draft-ietf-rddp-mpa-04.txt   draft-ietf-rddp-mpa-05.txt 
Remote Direct Data Placement Work Group P. Culley Remote Direct Data Placement Work Group P. Culley
INTERNET-DRAFT Hewlett-Packard Company INTERNET-DRAFT Hewlett-Packard Company
draft-ietf-rddp-mpa-04.txt U. Elzur draft-ietf-rddp-mpa-05.txt U. Elzur
Broadcom Corporation Broadcom Corporation
R. Recio R. Recio
IBM Corporation IBM Corporation
S. Bailey S. Bailey
Sandburst Corporation Sandburst Corporation
J. Carrier J. Carrier
Cray Inc. Cray Inc.
Expires: November 2006 May 30, 2006 Expires: December 2006 June 23, 2006
Marker PDU Aligned Framing for TCP Specification Marker PDU Aligned Framing for TCP Specification
Status of this Memo Status of this Memo
By submitting this Internet-Draft, each author represents that any By submitting this Internet-Draft, each author represents that any
applicable patent or other IPR claims of which he or she is aware applicable patent or other IPR claims of which he or she is aware
have been or will be disclosed, and any of which he or she becomes have been or will be disclosed, and any of which he or she becomes
aware will be disclosed, in accordance with Section 6 of BCP 79. aware will be disclosed, in accordance with Section 6 of BCP 79.
skipping to change at page 2, line 9 skipping to change at page 2, line 9
boundaries that DDP requires. MPA is fully compliant with applicable boundaries that DDP requires. MPA is fully compliant with applicable
TCP RFCs and can be utilized with existing TCP implementations. MPA TCP RFCs and can be utilized with existing TCP implementations. MPA
also supports integrated implementations that combine TCP, MPA and also supports integrated implementations that combine TCP, MPA and
DDP to reduce buffering requirements in the implementation and DDP to reduce buffering requirements in the implementation and
improve performance at the system level. improve performance at the system level.
Table of Contents Table of Contents
Status of this Memo 1 Status of this Memo 1
Abstract 1 Abstract 1
1 Glossary 7 1 Glossary 4
2 Introduction 10 2 Introduction 7
2.1 Motivation 10 2.1 Motivation 7
2.2 Protocol Overview 10 2.2 Protocol Overview 7
3 LLP and DDP requirements 14 3 MPA's interactions with DDP 11
3.1 TCP implementation Requirements to support MPA 14 4 MPA Full Operation Mode 13
3.1.1 TCP Transmit side 14 4.1 FPDU Format 13
3.1.2 TCP Receive side 14 4.2 Marker Format 14
3.2 MPA's interactions with DDP 16 4.3 MPA Markers 14
4 FPDU Formats 18 4.4 CRC Calculation 17
4.1 Marker Format 19 4.5 FPDU Size Considerations 20
5 Data Transfer Semantics 20 5 MPA's interactions with TCP 22
5.1 MPA Markers 20 5.1 MPA transmitters with a standard layered TCP 23
5.2 CRC Calculation 23 5.2 MPA receivers with a standard layered TCP 24
5.3 MPA on TCP Sender Segmentation 26 5.3 Optimized MPA/TCP transmitters 24
5.3.1 Effects of MPA on TCP Segmentation 27 5.3.1 Effects of Optimized MPA/TCP Segmentation 25
5.3.2 FPDU Size Considerations 29 5.4 Optimized MPA/TCP receivers 27
5.4 MPA Receiver FPDU Identification 30 6 MPA Receiver FPDU Identification 28
5.4.1 Re-segmenting Middle boxes and non MPA-aware TCP senders 31 6.1 Re-segmenting Middle boxes and non optimized MPA/TCP senders29
6 Connection Semantics 32 7 Connection Semantics 30
6.1 Connection setup 32 7.1 Connection setup 30
6.1.1 MPA Request and Reply Frame Format 34 7.1.1 MPA Request and Reply Frame Format 32
6.1.2 Connection Startup Rules 35 7.1.2 Connection Startup Rules 33
6.1.3 Example Delayed Startup sequence 38 7.1.3 Example Delayed Startup sequence 36
6.1.4 Use of Private Data 41 7.1.4 Use of Private Data 39
6.1.5 "Dual stack" implementations 44 7.1.5 "Dual stack" implementations 42
6.2 Normal Connection Teardown 45 7.2 Normal Connection Teardown 43
7 Error Semantics 46 8 Error Semantics 44
8 Security Considerations 47 9 Security Considerations 45
8.1 Protocol-specific Security Considerations 47 9.1 Protocol-specific Security Considerations 45
8.1.1 Spoofing 47 9.1.1 Spoofing 45
8.1.2 Eavesdropping 48 9.1.2 Eavesdropping 46
8.2 Introduction to Security Options 49 9.2 Introduction to Security Options 47
8.3 Using IPsec With MPA 49 9.3 Using IPsec With MPA 47
8.4 Requirements for IPsec Encapsulation of MPA/DDP 50 9.4 Requirements for IPsec Encapsulation of MPA/DDP 48
9 IANA Considerations 51 10 IANA Considerations 49
10 References 52 11 References 50
10.1 Normative References 52 11.1 Normative References 50
10.2 Informative References 52 11.2 Informative References 50
11 Appendix 54 12 Appendix 52
11.1 Analysis of MPA over TCP Operations 54 12.1 Analysis of MPA over TCP Operations 52
11.1.1 Assumptions 55 12.1.1 Assumptions 53
11.1.2 The Value of FPDU Alignment 56 12.1.2 The Value of FPDU Alignment 54
11.2 Receiver implementation 63 12.2 Receiver implementation 61
11.2.1 Network Layer Reassembly Buffers 63 12.2.1 Network Layer Reassembly Buffers 61
11.2.2 TCP Reassembly buffers 64 12.2.2 TCP Reassembly buffers 62
11.3 IETF Implementation Interoperability with RDMA Consortium 12.3 IETF Implementation Interoperability with RDMA Consortium
Protocols 65 Protocols 63
11.3.1 Negotiated Parameters 65 12.3.1 Negotiated Parameters 63
11.3.2 RDMAC RNIC and Non-permissive IETF RNIC 66 12.3.2 RDMAC RNIC and Non-permissive IETF RNIC 64
11.3.3 RDMAC RNIC and Permissive IETF RNIC 68 12.3.3 RDMAC RNIC and Permissive IETF RNIC 66
11.3.4 Non-Permissive IETF RNIC and Permissive IETF RNIC 69 12.3.4 Non-Permissive IETF RNIC and Permissive IETF RNIC 67
12 Author's Addresses 70 13 Author's Addresses 68
13 Acknowledgments 71 14 Acknowledgments 69
Full Copyright Statement 74 Full Copyright Statement 72
Intellectual Property 74 Intellectual Property 72
Table of Figures Table of Figures
Figure 1 ULP MPA TCP Layering 11 Figure 1 ULP MPA TCP Layering 8
Figure 2 FPDU Format 18 Figure 2 FPDU Format 13
Figure 3 Marker Format 19 Figure 3 Marker Format 14
Figure 4 Example FPDU Format with Marker 21 Figure 4 Example FPDU Format with Marker 16
Figure 5 Annotated Hex Dump of an FPDU 25 Figure 5 Annotated Hex Dump of an FPDU 19
Figure 6 Annotated Hex Dump of an FPDU with Marker 26 Figure 6 Annotated Hex Dump of an FPDU with Marker 20
Figure 7 MPA Request/Reply Frame 34 Figure 7 Fully layered implementation 22
Figure 8: Example Delayed Startup negotiation 39 Figure 8 Optimized MPA/TCP implementation 22
Figure 9: Example Immediate Startup negotiation 42 Figure 9 MPA Request/Reply Frame 32
Figure 10: Non-aligned FPDU freely placed in TCP octet stream 58 Figure 10: Example Delayed Startup negotiation 37
Figure 11: Aligned FPDU placed immediately after TCP header 59 Figure 11: Example Immediate Startup negotiation 40
Figure 12. Connection Parameters for the RNIC Types. 66 Figure 12: Non-aligned FPDU freely placed in TCP octet stream 56
Figure 13: MPA negotiation between an RDMAC RNIC and a Non-permissive Figure 13: Aligned FPDU placed immediately after TCP header 57
IETF RNIC. 67 Figure 14. Connection Parameters for the RNIC Types. 64
Figure 14: MPA negotiation between an RDMAC RNIC and a Permissive Figure 15: MPA negotiation between an RDMAC RNIC and a Non-permissive
IETF RNIC. 68 IETF RNIC. 65
Figure 15: MPA negotiation between a Non-permissive IETF RNIC and a Figure 16: MPA negotiation between an RDMAC RNIC and a Permissive
Permissive IETF RNIC. 69 IETF RNIC. 66
Figure 17: MPA negotiation between a Non-permissive IETF RNIC and a
Permissive IETF RNIC. 67
Revision history [To be deleted prior to RFC publication] Revision history [To be deleted prior to RFC publication]
[draft-ietf-rddp-mpa-04] workgroup draft with following changes: [draft-ietf-rddp-mpa-05] workgroup draft with following changes:
Numerous capitalization and "" adjustments, tried to make more
consistent.
Added some missing capitalized terms to glossary
Removed company specific "use as is" boilerplate paragraph
Fixed up some contact information and cross references.
Removed reference to expired draft-elzur-iwarp-mpa-tcp-analysis-
00.txt
Suggested MTU to be used to determine EMSS, when otherwise not
available; removed technology specific lengths per AD suggestion
Tweaked text around disabling Nagle so that it is no longer
implied that that is all that is necessary to achieve proper
segmentation behavior
Revamped section 5.3.1 for improved clarity
[draft-ietf-rddp-mpa-03] workgroup draft with following changes:
Tweaked abstract to give a bit more information.
Tightened definition and usage of "deliver"
Cleaned up usage of terms "FPDU Alignment" and "Header
Alignment"
Rearranged overview sections with stack and glossary earlier
Mentioned how an non-MPA-Aware TCP MPA receiver deals with out
of order segments (it doesn't have to...)
Fixed description of out of order segment handling in section
3.1.1
Added text saying that ordering and completion indications are
used to deliver to DDP
Added redundant text indicating low two bits of FPDUPTR must
always be zero and treated as such in Section 4.1
Added redundant text indicating Markers are always included in a
CRC calculation
Removed indication saying that an implementation can "ignore" an
administrative input to not use CRCs; clarified that both ends
have to agree to not use CRC (as originally intended).
Changed example FPDU hex dump format for greater clarity
Clarified that EMSS shrinking below 128 bytes is the condition
(rather than "very small sizes")
Put connection startup rules after the start frame formats
Added Initiator Private Data to figure 9
Removed or Clarified use of RNIC term
Added intro to IETF/RDMAC interoperability appendix and gave a
web reference for docs; also recommended use of "permissive IETF
RNIC"
Numerous minor clarifications
Updated Boilerplates per current requirements
[draft-ietf-rddp-mpa-02] workgroup draft with following changes:
Made IPsec must implement, optional to use.
Updated Marker language to clarify that it points to ULPDU
Length even when Marker precedes FPDU.
Clarified when to start Markers use (in Full Operation mode).
Added informative text on interoperability with RDMAC RNICs.
Reduced Private Data to 512 octets max.
Clarified CRC use description, must be used unless data is at
least as well protected by another means.
Clarified CRC disabled mode; CRC field is always valid.
Added Security text.
Changed DDP and RDMAP version numbers in hex dumps (Fig 5, 6)
and adjusted CRC accordingly.
[draft-ietf-rddp-mpa-01] workgroup draft with following changes:
Added the "R" bit (Rejected) to the MPA Reply Frame and
described its semantics.
Added some comments on recent decisions regarding startup.
Updated RFC3667 boilerplate.
[draft-ietf-rddp-mpa-00] workgroup draft with following changes:
Changed "Start Key" to two separate startup frames to facilitate
identification of incorrect active/active startup.
Changed Active/Passive nomenclature to Initiator/Responder to
reduce confusion with TCP startup and verbs doc (which used
opposite sense).
Added Private Data to the startup key sequences. This also
required describing the motivation and expected usage models
along with some interface hints. Removed the Private Data stuff
from appendix.
Added example "Immediate" startup with TCP and explanation.
[draft-culley-iwarp-mpa-03]
Add option to allow receivers to specify Marker use.
Add option that allows both sides to agree not to use CRC.
Added startup declaration "Start Key" with options and larger
MPA mode recognition "key".
Updated MPA/DDP connection startup rules and sequence to deal
with "Start Key".
Added Appendix that provides a more detailed analysis of the
effects of MPA on TCP data streams.
Added appendix that describes a mechanism to deal with "Private
Data" prior to full MPA/DDP operation.
[draft-culley-iwarp-mpa-02]
Enhanced descriptions of how MPA is used over an unmodified TCP.
Removed "No Packing" text.
Made MPA an adaptation layer for DDP, instead of a generalized
framing solution.
Added clarifications of the MPA/TCP interaction for optimized Document restructuring to differentiate between fully layered
implementations and that any such optimizations are to be used MPA on TCP implementations and optimized MPA/TCP
only when requested by MPA. implementations. This involved somewhat blurring the artificial
layer between MPA and an MPA-aware TCP. This involved a bit of
terminology change.
[draft-culley-iwarp-mpa-01] initial draft. Re-wrote the requirement to avoid duplicate segments during TCP
out of order passing to MPA; this is now a co-responsibility
between MPA/TCP; also explained that the requirement was to
avoid data corruption through bypassing MPA CRCs and other
checks.
1 Glossary 1 Glossary
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in
this document are to be interpreted as described in RFC 2119. this document are to be interpreted as described in [RFC2119].
Consumer - the ULPs or applications that lie above MPA and DDP. The Consumer - the ULPs or applications that lie above MPA and DDP. The
Consumer is responsible for making TCP connections, starting MPA Consumer is responsible for making TCP connections, starting MPA
and DDP connections, and generally controlling operations. and DDP connections, and generally controlling operations.
Delivery - (Delivered, Delivers) - For MPA, Delivery is defined as Delivery - (Delivered, Delivers) - For MPA, Delivery is defined as
the process of informing DDP that a particular PDU is ordered for the process of informing DDP that a particular PDU is ordered for
use. A PDU is Delivered in the exact order that it was sent by use. A PDU is Delivered in the exact order that it was sent by
the original sender; MPA uses TCP's byte stream ordering to the original sender; MPA uses TCP's byte stream ordering to
determine when Delivery is possible. This is specifically determine when Delivery is possible. This is specifically
skipping to change at page 10, line 8 skipping to change at page 7, line 8
ULPDU - Upper Layer Protocol Data Unit. The data record defined by ULPDU - Upper Layer Protocol Data Unit. The data record defined by
the layer above MPA (DDP). ULPDU corresponds to DDP's DDP the layer above MPA (DDP). ULPDU corresponds to DDP's DDP
segment. segment.
ULPDU_Length - a field in the FPDU describing the length of the ULPDU_Length - a field in the FPDU describing the length of the
included ULPDU. included ULPDU.
2 Introduction 2 Introduction
This section discusses the reason for creating MPA on TCP and a This section discusses the reason for creating MPA on TCP and a
general overview of the protocol. Later sections show the MPA general overview of the protocol.
headers (see section 4 on page 18), and detailed protocol
requirements and characteristics (see section 5 on page 20), as well
as Connection Semantics (section 6 on page 31), Error Semantics
(section 7 on page 46), and Security Considerations (section 8 on
page 47).
2.1 Motivation 2.1 Motivation
The Direct Data Placement protocol [DDP], when used with TCP [RFC793] The Direct Data Placement protocol [DDP], when used with TCP [RFC793]
requires a mechanism to detect record boundaries. The DDP records requires a mechanism to detect record boundaries. The DDP records
are referred to as Upper Layer Protocol Data Units by this document. are referred to as Upper Layer Protocol Data Units by this document.
The ability to locate the Upper Layer Protocol Data Unit (ULPDU) The ability to locate the Upper Layer Protocol Data Unit (ULPDU)
boundary is useful to a hardware network adapter that uses DDP to boundary is useful to a hardware network adapter that uses DDP to
directly place the data in the application buffer based on the directly place the data in the application buffer based on the
control information carried in the ULPDU header. This may be done control information carried in the ULPDU header. This may be done
skipping to change at page 11, line 10 skipping to change at page 8, line 10
2.2 Protocol Overview 2.2 Protocol Overview
The layering of PDUs with MPA is shown in Figure 1, below. The layering of PDUs with MPA is shown in Figure 1, below.
+------------------+ +------------------+
| ULP client | | ULP client |
+------------------+ <- Consumer messages +------------------+ <- Consumer messages
| DDP | | DDP |
+------------------+ <- ULPDUs +------------------+ <- ULPDUs
| MPA | | MPA* |
+------------------+ <- FPDUs (containing ULPDUs) +------------------+ <- FPDUs (containing ULPDUs)
| TCP* | | TCP* |
+------------------+ <- TCP Segments (containing FPDUs) +------------------+ <- TCP Segments (containing FPDUs)
| IP etc. | | IP etc. |
+------------------+ +------------------+
* TCP or MPA-aware TCP. * These may be fully layered or optimized together.
Figure 1 ULP MPA TCP Layering Figure 1 ULP MPA TCP Layering
MPA is described as an extra layer above TCP and below DDP. The MPA is described as an extra layer above TCP and below DDP. The
operation sequence is: operation sequence is:
1. A TCP connection is established by ULP action. This is done 1. A TCP connection is established by ULP action. This is done
using methods not described by this specification. The ULP may using methods not described by this specification. The ULP may
exchange some amount of data in streaming mode prior to starting exchange some amount of data in streaming mode prior to starting
MPA, but is not required to do so. MPA, but is not required to do so.
2. The Consumer negotiates the use of DDP and MPA at both ends of a 2. The Consumer negotiates the use of DDP and MPA at both ends of a
connection. The mechanisms to do this are not described in this connection. The mechanisms to do this are not described in this
specification. The negotiation may be done in streaming mode, or specification. The negotiation may be done in streaming mode, or
by some other mechanism (such as a pre-arranged port number). by some other mechanism (such as a pre-arranged port number).
3. The ULP activates MPA on each end in the Startup Phase, either as 3. The ULP activates MPA on each end in the Startup Phase, either as
an Initiator or a Responder, as determined by the ULP. This mode an Initiator or a Responder, as determined by the ULP. This mode
verifies the usage of MPA, specifies the use of CRC and Markers, verifies the usage of MPA, specifies the use of CRC and Markers,
and allows the ULP to communicate some additional data via a and allows the ULP to communicate some additional data via a
Private Data exchange. See section 6.1 Connection setup for more Private Data exchange. See section 7.1 Connection setup for more
details on the startup process. details on the startup process.
4. At the end of the Startup Phase, the ULP puts MPA (and DDP) into 4. At the end of the Startup Phase, the ULP puts MPA (and DDP) into
Full Operation and begins sending DDP data as further described Full Operation and begins sending DDP data as further described
below. In this document, DDP data chunks are called ULPDUs. For below. In this document, DDP data chunks are called ULPDUs. For
a description of the DDP data, see [DDP]. a description of the DDP data, see [DDP].
Following is a description of data transfer when MPA is in Full Following is a description of data transfer when MPA is in Full
Operation. Operation.
skipping to change at page 12, line 9 skipping to change at page 9, line 9
for this value. MPA derives this information from TCP or IP, for this value. MPA derives this information from TCP or IP,
when it is available, or chooses a reasonable value. when it is available, or chooses a reasonable value.
2. DDP creates ULPDUs of MULPDU size or smaller, and hands them to 2. DDP creates ULPDUs of MULPDU size or smaller, and hands them to
MPA at the sender. MPA at the sender.
3. MPA creates a Framed Protocol Data Unit (FPDU) by pre-pending a 3. MPA creates a Framed Protocol Data Unit (FPDU) by pre-pending a
header, optionally inserting Markers, and appending a CRC field header, optionally inserting Markers, and appending a CRC field
after the ULPDU and PAD (if any). MPA delivers the FPDU to TCP. after the ULPDU and PAD (if any). MPA delivers the FPDU to TCP.
4. The TCP sender puts the FPDUs into the TCP stream. If the TCP 4. The TCP sender puts the FPDUs into the TCP stream. If the sender
Sender is MPA-aware, it segments the TCP stream in such a way is optimized MPA/TCP, it segments the TCP stream in such a way
that a TCP Segment boundary is also the boundary of an FPDU. TCP that a TCP Segment boundary is also the boundary of an FPDU. TCP
then passes each segment to the IP layer for transmission. then passes each segment to the IP layer for transmission.
5. The TCP receiver may be MPA-aware or may not be MPA-aware. If it 5. The receiver may or may not be optimized. If it is optimized
is MPA-aware, it may separate passing the TCP payload to MPA from MPA/TCP, it may separate passing the TCP payload to MPA from
passing the TCP payload ordering information to MPA. In either passing the TCP payload ordering information to MPA. In either
case, RFC compliant TCP wire behavior is observed at both the case, RFC compliant TCP wire behavior is observed at both the
sender and receiver. sender and receiver.
6. The MPA receiver locates and assembles complete FPDUs within the 6. The MPA receiver locates and assembles complete FPDUs within the
stream, verifies their integrity, and removes MPA Markers (when stream, verifies their integrity, and removes MPA Markers (when
present), ULPDU_Length, PAD and the CRC field. present), ULPDU_Length, PAD and the CRC field.
7. MPA then provides the complete ULPDUs to DDP. MPA may also 7. MPA then provides the complete ULPDUs to DDP. MPA may also
separate passing MPA payload to DDP from passing the MPA payload separate passing MPA payload to DDP from passing the MPA payload
ordering information. ordering information.
MPA-aware TCP is a TCP layer which potentially contains some A fully layered MPA on TCP is implemented as a data stream ULP for
additional semantics as defined in this document. MPA is implemented TCP and is therefore RFC compliant.
as a data stream ULP for TCP and is therefore RFC compliant. MPA-
aware TCP is RFC compliant.
An MPA-aware TCP sender is able to segment the data stream such that An optimized MPA/TCP uses a TCP layer which potentially contains some
TCP segments begin with FPDUs (FPDU Alignment). This has significant additional semantics as defined in this document. It is completely
advantages for receivers. When segments arrive with aligned FPDUs interoperable with a fully layered MPA on TCP implementation and is
the receiver usually need not buffer any portion of the segment, also RFC compliant.
allowing DDP to place it in its destination memory immediately, thus
avoiding copies from intermediate buffers (DDP's reason for
existence).
MPA with an MPA-aware TCP receiver allows a DDP on MPA implementation An optimized MPA/TCP sender is able to segment the data stream such
to locate the start of ULPDUs that may be received out of order. It that TCP segments begin with FPDUs (FPDU Alignment). This has
significant advantages for receivers. When segments arrive with
aligned FPDUs the receiver usually need not buffer any portion of the
segment, allowing DDP to place it in its destination memory
immediately, thus avoiding copies from intermediate buffers (DDP's
reason for existence).
An optimized MPA/TCP receiver allows a DDP on MPA implementation to
locate the start of ULPDUs that may be received out of order. It
also allows the implementation to determine if the entire ULPDU has also allows the implementation to determine if the entire ULPDU has
been received. As a result, MPA can pass out of order ULPDUs to DDP been received. As a result, MPA can pass out of order ULPDUs to DDP
for immediate use. This enables a DDP on MPA implementation to save for immediate use. This enables a DDP on MPA implementation to save
a significant amount of intermediate storage by placing the ULPDUs in a significant amount of intermediate storage by placing the ULPDUs in
the right locations in the application buffers when they arrive, the right locations in the application buffers when they arrive,
rather than waiting until full ordering can be restored. rather than waiting until full ordering can be restored.
The ability of a receiver to recover out of order ULPDUs is optional The ability of a receiver to recover out of order ULPDUs is optional
and declared to the transmitter during startup. When the receiver and declared to the transmitter during startup. When the receiver
declares that it does not support out of order recovery, the declares that it does not support out of order recovery, the
transmitter does not add the control information to the data stream transmitter does not add the control information to the data stream
needed for out of order recovery. needed for out of order recovery.
If TCP is not MPA-aware, then MPA receives a strictly ordered stream If the receiver is fully layered, then MPA receives a strictly
of data and does not deal with out of order ULPDUs. In this case MPA ordered stream of data and does not deal with out of order ULPDUs.
passes each ULPDU to DDP when the last bytes arrive from TCP, along In this case MPA passes each ULPDU to DDP when the last bytes arrive
with the indication that they are in order. from TCP, along with the indication that they are in order.
MPA implementations that support recovery of out of order ULPDUs MUST MPA implementations that support recovery of out of order ULPDUs MUST
support a mechanism to indicate the ordering of ULPDUs as the sender support a mechanism to indicate the ordering of ULPDUs as the sender
transmitted them and indicate when missing intermediate segments transmitted them and indicate when missing intermediate segments
arrive. These mechanisms allow DDP to reestablish record ordering arrive. These mechanisms allow DDP to reestablish record ordering
and report Delivery of complete messages (groups of records). and report Delivery of complete messages (groups of records).
MPA also addresses enhanced data integrity. Some users of TCP have MPA also addresses enhanced data integrity. Some users of TCP have
noted that the TCP checksum is not as strong as could be desired (see noted that the TCP checksum is not as strong as could be desired (see
[CRCTCP]). Studies such as [CRCTCP] have shown that the TCP checksum [CRCTCP]). Studies such as [CRCTCP] have shown that the TCP checksum
skipping to change at page 14, line 5 skipping to change at page 11, line 5
MPA includes a CRC check to increase the ULPDU data integrity to the MPA includes a CRC check to increase the ULPDU data integrity to the
level provided by other modern protocols, such as SCTP [RFC2960]. It level provided by other modern protocols, such as SCTP [RFC2960]. It
is possible to disable this CRC check, however CRCs MUST be enabled is possible to disable this CRC check, however CRCs MUST be enabled
unless it is clear that the end to end connection through the network unless it is clear that the end to end connection through the network
has data integrity at least as good as a MPA with CRC enabled (for has data integrity at least as good as a MPA with CRC enabled (for
example when IPsec is implemented end to end). DDP's ULP expects example when IPsec is implemented end to end). DDP's ULP expects
this level of data integrity and therefore the ULP does not have to this level of data integrity and therefore the ULP does not have to
provide its own duplicate data integrity and error recovery for lost provide its own duplicate data integrity and error recovery for lost
data. data.
3 LLP and DDP requirements 3 MPA's interactions with DDP
The following sections describe requirements on TCP and DDP to
utilize MPA. The DDP requirements enable the correct operation over
MPA and TCP (as opposed to DDP over SCTP or other LLPs).
The TCP requirements are mostly intended to support the MPA-aware TCP
variation, which allows implementations that require less buffer
memory and may provide better overall system performance.
3.1 TCP implementation Requirements to support MPA
The TCP implementation MUST inform MPA when the TCP connection is
closed or has begun closing the connection (e.g. received a FIN).
3.1.1 TCP Transmit side
To provide optimum performance, an MPA-aware transmit side TCP
implementation SHOULD be enabled to:
* With an EMSS large enough to contain the FPDU(s), segment the
outgoing TCP stream such that the first octet of every TCP
Segment begins with an FPDU. Multiple FPDUs MAY be packed into a
single TCP segment as long as they are entirely contained in the
TCP segment.
* Report the current EMSS to the MPA transmit layer.
An MPA-aware TCP transmit side implementation MUST continue to use
the method of segmentation expected by non-MPA applications (and
described in TCP RFCs) when MPA is not enabled on the connection.
When MPA is enabled above an MPA-aware TCP, it SHOULD specifically
enable the segmentation rules described above for the DDP segments
(FPDUs) posted for transmission.
If the transmit side TCP implementation is not able to segment the
TCP stream as indicated above, MPA SHOULD make a best effort to
achieve that result. For example, using the TCP_NODELAY socket
option to disable the Nagle algorithm will usually result in many of
the segments starting with an FPDU.
If the transmit side TCP implementation is not able to report the
EMSS, MPA SHOULD use the current MTU value to establish a likely FPDU
size, taking into account the various expected header sizes.
3.1.2 TCP Receive side
When an MPA receive implementation and the MPA-aware receive side TCP
implementation support handling out of order ULPDUs, the TCP receive
implementation SHOULD be enabled to:
* Pass incoming TCP segments to MPA as soon as they have been
received and validated, even if not received in order. The TCP
layer MUST have committed to keeping each segment before it can
be passed to the MPA. This means that the segment must have
passed the TCP, IP, and lower layer data integrity validation
(i.e., checksum), must be in the receive window, must not be a
duplicate, must be part of the same epoch (if timestamps are used
to verify this) and any other checks required by TCP RFCs. The
segment MUST NOT be passed to MPA more than once unless
explicitly requested (see Section 7).
This is not to imply that the data must be completely ordered
before use. An implementation MAY accept out of order segments,
SACK them [RFC2018], and pass them to DDP immediately, before the
reception of the segments needed to fill in the gaps arrive.
Such an implementation MUST "commit" to the data early on, and
MUST NOT overwrite it even if (or when) duplicate data arrives.
MPA expects to utilize this "commit" to allow the passing of
ULPDUs to DDP when they arrive, independent of ordering. DDP
uses the passed ULPDU to "place" the DDP segments (see [DDP] for
more details).
* Provide a mechanism to indicate the ordering of TCP segments as
the sender transmitted them. One possible mechanism might be
attaching the TCP sequence number to each segment.
* Provide a mechanism to indicate when a given TCP segment (and the
prior TCP stream) is complete. One possible mechanism might be
to utilize the leading (left) edge of the TCP Receive Window.
MPA uses the ordering and completion indications to inform DDP
when a ULPDU is complete; MPA Delivers the FPDU to DDP. DDP uses
the indications to "deliver" its messages to the DDP consumer
(see [DDP] for more details).
DDP on MPA MUST utilize these two mechanisms to establish the
Delivery semantics that DDP's consumers agree to. These
semantics are described fully in [DDP]. These include
requirements on DDP's consumer to respect ownership of buffers
prior to the time that DDP delivers them to the Consumer.
An MPA-aware TCP receive side implementation MUST continue to buffer
TCP segments until completely ordered and then deliver them as
expected by non-MPA applications (and described in TCP RFCs) when MPA
is not enabled on the connection. When MPA is enabled above an MPA-
aware TCP, TCP SHOULD enable the in and out of order passing of data,
and the separate ordering information as described above.
When an MPA receive implementation is coupled with a TCP receive
implementation that does not support the preceding mechanisms, TCP
passes and Delivers incoming stream data to MPA in order.
3.2 MPA's interactions with DDP
DDP requires MPA to maintain DDP record boundaries from the sender to DDP requires MPA to maintain DDP record boundaries from the sender to
the receiver. When using MPA on TCP to send data, DDP provides the receiver. When using MPA on TCP to send data, DDP provides
records (ULPDUs) to MPA. MPA will use the reliable transmission records (ULPDUs) to MPA. MPA will use the reliable transmission
abilities of TCP to transmit the data, and will insert appropriate abilities of TCP to transmit the data, and will insert appropriate
additional information into the TCP stream to allow the MPA receiver additional information into the TCP stream to allow the MPA receiver
to locate the record boundary information. to locate the record boundary information.
As such, MPA accepts complete records (ULPDUs) from DDP at the sender As such, MPA accepts complete records (ULPDUs) from DDP at the sender
and returns them to DDP at the receiver. and returns them to DDP at the receiver.
MPA combined with an MPA-aware TCP can only ensure FPDU Alignment MPA MUST encapsulate the ULPDU such that there is exactly one ULPDU
with the TCP Header if the FPDU is less than or equal to TCP's EMSS. contained in one FPDU.
Since FPDU Alignment is generally desired by the receiver, DDP must
cooperate with MPA to ensure FPDUs' lengths do not exceed the EMSS MPA over a standard TCP stack can usually provide FPDU Alignment with
under normal conditions. This is done with the MULPDU mechanism. the TCP Header if the FPDU is equal to TCP's EMSS. An optimized
MPA/TCP stack can also maintain alignment as long as the FPDU is less
than or equal to TCP's EMSS. Since FPDU Alignment is generally
desired by the receiver, DDP must cooperate with MPA to ensure FPDUs'
lengths do not exceed the EMSS under normal conditions. This is done
with the MULPDU mechanism.
MPA provides information to DDP on the current maximum size of the MPA provides information to DDP on the current maximum size of the
record that is acceptable to send (MULPDU). DDP SHOULD limit each record that is acceptable to send (MULPDU). DDP SHOULD limit each
record size to MULPDU. The range of MULPDU values MUST be between record size to MULPDU. The range of MULPDU values MUST be between
128 octets and 64768 octets, inclusive. 128 octets and 64768 octets, inclusive.
The sending DDP MUST NOT post a ULPDU larger than 64768 octets to The sending DDP MUST NOT post a ULPDU larger than 64768 octets to
MPA. DDP MAY post a ULPDU of any size between one and 64768 octets, MPA. DDP MAY post a ULPDU of any size between one and 64768 octets,
however MPA is not REQUIRED to support a ULPDU Length that is greater however MPA is not REQUIRED to support a ULPDU Length that is greater
than the current MULPDU. than the current MULPDU.
skipping to change at page 18, line 5 skipping to change at page 13, line 5
might be to allow DDP to see the current outgoing TCP Ack might be to allow DDP to see the current outgoing TCP Ack
sequence number. sequence number.
* Provide an indication to DDP that the TCP has closed or has begun * Provide an indication to DDP that the TCP has closed or has begun
to close the connection (e.g. received a FIN). to close the connection (e.g. received a FIN).
MPA MUST provide the protocol version negotiated with its peer to MPA MUST provide the protocol version negotiated with its peer to
DDP. DDP will use this version to set the version in its header and DDP. DDP will use this version to set the version in its header and
to report the version to [RDMAP]. to report the version to [RDMAP].
4 FPDU Formats 4 MPA Full Operation Mode
The following sections describe the main semantics of the full
operation mode of MPA.
4.1 FPDU Format
MPA senders create FPDUs out of ULPDUs. The format of an FPDU shown MPA senders create FPDUs out of ULPDUs. The format of an FPDU shown
below MUST be used for all MPA FPDUs. For purposes of clarity, below MUST be used for all MPA FPDUs. For purposes of clarity,
Markers are not shown in Figure 2. Markers are not shown in Figure 2.
0 1 2 3 0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| ULPDU_Length | | | ULPDU_Length | |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +
skipping to change at page 18, line 41 skipping to change at page 13, line 46
support the largest IP datagrams for IPv4 or IPv6. support the largest IP datagrams for IPv4 or IPv6.
PAD: The PAD field trails the ULPDU and contains between zero and PAD: The PAD field trails the ULPDU and contains between zero and
three octets of data. The pad data MUST be set to zero by the sender three octets of data. The pad data MUST be set to zero by the sender
and ignored by the receiver (except for CRC checking). The length of and ignored by the receiver (except for CRC checking). The length of
the pad is set so as to make the size of the FPDU an integral the pad is set so as to make the size of the FPDU an integral
multiple of four. multiple of four.
CRC: 32 bits, When CRCs are enabled, this field contains a CRC32C CRC: 32 bits, When CRCs are enabled, this field contains a CRC32C
check value, which is used to verify the entire contents of the FPDU, check value, which is used to verify the entire contents of the FPDU,
using CRC32C. See section 5.2 CRC Calculation on page 23. When CRCs using CRC32C. See section 4.4 CRC Calculation on page 17. When CRCs
are not enabled, this field is still present, may contain any value, are not enabled, this field is still present, may contain any value,
and MUST NOT be checked. and MUST NOT be checked.
The FPDU adds a minimum of 6 octets to the length of the ULPDU. In The FPDU adds a minimum of 6 octets to the length of the ULPDU. In
addition, the total length of the FPDU will include the length of any addition, the total length of the FPDU will include the length of any
Markers and from 0 to 3 pad octets added to round-up the ULPDU size. Markers and from 0 to 3 pad octets added to round-up the ULPDU size.
4.1 Marker Format 4.2 Marker Format
The format of a Marker MUST be as specified in Figure 3: The format of a Marker MUST be as specified in Figure 3:
0 1 2 3 0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| RESERVED | FPDUPTR | | RESERVED | FPDUPTR |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
Figure 3 Marker Format Figure 3 Marker Format
RESERVED: The Reserved field MUST be set to zero on transmit and RESERVED: The Reserved field MUST be set to zero on transmit and
ignored on receive (except for CRC calculation). ignored on receive (except for CRC calculation).
FPDUPTR: The FPDU Pointer is a relative pointer, 16-bits long, FPDUPTR: The FPDU Pointer is a relative pointer, 16-bits long,
interpreted as an unsigned integer that indicates the number of interpreted as an unsigned integer that indicates the number of
octets in the TCP stream from the beginning of the ULPDU Length field octets in the TCP stream from the beginning of the ULPDU Length field
to the first octet of the entire Marker. The least significant two to the first octet of the entire Marker. The least significant two
bits MUST always be set to zero at the transmitter, and the receivers bits MUST always be set to zero at the transmitter, and the receivers
MUST always treat these as zero for calculations. MUST always treat these as zero for calculations.
5 Data Transfer Semantics 4.3 MPA Markers
This section discusses some characteristics and behavior of the MPA
protocol as well as implications of that protocol.
5.1 MPA Markers
MPA Markers are used to identify the start of FPDUs when packets are MPA Markers are used to identify the start of FPDUs when packets are
received out of order. This is done by locating the Markers at fixed received out of order. This is done by locating the Markers at fixed
intervals in the data stream (which is correlated to the TCP sequence intervals in the data stream (which is correlated to the TCP sequence
number) and using the Marker value to locate the preceding FPDU number) and using the Marker value to locate the preceding FPDU
start. start.
All MPA Markers are included in the containing FPDU CRC calculation All MPA Markers are included in the containing FPDU CRC calculation
(when both CRCs and Markers are in use). (when both CRCs and Markers are in use).
The MPA receiver's ability to locate out of order FPDUs and pass the The MPA receiver's ability to locate out of order FPDUs and pass the
ULPDUs to DDP is implementation dependent. MPA/DDP allows those ULPDUs to DDP is implementation dependent. MPA/DDP allows those
receivers that are able to deal with out of order FPDUs in this way receivers that are able to deal with out of order FPDUs in this way
to require the insertion of Markers in the data stream. When the to require the insertion of Markers in the data stream. When the
receiver cannot deal with out of order FPDUs in this way, it may receiver cannot deal with out of order FPDUs in this way, it may
disable the insertion of Markers at the sender. All MPA senders MUST disable the insertion of Markers at the sender. All MPA senders MUST
be able to generate Markers when their use is declared by the be able to generate Markers when their use is declared by the
opposing receiver (see section 6.1 Connection setup on page 32). opposing receiver (see section 7.1 Connection setup on page 30).
When Markers are enabled, MPA senders MUST insert a Marker into the When Markers are enabled, MPA senders MUST insert a Marker into the
data stream at a 512 octet periodic interval in the TCP Sequence data stream at a 512 octet periodic interval in the TCP Sequence
Number Space. The Marker contains a 16 bit unsigned integer referred Number Space. The Marker contains a 16 bit unsigned integer referred
to as the FPDUPTR (FPDU Pointer). to as the FPDUPTR (FPDU Pointer).
If the FPDUPTR's value is non-zero, the FPDU Pointer is a 16 bit If the FPDUPTR's value is non-zero, the FPDU Pointer is a 16 bit
relative back-pointer. FPDUPTR MUST contain the number of octets in relative back-pointer. FPDUPTR MUST contain the number of octets in
the TCP stream from the beginning of the ULPDU Length field to the the TCP stream from the beginning of the ULPDU Length field to the
first octet of the Marker, unless the Marker falls between FPDUs. first octet of the Marker, unless the Marker falls between FPDUs.
skipping to change at page 21, line 10 skipping to change at page 15, line 24
Marker MUST be included in the CRC calculation of the FPDU following Marker MUST be included in the CRC calculation of the FPDU following
the Marker (if CRCs are being generated or checked). Thus an FPDUPTR the Marker (if CRCs are being generated or checked). Thus an FPDUPTR
value of 0x0000 means that immediately following the Marker is an value of 0x0000 means that immediately following the Marker is an
FPDU header (the ULPDU Length field). FPDU header (the ULPDU Length field).
Since all FPDUs are integral multiples of 4 octets, the bottom two Since all FPDUs are integral multiples of 4 octets, the bottom two
bits of the FPDUPTR as calculated by the sender are zero. MPA bits of the FPDUPTR as calculated by the sender are zero. MPA
reserves these bits so they MUST be treated as zero for computation reserves these bits so they MUST be treated as zero for computation
at the receiver. at the receiver.
When Markers are enabled (see section 6.1 Connection setup on page When Markers are enabled (see section 7.1 Connection setup on page
32), the MPA Markers MUST be inserted immediately preceding the first 30), the MPA Markers MUST be inserted immediately preceding the first
FPDU of Full Operation phase, and at every 512th octet of the TCP FPDU of Full Operation phase, and at every 512th octet of the TCP
octet stream thereafter. As a result, the first Marker has an octet stream thereafter. As a result, the first Marker has an
FPDUPTR value of 0x0000. If the first Marker begins at octet FPDUPTR value of 0x0000. If the first Marker begins at octet
sequence number SeqStart, then Markers are inserted such that the sequence number SeqStart, then Markers are inserted such that the
first octet of the Marker is at octet sequence number SeqNum if the first octet of the Marker is at octet sequence number SeqNum if the
remainder of (SeqNum - SeqStart) mod 512 is zero. Note that SeqNum remainder of (SeqNum - SeqStart) mod 512 is zero. Note that SeqNum
can wrap. can wrap.
For example, if the TCP sequence number were used to calculate the For example, if the TCP sequence number were used to calculate the
insertion point of the Marker, the starting TCP sequence number is insertion point of the Marker, the starting TCP sequence number is
skipping to change at page 22, line 4 skipping to change at page 16, line 23
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| (0x0000) | FPDU ptr (0x000C) | | (0x0000) | FPDU ptr (0x000C) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| ULPDU (octets 10-15) | | ULPDU (octets 10-15) |
| +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| | PAD (2 octets:0,0) | | | PAD (2 octets:0,0) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| CRC | | CRC |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
Figure 4 Example FPDU Format with Marker Figure 4 Example FPDU Format with Marker
MPA Receivers MUST preserve ULPDU boundaries when passing data to MPA Receivers MUST preserve ULPDU boundaries when passing data to
DDP. MPA Receivers MUST pass the ULPDU data and the ULPDU Length to DDP. MPA Receivers MUST pass the ULPDU data and the ULPDU Length to
DDP and not the Markers, headers, and CRC. DDP and not the Markers, headers, and CRC.
5.2 CRC Calculation 4.4 CRC Calculation
An MPA implementation MUST implement CRC support and MUST either: An MPA implementation MUST implement CRC support and MUST either:
(1) always use CRCs; The MPA provider at is not REQUIRED to support (1) always use CRCs; The MPA provider at is not REQUIRED to support
an administrator's request that CRCs not be used. an administrator's request that CRCs not be used.
or or
(2a) only indicate a preference to not use CRCs on the explicit (2a) only indicate a preference to not use CRCs on the explicit
request of the system administrator, via an interface not defined request of the system administrator, via an interface not defined
skipping to change at page 23, line 34 skipping to change at page 17, line 34
from undetected errors as an end-to-end CRC32c. from undetected errors as an end-to-end CRC32c.
The process MUST be invisible to the ULP. The process MUST be invisible to the ULP.
After receipt of an MPA startup declaration indicating that its peer After receipt of an MPA startup declaration indicating that its peer
requires CRCs, an MPA instance MUST continue generating and checking requires CRCs, an MPA instance MUST continue generating and checking
CRCs until the connection terminates. If an MPA instance has CRCs until the connection terminates. If an MPA instance has
declared that it does not require CRCs, it MUST turn off CRC checking declared that it does not require CRCs, it MUST turn off CRC checking
immediately after receipt of an MPA mode declaration indicating that immediately after receipt of an MPA mode declaration indicating that
its peer also does not require CRCs. It MAY continue generating its peer also does not require CRCs. It MAY continue generating
CRCs. See section 6.1 Connection setup on page 32 for details on the CRCs. See section 7.1 Connection setup on page 30 for details on the
MPA startup. MPA startup.
When sending an FPDU, the sender MUST include a CRC field. When CRCs When sending an FPDU, the sender MUST include a CRC field. When CRCs
are enabled, the CRC field in the MPA FPDU MUST be computed using the are enabled, the CRC field in the MPA FPDU MUST be computed using the
CRC32C polynomial in the manner described in the iSCSI Protocol CRC32C polynomial in the manner described in the iSCSI Protocol
[iSCSI] document for Header and Data Digests. [iSCSI] document for Header and Data Digests.
The fields which MUST be included in the CRC calculation when sending The fields which MUST be included in the CRC calculation when sending
an FPDU are as follows: an FPDU are as follows:
skipping to change at page 24, line 36 skipping to change at page 18, line 36
MUST first perform the following: MUST first perform the following:
1) Calculate the CRC of the incoming FPDU in the same fashion as 1) Calculate the CRC of the incoming FPDU in the same fashion as
defined above. defined above.
2) Verify that the calculated CRC-32c value is the same as the 2) Verify that the calculated CRC-32c value is the same as the
received CRC-32c value found in the FPDU CRC field. If not, the received CRC-32c value found in the FPDU CRC field. If not, the
receiver MUST treat the FPDU as an invalid FPDU. receiver MUST treat the FPDU as an invalid FPDU.
The procedure for handling invalid FPDUs is covered in the Error The procedure for handling invalid FPDUs is covered in the Error
Section (see section 7 on page 46) Section (see section 8 on page 44)
The following is an annotated hex dump of an example FPDU sent as the The following is an annotated hex dump of an example FPDU sent as the
first FPDU on the stream. As such, it starts with a Marker. The first FPDU on the stream. As such, it starts with a Marker. The
FPDU contains a 42 octet ULPDU (an example DDP segment) which in turn FPDU contains a 42 octet ULPDU (an example DDP segment) which in turn
contains 24 octets of the contained ULPDU, which is a data load that contains 24 octets of the contained ULPDU, which is a data load that
is all zeros. The CRC32c has been correctly calculated and can be is all zeros. The CRC32c has been correctly calculated and can be
used as a reference. See the [DDP] and [RDMAP] specification for used as a reference. See the [DDP] and [RDMAP] specification for
definitions of the DDP Control field, Queue, MSN, MO, and Send Data. definitions of the DDP Control field, Queue, MSN, MO, and Send Data.
Octet Contents Annotation Octet Contents Annotation
skipping to change at page 26, line 45 skipping to change at page 20, line 45
0203 14 0203 14
0204 00 DDP Send Data (24 octets of zeros) 0204 00 DDP Send Data (24 octets of zeros)
... ...
021b 00 021b 00
021c 84 CRC32c 021c 84 CRC32c
021d 92 021d 92
021e 58 021e 58
021f 98 021f 98
Figure 6 Annotated Hex Dump of an FPDU with Marker Figure 6 Annotated Hex Dump of an FPDU with Marker
5.3 MPA on TCP Sender Segmentation 4.5 FPDU Size Considerations
MPA defines the Maximum Upper Layer Protocol Data Unit (MULPDU) as
the size of the largest ULPDU fitting in an FPDU. For an empty TCP
Segment, MULPDU is EMSS minus the FPDU overhead (6 octets) minus
space for Markers and pad octets.
The maximum ULPDU Length for a single ULPDU when Markers are
present MUST be computed as:
MULPDU = EMSS - (6 + 4 * Ceiling(EMSS / 512) + EMSS mod 4)
The formula above accounts for the worst-case number of Markers.
The maximum ULPDU Length for a single ULPDU when Markers are NOT
present MUST be computed as:
MULPDU = EMSS - (6 + EMSS mod 4)
As a further optimization of the wire efficiency an MPA
implementation MAY dynamically adjust the MULPDU (see section 5 for
latency and wire efficiency trade-offs). When one or more FPDUs are
already packed into a TCP Segment, MULPDU MAY be reduced accordingly.
DDP SHOULD provide ULPDUs that are as large as possible, but less
than or equal to MULPDU.
If the TCP implementation needs to adjust EMSS to support MTU changes
or changing TCP options, the MULPDU value is changed accordingly.
In certain rare situations, the EMSS may shrink below 128 octets in
size. If this occurs, the MPA on TCP sender MUST NOT shrink the
MULPDU below 128 octets and is not REQUIRED to follow the
segmentation rules in Sections 5.1 and 5.3.
If one or more FPDUs are already packed into a TCP segment, such that
the remaining room is less than 128 octets, MPA MUST NOT provide a
MULPDU smaller than 128. In this case, MPA would typically provide a
MULPDU for the next full sized segment, but may still pack the next
FPDU into the small remaining room, provide that the next FPDU is
small enough to fit.
The value 128 is chosen as to allow DDP designers room for the DDP
Header and some user data.
5 MPA's interactions with TCP
The following sections describe MPA's interactions with TCP. We will
discuss two significant cases; using a standard layered TCP stack
with MPA attached above a TCP socket, and using an optimized MPA-
aware TCP with an MPA implementation that takes advantage of the
extra optimizations. Other implementations are possible.
+-----------------------------------+
| +-----+ +-----------------+ |
| | MPA | | Other Protocols | |
| +-----+ +-----------------+ |
| || || |
| ----- socket API -------------- |
| || |
| +-----+ |
| | TCP | |
| +-----+ |
| || |
| +-----+ |
| | IP | |
| +-----+ |
+-----------------------------------+
Figure 7 Fully layered implementation
The Fully layered implementation is described for completeness;
however, the user is cautioned that the reduced probability of FPDU
alignment when transmitting with this implementation will tend to
introduce a higher overhead at optimized receivers. In addition, the
lack of out-of-order receive processing will significantly reduce the
value of DDP/MPA by imposing higher buffering and copying overhead in
the local receiver.
+-----------------------------------+
| +-----------+ +-----------------+ |
| | Optimized | | Other Protocols | |
| | MPA/TCP | +-----------------+ |
| +-----------+ || |
| \\ --- socket API --- |
| \\ || |
| \\ +-----+ |
| \\ | TCP | |
| \\ +-----+ |
| \\ // |
| +-------+ |
| | IP | |
| +-------+ |
+-----------------------------------+
Figure 8 Optimized MPA/TCP implementation
The optimized MPA/TCP implementations described below are only
applicable to MPA, all other TCP applications continue to use the
standard TCP stacks and interfaces.
5.1 MPA transmitters with a standard layered TCP
MPA transmitters SHOULD calculate a MULPDU as described in section
4.5 If the TCP implementation allows EMSS to be determined by MPA,
that value should be used. If the transmit side TCP implementation
is not able to report the EMSS, MPA SHOULD use the current MTU value
to establish a likely FPDU size, taking into account the various
expected header sizes.
MPA transmitters SHOULD also use whatever facilities the TCP stack
presents to cause the TCP transmitter to start TCP segments at FPDU
boundaries. Multiple FPDUs MAY be packed into a single TCP segment
as determined by the EMSS calculation as long as they are entirely
contained in the TCP segment.
For example, passing FPDU buffers sized to the current EMSS to the
TCP socket and using the TCP_NODELAY socket option to disable the
Nagle [RFC0896] algorithm will usually result in many of the segments
starting with an FPDU.
It is recognized that various effects can cause a FPDU alignment to
be lost. Following are a few of the effects:
* ULPDUs that are smaller than the MULPDU. If these are sent in a
continuous stream, FPDU alignment will be lost. Note that
careful use of a dynamic MULPDU can help in this case; the MULPDU
for future FPDUs can be adjusted to re-establish alignment with
the segments based on the current EMSS.
* Sending enough data that the TCP receive window limit is reached.
TCP may send a smaller segment to exactly fill the receive
window.
* Sending data when TCP is operating up against the congestion
window. If TCP is not tracking the congestion window in
segments, it may transmit a smaller segment to exactly fill the
receive window.
* Changes in EMSS due to varying TCP options, or changes in MTU.
If FPDU alignment with TCP segments is lost for any reason, the
alignment is regained after a break in transmission where the TCP
send buffers are emptied. Many usage models for DDP/MPA will include
such breaks.
MPA receivers are REQUIRED to be able to operate correctly even if
alignment is lost (see section 6).
5.2 MPA receivers with a standard layered TCP
MPA receivers will get TCP data in the usual ordered stream. The
receivers MUST identify FPDU boundaries by using the ULPDU_LENGTH
field, as described in section 6. Receivers MAY utilize markers to
check for FPDU boundary consistency, but they are NOT required to
examine the markers to determine the FPDU boundaries.
5.3 Optimized MPA/TCP transmitters
The various TCP RFCs allow considerable choice in segmenting a TCP The various TCP RFCs allow considerable choice in segmenting a TCP
stream. In order to optimize FPDU recovery at the MPA receiver, MPA stream. In order to optimize FPDU recovery at the MPA receiver, an
specifies additional segmentation rules. optimized MPA/TCP implementation uses additional segmentation rules.
MPA MUST encapsulate the ULPDU such that there is exactly one ULPDU To provide optimum performance, an optimized MPA/TCP transmit side
contained in one FPDU. implementation SHOULD be enabled to:
An MPA-aware TCP sender SHOULD, when enabled for MPA, on TCP * With an EMSS large enough to contain the FPDU(s), segment the
implementations that support this, and with an EMSS large enough to outgoing TCP stream such that the first octet of every TCP
contain at least one FPDU, segment the outbound TCP stream such that Segment begins with an FPDU. Multiple FPDUs MAY be packed into a
each TCP segment begins with an FPDU, and fully contains all included single TCP segment as long as they are entirely contained in the
FPDUs. TCP segment.
Implementation note: To achieve the previous segmentation rule, * Report the current EMSS from the TCP to the MPA transmit layer.
an MPA-aware TCP sender implementation SHOULD disable TCP's
Nagle [RFC0896] algorithm, communicate the FPDU boundaries to
TCP, and make other minor changes such as the reporting of EMSS
to MPA.
There are exceptions to the above rule. Once an ULPDU is provided to There are exceptions to the above rule. Once an ULPDU is provided to
MPA, the MPA on TCP sender MUST transmit it or fail the connection; MPA, the MPA/TCP sender MUST transmit it or fail the connection; it
it cannot be repudiated. As a result, during changes in MTU and cannot be repudiated. As a result, during changes in MTU and EMSS,
EMSS, or when TCP's Receive Window size (RWIN) becomes too small, it or when TCP's Receive Window size (RWIN) becomes too small, it may be
may be necessary to send FPDUs that do not conform to the necessary to send FPDUs that do not conform to the segmentation rule
segmentation rule above. above.
A possible, but less desirable, alternative is to use IP A possible, but less desirable, alternative is to use IP
fragmentation on accepted FPDUs to deal with MTU reductions or fragmentation on accepted FPDUs to deal with MTU reductions or
extremely small EMSS. extremely small EMSS.
The sender MUST still format the FPDU according to FPDU format as The sender MUST still format the FPDU according to FPDU format as
shown in Figure 2. shown in Figure 2.
On a retransmission, TCP does not necessarily preserve original TCP On a retransmission, TCP does not necessarily preserve original TCP
segmentation boundaries. This can lead to the loss of FPDU Alignment segmentation boundaries. This can lead to the loss of FPDU Alignment
and containment within a TCP segment during TCP retransmissions. An and containment within a TCP segment during TCP retransmissions. An
MPA-aware TCP sender SHOULD try to preserve original TCP segmentation optimized MPA/TCP sender SHOULD try to preserve original TCP
boundaries on a retransmission. segmentation boundaries on a retransmission.
5.3.1 Effects of MPA on TCP Segmentation 5.3.1 Effects of Optimized MPA/TCP Segmentation
DDP/MPA senders will fill TCP segments to the EMSS with a single FPDU Optimized MPA/TCP senders will fill TCP segments to the EMSS with a
when a DDP message is large enough. Since the DDP message may not single FPDU when a DDP message is large enough. Since the DDP
exactly fit into TCP segments, a "message tail" often occurs that message may not exactly fit into TCP segments, a "message tail" often
results in an FPDU that is smaller than a single TCP segment. occurs that results in an FPDU that is smaller than a single TCP
Additionally some DDP messages may be considerably shorter than the segment. Additionally some DDP messages may be considerably shorter
EMSS. If a small FPDU is sent in a single TCP segment the result is than the EMSS. If a small FPDU is sent in a single TCP segment the
a "short" TCP segment. result is a "short" TCP segment.
Applications expected to see strong advantages from Direct Data Applications expected to see strong advantages from Direct Data
Placement include transaction-based applications and throughput Placement include transaction-based applications and throughput
applications. Request/response protocols typically send one FPDU per applications. Request/response protocols typically send one FPDU per
TCP segment and then wait for a response. Under these conditions, TCP segment and then wait for a response. Under these conditions,
these "short" TCP segments are an appropriate and expected effect of these "short" TCP segments are an appropriate and expected effect of
the segmentation. the segmentation.
Another possibility is that the application might be sending multiple Another possibility is that the application might be sending multiple
messages (FPDUs) to the same endpoint before waiting for a response. messages (FPDUs) to the same endpoint before waiting for a response.
skipping to change at page 28, line 4 skipping to change at page 25, line 24
Applications expected to see strong advantages from Direct Data Applications expected to see strong advantages from Direct Data
Placement include transaction-based applications and throughput Placement include transaction-based applications and throughput
applications. Request/response protocols typically send one FPDU per applications. Request/response protocols typically send one FPDU per
TCP segment and then wait for a response. Under these conditions, TCP segment and then wait for a response. Under these conditions,
these "short" TCP segments are an appropriate and expected effect of these "short" TCP segments are an appropriate and expected effect of
the segmentation. the segmentation.
Another possibility is that the application might be sending multiple Another possibility is that the application might be sending multiple
messages (FPDUs) to the same endpoint before waiting for a response. messages (FPDUs) to the same endpoint before waiting for a response.
In this case, the segmentation policy would tend to reduce the In this case, the segmentation policy would tend to reduce the
available connection bandwidth by under-filling the TCP segments. available connection bandwidth by under-filling the TCP segments.
TCP implementations often utilize the Nagle [RFC0896] algorithm to Standard TCP implementations often utilize the Nagle [RFC0896]
ensure that segments are filled to the EMSS whenever the round trip algorithm to ensure that segments are filled to the EMSS whenever the
latency is large enough that the source stream can fully fill round trip latency is large enough that the source stream can fully
segments before Acks arrive. The algorithm does this by delaying the fill segments before Acks arrive. The algorithm does this by
transmission of TCP segments until a ULP can fill a segment, or until delaying the transmission of TCP segments until a ULP can fill a
an ACK arrives from the far side. The algorithm thus allows for segment, or until an ACK arrives from the far side. The algorithm
smaller segments when latencies are shorter to keep the ULP's end to thus allows for smaller segments when latencies are shorter to keep
end latency to reasonable levels. the ULP's end to end latency to reasonable levels.
The Nagle algorithm is not mandatory to use [RFC1122]. The Nagle algorithm is not mandatory to use [RFC1122].
If Nagle or other algorithms for detecting the availability of When used with optimized MPA/TCP stacks, Nagle and similar algorithms
multiple FPDUs for transmission is used, "packing" of multiple FPDUs can result in the "packing" of multiple FPDUs into TCP segments.
into TCP segments can occur.
If a "message tail", small DDP messages, or the start of a larger DDP If a "message tail", small DDP messages, or the start of a larger DDP
message are available, MPA MAY pack multiple FPDUs into TCP segments. message are available, MPA MAY pack multiple FPDUs into TCP segments.
When this is done, the TCP segments can be more fully utilized, but, When this is done, the TCP segments can be more fully utilized, but,
due to the size constraints of FPDUs, segments may not be filled to due to the size constraints of FPDUs, segments may not be filled to
the EMSS. the EMSS. A dynamic MULPDU that informs DDP of the size of the
remaining TCP segment space makes filling the TCP segment more
effective.
Note that MPA receivers must do more processing of a TCP segment Note that MPA receivers must do more processing of a TCP segment
that contains multiple FPDUs, this may affect the performance of that contains multiple FPDUs, this may affect the performance of
some receiver implementations. some receiver implementations.
It is up to the ULP to decide if Nagle is useful with DDP/MPA. Note It is up to the ULP to decide if Nagle is useful with DDP/MPA. Note
that many of the applications expected to take advantage of MPA/DDP that many of the applications expected to take advantage of MPA/DDP
prefer to avoid the extra delays caused by Nagle. In such scenarios prefer to avoid the extra delays caused by Nagle. In such scenarios
it is anticipated there will be minimal opportunity for packing at it is anticipated there will be minimal opportunity for packing at
the transmitter and receivers may choose to optimize their the transmitter and receivers may choose to optimize their
performance for this anticipated behavior. performance for this anticipated behavior.
Therefore, the application is expected to set TCP parameters such Therefore, the application is expected to set TCP parameters such
that it can trade off latency and wire efficiency. This is that it can trade off latency and wire efficiency. This is
accomplished by setting the TCP_NODELAY socket option (which disables accomplished by setting the TCP_NODELAY socket option (which disables
Nagle). Nagle).
When latency is not critical, application is expected to leave Nagle When latency is not critical, application is expected to leave Nagle
enabled. In this case the TCP implementation may pack any available enabled. In this case the TCP implementation may pack any available
stream data into TCP segments so that the segments are filled to the FPDUs into TCP segments so that the segments are filled to the EMSS.
EMSS. If the amount of data available is not enough to fill the TCP If the amount of data available is not enough to fill the TCP segment
segment when it is prepared for transmission, TCP can send the when it is prepared for transmission, TCP can send the segment partly
segment partly filled, or use the Nagle algorithm to wait for the ULP filled, or use the Nagle algorithm to wait for the ULP to post more
to post more data (discussed below). data.
5.3.2 FPDU Size Considerations
MPA defines the Maximum Upper Layer Protocol Data Unit (MULPDU) as
the size of the largest ULPDU fitting in an FPDU. For an empty TCP
Segment, MULPDU is EMSS minus the FPDU overhead (6 octets) minus
space for Markers and pad octets.
The maximum ULPDU Length for a single ULPDU when Markers are
present MUST be computed as:
MULPDU = EMSS - (6 + 4 * Ceiling(EMSS / 512) + EMSS mod 4)
The formula above accounts for the worst-case number of Markers. 5.4 Optimized MPA/TCP receivers
The maximum ULPDU Length for a single ULPDU when Markers are NOT When an MPA receive implementation and the MPA-aware receive side TCP
present MUST be computed as: implementation support handling out of order ULPDUs, the TCP receive
implementation SHOULD be enabled to perform the following functions:
MULPDU = EMSS - (6 + EMSS mod 4) 1) The implementation SHOULD pass incoming TCP segments to MPA as
soon as they have been received and validated, even if not
received in order. The TCP layer MUST have committed to keeping
each segment before it can be passed to the MPA. This means that
the segment must have passed the TCP, IP, and lower layer data
integrity validation (i.e., checksum), must be in the receive
window, must be part of the same epoch (if timestamps are used to
verify this) and any other checks required by TCP RFCs.
As a further optimization of the wire efficiency an MPA This is not to imply that the data must be completely ordered
implementation MAY dynamically adjust the MULPDU (see section 5.3.1 before use. An implementation MAY accept out of order segments,
for latency and wire efficiency trade-offs). When one or more FPDUs SACK them [RFC2018], and pass them to MPA immediately, before the
are already packed into a TCP Segment, MULPDU MAY be reduced reception of the segments needed to fill in the gaps arrive.
accordingly. MPA expects to utilize these segments when they are complete
FPDUs or can be combined into complete FPDUs to allow the passing
of ULPDUs to DDP when they arrive, independent of ordering. DDP
uses the passed ULPDU to "place" the DDP segments (see [DDP] for
more details).
DDP SHOULD provide ULPDUs that are as large as possible, but less Since MPA performs a CRC calculation and other checks on received
than or equal to MULPDU. FPDUs, the MPA/TCP implementation MUST ensure that any TCP
segments that duplicate data already received and processed (as
can happen during TCP retries) do not overwrite already received
and processed FPDUs. This avoids the possibility that duplicate
data may corrupt already validated FPDUs.
If the TCP implementation needs to adjust EMSS to support MTU 2) The implementation MUST provide a mechanism to indicate the
changes, the MULPDU value is changed accordingly. ordering of TCP segments as the sender transmitted them. One
possible mechanism might be attaching the TCP sequence number to
each segment.
In certain rare situations, the EMSS may shrink below 128 octets in 3) The implementation MUST provide a mechanism to indicate when a
size. If this occurs, the MPA on TCP sender MUST NOT shrink the given TCP segment (and the prior TCP stream) is complete. One
MULPDU below 128 octets and is not REQUIRED to follow the possible mechanism might be to utilize the leading (left) edge of
segmentation rules in Section 5.3 MPA on TCP Sender Segmentation on the TCP Receive Window.
page 26.
If one or more FPDUs are already packed into a TCP segment, such that MPA uses the ordering and completion indications to inform DDP
the remaining room is less than 128 octets, MPA MUST NOT provide a when a ULPDU is complete; MPA Delivers the FPDU to DDP. DDP uses
MULPDU smaller than 128. In this case, MPA would typically provide a the indications to "deliver" its messages to the DDP consumer
MULPDU for the next full sized segment, but may still pack the next (see [DDP] for more details).
FPDU into the small remaining room, provide that the next FPDU is
small enough to fit.
The value 128 is chosen as to allow DDP designers room for the DDP DDP on MPA MUST utilize these two mechanisms to establish the
Header and some user data. Delivery semantics that DDP's consumers agree to. These
semantics are described fully in [DDP]. These include
requirements on DDP's consumer to respect ownership of buffers
prior to the time that DDP delivers them to the Consumer.
5.4 MPA Receiver FPDU Identification 6 MPA Receiver FPDU Identification
An MPA receiver MUST first verify the FPDU before passing the ULPDU An MPA receiver MUST first verify the FPDU before passing the ULPDU
to DDP. To do this, the receiver MUST: to DDP. To do this, the receiver MUST:
* locate the start of the FPDU unambiguously, * locate the start of the FPDU unambiguously,
* verify its CRC (if CRC checking is enabled). * verify its CRC (if CRC checking is enabled).
If the above conditions are true, the MPA receiver passes the ULPDU If the above conditions are true, the MPA receiver passes the ULPDU
to DDP. to DDP.
To detect the start of the FPDU unambiguously one of the following To detect the start of the FPDU unambiguously one of the following
MUST be used: MUST be used:
1: In an ordered TCP stream, the ULPDU Length field in the current 1: In an ordered TCP stream, the ULPDU Length field in the current
FPDU when FPDU has a valid CRC, can be used to identify the FPDU when FPDU has a valid CRC, can be used to identify the
beginning of the next FPDU. beginning of the next FPDU.
2: For receivers that support out of order reception of FPDUs (see 2: For optimized MPA/TCP receivers that support out of order
section 5.1 MPA Markers on page 20) a Marker can always be used reception of FPDUs (see section 4.3 MPA Markers on page 14) a
to locate the beginning of an FPDU (in FPDUs with valid CRCs). Marker can always be used to locate the beginning of an FPDU (in
Since the location of the Marker is known in the octet stream FPDUs with valid CRCs). Since the location of the Marker is
(sequence number space), the Marker can always be found. known in the octet stream (sequence number space), the Marker can
always be found.
3: Having found an FPDU by means of a Marker, following contiguous 3: Having found an FPDU by means of a Marker, an optimized MPA/TCP
FPDUs can be found by using the ULPDU Length fields (from FPDUs receiver can find following contiguous FPDUs by using the ULPDU
with valid CRCs) to establish the next FPDU boundary. Length fields (from FPDUs with valid CRCs) to establish the next
FPDU boundary.
The ULPDU Length field (see section 4) MUST be used to determine if The ULPDU Length field (see section 4) MUST be used to determine if
the entire FPDU is present before forwarding the ULPDU to DDP. the entire FPDU is present before forwarding the ULPDU to DDP.
CRC calculation is discussed in section 5.2 on page 23 above. CRC calculation is discussed in section 4.4 on page 17 above.
5.4.1 Re-segmenting Middle boxes and non MPA-aware TCP senders 6.1 Re-segmenting Middle boxes and non optimized MPA/TCP senders
Since MPA on MPA-aware TCP senders start FPDUs on TCP segment Since MPA senders often start FPDUs on TCP segment boundaries, a
boundaries, a receiving DDP on MPA on TCP implementation may be able receiving optimized MPA/TCP implementation may be able to optimize
to optimize the reception of data in various ways. the reception of data in various ways.
However, MPA receivers MUST NOT depend on FPDU Alignment on TCP However, MPA receivers MUST NOT depend on FPDU Alignment on TCP
segment boundaries. segment boundaries.
Some MPA senders may be unable to conform to the sender requirements Some MPA senders may be unable to conform to the sender requirements
because their implementation of TCP is not designed with MPA in mind. because their implementation of TCP is not designed with MPA in mind.
Even if the sender is MPA-aware, the network may contain "middle Even for optimized MPA/TCP senders, the network may contain "middle
boxes" which modify the TCP stream by changing the segmentation. boxes" which modify the TCP stream by changing the segmentation.
This is generally interoperable with TCP and its users and MPA must This is generally interoperable with TCP and its users and MPA must
be no exception. be no exception.
The presence of Markers in MPA (when enabled) allows an MPA receiver The presence of Markers in MPA (when enabled) allows an optimized
to recover the FPDUs despite these obstacles, although it may be MPA/TCP receiver to recover the FPDUs despite these obstacles,
necessary to utilize additional buffering at the receiver to do so. although it may be necessary to utilize additional buffering at the
receiver to do so.
Some of the cases that a receiver may have to contend with are listed Some of the cases that a receiver may have to contend with are listed
below as a reminder to the implementer: below as a reminder to the implementer:
* A single Aligned and complete FPDU, either in order, or out of * A single Aligned and complete FPDU, either in order, or out of
order: This can be passed to DDP as soon as validated, and order: This can be passed to DDP as soon as validated, and
Delivered when ordering is established. Delivered when ordering is established.
* Multiple FPDUs in a TCP segment, aligned and fully contained, * Multiple FPDUs in a TCP segment, aligned and fully contained,
either in order, or out of order: These can be passed to DDP as either in order, or out of order: These can be passed to DDP as
skipping to change at page 32, line 5 skipping to change at page 30, line 5
DDP as soon as validated, and Delivered when ordering is DDP as soon as validated, and Delivered when ordering is
established. If the whole FPDU is not available, the receiver established. If the whole FPDU is not available, the receiver
should buffer until the remainder of the FPDU arrives. should buffer until the remainder of the FPDU arrives.
* Combinations of Unaligned or incomplete FPDUs (and potentially * Combinations of Unaligned or incomplete FPDUs (and potentially
other complete FPDUs) in the same TCP segment: If any FPDU is other complete FPDUs) in the same TCP segment: If any FPDU is
present in its entirety, or can be completed with portions present in its entirety, or can be completed with portions
already available, it can be passed to DDP as soon as validated, already available, it can be passed to DDP as soon as validated,
and Delivered when ordering is established. and Delivered when ordering is established.
6 Connection Semantics 7 Connection Semantics
6.1 Connection setup 7.1 Connection setup
MPA requires that the Consumer MUST activate MPA, and any TCP MPA requires that the Consumer MUST activate MPA, and any TCP
enhancements for MPA, on a TCP half connection at the same location enhancements for MPA, on a TCP half connection at the same location
in the octet stream at both the sender and the receiver. This is in the octet stream at both the sender and the receiver. This is
required in order for the Marker scheme to correctly locate the required in order for the Marker scheme to correctly locate the
Markers (if enabled) and to correctly locate the first FPDU. Markers (if enabled) and to correctly locate the first FPDU.
MPA, and any TCP enhancements for MPA are enabled by the ULP in both MPA, and any TCP enhancements for MPA are enabled by the ULP in both
directions at once at an endpoint. directions at once at an endpoint.
This can be accomplished several ways, and is left up to DDP's ULP: This can be accomplished several ways, and is left up to DDP's ULP:
* DDP's ULP MAY require DDP on MPA startup immediately after TCP * DDP's ULP MAY require DDP on MPA startup immediately after TCP
connection setup. This has the advantage that no streaming mode connection setup. This has the advantage that no streaming mode
negotiation is needed. An example of such a protocol is shown in negotiation is needed. An example of such a protocol is shown in
Figure 9: Example Immediate Startup negotiation on page 42. Figure 11: Example Immediate Startup negotiation on page 40.
This may be accomplished by using a well-known port, or a service This may be accomplished by using a well-known port, or a service
locator protocol to locate an appropriate port on which DDP on locator protocol to locate an appropriate port on which DDP on
MPA is expected to operate. MPA is expected to operate.
* DDP's ULP MAY negotiate the start of DDP on MPA sometime after a * DDP's ULP MAY negotiate the start of DDP on MPA sometime after a
normal TCP startup, using TCP streaming data exchanges on the normal TCP startup, using TCP streaming data exchanges on the
same connection. The exchange establishes that DDP on MPA (as same connection. The exchange establishes that DDP on MPA (as
well as other ULPs) will be used, and exactly locates the point well as other ULPs) will be used, and exactly locates the point
in the octet stream where MPA is to begin operation. Note that in the octet stream where MPA is to begin operation. Note that
such a negotiation protocol is outside the scope of this such a negotiation protocol is outside the scope of this
specification. A simplified example of such a protocol is shown specification. A simplified example of such a protocol is shown
in Figure 8: Example Delayed Startup negotiation on page 39. in Figure 10: Example Delayed Startup negotiation on page 37.
An MPA endpoint operates in two distinct phases. An MPA endpoint operates in two distinct phases.
The Startup Phase is used to verify correct MPA setup, exchange CRC The Startup Phase is used to verify correct MPA setup, exchange CRC
and Marker configuration, and optionally pass Private Data between and Marker configuration, and optionally pass Private Data between
endpoints prior to completing a DDP connection. During this phase, endpoints prior to completing a DDP connection. During this phase,
specifically formatted frames are exchanged as TCP byte streams specifically formatted frames are exchanged as TCP byte streams
without using CRCs or Markers. During this phase a DDP endpoint need without using CRCs or Markers. During this phase a DDP endpoint need
not be "bound" to the MPA connection. In fact, the choice of DDP not be "bound" to the MPA connection. In fact, the choice of DDP
endpoint and its operating parameters may not be known until the endpoint and its operating parameters may not be known until the
skipping to change at page 34, line 5 skipping to change at page 32, line 5
they can be rejected and an error reported. they can be rejected and an error reported.
The ULP is responsible for determining which side is Initiator or The ULP is responsible for determining which side is Initiator or
Responder. For client/server type ULPs this is easy. For peer-peer Responder. For client/server type ULPs this is easy. For peer-peer
ULPs (which might utilize a TCP style active/active startup), some ULPs (which might utilize a TCP style active/active startup), some
mechanism (not defined by this specification) must be established, or mechanism (not defined by this specification) must be established, or
some streaming mode data exchanged prior to MPA startup to determine some streaming mode data exchanged prior to MPA startup to determine
the side which starts in Initiator and which starts in Responder MPA the side which starts in Initiator and which starts in Responder MPA
mode. mode.
6.1.1 MPA Request and Reply Frame Format 7.1.1 MPA Request and Reply Frame Format
0 1 2 3 0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
0 | | 0 | |
+ Key (16 bytes containing "MPA ID Req Frame") + + Key (16 bytes containing "MPA ID Req Frame") +
4 | (4D 50 41 20 49 44 20 52 65 71 20 46 72 61 6D 65) | 4 | (4D 50 41 20 49 44 20 52 65 71 20 46 72 61 6D 65) |
+ Or (16 bytes containing "MPA ID Rep Frame") + + Or (16 bytes containing "MPA ID Rep Frame") +
8 | (4D 50 41 20 49 44 20 52 65 70 20 46 72 61 6D 65) | 8 | (4D 50 41 20 49 44 20 52 65 70 20 46 72 61 6D 65) |
+ + + +
skipping to change at page 34, line 27 skipping to change at page 32, line 27
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
16 |M|C|R| Res | Rev | PD_Length | 16 |M|C|R| Res | Rev | PD_Length |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| | | |
~ ~ ~ ~
~ Private Data ~ ~ Private Data ~
| | | |
| +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| | | |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
Figure 7 MPA Request/Reply Frame Figure 9 MPA Request/Reply Frame
Key: This field contains the "key" used to validate that the sender Key: This field contains the "key" used to validate that the sender
is an MPA sender. Initiator mode senders MUST set this field to is an MPA sender. Initiator mode senders MUST set this field to
the fixed value "MPA ID Req frame" or (in byte order) 4D 50 41 20 the fixed value "MPA ID Req frame" or (in byte order) 4D 50 41 20
49 44 20 52 65 71 20 46 72 61 6D 65 (in hexadecimal). Responder 49 44 20 52 65 71 20 46 72 61 6D 65 (in hexadecimal). Responder
mode receivers MUST check this field for the same value, and mode receivers MUST check this field for the same value, and
close the connection and report an error locally if any other close the connection and report an error locally if any other
value is detected. Responder mode senders MUST set this field to value is detected. Responder mode senders MUST set this field to
the fixed value "MPA ID Rep frame" or (in byte order) 4D 50 41 20 the fixed value "MPA ID Rep frame" or (in byte order) 4D 50 41 20
49 44 20 52 65 70 20 46 72 61 6D 65 (in hexadecimal). Initiator 49 44 20 52 65 70 20 46 72 61 6D 65 (in hexadecimal). Initiator
mode receivers MUST check this field for the same value, and mode receivers MUST check this field for the same value, and
close the connection and report an error locally if any other close the connection and report an error locally if any other
value is detected. value is detected.
M: This bit, when sent in an MPA Request Frame or an MPA Reply Frame, M: This bit, when sent in an MPA Request Frame or an MPA Reply Frame,
declares a receiver's requirement for Markers. When in a declares a receiver's requirement for Markers. When in a
received MPA Request Frame or MPA Reply Frame and the value is received MPA Request Frame or MPA Reply Frame and the value is
'0', Markers MUST NOT be added to the data stream by the sender. '0', Markers MUST NOT be added to the data stream by the sender.
When '1' Markers MUST be added as described in section 5.1 MPA When '1' Markers MUST be added as described in section 4.3 MPA
Markers on page 20. Markers on page 14.
C: This bit declares an endpoint's preferred CRC usage. When this C: This bit declares an endpoint's preferred CRC usage. When this
field is '0' in the MPA Request Frame and the MPA Reply Frame, field is '0' in the MPA Request Frame and the MPA Reply Frame,
CRCs MUST not be checked and need not be generated by either CRCs MUST not be checked and need not be generated by either
endpoint. When this bit is '1' in either the MPA Request Frame endpoint. When this bit is '1' in either the MPA Request Frame
or MPA Reply Frame, CRCs MUST be generated and checked by both or MPA Reply Frame, CRCs MUST be generated and checked by both
endpoints. Note that even when not in use, the CRC field remains endpoints. Note that even when not in use, the CRC field remains
present in the FPDU. When CRCs are not in use, the CRC field present in the FPDU. When CRCs are not in use, the CRC field
MUST be considered valid for FPDU checking regardless of its MUST be considered valid for FPDU checking regardless of its
contents. contents.
skipping to change at page 35, line 38 skipping to change at page 33, line 38
field, or if the length of the Private Data field exceeds 512 field, or if the length of the Private Data field exceeds 512
octets, the receiver MUST close the connection and report an octets, the receiver MUST close the connection and report an
error locally. Otherwise, the MPA receiver should pass the error locally. Otherwise, the MPA receiver should pass the
PD_Length value and Private Data to the ULP. PD_Length value and Private Data to the ULP.
Private Data: This field may contain any value defined by ULPs or may Private Data: This field may contain any value defined by ULPs or may
not be present. The Private Data field MUST between 0 and 512 not be present. The Private Data field MUST between 0 and 512
octets in length. ULPs define how to size, set, and validate octets in length. ULPs define how to size, set, and validate
this field within these limits. this field within these limits.
6.1.2 Connection Startup Rules 7.1.2 Connection Startup Rules
The following rules apply to MPA connection Startup Phase: The following rules apply to MPA connection Startup Phase:
1. When MPA is started in the Initiator mode, the MPA implementation 1. When MPA is started in the Initiator mode, the MPA implementation
MUST send a valid MPA Request Frame. The MPA Request Frame MAY MUST send a valid MPA Request Frame. The MPA Request Frame MAY
include ULP supplied Private Data. include ULP supplied Private Data.
2. When MPA is started in the Responder mode, the MPA implementation 2. When MPA is started in the Responder mode, the MPA implementation
MUST wait until a MPA Request Frame is received and validated MUST wait until a MPA Request Frame is received and validated
before entering full MPA/DDP operation. before entering full MPA/DDP operation.
skipping to change at page 37, line 5 skipping to change at page 35, line 5
Note: this requirement is present to allow the Initiator time to Note: this requirement is present to allow the Initiator time to
get its receiver into Full Operation before an FPDU arrives, get its receiver into Full Operation before an FPDU arrives,
avoiding potential race conditions at the Initiator. This avoiding potential race conditions at the Initiator. This
was also subject to some debate in the work group before was also subject to some debate in the work group before
rough consensus was reached. Eliminating this requirement rough consensus was reached. Eliminating this requirement
would allow faster startup in some types of applications. would allow faster startup in some types of applications.
However, that would also make certain implementations However, that would also make certain implementations
(particularly "dual stack") much harder. (particularly "dual stack") much harder.
5. If a received "Key" does not match the expected value, (See 6.1.1 5. If a received "Key" does not match the expected value, (See 7.1.1
MPA Request and Reply Frame Format above) the TCP/DDP connection MPA Request and Reply Frame Format above) the TCP/DDP connection
MUST be closed, and an error returned to the ULP. MUST be closed, and an error returned to the ULP.
6. The received Private Data fields may be used by Consumers at 6. The received Private Data fields may be used by Consumers at
either end to further validate the connection, and set up DDP or either end to further validate the connection, and set up DDP or
other ULP parameters. The Initiator ULP MAY close the other ULP parameters. The Initiator ULP MAY close the
TCP/MPA/DDP connection as a result of validating the Private Data TCP/MPA/DDP connection as a result of validating the Private Data
fields. The Responder SHOULD return a MPA Reply Frame with the fields. The Responder SHOULD return a MPA Reply Frame with the
"Reject Connection" Bit set to '1' if the validation of the "Reject Connection" Bit set to '1' if the validation of the
Private Data is not acceptable to the ULP. Private Data is not acceptable to the ULP.
skipping to change at page 38, line 5 skipping to change at page 36, line 5
the PD_Length, or the application buffer. If any of the above the PD_Length, or the application buffer. If any of the above
fails, the startup frame MUST be considered improperly formatted. fails, the startup frame MUST be considered improperly formatted.
10. MPA implementations SHOULD implement a reasonable timeout while 10. MPA implementations SHOULD implement a reasonable timeout while
waiting for the entire startup frames; this prevents certain waiting for the entire startup frames; this prevents certain
denial of service attacks. ULPs SHOULD implement a reasonable denial of service attacks. ULPs SHOULD implement a reasonable
timeout while waiting for FPDUs, ULPDUs and application level timeout while waiting for FPDUs, ULPDUs and application level
messages to guard against application failures and certain denial messages to guard against application failures and certain denial
of service attacks. of service attacks.
6.1.3 Example Delayed Startup sequence 7.1.3 Example Delayed Startup sequence
A variety of startup sequences are possible when using MPA on TCP. A variety of startup sequences are possible when using MPA on TCP.
Following is an example of an MPA/DDP startup that occurs after TCP Following is an example of an MPA/DDP startup that occurs after TCP
has been running for a while and has exchanged some amount of has been running for a while and has exchanged some amount of
streaming data. This example does not use any Private Data (an streaming data. This example does not use any Private Data (an
example that does is shown later in 6.1.4.2 Example Immediate Startup example that does is shown later in 7.1.4.2 Example Immediate Startup
using Private Data on page 42), although it is perfectly legal to using Private Data on page 40), although it is perfectly legal to
include the Private Data. Note that since the example does not use include the Private Data. Note that since the example does not use
any Private Data, there are no ULP interactions shown between any Private Data, there are no ULP interactions shown between
receiving "Startup frames" and putting MPA into Full Operation. receiving "Startup frames" and putting MPA into Full Operation.
Initiator Responder Initiator Responder
+---------------------------+ +---------------------------+
|ULP streaming mode | |ULP streaming mode |
| <Hello> request to | | <Hello> request to |
| transition to DDP/MPA | +--------------------------+ | transition to DDP/MPA | +--------------------------+
skipping to change at page 39, line 41 skipping to change at page 37, line 41
| <MPA Reply Frame> | +--------------------------+ | <MPA Reply Frame> | +--------------------------+
|Consumer binds DDP to MPA, | |Consumer binds DDP to MPA, |
|DDP/MPA begins full | |DDP/MPA begins full |
|operation. | |operation. |
|MPA sends first FPDU (as | +--------------------------+ |MPA sends first FPDU (as | +--------------------------+
|DDP ULPDUs become | ========> |MPA Receives first FPDU. | |DDP ULPDUs become | ========> |MPA Receives first FPDU. |
|available). | |MPA sends first FPDU (as | |available). | |MPA sends first FPDU (as |
+---------------------------+ |DDP ULPDUs become | +---------------------------+ |DDP ULPDUs become |
<====== |available. | <====== |available. |
+--------------------------+ +--------------------------+
Figure 8: Example Delayed Startup negotiation Figure 10: Example Delayed Startup negotiation
An example Delayed Startup sequence is described below: An example Delayed Startup sequence is described below:
* Active and passive sides start up a TCP connection in the * Active and passive sides start up a TCP connection in the
usual fashion, probably using sockets APIs. They exchange usual fashion, probably using sockets APIs. They exchange
some amount of streaming mode data. At some point one side some amount of streaming mode data. At some point one side
(the MPA Initiator) sends streaming mode data that (the MPA Initiator) sends streaming mode data that
effectively says "Hello, Lets go into MPA/DDP mode." effectively says "Hello, Lets go into MPA/DDP mode."
* When the remote side (the MPA Responder) gets this streaming mode * When the remote side (the MPA Responder) gets this streaming mode
message, the Consumer would send a last streaming mode message message, the Consumer would send a last streaming mode message
skipping to change at page 41, line 5 skipping to change at page 39, line 5
would report this message to the Consumer. The Consumer can would report this message to the Consumer. The Consumer can
then accept the MPA/DDP connection, or close or reset the TCP then accept the MPA/DDP connection, or close or reset the TCP
connection to abort the process. connection to abort the process.
* On determining that the Connection is acceptable, the * On determining that the Connection is acceptable, the
Initiating Consumer would use an appropriate API to bind the Initiating Consumer would use an appropriate API to bind the
TCP/MPA connections to a DDP endpoint thus enabling MPA/DDP TCP/MPA connections to a DDP endpoint thus enabling MPA/DDP
into Full Operation. MPA/DDP would begin sending DDP into Full Operation. MPA/DDP would begin sending DDP
messages as MPA FPDUs. messages as MPA FPDUs.
6.1.4 Use of Private Data 7.1.4 Use of Private Data
This section is advisory in nature, in that it suggests a method that This section is advisory in nature, in that it suggests a method that
a ULP can deal with pre-DDP connection information exchange. a ULP can deal with pre-DDP connection information exchange.
6.1.4.1 Motivation 7.1.4.1 Motivation
Prior RDMA protocols have been developed that provide Private Data Prior RDMA protocols have been developed that provide Private Data
via out of band mechanisms. As a result, many applications now via out of band mechanisms. As a result, many applications now
expect some form of Private Data to be available for application use expect some form of Private Data to be available for application use
prior to setting up the DDP/RDMA connection. Following are some prior to setting up the DDP/RDMA connection. Following are some
examples of the use of Private Data. examples of the use of Private Data.
An RDMA Endpoint (referred to as a Queue Pair, or QP, in InfiniBand An RDMA Endpoint (referred to as a Queue Pair, or QP, in InfiniBand
and the [VERBS]) must be associated with a Protection Domain. No and the [VERBS]) must be associated with a Protection Domain. No
receive operations may be posted to the endpoint before it is receive operations may be posted to the endpoint before it is
skipping to change at page 42, line 12 skipping to change at page 40, line 12
exchanged using datagrams before actually starting the RDMA exchanged using datagrams before actually starting the RDMA
connection. connection.
This draft allows for small amounts of Private Data to be exchanged This draft allows for small amounts of Private Data to be exchanged
as part of the MPA startup sequence. The actual Private Data fields as part of the MPA startup sequence. The actual Private Data fields
are carried in the MPA Request Frame, and the MPA Reply Frame. are carried in the MPA Request Frame, and the MPA Reply Frame.
If larger amounts of Private Data or more negotiation is necessary, If larger amounts of Private Data or more negotiation is necessary,
TCP streaming mode messages may be exchanged prior to enabling MPA. TCP streaming mode messages may be exchanged prior to enabling MPA.
6.1.4.2 Example Immediate Startup using Private Data 7.1.4.2 Example Immediate Startup using Private Data
Initiator Responder Initiator Responder
+---------------------------+ +---------------------------+
|TCP SYN sent | +--------------------------+ |TCP SYN sent | +--------------------------+
+---------------------------+ --------> |TCP gets SYN packet; | +---------------------------+ --------> |TCP gets SYN packet; |
+---------------------------+ | Sends SYN-Ack | +---------------------------+ | Sends SYN-Ack |
|TCP gets SYN-Ack | <-------- +--------------------------+ |TCP gets SYN-Ack | <-------- +--------------------------+
| Sends Ack | | Sends Ack |
+---------------------------+ --------> +--------------------------+ +---------------------------+ --------> +--------------------------+
skipping to change at page 42, line 51 skipping to change at page 40, line 51
|Consumer examines Private | |Consumer examines Private |
|Data, binds DDP to MPA, | |Data, binds DDP to MPA, |
|and enables DDP/MPA to | |and enables DDP/MPA to |
|begin Full Operation. | |begin Full Operation. |
|MPA sends first FPDU (as | +--------------------------+ |MPA sends first FPDU (as | +--------------------------+
|DDP ULPDUs become | ========> |MPA Receives first FPDU. | |DDP ULPDUs become | ========> |MPA Receives first FPDU. |
|available). | |MPA sends first FPDU (as | |available). | |MPA sends first FPDU (as |
+---------------------------+ |DDP ULPDUs become | +---------------------------+ |DDP ULPDUs become |
<====== |available. | <====== |available. |
+--------------------------+ +--------------------------+
Figure 9: Example Immediate Startup negotiation Figure 11: Example Immediate Startup negotiation
Note: the exact order of when MPA is started in the TCP connection Note: the exact order of when MPA is started in the TCP connection
sequence is implementation dependent; the above diagram shows one sequence is implementation dependent; the above diagram shows one
possible sequence. Also, the Initiator "Ack" to the Responder's possible sequence. Also, the Initiator "Ack" to the Responder's
"SYN-Ack" may be combined into the same TCP segment containing "SYN-Ack" may be combined into the same TCP segment containing
the MPA Request Frame (as is allowed by TCP RFCs). the MPA Request Frame (as is allowed by TCP RFCs).
The example immediate startup sequence is described below: The example immediate startup sequence is described below:
* The passive side (Responding Consumer) would listen on the TCP * The passive side (Responding Consumer) would listen on the TCP
skipping to change at page 44, line 21 skipping to change at page 42, line 21
If the "rejected Connection" bit is set to a '1', MPA will If the "rejected Connection" bit is set to a '1', MPA will
close the TCP connection and exit. close the TCP connection and exit.
If the "Rejected Connection" bit is set to a '0', and on If the "Rejected Connection" bit is set to a '0', and on
determining from the MPA Reply Frame Private Data that the determining from the MPA Reply Frame Private Data that the
Connection is acceptable, the Initiating Consumer would use Connection is acceptable, the Initiating Consumer would use
an appropriate API to bind the TCP/MPA connections to a DDP an appropriate API to bind the TCP/MPA connections to a DDP
endpoint thus enabling MPA/DDP into Full Operation. MPA/DDP endpoint thus enabling MPA/DDP into Full Operation. MPA/DDP
would begin sending DDP messages as MPA FPDUs. would begin sending DDP messages as MPA FPDUs.
6.1.5 "Dual stack" implementations 7.1.5 "Dual stack" implementations
MPA/DDP implementations are commonly expected to be implemented as MPA/DDP implementations are commonly expected to be implemented as
part of a "dual stack" architecture. One "stack" is the traditional part of a "dual stack" architecture. One "stack" is the traditional
TCP stack, usually with a sockets interface API (Application TCP stack, usually with a sockets interface API (Application
Programming Interface). The second stack is the MPA/DDP "stack" with Programming Interface). The second stack is the MPA/DDP "stack" with
its own API, and potentially separate code or hardware to deal with its own API, and potentially separate code or hardware to deal with
the MPA/DDP data. Of course, implementations may vary, so the the MPA/DDP data. Of course, implementations may vary, so the
following comments are of an advisory nature only. following comments are of an advisory nature only.
The use of the two "stacks" offers advantages: The use of the two "stacks" offers advantages:
skipping to change at page 45, line 33 skipping to change at page 43, line 33
message" as part of its Responder DDP/MPA enable function. This message" as part of its Responder DDP/MPA enable function. This
allows the DDP/MPA stack to more easily manage the conversion to allows the DDP/MPA stack to more easily manage the conversion to
DDP/MPA mode (and avoid problems with a very fast return of the DDP/MPA mode (and avoid problems with a very fast return of the
MPA Request Frame from the Initiator side). MPA Request Frame from the Initiator side).
Note: Regardless of the "stack" architecture used, TCP's rules MUST Note: Regardless of the "stack" architecture used, TCP's rules MUST
be followed. For example, if network data is lost, re-segmented be followed. For example, if network data is lost, re-segmented
or re-ordered, TCP MUST recover appropriately even when this or re-ordered, TCP MUST recover appropriately even when this
occurs while switching stacks. occurs while switching stacks.
6.2 Normal Connection Teardown 7.2 Normal Connection Teardown
Each half connection of MPA terminates when DDP closes the Each half connection of MPA terminates when DDP closes the
corresponding TCP half connection. corresponding TCP half connection.
A mechanism SHOULD be provided by MPA to DDP for DDP to be made aware A mechanism SHOULD be provided by MPA to DDP for DDP to be made aware
that a graceful close of the LLP connection has been received by the that a graceful close of the LLP connection has been received by the
LLP (e.g. FIN is received). LLP (e.g. FIN is received).
7 Error Semantics 8 Error Semantics
The following errors MUST be detected by MPA and the codes SHOULD be The following errors MUST be detected by MPA and the codes SHOULD be
provided to DDP or other Consumer: provided to DDP or other Consumer:
Code Error Code Error
1 TCP connection closed, terminated or lost. This includes lost 1 TCP connection closed, terminated or lost. This includes lost
by timeout, too many retries, RST received or FIN received. by timeout, too many retries, RST received or FIN received.
2 Received MPA CRC does not match the calculated value for the 2 Received MPA CRC does not match the calculated value for the
skipping to change at page 46, line 34 skipping to change at page 44, line 34
made when a gap creating an out of order sequence is closed made when a gap creating an out of order sequence is closed
and any time a Marker points to an already identified FPDU. and any time a Marker points to an already identified FPDU.
It is OPTIONAL for a receiver to check each Marker, if It is OPTIONAL for a receiver to check each Marker, if
multiple Markers are present in an FPDU, or if the segment is multiple Markers are present in an FPDU, or if the segment is
received in order. received in order.
4 Invalid MPA Request Frame or MPA Response Frame received. In 4 Invalid MPA Request Frame or MPA Response Frame received. In
this case, the TCP connection MUST be immediately closed. DDP this case, the TCP connection MUST be immediately closed. DDP
and other ULPs should treat this similar to code 1, above. and other ULPs should treat this similar to code 1, above.
When conditions 2 or 3 above are detected, an MPA-aware TCP When conditions 2 or 3 above are detected, an optimized MPA/TCP
implementation MAY choose to silently drop the TCP segment rather implementation MAY choose to silently drop the TCP segment rather
than reporting the error to DDP. In this case, the sending TCP will than reporting the error to DDP. In this case, the sending TCP will
retry the segment, usually correcting the error, unless the problem retry the segment, usually correcting the error, unless the problem
was at the source. In that case, the source will usually exceed the was at the source. In that case, the source will usually exceed the
number of retries and terminate the connection. number of retries and terminate the connection.
Once MPA delivers an error of any type, it MUST NOT pass or deliver Once MPA delivers an error of any type, it MUST NOT pass or deliver
any additional FPDUs on that half connection. any additional FPDUs on that half connection.
For Error codes 2 and 3, MPA MUST NOT close the TCP connection For Error codes 2 and 3, MPA MUST NOT close the TCP connection
following a reported error. Closing the connection is the following a reported error. Closing the connection is the
responsibility of DDP's ULP. responsibility of DDP's ULP.
Note that since MPA will not Deliver any FPDUs on a half Note that since MPA will not Deliver any FPDUs on a half
connection following an error detected on the receive side of connection following an error detected on the receive side of
that connection, DDP's ULP is expected to tear down the that connection, DDP's ULP is expected to tear down the
connection. This may not occur until after one or more last connection. This may not occur until after one or more last
messages are transmitted on the opposite half connection. This messages are transmitted on the opposite half connection. This
allows a diagnostic error message to be sent. allows a diagnostic error message to be sent.
8 Security Considerations 9 Security Considerations
This section discusses the security considerations for MPA. This section discusses the security considerations for MPA.
8.1 Protocol-specific Security Considerations 9.1 Protocol-specific Security Considerations
The vulnerabilities of MPA to third-party attacks are no greater than The vulnerabilities of MPA to third-party attacks are no greater than
any other protocol running over TCP. A third party, by sending any other protocol running over TCP. A third party, by sending
packets into the network that are delivered to an MPA receiver, could packets into the network that are delivered to an MPA receiver, could
launch a variety of attacks that take advantage of how MPA operates. launch a variety of attacks that take advantage of how MPA operates.
For example, a third party could send random packets that are valid For example, a third party could send random packets that are valid
for TCP, but contain no FPDU headers. An MPA receiver reports an for TCP, but contain no FPDU headers. An MPA receiver reports an
error to DDP when any packet arrives that cannot be validated as an error to DDP when any packet arrives that cannot be validated as an
FPDU when properly located on an FPDU boundary. A third party could FPDU when properly located on an FPDU boundary. A third party could
also send packets that are valid for TCP, MPA, and DDP, but do not also send packets that are valid for TCP, MPA, and DDP, but do not
skipping to change at page 47, line 37 skipping to change at page 45, line 37
would likewise be severely impacted. Range checking on path MTU would likewise be severely impacted. Range checking on path MTU
sizes in ICMP packets may be used to prevent such attacks. sizes in ICMP packets may be used to prevent such attacks.
[RDMAP] and [DDP] are used to control, read and write data buffers [RDMAP] and [DDP] are used to control, read and write data buffers
over IP networks. Therefore, the control and the data packets of over IP networks. Therefore, the control and the data packets of
these protocols are vulnerable to the spoofing, tampering and these protocols are vulnerable to the spoofing, tampering and
information disclosure attacks listed below. In addition, Connection information disclosure attacks listed below. In addition, Connection
to/from an unauthorized or unauthenticated endpoint is a potential to/from an unauthorized or unauthenticated endpoint is a potential
problem with most applications using RDMA, DDP, and MPA. problem with most applications using RDMA, DDP, and MPA.
8.1.1 Spoofing 9.1.1 Spoofing
Spoofing attacks can be launched by the Remote Peer, or by a network Spoofing attacks can be launched by the Remote Peer, or by a network
based attacker. A network based spoofing attack applies to all based attacker. A network based spoofing attack applies to all
Remote Peers. Because the MPA Stream requires a TCP Stream in the Remote Peers. Because the MPA Stream requires a TCP Stream in the
ESTABLISHED state, certain types of traditional forms of wire attacks ESTABLISHED state, certain types of traditional forms of wire attacks
do not apply -- an end-to-end handshake must have occurred to do not apply -- an end-to-end handshake must have occurred to
establish the MPA Stream. So, the only form of spoofing that applies establish the MPA Stream. So, the only form of spoofing that applies
is one when a remote node can both send and receive packets. Yet is one when a remote node can both send and receive packets. Yet
even with this limitation the Stream is still exposed to the even with this limitation the Stream is still exposed to the
following spoofing attacks. following spoofing attacks.
8.1.1.1 Impersonation 9.1.1.1 Impersonation
A network based attacker can impersonate a legal MPA/DDP/RDMAP peer A network based attacker can impersonate a legal MPA/DDP/RDMAP peer
(by spoofing a legal IP address), and establish an MPA/DDP/RDMAP (by spoofing a legal IP address), and establish an MPA/DDP/RDMAP
Stream with the victim. End to end authentication (i.e. IPsec or ULP Stream with the victim. End to end authentication (i.e. IPsec or ULP
authentication) provides protection against this attack. authentication) provides protection against this attack.
8.1.1.2 Stream Hijacking 9.1.1.2 Stream Hijacking
Stream hijacking happens when a network based attacker follows the Stream hijacking happens when a network based attacker follows the
Stream establishment phase, and waits until the authentication phase Stream establishment phase, and waits until the authentication phase
(if such a phase exists) is completed successfully. He can then (if such a phase exists) is completed successfully. He can then
spoof the IP address and re-direct the Stream from the victim to its spoof the IP address and re-direct the Stream from the victim to its
own machine. For example, an attacker can wait until an iSCSI own machine. For example, an attacker can wait until an iSCSI
authentication is completed successfully, and hijack the iSCSI authentication is completed successfully, and hijack the iSCSI
Stream. Stream.
The best protection against this form of attack is end-to-end The best protection against this form of attack is end-to-end
integrity protection and authentication, such as IPsec to prevent integrity protection and authentication, such as IPsec to prevent
spoofing. Another option is to provide physical security. spoofing. Another option is to provide physical security.
Discussion of physical security is out of scope for this document. Discussion of physical security is out of scope for this document.
8.1.1.3 Man in the Middle Attack 9.1.1.3 Man in the Middle Attack
If a network based attacker has the ability to delete, inject replay, If a network based attacker has the ability to delete, inject replay,
or modify packets which will still be accepted by MPA (e.g., TCP or modify packets which will still be accepted by MPA (e.g., TCP
sequence number is correct, FPDU is valid etc.) then the Stream can sequence number is correct, FPDU is valid etc.) then the Stream can
be exposed to a man in the middle attack. The attacker could be exposed to a man in the middle attack. The attacker could
potentially use the services of [DDP] and [RDMAP] to read the potentially use the services of [DDP] and [RDMAP] to read the
contents of the associated data buffer, modify the contents of the contents of the associated data buffer, modify the contents of the
associated data buffer, or to disable further access to the buffer. associated data buffer, or to disable further access to the buffer.
The only countermeasure for this form of attack is to either secure The only countermeasure for this form of attack is to either secure
the MPA/DDP/RDMAP Stream (i.e. integrity protect) or attempt to the MPA/DDP/RDMAP Stream (i.e. integrity protect) or attempt to
skipping to change at page 48, line 44 skipping to change at page 46, line 44
integrity protection and authentication, such as IPsec, to prevent integrity protection and authentication, such as IPsec, to prevent
spoofing or tampering. If Stream or session level authentication and spoofing or tampering. If Stream or session level authentication and
integrity protection are not used, then a man-in-the-middle attack integrity protection are not used, then a man-in-the-middle attack
can occur, enabling spoofing and tampering. can occur, enabling spoofing and tampering.
Another approach is to restrict access to only the local subnet/link, Another approach is to restrict access to only the local subnet/link,
and provide some mechanism to limit access, such as physical security and provide some mechanism to limit access, such as physical security
or 802.1.x. This model is an extremely limited deployment scenario, or 802.1.x. This model is an extremely limited deployment scenario,
and will not be further examined here. and will not be further examined here.
8.1.2 Eavesdropping 9.1.2 Eavesdropping
Generally speaking, Stream confidentiality protects against Generally speaking, Stream confidentiality protects against
eavesdropping. Stream and/or session authentication and integrity eavesdropping. Stream and/or session authentication and integrity
protection is a counter measurement against various spoofing and protection is a counter measurement against various spoofing and
tampering attacks. The effectiveness of authentication and integrity tampering attacks. The effectiveness of authentication and integrity
against a specific attack, depend on whether the authentication is against a specific attack, depend on whether the authentication is
machine level authentication (as the one provided by IPsec), or ULP machine level authentication (as the one provided by IPsec), or ULP
authentication. authentication.
8.2 Introduction to Security Options 9.2 Introduction to Security Options
The following security services can be applied to an MPA/DDP/RDMAP The following security services can be applied to an MPA/DDP/RDMAP
Stream: Stream:
1. Session confidentiality - protects against eavesdropping. 1. Session confidentiality - protects against eavesdropping.
2. Per-packet data source authentication - protects against the 2. Per-packet data source authentication - protects against the
following spoofing attacks: network based impersonation, Stream following spoofing attacks: network based impersonation, Stream
hijacking, and man in the middle. hijacking, and man in the middle.
skipping to change at page 49, line 45 skipping to change at page 47, line 45
promising approach called "channel binding". From [NFSv4CHANNEL]: promising approach called "channel binding". From [NFSv4CHANNEL]:
"The concept of channel bindings allows applications to prove "The concept of channel bindings allows applications to prove
that the end-points of two secure channels at different network that the end-points of two secure channels at different network
layers are the same by binding authentication at one channel to layers are the same by binding authentication at one channel to
the session protection at the other channel. The use of channel the session protection at the other channel. The use of channel
bindings allows applications to delegate session protection to bindings allows applications to delegate session protection to
lower layers, which may significantly improve performance for lower layers, which may significantly improve performance for
some applications." some applications."
8.3 Using IPsec With MPA 9.3 Using IPsec With MPA
IPsec can be used to protect against the packet injection attacks IPsec can be used to protect against the packet injection attacks
outlined above. Because IPsec is designed to secure individual IP outlined above. Because IPsec is designed to secure individual IP
packets, MPA can run above IPsec without change. IPsec packets are packets, MPA can run above IPsec without change. IPsec packets are
processed (e.g., integrity checked and decrypted) in the order they processed (e.g., integrity checked and decrypted) in the order they
are received, and an MPA receiver will process the decrypted FPDUs are received, and an MPA receiver will process the decrypted FPDUs
contained in these packets in the same manner as FPDUs contained in contained in these packets in the same manner as FPDUs contained in
unsecured IP packets. unsecured IP packets.
MPA Implementations MUST implement IPsec as described in Section 8.4 MPA Implementations MUST implement IPsec as described in Section 9.4
below. The use of IPsec is up to ULPs and administrators. below. The use of IPsec is up to ULPs and administrators.
8.4 Requirements for IPsec Encapsulation of MPA/DDP 9.4 Requirements for IPsec Encapsulation of MPA/DDP
The IP Storage working group has spent significant time and effort to The IP Storage working group has spent significant time and effort to
define the normative IPsec requirements for IP Storage [RFC3723]. define the normative IPsec requirements for IP Storage [RFC3723].
Portions of that specification are applicable to a wide variety of Portions of that specification are applicable to a wide variety of
protocols, including the RDDP protocol suite. In order to not protocols, including the RDDP protocol suite. In order to not
replicate this effort, an MPA ON TCP implementation MUST follow the replicate this effort, an MPA on TCP implementation MUST follow the
requirements defined in RFC3723 Section 2.3 and Section 5, including requirements defined in RFC3723 Section 2.3 and Section 5, including
the associated normative references for those sections. the associated normative references for those sections.
Additionally, since IPsec acceleration hardware may only be able to Additionally, since IPsec acceleration hardware may only be able to
handle a limited number of active IKE Phase 2 SAs, Phase 2 delete handle a limited number of active IKE Phase 2 SAs, Phase 2 delete
messages MAY be sent for idle SAs, as a means of keeping the number messages MAY be sent for idle SAs, as a means of keeping the number
of active Phase 2 SAs to a minimum. The receipt of an IKE Phase 2 of active Phase 2 SAs to a minimum. The receipt of an IKE Phase 2
delete message MUST NOT be interpreted as a reason for tearing down delete message MUST NOT be interpreted as a reason for tearing down
an DDP/RDMA Stream. Rather, it is preferable to leave the Stream up, an DDP/RDMA Stream. Rather, it is preferable to leave the Stream up,
and if additional traffic is sent on it, to bring up another IKE and if additional traffic is sent on it, to bring up another IKE
Phase 2 SA to protect it. This avoids the potential for continually Phase 2 SA to protect it. This avoids the potential for continually
bringing Streams up and down. bringing Streams up and down.
Note that there are serious security issues if IPsec is not Note that there are serious security issues if IPsec is not
implemented end-to-end. For example, if IPsec is implemented as a implemented end-to-end. For example, if IPsec is implemented as a
tunnel in the middle of the network, any hosts between the peer and tunnel in the middle of the network, any hosts between the peer and
the IPsec tunneling device can freely attack the unprotected Stream. the IPsec tunneling device can freely attack the unprotected Stream.
9 IANA Considerations 10 IANA Considerations
No IANA actions are required by this document. No IANA actions are required by this document.
If a well-known port is chosen as the mechanism to identify a DDP on If a well-known port is chosen as the mechanism to identify a DDP on
MPA on TCP, the well-known port must be registered with IANA. MPA on TCP, the well-known port must be registered with IANA.
Because the use of the port is DDP specific, registration of the port Because the use of the port is DDP specific, registration of the port
with IANA is left to DDP. with IANA is left to DDP.
10 References 11 References
10.1 Normative References 11.1 Normative References
[iSCSI] Satran, J., Internet Small Computer Systems Interface [iSCSI] Satran, J., Internet Small Computer Systems Interface
(iSCSI), RFC 3720, April 2004. (iSCSI), RFC 3720, April 2004.
[RFC1191] Mogul, J., and Deering, S., "Path MTU Discovery", RFC 1191, [RFC1191] Mogul, J., and Deering, S., "Path MTU Discovery", RFC 1191,
November 1990. November 1990.
[RFC2018] Mathis, M., Mahdavi, J., Floyd, S., Romanow, A., "TCP [RFC2018] Mathis, M., Mahdavi, J., Floyd, S., Romanow, A., "TCP
Selective Acknowledgment Options", RFC 2018, October 1996. Selective Acknowledgment Options", RFC 2018, October 1996.
[RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
Requirement Levels", BCP 14, RFC 2119, March 1997.
[RFC3723] Aboba B., et al, "Securing Block Storage Protocols over [RFC3723] Aboba B., et al, "Securing Block Storage Protocols over
IP", RFC3723, April 2004. IP", RFC3723, April 2004.
[RFC793] Postel, J., "Transmission Control Protocol - DARPA Internet [RFC793] Postel, J., "Transmission Control Protocol - DARPA Internet
Program Protocol Specification", RFC 793, September 1981. Program Protocol Specification", RFC 793, September 1981.
[RDMASEC] Pinkerton J., Deleganes E., Bitan S., "DDP/RDMAP [RDMASEC] Pinkerton J., Deleganes E., Bitan S., "DDP/RDMAP
Security", draft-ietf-rddp-security-09.txt (work in progress), Security", draft-ietf-rddp-security-09.txt (work in progress),
MAY 2006. MAY 2006.
10.2 Informative References 11.2 Informative References
[CRCTCP] Stone J., Partridge, C., "When the CRC and TCP checksum [CRCTCP] Stone J., Partridge, C., "When the CRC and TCP checksum
disagree", ACM Sigcomm, Sept. 2000. disagree", ACM Sigcomm, Sept. 2000.
[DAT-API] DAT Collaborative, "kDAPL (Kernel Direct Access Programming [DAT-API] DAT Collaborative, "kDAPL (Kernel Direct Access Programming
Library) and uDAPL (User Direct Access Programming Library)", Library) and uDAPL (User Direct Access Programming Library)",
http://www.datcollaborative.org. http://www.datcollaborative.org.
[DDP] H. Shah et al., "Direct Data Placement over Reliable [DDP] H. Shah et al., "Direct Data Placement over Reliable
Transports", draft-ietf-rddp-ddp-06.txt (Work in progress), May Transports", draft-ietf-rddp-ddp-06.txt (Work in progress), May
skipping to change at page 52, line 50 skipping to change at page 50, line 53
[IT-API] The Open Group, "Interconnect Transport API (IT-API)" [IT-API] The Open Group, "Interconnect Transport API (IT-API)"
Version 2.1, http://www.opengroup.org. Version 2.1, http://www.opengroup.org.
[RFC2401] Atkinson, R., Kent, S., "Security Architecture for the [RFC2401] Atkinson, R., Kent, S., "Security Architecture for the
Internet Protocol", RFC 2401, November 1998. Internet Protocol", RFC 2401, November 1998.
[RFC0896] J. Nagle, "Congestion Control in IP/TCP Internetworks", RFC [RFC0896] J. Nagle, "Congestion Control in IP/TCP Internetworks", RFC
896, January 1984. 896, January 1984.
[NagleDAck] Minshall G., Mogul, J., Saito, Y., Verghese, B.,
"Application performance pitfalls and TCP's Nagle algorithm",
Workshop on Internet Server Performance, May 1999.
[NFSv4CHANNEL] Williams, N., "On the Use of Channel Bindings to [NFSv4CHANNEL] Williams, N., "On the Use of Channel Bindings to
Secure Channels", Internet-Draft draft-ietf-nfsv4-channel- Secure Channels", Internet-Draft draft-ietf-nfsv4-channel-
bindings-02.txt, July 2004. bindings-02.txt, July 2004.
[RDMAP] R. Recio et al., "RDMA Protocol Specification", [RDMAP] R. Recio et al., "RDMA Protocol Specification",
draft-ietf-rddp-rdmap-06.txt, May 2006. draft-ietf-rddp-rdmap-06.txt, May 2006.
[RFC2960] R. Stewart et al., "Stream Control Transmission Protocol", [RFC2960] R. Stewart et al., "Stream Control Transmission Protocol",
RFC 2960, October 2000. RFC 2960, October 2000.
[RFC792] Postel, J., "Internet Control Message Protocol", September [RFC792] Postel, J., "Internet Control Message Protocol", September
1981 1981
[RFC1122] Braden, R.T., "Requirements for Internet hosts - [RFC1122] Braden, R.T., "Requirements for Internet hosts -
communication layers", October 1989. communication layers", October 1989.
[VERBS] J. Hilland et al., "RDMA Protocol Verbs Specification", [VERBS] J. Hilland et al., "RDMA Protocol Verbs Specification",
draft-hilland-iwarp-verbs-v1.0-RDMAC.pdf April 2003, draft-hilland-iwarp-verbs-v1.0-RDMAC.pdf April 2003,
http://www.rdmaconsortium.org. http://www.rdmaconsortium.org.
11 Appendix 12 Appendix
This appendix is for information only and is NOT part of the This appendix is for information only and is NOT part of the
standard. standard.
The appendix covers three topics; The appendix covers three topics;
Section 11.1 is an analysis of MPA on TCP and why it is useful to Section 12.1 is an analysis of MPA on TCP and why it is useful to
integrate MPA with TCP (with modifications to typical TCP integrate MPA with TCP (with modifications to typical TCP
implementations) to reduce overall system buffering and overhead. implementations) to reduce overall system buffering and overhead.
Section 11.2 covers some MPA receiver implementation notes. Section 12.2 covers some MPA receiver implementation notes.
Section 11.3 covers methods of making MPA implementations Section 12.3 covers methods of making MPA implementations
interoperate with both IETF and RDMA Consortium versions of the interoperate with both IETF and RDMA Consortium versions of the
protocols. protocols.
11.1 Analysis of MPA over TCP Operations 12.1 Analysis of MPA over TCP Operations
This appendix analyzes the impact of MPA on the TCP sender, receiver, This appendix analyzes the impact of MPA on the TCP sender, receiver,
and wire protocol. and wire protocol.
One of MPA's high level goals is to provide enough information, when One of MPA's high level goals is to provide enough information, when
combined with the Direct Data Placement Protocol [DDP], to enable combined with the Direct Data Placement Protocol [DDP], to enable
out-of-order placement of DDP payload into the final Upper Layer out-of-order placement of DDP payload into the final Upper Layer
Protocol (ULP) buffer. Note that DDP separates the act of placing Protocol (ULP) buffer. Note that DDP separates the act of placing
data into a ULP buffer from that of notifying the ULP that the ULP data into a ULP buffer from that of notifying the ULP that the ULP
buffer is available for use. In DDP terminology, the former is buffer is available for use. In DDP terminology, the former is
skipping to change at page 55, line 5 skipping to change at page 53, line 5
(FPDU) (if there is payload present). (FPDU) (if there is payload present).
2) that there be an integral number of FPDUs in a TCP segment (under 2) that there be an integral number of FPDUs in a TCP segment (under
conditions where the Path MTU is not changing). conditions where the Path MTU is not changing).
This Appendix concludes that the scaling advantages of FPDU Alignment This Appendix concludes that the scaling advantages of FPDU Alignment
are strong, based primarily on fairly drastic TCP receive buffer are strong, based primarily on fairly drastic TCP receive buffer
reduction requirements and simplified receive handling. The analysis reduction requirements and simplified receive handling. The analysis
also shows that there is little effect to TCP wire behavior. also shows that there is little effect to TCP wire behavior.
11.1.1 Assumptions 12.1.1 Assumptions
11.1.1.1 MPA is layered beneath DDP [DDP] 12.1.1.1 MPA is layered beneath DDP [DDP]
MPA is an adaptation layer between DDP and TCP. DDP requires MPA is an adaptation layer between DDP and TCP. DDP requires
preservation of DDP segment boundaries and a CRC32C digest covering preservation of DDP segment boundaries and a CRC32C digest covering
the DDP header and data. MPA adds these features to the TCP stream the DDP header and data. MPA adds these features to the TCP stream
so that DDP over TCP has the same basic properties as DDP over SCTP. so that DDP over TCP has the same basic properties as DDP over SCTP.
11.1.1.2 MPA preserves DDP message framing 12.1.1.2 MPA preserves DDP message framing
MPA was designed as a framing layer specifically for DDP and was not MPA was designed as a framing layer specifically for DDP and was not
intended as a general-purpose framing layer for any other ULP using intended as a general-purpose framing layer for any other ULP using
TCP. TCP.
A framing layer allows ULPs using it to receive indications from the A framing layer allows ULPs using it to receive indications from the
transport layer only when complete ULPDUs are present. As a framing transport layer only when complete ULPDUs are present. As a framing
layer, MPA is not aware of the content of the DDP PDU, only that it layer, MPA is not aware of the content of the DDP PDU, only that it
has received and, if necessary, reassembled a complete PDU for has received and, if necessary, reassembled a complete PDU for
Delivery to the DDP. Delivery to the DDP.
11.1.1.3 The size of the ULPDU passed to MPA is less than EMSS under 12.1.1.3 The size of the ULPDU passed to MPA is less than EMSS under
normal conditions normal conditions
To make reception of a complete DDP PDU on every received segment To make reception of a complete DDP PDU on every received segment
possible, DDP passes to MPA a PDU that is no larger than the EMSS of possible, DDP passes to MPA a PDU that is no larger than the EMSS of
the underlying fabric. Each FPDU that MPA creates contains the underlying fabric. Each FPDU that MPA creates contains
sufficient information for the receiver to directly place the ULP sufficient information for the receiver to directly place the ULP
payload in the correct location in the correct receive buffer. payload in the correct location in the correct receive buffer.
Edge cases when this condition does not occur are dealt with, but do Edge cases when this condition does not occur are dealt with, but do
not need to be on the fast path not need to be on the fast path
11.1.1.4 Out-of-order placement but NO out-of-order Delivery 12.1.1.4 Out-of-order placement but NO out-of-order Delivery
DDP receives complete DDP PDUs from MPA. Each DDP PDU contains the DDP receives complete DDP PDUs from MPA. Each DDP PDU contains the
information necessary to place its ULP payload directly in the information necessary to place its ULP payload directly in the
correct location in host memory. correct location in host memory.
Because each DDP segment is self-describing, it is possible for DDP Because each DDP segment is self-describing, it is possible for DDP
segments received out of order to have their ULP payload placed segments received out of order to have their ULP payload placed
immediately in the ULP receive buffer. immediately in the ULP receive buffer.
Data delivery to the ULP is guaranteed to be in the order the data Data delivery to the ULP is guaranteed to be in the order the data
was sent. DDP only indicates data delivery to the ULP after TCP has was sent. DDP only indicates data delivery to the ULP after TCP has
acknowledged the complete byte stream. acknowledged the complete byte stream.
11.1.2 The Value of FPDU Alignment 12.1.2 The Value of FPDU Alignment
Significant receiver optimizations can be achieved when Header Significant receiver optimizations can be achieved when Header
Alignment and complete FPDUs are the common case. The optimizations Alignment and complete FPDUs are the common case. The optimizations
allow utilizing significantly fewer buffers on the receiver and less allow utilizing significantly fewer buffers on the receiver and less
computation per FPDU. The net effect is the ability to build a computation per FPDU. The net effect is the ability to build a
"flow-through" receiver that enables TCP-based solutions to scale to "flow-through" receiver that enables TCP-based solutions to scale to
10G and beyond in an economical way. The optimizations are 10G and beyond in an economical way. The optimizations are
especially relevant to hardware implementations of receivers that especially relevant to hardware implementations of receivers that
process multiple protocol layers - Data Link Layer (e.g., Ethernet), process multiple protocol layers - Data Link Layer (e.g., Ethernet),
Network and Transport Layer (e.g., TCP/IP), and even some ULP on top Network and Transport Layer (e.g., TCP/IP), and even some ULP on top
skipping to change at page 57, line 36 skipping to change at page 55, line 36
continue - while Ethernet speeds have scaled by 1000 (from 10 continue - while Ethernet speeds have scaled by 1000 (from 10
megabit/sec to 10 gigabit/sec), I/O bus bandwidth of volume CPU megabit/sec to 10 gigabit/sec), I/O bus bandwidth of volume CPU
architectures has scaled from ~2 MB/sec to ~2 GB/sec (PC-XT bus to architectures has scaled from ~2 MB/sec to ~2 GB/sec (PC-XT bus to
PCI-X DDR). Under these conditions, the FPDU Alignment approach PCI-X DDR). Under these conditions, the FPDU Alignment approach
allows BufferSizeAF to be indifferent to network speed. It is allows BufferSizeAF to be indifferent to network speed. It is
primarily a function of the local processing time for a given frame. primarily a function of the local processing time for a given frame.
Thus when the FPDU Alignment approach is used, receive buffering is Thus when the FPDU Alignment approach is used, receive buffering is
expected to scale gracefully (i.e. less than linear scaling) as expected to scale gracefully (i.e. less than linear scaling) as
network speed is increased. network speed is increased.
11.1.2.1 Impact of lack of FPDU Alignment on the receiver computational 12.1.2.1 Impact of lack of FPDU Alignment on the receiver computational
load and complexity load and complexity
The receiver must perform IP and TCP processing, and then perform The receiver must perform IP and TCP processing, and then perform
FPDU CRC checks, before it can trust the FPDU header placement FPDU CRC checks, before it can trust the FPDU header placement
information. For simplicity of the description, the assumption is information. For simplicity of the description, the assumption is
that a FPDU is carried in no more than 2 TCP segments. In reality, that a FPDU is carried in no more than 2 TCP segments. In reality,
with no FPDU Alignment, an FPDU can be carried by more than 2 TCP with no FPDU Alignment, an FPDU can be carried by more than 2 TCP
segments (e.g., if the PMTU was reduced). segments (e.g., if the PMTU was reduced).
----++-----------------------------++-----------------------++----- ----++-----------------------------++-----------------------++-----
+---||---------------+ +--------||--------+ +----------||----+ +---||---------------+ +--------||--------+ +----------||----+
| TCP Seg X-1 | | TCP Seg X | | TCP Seg X+1 | | TCP Seg X-1 | | TCP Seg X | | TCP Seg X+1 |
+---||---------------+ +--------||--------+ +----------||----+ +---||---------------+ +--------||--------+ +----------||----+
----++-----------------------------++-----------------------++----- ----++-----------------------------++-----------------------++-----
FPDU #N-1 FPDU #N FPDU #N-1 FPDU #N
Figure 10: Non-aligned FPDU freely placed in TCP octet stream Figure 12: Non-aligned FPDU freely placed in TCP octet stream
The receiver algorithm for processing TCP segments (e.g., TCP segment The receiver algorithm for processing TCP segments (e.g., TCP segment
#X in Figure 10: Non-aligned FPDU freely placed in TCP octet stream) #X in Figure 12: Non-aligned FPDU freely placed in TCP octet stream)
carrying non-aligned FPDUs (in-order or out-of-order) includes: carrying non-aligned FPDUs (in-order or out-of-order) includes:
Data Link Layer processing (whole frame) - typically including a Data Link Layer processing (whole frame) - typically including a
CRC calculation. CRC calculation.
1. Network Layer processing (assuming not an IP fragment, the 1. Network Layer processing (assuming not an IP fragment, the
whole Data Link Layer frame contains one IP datagram. IP whole Data Link Layer frame contains one IP datagram. IP
fragments should be reassembled in a local buffer. This is fragments should be reassembled in a local buffer. This is
not a performance optimization goal) not a performance optimization goal)
skipping to change at page 59, line 52 skipping to change at page 57, line 52
actively detect presence or loss of FPDU Alignment for every TCP actively detect presence or loss of FPDU Alignment for every TCP
segment received. segment received.
+--------------------------+ +--------------------------+ +--------------------------+ +--------------------------+
+--|--------------------------+ +--|--------------------------+ +--|--------------------------+ +--|--------------------------+
| | TCP Seg X | | | TCP Seg X+1 | | | TCP Seg X | | | TCP Seg X+1 |
+--|--------------------------+ +--|--------------------------+ +--|--------------------------+ +--|--------------------------+
+--------------------------+ +--------------------------+ +--------------------------+ +--------------------------+
FPDU #N FPDU #N+1 FPDU #N FPDU #N+1
Figure 11: Aligned FPDU placed immediately after TCP header Figure 13: Aligned FPDU placed immediately after TCP header
The receiver algorithm for FPDU Aligned frames (in-order or out-of- The receiver algorithm for FPDU Aligned frames (in-order or out-of-
order) includes: order) includes:
1) Data Link Layer processing (whole frame) - typically 1) Data Link Layer processing (whole frame) - typically
including a CRC calculation. including a CRC calculation.
2) Network Layer processing (assuming not an IP fragment, the 2) Network Layer processing (assuming not an IP fragment, the
whole Data Link Layer frame contains one IP datagram. IP whole Data Link Layer frame contains one IP datagram. IP
fragments should be reassembled in a local buffer. This is fragments should be reassembled in a local buffer. This is
not a performance optimization goal) not a performance optimization goal)
3) Transport Layer processing -- TCP protocol processing, header 3) Transport Layer processing -- TCP protocol processing, header
and checksum checks. and checksum checks.
a. Classify incoming TCP segment using the 5 tuple (IP SRC, a. Classify incoming TCP segment using the 5 tuple (IP SRC,
IP DST, TCP SRC Port, TCP DST Port, protocol) IP DST, TCP SRC Port, TCP DST Port, protocol)
4) Check for Header Alignment. (Described in detail in Section 4) Check for Header Alignment. (Described in detail in Section
5.4). Assuming Header Alignment for the rest of the 6). Assuming Header Alignment for the rest of the algorithm
algorithm below. below.
a. If the header is not aligned, see the algorithm defined a. If the header is not aligned, see the algorithm defined
in the prior section. in the prior section.
5) If TCP is in-order or out-of-order the MPA header is at the 5) If TCP is in-order or out-of-order the MPA header is at the
beginning of the current TCP payload. Get the FPDU length beginning of the current TCP payload. Get the FPDU length
from the FPDU header. from the FPDU header.
6) Calculate CRC over FPDU 6) Calculate CRC over FPDU
skipping to change at page 61, line 24 skipping to change at page 59, line 24
along with the high probability that at least one complete FPDU is along with the high probability that at least one complete FPDU is
found with every TCP segment, allows the receiver to perform data found with every TCP segment, allows the receiver to perform data
placement for out-of-order TCP segments with no need for intermediate placement for out-of-order TCP segments with no need for intermediate
buffering. Essentially the TCP receive buffer has been eliminated buffering. Essentially the TCP receive buffer has been eliminated
and TCP reassembly is done in place within the ULP buffer. and TCP reassembly is done in place within the ULP buffer.
In case FPDU Alignment is not found, the receiver should follow the In case FPDU Alignment is not found, the receiver should follow the
algorithm for non aligned FPDU reception which may be slower and less algorithm for non aligned FPDU reception which may be slower and less
efficient. efficient.
11.1.2.2 FPDU Alignment effects on TCP wire protocol 12.1.2.2 FPDU Alignment effects on TCP wire protocol
An MPA-aware TCP exposes its EMSS to MPA. MPA uses the EMSS to In an optimized MPA/TCP implementation, TCP exposes its EMSS to
calculate its MULPDU, which it then exposes to DDP, its ULP. DDP MPA. MPA uses the EMSS to calculate its MULPDU, which it then
uses the MULPDU to segment its payload so that each FPDU sent by exposes to DDP, its ULP. DDP uses the MULPDU to segment its
MPA fits completely into one TCP segment. This has no impact on payload so that each FPDU sent by MPA fits completely into one
wire protocol and exposing this information is already supported TCP segment. This has no impact on wire protocol and exposing
on many TCP implementations, including all modern flavors of BSD this information is already supported on many TCP
networking, through the TCP_MAXSEG socket option. implementations, including all modern flavors of BSD networking,
through the TCP_MAXSEG socket option.
In the common case, the ULP (i.e. DDP over MPA) messages provided to In the common case, the ULP (i.e. DDP over MPA) messages provided to
the TCP layer are segmented to MULPDU size. It is assumed that the the TCP layer are segmented to MULPDU size. It is assumed that the
ULP message size is bounded by MULPDU, such that a single ULP message ULP message size is bounded by MULPDU, such that a single ULP message
can be encapsulated in a single TCP segment. Therefore, in the can be encapsulated in a single TCP segment. Therefore, in the
common case, there is no increase in the number of TCP segments common case, there is no increase in the number of TCP segments
emitted. For smaller ULP messages, the sender can also apply emitted. For smaller ULP messages, the sender can also apply
packing, i.e. the sender packs as many complete FPDUs as possible packing, i.e. the sender packs as many complete FPDUs as possible
into one TCP segment. The requirement to always have a complete FPDU into one TCP segment. The requirement to always have a complete FPDU
may increase the number of TCP segments emitted. Typically, a ULP may increase the number of TCP segments emitted. Typically, a ULP
skipping to change at page 62, line 23 skipping to change at page 60, line 24
the EMSS. Another class of applications with many small outstanding the EMSS. Another class of applications with many small outstanding
buffers (as compared to EMSS) is expected to use packing when buffers (as compared to EMSS) is expected to use packing when
applicable. Transaction oriented applications are also optimal. applicable. Transaction oriented applications are also optimal.
TCP retransmission is another area that can affect sender behavior. TCP retransmission is another area that can affect sender behavior.
TCP supports retransmission of the exact, originally transmitted TCP supports retransmission of the exact, originally transmitted
segment (see [RFC793] section 2.6, [RFC793] section 3.7 "managing the segment (see [RFC793] section 2.6, [RFC793] section 3.7 "managing the
window" and [RFC1122] section 4.2.2.15). In the unlikely event that window" and [RFC1122] section 4.2.2.15). In the unlikely event that
part of the original segment has been received and acknowledged by part of the original segment has been received and acknowledged by
the remote peer (e.g., a re-segmenting middle box, as documented in the remote peer (e.g., a re-segmenting middle box, as documented in
5.4.1 Re-segmenting Middle boxes and non MPA-aware TCP senders on Section 6.1, Re-segmenting Middle boxes and non optimized MPA/TCP
page 31), a better available bandwidth utilization may be possible by senders on page 29), a better available bandwidth utilization may be
re-transmitting only the missing octets. If an MPA-aware TCP possible by re-transmitting only the missing octets. If an optimized
retransmits complete FPDUs, there may be some marginal bandwidth MPA/TCP retransmits complete FPDUs, there may be some marginal
loss. bandwidth loss.
Another area where a change in the TCP segment number may have impact Another area where a change in the TCP segment number may have impact
is that of Slow Start and Congestion Avoidance. Slow-start is that of Slow Start and Congestion Avoidance. Slow-start
exponential increase is measured in segments per second, as the exponential increase is measured in segments per second, as the
algorithm focuses on the overhead per segment at the source for algorithm focuses on the overhead per segment at the source for
congestion that eventually results in dropped segments. Slow-start congestion that eventually results in dropped segments. Slow-start
exponential bandwidth growth for MPA-aware TCP is similar to any TCP exponential bandwidth growth for optimized MPA/TCP is similar to any
implementation. Congestion Avoidance allows for a linear growth in TCP implementation. Congestion Avoidance allows for a linear growth
available bandwidth when recovering after a packet drop. Similar to in available bandwidth when recovering after a packet drop. Similar
the analysis for slow-start, MPA-aware TCP doesn't change the to the analysis for slow-start, optimized MPA/TCP doesn't change the
behavior of the algorithm. Therefore the average size of the segment behavior of the algorithm. Therefore the average size of the segment
versus EMSS is not a major factor in the assessment of the bandwidth versus EMSS is not a major factor in the assessment of the bandwidth
growth for a sender. Both Slow Start and Congestion Avoidance for an growth for a sender. Both Slow Start and Congestion Avoidance for an
MPA-aware TCP will behave similarly to any TCP sender and allow an optimized MPA/TCP will behave similarly to any TCP sender and allow
MPA-aware TCP to enjoy the theoretical performance limits of the an optimized MPA/TCP to enjoy the theoretical performance limits of
algorithms. the algorithms.
In summary, the ULP messages generated at the sender (e.g., the In summary, the ULP messages generated at the sender (e.g., the
amount of messages grouped for every transmission request) and amount of messages grouped for every transmission request) and
message size distribution has the most significant impact over the message size distribution has the most significant impact over the
number of TCP segments emitted. The worst case effect for certain number of TCP segments emitted. The worst case effect for certain
ULPs (with average message size of EMSS/2+1 to EMSS), is bounded by ULPs (with average message size of EMSS/2+1 to EMSS), is bounded by
an increase of up to 2x in the number of TCP segments and an increase of up to 2x in the number of TCP segments and
acknowledges. In reality the effect is expected to be marginal. acknowledges. In reality the effect is expected to be marginal.
11.2 Receiver implementation 12.2 Receiver implementation
Transport & Network Layer Reassembly Buffers: Transport & Network Layer Reassembly Buffers:
The use of reassembly buffers (either TCP reassembly buffers or IP The use of reassembly buffers (either TCP reassembly buffers or IP
fragmentation reassembly buffers) is implementation dependent. When fragmentation reassembly buffers) is implementation dependent. When
MPA is enabled, reassembly buffers are needed if out of order packets MPA is enabled, reassembly buffers are needed if out of order packets
arrive and Markers are not enabled. Buffers are also needed if FPDU arrive and Markers are not enabled. Buffers are also needed if FPDU
Alignment is lost or if IP fragmentation occurs. This is because the Alignment is lost or if IP fragmentation occurs. This is because the
incoming out of order segment may not contain enough information for incoming out of order segment may not contain enough information for
MPA to process all of the FPDU. For cases where a re-segmenting MPA to process all of the FPDU. For cases where a re-segmenting
middle box is present, or where the TCP sender is not MPA-aware, the middle box is present, or where the TCP sender is not optimized, the
presence of Markers significantly reduces the amount of buffering presence of Markers significantly reduces the amount of buffering
needed. needed.
Recovery from IP Fragmentation must be transparent to the MPA Recovery from IP Fragmentation must be transparent to the MPA
Consumers. Consumers.
11.2.1 Network Layer Reassembly Buffers 12.2.1 Network Layer Reassembly Buffers
Most IP implementations set the IP Don't Fragment bit. Thus upon a Most IP implementations set the IP Don't Fragment bit. Thus upon a
path MTU change, intermediate devices drop the IP datagram if it is path MTU change, intermediate devices drop the IP datagram if it is
too large and reply with an ICMP message which tells the source TCP too large and reply with an ICMP message which tells the source TCP
that the path MTU has changed. This causes TCP to emit segments that the path MTU has changed. This causes TCP to emit segments
conformant with the new path MTU size. Thus IP fragments under most conformant with the new path MTU size. Thus IP fragments under most
conditions should never occur at the receiver. But it is possible. conditions should never occur at the receiver. But it is possible.
There are several options for implementation of network layer There are several options for implementation of network layer
reassembly buffers: reassembly buffers:
skipping to change at page 64, line 20 skipping to change at page 62, line 20
multiple IP datagrams that have all been fragmented). multiple IP datagrams that have all been fragmented).
Note that if the Remote Peer does not implement re-segmentation of Note that if the Remote Peer does not implement re-segmentation of
the data stream upon receiving the ICMP reply updating the path MTU, the data stream upon receiving the ICMP reply updating the path MTU,
it is possible to halt forward progress because the opposite peer it is possible to halt forward progress because the opposite peer
would continue to retransmit using a transport segment size that is would continue to retransmit using a transport segment size that is
too large. This deadlock scenario is no different than if the fabric too large. This deadlock scenario is no different than if the fabric
MTU (not last hop MTU) was reduced after connection setup, and the MTU (not last hop MTU) was reduced after connection setup, and the
remote Node's behavior is not compliant with [RFC1122]. remote Node's behavior is not compliant with [RFC1122].
11.2.2 TCP Reassembly buffers 12.2.2 TCP Reassembly buffers
A TCP reassembly buffer is also needed. TCP reassembly buffers are A TCP reassembly buffer is also needed. TCP reassembly buffers are
needed if FPDU Alignment is lost when using TCP with MPA or when the needed if FPDU Alignment is lost when using TCP with MPA or when the
MPA FPDU spans multiple TCP segments. Buffers are also needed if MPA FPDU spans multiple TCP segments. Buffers are also needed if
Markers are disabled and out of order packets arrive. Markers are disabled and out of order packets arrive.
Since lost FPDU Alignment often means that FPDUs are incomplete, an Since lost FPDU Alignment often means that FPDUs are incomplete, an
MPA on TCP implementation must have a reassembly buffer large enough MPA on TCP implementation must have a reassembly buffer large enough
to recover an FPDU that is less than or equal to the MTU of the to recover an FPDU that is less than or equal to the MTU of the
locally attached link (this should be the largest possible advertised locally attached link (this should be the largest possible advertised
skipping to change at page 65, line 5 skipping to change at page 63, line 5
deadlock the MPA algorithm. If the path MTU is reduced, FPDU deadlock the MPA algorithm. If the path MTU is reduced, FPDU
Alignment requires the source TCP to re-segment the data stream to Alignment requires the source TCP to re-segment the data stream to
the new path MTU. The source MPA will detect this condition and the new path MTU. The source MPA will detect this condition and
reduce the MPA segment size, but any FPDUs already posted to the reduce the MPA segment size, but any FPDUs already posted to the
source TCP will be re-segmented and lose FPDU Alignment. If the source TCP will be re-segmented and lose FPDU Alignment. If the
destination does not support a TCP reassembly buffer, these segments destination does not support a TCP reassembly buffer, these segments
can never be successfully transmitted and the protocol deadlocks. can never be successfully transmitted and the protocol deadlocks.
When a complete FPDU is received, processing continues normally. When a complete FPDU is received, processing continues normally.
11.3 IETF Implementation Interoperability with RDMA Consortium Protocols 12.3 IETF Implementation Interoperability with RDMA Consortium Protocols
The RDMA Consortium created early specifications of the MPA/DDP/RDMA The RDMA Consortium created early specifications of the MPA/DDP/RDMA
protocols and some manufacturers created implementations of those protocols and some manufacturers created implementations of those
protocols before the IETF versions were finalized. These protocols protocols before the IETF versions were finalized. These protocols
and are very similar to the IETF versions making it possible for and are very similar to the IETF versions making it possible for
implementations to be created or modified to support either set of implementations to be created or modified to support either set of
specifications. For those interested, the RDMA Consortium protocol specifications. For those interested, the RDMA Consortium protocol
documents can be obtained at http://www.rdmaconsortium.org. documents can be obtained at http://www.rdmaconsortium.org.
In this section, implementations of MPA/DDP/RDMA that conform to the In this section, implementations of MPA/DDP/RDMA that conform to the
skipping to change at page 65, line 33 skipping to change at page 63, line 33
Request/Reply messages), there is no reason to believe an IETF RNIC Request/Reply messages), there is no reason to believe an IETF RNIC
will interoperate with an RDMAC RNIC because of the differences in will interoperate with an RDMAC RNIC because of the differences in
the version number in the DDP and RDMAP headers on the wire. the version number in the DDP and RDMAP headers on the wire.
Therefore, the ULP or other supporting entity at the RDMAC RNIC must Therefore, the ULP or other supporting entity at the RDMAC RNIC must
implement MPA Request/Reply Frames on behalf of the RNIC in order to implement MPA Request/Reply Frames on behalf of the RNIC in order to
negotiate the connection parameters. The following section describes negotiate the connection parameters. The following section describes
the results following the exchange of the MPA Request/Reply Frames the results following the exchange of the MPA Request/Reply Frames
before the conversion from streaming to RDMA mode. before the conversion from streaming to RDMA mode.
11.3.1 Negotiated Parameters 12.3.1 Negotiated Parameters
Three types of RNICs are considered: Three types of RNICs are considered:
Upgraded RDMAC RNIC - an RNIC implementing the RDMAC protocols which Upgraded RDMAC RNIC - an RNIC implementing the RDMAC protocols which
has a ULP or other supporting entity that exchanges the MPA has a ULP or other supporting entity that exchanges the MPA
Request/Reply Frames in streaming mode before the conversion to Request/Reply Frames in streaming mode before the conversion to
RDMA mode. RDMA mode.
Non-permissive IETF RNIC - an RNIC implementing the IETF protocols Non-permissive IETF RNIC - an RNIC implementing the IETF protocols
which is not capable of implementing the RDMAC protocols. Such which is not capable of implementing the RDMAC protocols. Such
an RNIC can only interoperate with other IETF RNICs. an RNIC can only interoperate with other IETF RNICs.
Permissive IETF RNIC - an RNIC implementing the IETF protocols which Permissive IETF RNIC - an RNIC implementing the IETF protocols which
is capable of implementing the RDMAC protocols on a per is capable of implementing the RDMAC protocols on a per
connection basis. connection basis.
The Permissive IETF RNIC is recommended for those implementers that The Permissive IETF RNIC is recommended for those implementers that
want maximum interoperability with other RNIC implementations. want maximum interoperability with other RNIC implementations.
The values used by these three RNIC types for the MPA, DDP, and RDMAP The values used by these three RNIC types for the MPA, DDP, and RDMAP
versions as well as MPA Markers and CRC are summarized in Figure 12. versions as well as MPA Markers and CRC are summarized in Figure 14.
+----------------++-----------+-----------+-----------+-----------+ +----------------++-----------+-----------+-----------+-----------+
| RNIC TYPE || DDP/RDMAP | MPA | MPA | MPA | | RNIC TYPE || DDP/RDMAP | MPA | MPA | MPA |
| || Version | Revision | Markers | CRC | | || Version | Revision | Markers | CRC |
+----------------++-----------+-----------+-----------+-----------+ +----------------++-----------+-----------+-----------+-----------+
+----------------++-----------+-----------+-----------+-----------+ +----------------++-----------+-----------+-----------+-----------+
| RDMAC || 0 | 0 | 1 | 1 | | RDMAC || 0 | 0 | 1 | 1 |
| || | | | | | || | | | |
+----------------++-----------+-----------+-----------+-----------+ +----------------++-----------+-----------+-----------+-----------+
| IETF || 1 | 1 | 0 or 1 | 0 or 1 | | IETF || 1 | 1 | 0 or 1 | 0 or 1 |
| Non-permissive || | | | | | Non-permissive || | | | |
+----------------++-----------+-----------+-----------+-----------+ +----------------++-----------+-----------+-----------+-----------+
| IETF || 1 or 0 | 1 or 0 | 0 or 1 | 0 or 1 | | IETF || 1 or 0 | 1 or 0 | 0 or 1 | 0 or 1 |
| permissive || | | | | | permissive || | | | |
+----------------++-----------+-----------+-----------+-----------+ +----------------++-----------+-----------+-----------+-----------+
Figure 12. Connection Parameters for the RNIC Types. Figure 14. Connection Parameters for the RNIC Types.
For MPA Markers and MPA CRC, enabled=1, disabled=0. For MPA Markers and MPA CRC, enabled=1, disabled=0.
It is assumed there is no mixing of versions allowed between MPA, DDP It is assumed there is no mixing of versions allowed between MPA, DDP
and RDMAP. The RNIC either generates the RDMAC protocols on the wire and RDMAP. The RNIC either generates the RDMAC protocols on the wire
(version is zero) or the IETF protocols (version is one). (version is zero) or the IETF protocols (version is one).
During the exchange of the MPA Request/Reply Frames, each peer During the exchange of the MPA Request/Reply Frames, each peer
provides its MPA Revision, Marker preference (M: 0=disabled, provides its MPA Revision, Marker preference (M: 0=disabled,
1=enabled), and CRC preference. The MPA Revision provided in the MPA 1=enabled), and CRC preference. The MPA Revision provided in the MPA
Request Frame and the MPA Reply Frame may differ. Request Frame and the MPA Reply Frame may differ.
skipping to change at page 66, line 47 skipping to change at page 64, line 47
DDP and RDMAP, no mixing of versions is allowed. Moreover, the DDP DDP and RDMAP, no mixing of versions is allowed. Moreover, the DDP
and RDMAP version MUST be identical in the two directions. The RNIC and RDMAP version MUST be identical in the two directions. The RNIC
either generates the RDMAC protocols on the wire (version is zero) or either generates the RDMAC protocols on the wire (version is zero) or
the IETF protocols (version is one). the IETF protocols (version is one).
In the following sections, the figures do not discuss CRC negotiation In the following sections, the figures do not discuss CRC negotiation
because there is no interoperability issue for CRCs. Since the RDMAC because there is no interoperability issue for CRCs. Since the RDMAC
RNIC will always request CRC use, then, according to the IETF MPA RNIC will always request CRC use, then, according to the IETF MPA
specification, both peers MUST generate and check CRCs. specification, both peers MUST generate and check CRCs.
11.3.2 RDMAC RNIC and Non-permissive IETF RNIC 12.3.2 RDMAC RNIC and Non-permissive IETF RNIC
Figure 13 shows that a Non-permissive IETF RNIC cannot interoperate Figure 15 shows that a Non-permissive IETF RNIC cannot interoperate
with an RDMAC RNIC, despite the fact that both peers exchange MPA with an RDMAC RNIC, despite the fact that both peers exchange MPA
Request/Reply Frames. For a Non-permissive IETF RNIC, the MPA Request/Reply Frames. For a Non-permissive IETF RNIC, the MPA
negotiation has no effect on the DDP/RDMAP version and it is unable negotiation has no effect on the DDP/RDMAP version and it is unable
to interoperate with the RDMAC RNIC. to interoperate with the RDMAC RNIC.
The rows in the figure show the state of the Marker field in the MPA The rows in the figure show the state of the Marker field in the MPA
Request Frame sent by the MPA Initiator. The columns show the state Request Frame sent by the MPA Initiator. The columns show the state
of the Marker field in the MPA Reply Frame sent by the MPA Responder. of the Marker field in the MPA Reply Frame sent by the MPA Responder.
Each type of RNIC is shown as an Initiator and a Responder. The Each type of RNIC is shown as an Initiator and a Responder. The
connection results are shown in the lower right corner, at the connection results are shown in the lower right corner, at the
skipping to change at page 67, line 35 skipping to change at page 65, line 35
+---------+----------+------++-------+-------+-------+ +---------+----------+------++-------+-------+-------+
| | RDMAC | M=1 || V=0 | close | close | | | RDMAC | M=1 || V=0 | close | close |
| | | || M=1/1 | | | | | | || M=1/1 | | |
| +----------+------++-------+-------+-------+ | +----------+------++-------+-------+-------+
| MPA | | M=0 || close | V=1 | V=1 | | MPA | | M=0 || close | V=1 | V=1 |
|Initiator| IETF | || | M=0/0 | M=0/1 | |Initiator| IETF | || | M=0/0 | M=0/1 |
| |Non-perms.+------++-------+-------+-------+ | |Non-perms.+------++-------+-------+-------+
| | | M=1 || close | V=1 | V=1 | | | | M=1 || close | V=1 | V=1 |
| | | || | M=1/0 | M=1/1 | | | | || | M=1/0 | M=1/1 |
+---------+----------+------++-------+-------+-------+ +---------+----------+------++-------+-------+-------+
Figure 13: MPA negotiation between an RDMAC RNIC and a Non-permissive Figure 15: MPA negotiation between an RDMAC RNIC and a Non-permissive
IETF RNIC. IETF RNIC.
11.3.2.1 RDMAC RNIC Initiator 12.3.2.1 RDMAC RNIC Initiator
If the RDMAC RNIC is the MPA Initiator, its ULP sends an MPA Request If the RDMAC RNIC is the MPA Initiator, its ULP sends an MPA Request
Frame with Rev field set to zero and the M and C bits set to one. Frame with Rev field set to zero and the M and C bits set to one.
Because the Non-permissive IETF RNIC cannot dynamically downgrade the Because the Non-permissive IETF RNIC cannot dynamically downgrade the
version number it uses for DDP and RDMAP, it would send an MPA Reply version number it uses for DDP and RDMAP, it would send an MPA Reply
Frame with the Rev field equal to one and then gracefully close the Frame with the Rev field equal to one and then gracefully close the
connection. connection.
11.3.2.2 Non-Permissive IETF RNIC Initiator 12.3.2.2 Non-Permissive IETF RNIC Initiator
If the Non-permissive IETF RNIC is the MPA Initiator, it sends an MPA If the Non-permissive IETF RNIC is the MPA Initiator, it sends an MPA
Request Frame with Rev field equal to one. The ULP or supporting Request Frame with Rev field equal to one. The ULP or supporting
entity for the RDMAC RNIC responds with an MPA Reply Frame that has entity for the RDMAC RNIC responds with an MPA Reply Frame that has
the Rev field equal to zero and the M bit set to one. The Non- the Rev field equal to zero and the M bit set to one. The Non-
permissive IETF RNIC will gracefully close the connection after it permissive IETF RNIC will gracefully close the connection after it
reads the incompatible Rev field in the MPA Reply Frame. reads the incompatible Rev field in the MPA Reply Frame.
11.3.3 RDMAC RNIC and Permissive IETF RNIC 12.3.3 RDMAC RNIC and Permissive IETF RNIC
Figure 14 shows that a Permissive IETF RNIC can interoperate with an Figure 16 shows that a Permissive IETF RNIC can interoperate with an
RDMAC RNIC regardless of its Marker preference. The figure uses the RDMAC RNIC regardless of its Marker preference. The figure uses the
same format as shown with the Non-permissive IETF RNIC. same format as shown with the Non-permissive IETF RNIC.
+---------------------------++-----------------------+ +---------------------------++-----------------------+
| MPA || MPA | | MPA || MPA |
| CONNECT || Responder | | CONNECT || Responder |
| MODE +-----------------++-------+---------------+ | MODE +-----------------++-------+---------------+
| | RNIC || RDMAC | IETF | | | RNIC || RDMAC | IETF |
| | TYPE || | Permissive | | | TYPE || | Permissive |
| | +------++-------+-------+-------+ | | +------++-------+-------+-------+
skipping to change at page 68, line 30 skipping to change at page 66, line 30
+---------+----------+------++-------+-------+-------+ +---------+----------+------++-------+-------+-------+
| | RDMAC | M=1 || V=0 | N/A | V=0 | | | RDMAC | M=1 || V=0 | N/A | V=0 |
| | | || M=1/1 | | M=1/1 | | | | || M=1/1 | | M=1/1 |
| +----------+------++-------+-------+-------+ | +----------+------++-------+-------+-------+
| MPA | | M=0 || V=0 | V=1 | V=1 | | MPA | | M=0 || V=0 | V=1 | V=1 |
|Initiator| IETF | || M=1/1 | M=0/0 | M=0/1 | |Initiator| IETF | || M=1/1 | M=0/0 | M=0/1 |
| |Permissive+------++-------+-------+-------+ | |Permissive+------++-------+-------+-------+
| | | M=1 || V=0 | V=1 | V=1 | | | | M=1 || V=0 | V=1 | V=1 |
| | | || M=1/1 | M=1/0 | M=1/1 | | | | || M=1/1 | M=1/0 | M=1/1 |
+---------+----------+------++-------+-------+-------+ +---------+----------+------++-------+-------+-------+
Figure 14: MPA negotiation between an RDMAC RNIC and a Permissive Figure 16: MPA negotiation between an RDMAC RNIC and a Permissive
IETF RNIC. IETF RNIC.
A truly Permissive IETF RNIC will recognize an RDMAC RNIC from the A truly Permissive IETF RNIC will recognize an RDMAC RNIC from the
Rev field of the MPA Req/Rep Frames and then adjust its receive Rev field of the MPA Req/Rep Frames and then adjust its receive
Marker state and DDP/RDMAP version to accommodate the RDMAC RNIC. As Marker state and DDP/RDMAP version to accommodate the RDMAC RNIC. As
a result, as an MPA Responder, the Permissive IETF RNIC will never a result, as an MPA Responder, the Permissive IETF RNIC will never
return an MPA Reply Frame with the M bit set to zero. This case is return an MPA Reply Frame with the M bit set to zero. This case is
shown as a not applicable (N/A) in Figure 14. shown as a not applicable (N/A) in Figure 16.
11.3.3.1 RDMAC RNIC Initiator 12.3.3.1 RDMAC RNIC Initiator
When the RDMAC RNIC is the MPA Initiator, its ULP or other supporting When the RDMAC RNIC is the MPA Initiator, its ULP or other supporting
entity prepares an MPA Request message and sets the revision to zero entity prepares an MPA Request message and sets the revision to zero
and the M bit and C bit to one. and the M bit and C bit to one.
The Permissive IETF Responder receives the MPA Request message and The Permissive IETF Responder receives the MPA Request message and
checks the revision field. Since it is capable of generating RDMAC checks the revision field. Since it is capable of generating RDMAC
DDP/RDMAP headers, it sends an MPA Reply message with revision set to DDP/RDMAP headers, it sends an MPA Reply message with revision set to
zero and the M and C bits set to one. The Responder must inform its zero and the M and C bits set to one. The Responder must inform its
ULP that it is generating version zero DDP/RDMAP messages. ULP that it is generating version zero DDP/RDMAP messages.
11.3.3.2 Permissive IETF RNIC Initiator 12.3.3.2 Permissive IETF RNIC Initiator
If the Permissive IETF RNIC is the MPA Initiator, it prepares the MPA If the Permissive IETF RNIC is the MPA Initiator, it prepares the MPA
Request Frame setting the Rev field to one. Regardless of the value Request Frame setting the Rev field to one. Regardless of the value
of the M bit in the MPA Request Frame, the ULP or other supporting of the M bit in the MPA Request Frame, the ULP or other supporting
entity for the RDMAC RNIC will create an MPA Reply Frame with Rev entity for the RDMAC RNIC will create an MPA Reply Frame with Rev
equal to zero and the M bit set to one. equal to zero and the M bit set to one.
When the Initiator reads the Rev field of the MPA Reply Frame and When the Initiator reads the Rev field of the MPA Reply Frame and
finds that its peer is an RDMAC RNIC, it must inform its ULP that it finds that its peer is an RDMAC RNIC, it must inform its ULP that it
should generate version zero DDP/RDMAP messages and enable MPA should generate version zero DDP/RDMAP messages and enable MPA
Markers and CRC. Markers and CRC.
11.3.4 Non-Permissive IETF RNIC and Permissive IETF RNIC 12.3.4 Non-Permissive IETF RNIC and Permissive IETF RNIC
For completeness, Figure 15 shows the results of MPA negotiation For completeness, Figure 17 shows the results of MPA negotiation
between a Non-permissive IETF RNIC and a Permissive IETF RNIC. The between a Non-permissive IETF RNIC and a Permissive IETF RNIC. The
important point from this figure is that an IETF RNIC cannot detect important point from this figure is that an IETF RNIC cannot detect
whether its peer is a Permissive or Non-permissive RNIC. whether its peer is a Permissive or Non-permissive RNIC.
+---------------------------++-------------------------------+ +---------------------------++-------------------------------+
| MPA || MPA | | MPA || MPA |
| CONNECT || Responder | | CONNECT || Responder |
| MODE +-----------------++---------------+---------------+ | MODE +-----------------++---------------+---------------+
| | RNIC || IETF | IETF | | | RNIC || IETF | IETF |
| | TYPE || Non-permissive| Permissive | | | TYPE || Non-permissive| Permissive |
skipping to change at page 69, line 42 skipping to change at page 67, line 42
| |Non-perms.+------++-------+-------+-------+-------+ | |Non-perms.+------++-------+-------+-------+-------+
| | | M=1 || V=1 | V=1 | V=1 | V=1 | | | | M=1 || V=1 | V=1 | V=1 | V=1 |
| | | || M=1/0 | M=1/1 | M=1/0 | M=1/1 | | | | || M=1/0 | M=1/1 | M=1/0 | M=1/1 |
| MPA +----------+------++-------+-------+-------+-------+ | MPA +----------+------++-------+-------+-------+-------+
|Initiator| | M=0 || V=1 | V=1 | V=1 | V=1 | |Initiator| | M=0 || V=1 | V=1 | V=1 | V=1 |
| | IETF | || M=0/0 | M=0/1 | M=0/0 | M=0/1 | | | IETF | || M=0/0 | M=0/1 | M=0/0 | M=0/1 |
| |Permissive+------++-------+-------+-------+-------+ | |Permissive+------++-------+-------+-------+-------+
| | | M=1 || V=1 | V=1 | V=1 | V=1 | | | | M=1 || V=1 | V=1 | V=1 | V=1 |
| | | || M=1/0 | M=1/1 | M=1/0 | M=1/1 | | | | || M=1/0 | M=1/1 | M=1/0 | M=1/1 |
+---------+----------+------++-------+-------+-------+-------+ +---------+----------+------++-------+-------+-------+-------+
Figure 15: MPA negotiation between a Non-permissive IETF RNIC and a Figure 17: MPA negotiation between a Non-permissive IETF RNIC and a
Permissive IETF RNIC. Permissive IETF RNIC.
12 Author's Addresses 13 Author's Addresses
Stephen Bailey Stephen Bailey
Sandburst Corporation Sandburst Corporation
600 Federal Street 600 Federal Street
Andover, MA 01810 USA Andover, MA 01810 USA
Phone: +1 978 689 1614 Phone: +1 978 689 1614
Email: steph@sandburst.com Email: steph@sandburst.com
Paul R. Culley Paul R. Culley
Hewlett-Packard Company Hewlett-Packard Company
skipping to change at page 71, line 5 skipping to change at page 69, line 5
Phone: 512-838-3685 Phone: 512-838-3685
Email: recio@us.ibm.com Email: recio@us.ibm.com
John Carrier John Carrier
Cray Inc. Cray Inc.
411 First Avenue S, Suite 600 411 First Avenue S, Suite 600
Seattle, WA 98104-2860 Seattle, WA 98104-2860
Phone: 206-701-2090 Phone: 206-701-2090
Email: carrier@cray.com Email: carrier@cray.com
13 Acknowledgments 14 Acknowledgments
Dwight Barron Dwight Barron
Hewlett-Packard Company Hewlett-Packard Company
20555 SH 249 20555 SH 249
Houston, Tx. USA 77070-2698 Houston, Tx. USA 77070-2698
Phone: 281-514-2769 Phone: 281-514-2769
Email: dwight.barron@hp.com Email: dwight.barron@hp.com
Jeff Chase Jeff Chase
Department of Computer Science Department of Computer Science
 End of changes. 144 change blocks. 
586 lines changed or deleted 513 lines changed or added

This html diff was produced by rfcdiff 1.32. The latest version is available from http://www.levkowetz.com/ietf/tools/rfcdiff/