (call ->tls_dev_add to install the new
   key in HW) once all records sent with the old key have been
   ACKed. At this point, all unacked records are SW-encrypted with the
   new key, and the old key is unused by both HW and retransmissions.
   - If there are no unacked records when userspace does
     setsockopt(TLS_TX), we can (try to) install the new key in HW
     immediately.
   - If yet another key has been provided via setsockopt(TLS_TX), we
     don't install intermediate keys, only the latest.
   - TCP notifies ktls of ACKs via the icsk_clean_acked callback. In
     case of a rekey, tls_icsk_clean_acked will record when all data
     sent with the most recent past key has been sent. The next call
     to sendmsg will install the new key in HW.
   - We close and push the current SW record before reenabling
     offload.

If ->tls_dev_add fails to install the new key in HW, we stay in SW
mode. We can add a counter to keep track of this.

In addition:

Because we can't change socket ops during a rekey, we'll also have to
modify do_tls_setsockopt_conf to check ctx->tx_conf and only call
either tls_set_device_offload or tls_set_sw_offload. RX already uses
the same ops for both TLS_HW and TLS_SW, so we could switch between HW
and SW mode on rekey.

An alternative would be to have a common sendmsg which locks
the socket and then calls the correct implementation. We'll need that
anyway for the offload under rekey case, so that would only add a test
to the SW path's ops (compared to the current code). That should allow
us to simplify build_protos a bit, but might have a performance
impact - we'll need to check it if we want to go that route.
=======================================================================

Changes since v4:
 - add counter for received KeyUpdate messages
 - improve wording in the documentation
 - improve handling of bogus messages when looking for KeyUpdate's
 - some coding style clean ups

Changes since v3:
 - rebase on top of net-next
 - rework tls_check_pending_rekey according to Jakub's feedback
 - add statistics for rekey: {RX,TX}REKEY{OK,ERROR}
 - some coding style clean ups
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 169 insertions, 52 deletions

diff --git a/net/tls/tls.h b/net/tls/tls.h
index e5e47452308a..774859b63f0d 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -145,7 +145,8 @@ void tls_err_abort(struct sock *sk, int err);
 int init_prot_info(struct tls_prot_info *prot,
 		   const struct tls_crypto_info *crypto_info,
 		   const struct tls_cipher_desc *cipher_desc);
-int tls_set_sw_offload(struct sock *sk, int tx);
+int tls_set_sw_offload(struct sock *sk, int tx,
+		       struct tls_crypto_info *new_crypto_info);
 void tls_update_rx_zc_capable(struct tls_context *tls_ctx);
 void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
 void tls_sw_strparser_done(struct tls_context *tls_ctx);
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index dc063c2c7950..e50b6e71df13 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -1227,7 +1227,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	context->resync_nh_reset = 1;
 
 	ctx->priv_ctx_rx = context;
-	rc = tls_set_sw_offload(sk, 0);
+	rc = tls_set_sw_offload(sk, 0, NULL);
 	if (rc)
 		goto release_ctx;
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 6b4b9f2749a6..9ee5a83c5b40 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -423,9 +423,10 @@ static __poll_t tls_sk_poll(struct file *file, struct socket *sock,
 	ctx = tls_sw_ctx_rx(tls_ctx);
 	psock = sk_psock_get(sk);
 
-	if (skb_queue_empty_lockless(&ctx->rx_list) &&
-	    !tls_strp_msg_ready(ctx) &&
-	    sk_psock_queue_empty(psock))
+	if ((skb_queue_empty_lockless(&ctx->rx_list) &&
+	     !tls_strp_msg_ready(ctx) &&
+	     sk_psock_queue_empty(psock)) ||
+	    READ_ONCE(ctx->key_update_pending))
 		mask &= ~(EPOLLIN | EPOLLRDNORM);
 
 	if (psock)
@@ -612,11 +613,13 @@ static int validate_crypto_info(const struct tls_crypto_info *crypto_info,
 static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 				  unsigned int optlen, int tx)
 {
-	struct tls_crypto_info *crypto_info;
-	struct tls_crypto_info *alt_crypto_info;
+	struct tls_crypto_info *crypto_info, *alt_crypto_info;
+	struct tls_crypto_info *old_crypto_info = NULL;
 	struct tls_context *ctx = tls_get_ctx(sk);
 	const struct tls_cipher_desc *cipher_desc;
 	union tls_crypto_context *crypto_ctx;
+	union tls_crypto_context tmp = {};
+	bool update = false;
 	int rc = 0;
 	int conf;
 
@@ -633,9 +636,21 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 
 	crypto_info = &crypto_ctx->info;
 
-	/* Currently we don't support set crypto info more than one time */
-	if (TLS_CRYPTO_INFO_READY(crypto_info))
-		return -EBUSY;
+	if (TLS_CRYPTO_INFO_READY(crypto_info)) {
+		/* Currently we only support setting crypto info more
+		 * than one time for TLS 1.3
+		 */
+		if (crypto_info->version != TLS_1_3_VERSION) {
+			TLS_INC_STATS(sock_net(sk), tx ? LINUX_MIB_TLSTXREKEYERROR
+						       : LINUX_MIB_TLSRXREKEYERROR);
+			return -EBUSY;
+		}
+
+		update = true;
+		old_crypto_info = crypto_info;
+		crypto_info = &tmp.info;
+		crypto_ctx = &tmp;
+	}
 
 	rc = copy_from_sockptr(crypto_info, optval, sizeof(*crypto_info));
 	if (rc) {
@@ -643,7 +658,14 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 		goto err_crypto_info;
 	}
 
-	rc = validate_crypto_info(crypto_info, alt_crypto_info);
+	if (update) {
+		/* Ensure that TLS version and ciphers are not modified */
+		if (crypto_info->version != old_crypto_info->version ||
+		    crypto_info->cipher_type != old_crypto_info->cipher_type)
+			rc = -EINVAL;
+	} else {
+		rc = validate_crypto_info(crypto_info, alt_crypto_info);
+	}
 	if (rc)
 		goto err_crypto_info;
 
@@ -673,11 +695,17 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXDEVICE);
 			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXDEVICE);
 		} else {
-			rc = tls_set_sw_offload(sk, 1);
+			rc = tls_set_sw_offload(sk, 1,
+						update ? crypto_info : NULL);
 			if (rc)
 				goto err_crypto_info;
-			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXSW);
-			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXSW);
+
+			if (update) {
+				TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXREKEYOK);
+			} else {
+				TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXSW);
+				TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXSW);
+			}
 			conf = TLS_SW;
 		}
 	} else {
@@ -687,14 +715,21 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICE);
 			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXDEVICE);
 		} else {
-			rc = tls_set_sw_offload(sk, 0);
+			rc = tls_set_sw_offload(sk, 0,
+						update ? crypto_info : NULL);
 			if (rc)
 				goto err_crypto_info;
-			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXSW);
-			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXSW);
+
+			if (update) {
+				TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXREKEYOK);
+			} else {
+				TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXSW);
+				TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXSW);
+			}
 			conf = TLS_SW;
 		}
-		tls_sw_strparser_arm(sk, ctx);
+		if (!update)
+			tls_sw_strparser_arm(sk, ctx);
 	}
 
 	if (tx)
@@ -713,6 +748,10 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 	return 0;
 
 err_crypto_info:
+	if (update) {
+		TLS_INC_STATS(sock_net(sk), tx ? LINUX_MIB_TLSTXREKEYERROR
+					       : LINUX_MIB_TLSRXREKEYERROR);
+	}
 	memzero_explicit(crypto_ctx, sizeof(*crypto_ctx));
 	return rc;
 }
diff --git a/net/tls/tls_proc.c b/net/tls/tls_proc.c
index 68982728f620..367666aa07b8 100644
--- a/net/tls/tls_proc.c
+++ b/net/tls/tls_proc.c
@@ -22,6 +22,11 @@ static const struct snmp_mib tls_mib_list[] = {
 	SNMP_MIB_ITEM("TlsRxDeviceResync", LINUX_MIB_TLSRXDEVICERESYNC),
 	SNMP_MIB_ITEM("TlsDecryptRetry", LINUX_MIB_TLSDECRYPTRETRY),
 	SNMP_MIB_ITEM("TlsRxNoPadViolation", LINUX_MIB_TLSRXNOPADVIOL),
+	SNMP_MIB_ITEM("TlsRxRekeyOk", LINUX_MIB_TLSRXREKEYOK),
+	SNMP_MIB_ITEM("TlsRxRekeyError", LINUX_MIB_TLSRXREKEYERROR),
+	SNMP_MIB_ITEM("TlsTxRekeyOk", LINUX_MIB_TLSTXREKEYOK),
+	SNMP_MIB_ITEM("TlsTxRekeyError", LINUX_MIB_TLSTXREKEYERROR),
+	SNMP_MIB_ITEM("TlsRxRekeyReceived", LINUX_MIB_TLSRXREKEYRECEIVED),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index bbf26cc4f6ee..47550d485819 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1314,6 +1314,10 @@ 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)) {
@@ -1720,6 +1724,36 @@ 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 +1773,7 @@ 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)
@@ -2684,12 +2718,22 @@ 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 +2745,47 @@ 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 +2798,30 @@ 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 +2829,33 @@ 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;