Using IKE Fragmentation for Large MessagesELVIS-PLUSRUsvan@elvis.rusecunet Security Networks AGantony.antony@secunet.comsecunet Security Networks AGsteffen.klassert@secunet.comcodelabs GmbHtobias@codelabs.ch This document describes issues with using Internet Key Exchange version 2 (IKEv2) fragmentation
for transmitting large messages on unreliable transport. The document proposes several approaches
for dealing with these issues: randomizing the order the fragments are sent, dispersing sending
fragments over time and selective retransmission of fragments based on information from the peer about their receiption.
The Internet Key Exchange version 2 (IKEv2) protocol is used for
key management in IPsec architecture. IKEv2 was originally defined on UDP transport, and, while
later IKEv2 extensions added TCP as a possible transport (, ),
UDP is still a preferred and mostly used transport for IKEv2.
When UDP is used as a transport, any IKEv2 message that exceeds MTU size is fragmented at IP layer.
IP fragmentation is known to cause problems with some intermediate devices that cannot correctly
procesess any IP fragments other than the first one. To deal with this, a protocol extension
was developed that allows fragmenting messages at IKE layer .
While IKEv2 fragmentation allows to avoid IP fragmentation of large messages, it lacks
any congestion control mechanisms, that may cause issues when the fragmented message
is large (with some definition of "large") and the network (or receiver's) capacity
is limited (with some definition of "limited"). This document defines several approaches
that can be used to mitigate these issues.
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT",
"RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted
as described in BCP 14 when, and only when,
they appear in all capitals, as shown here.
All multi-octet fields representing integers in this document are laid out in big
endian order (also known as "most significant byte first", or "network byte order").
It is expected that readers are familiar with the details of how IKEv2 fragmentation works.
At the time the IKE fragmentation mechanism was being developed, it was considered
that most IKEv2 messages would fit into the typical MTU size and only few of them could
exceed it. In particular, the IKE_AUTH messages containing certificates were concerned and
it was assumed at that time that "large" IKEv2 messages would be less than few Kbytes in size,
so that the number of IKE fragments for a message (with a typical MTU size) would be small.
Due to these considerations it was decided that no mechanism for acknowledging of receipt
of individual fragments is needed - all fragments of a message are transmitted (and retransmitted) at once,
as with IP fragmentation.
When postquantum cryptographic mechanisms started to be incorporated into IKEv2, the notion of "large"
for an IKEv2 message has changed from few Kbytes to several tens of Kbytes and
up to several hundreds of Kbytes .
When messages of this size are fragmented and all fragments are sent at once, it can happen that
either intermediate network devices or the final recipient are uncapable of handling that much data
at the rate it was sent, causing some fragments to be lost. Sender will eventually retransmit
all the message fragments, but since the disproportion between sending rate and network/recipient
limitations remain, it is likely that some fragments will be lost again. Since the restransmissions
are not adaptive, there is no guarantee that the message will eventually be drlivered even after several retransmissions.
This document defines several techniques that can be used to improve reliability
of transmitting large messages using IKEv2 fragmentation mechanism.
These techniques can be used independently of each other.
The techniques can be classified as unilateral actionsm, which do not require any actiona from the peer, and
bilateral actions that require mutual support by both sender and receiver.
The simplest technique is to change the order in which fragments are sent with each retransmission.
This will help in situation the recipient have limited buffer size for incoming packets
and cannot process the received fragments quickly enough to free the buffer.
This means that the some number of the first sent fragments will be processed while the rest will be dropped.
Changing the order in which the fragments are sent with each retransmission ensures that
the first sent packets will change each time, thus increasing the chances all fragments are delivered.
Another simple technique is to add some delay between sending each fragment, thus reducing
the rate with which data is being transmitted. Since the sender does not know what rate
is OK for the receiver, this document gives no advice what this delay should be.
If the sender uses exponential back-off when retransmitting, a sensible approach would be
to also increase delay between sending fragments with each retransmission.
In IKEv2 it is always the initiator that plays an active role in ensuring that both the request and the response
messages of an exchange are delivered (Section 2.1 of ). In particular, the initiator
periodically retransmits the request until it receives the response. With IKE fragmentation in case the response
message is fragmented, a situation is possible that the initiator receives only some of these fragments.
In this situation the initiator must retransmit the request, but if the request message has been fragmented too (the usual case),
there is no need to retransmit all fragments of the request message, it is enough to retransmit only
the first one (i.e., with the Fragment Number field equal to 1). This works because only this fragment
triggers re-sending the response (as specified in Section 2.6.1 of , all other fragments
are discarded and would only waste network resources.
Selective Retransmission of Fragments is an IKEv2 extension that allows, when supported by both peers,
to selectively retransmit only those fragments that weren't delivered.
This extension is negotiated by exchanging a new notification FRAGMENT_ACK_SUPPORTED in the IKE_SA_INIT exchange.
The Notify Message Type for this notification is <TBA by IANA>, Protocol ID and SPI Size are both set to 0
and the notification data is empty. Future specifications may make use of the notification data of this notification.
Implementations compliant with this document MUST ignore the content
of the notification data in the received FRAGMENT_ACK_SUPPORTED notification if it is not empty.
The negotiation only takes effect if peers also negotiate the use of IKE fragmentation, as defined
in Section 2.3 of . If IKE fragmentation is not negotiated, the FRAGMENT_ACK_SUPPORTED notifications
MUST be ignored.
If the selective retransmission of fragments is negotiated, the maximum number of fragments that an IKEv2 sender
can fragment an IKE message to, is limited to 65534, because the value 65535 (0xffff)
in the Total Fragments field of the Encrypted Fragment Payload (Section 2.5 of ) is used
as an indication that this is not a fragment, but instead a Fragment Acknowledgment message ().
When the initiator fragments the request message, it sends the fragments to the responder. If the peers
negotiated this extension and the responder received only some of the sent fragments, then the responder
can indicate which fragments are missing. For this purpose, it sends an IKEv2 response
message formatted in accordance with .
The initiator keeps retransmitting the request message until it receives at least one response message fragment.
If this extension is negotiated and the request message was sent fragmented and the responder has indicated that it has received
all its fragments in the latest Fragment Acknowledgment message, but no response message for the exchange is still received by the initiator,
the initiator MUST continue retransmitting the very first fragment of the request until it receives at least one
response message fragment.
When this happens and if there are still some missing response message fragments and the peers negotiated this extension,
the initiator can indicate which fragments are missing. For this purpose, it sends an IKEv2 request
message for the same exchange (with the same Message ID) formatted in accordance with .
Fragment Acknowledgment is an IKEv2 message that contains only the Encrypted Fragment payload
(see Section 2.5 of ) formatted as follows:
The Next Payload field is set to 0.
The Fragment Number field is set to 0xffff.
The Total Fragments field is set to 0xffff.
The Encrypted content field contains the information about the missing fragments represented
in the form defined in .
All other fields are filled in accordance with and .
If the peers negotiated this extension, the receiver will recognize that this message contains the fragment acknowledgment data.
If the message is successfully decrypted and verified, then the receiver extracts
the fragment acknowledgment data and obtains the information about the fragments that need to be retransmitted.
The receiver MUST ignore messages failed to pass the ICV verification.
The content of the Encrypted Fragment payload contains the fragment acknowledgment data in the following format.
Rcpt Status Packet Number (2 octets, unsigned integer) -- the ordinal number of this Fragment Acknowledgment message. Each new Fragment Acknowledgment
message MUST have this value greater than previous Fragment Acknowledgment messages sent by the host in the context of the current
IKEv2 message exchange, i.e. with the same IKE SPIs, Exchange Type, Message ID and a sender's role (so that
the initiator and the responder maintain these numbers for the messages they send independently). This field MUST NOT be zero,
packets with zero value MUST be ignored on receipt.
Total Fragments (2 octets, unsigned integer) -- when sending, this field MUST be set to the value from the
Total Fragments field in the Encrypted Fragment payloads (see Section 2.5 in that the sender of this packet
currently uses to reconstruct the fragmented message. On receipr, if the value in this field
is not equal to the value in the Total Fragments field in the in the Encrypted Fragment payload most recently sent
to the peer, then this Fragment Acknowledgment message MUST be silently ignored.
First Fragment Num (2 octets, unsigned integer) -- the number of the fragment that corresponds to the first significant
bit (the leftmost bit of the first octet) in the Fragment Acknowledgment Bitmap. This field MUST NOT be zero and
MUST NOT be greater than the value in the Total Fragments field. If these conditions are not met in the received packet,
the packet MUST be silently discarded.
Last Fragment Num (2 octets, unsigned integer) -- the number of the fragment that corresponds to the last significant bit
in the Fragment Acknowledgment Bitmap.This field MUST NOT be zero, MUST NOT be smaller than the value
in the First Fragment Num field and MUST NOT be greater than the value in the Total Fragments field.
If these conditions are not met in the received packet, the packet MUST be silently discarded.
Fragment Acknowledgment Bitmap (variable) -- this field contains a bitmap that represents receipt status for fragments with numbers
starting from the value from the First Fragment Num field till the value from the Last Fragment Num field. The bitmap is
interpreted as starting from the most significant (the leftmost) bit of the first octet of the field. The length of the bitmap
in octets is calculated as: (((Last Fragment Num) - (First Fragment Num)) / 8) + 1. The last octet of the bitmap may contain some
unused bits, these bits are ignored. Each bit in the bitmap represents the receipt status of the corresponding fragment -
it is set to 1 if the fragment was received and successfully processed and set to 0 if the fragment is missing.
TBD. Should discuss when to send messages with Fragment Acknowledgment data, how to handle them, how to keep
these messages small when the number of fragments is large, how to cope with PMTU discovery, etc.
Security of IKEv2 and the IKEv2 fragmentation extension is discussed in and respectfully.
Techniques proposed in this document do not affect security properties of the protocol.
This document defines a new Notify Message Type in the "IKEv2 Notify Message Status Types" registry under
the "Internet Key Exchange Version 2 (IKEv2) Parameters" registry group: This document was inspired by the draft "IKEv2 Fragment Acknowledgment Extension" .