File: rfc5046.html

package info (click to toggle)
doc-rfc 20230121-1
links: PTS, VCS
area: non-free
in suites: bookworm, forky, sid, trixie
size: 1,609,944 kB
file content (4757 lines) | stat: -rw-r--r-- 244,027 bytes
parent folder | download | duplicates (2)
<pre>Network Working Group                                              M. Ko
Request for Comments: 5046                               IBM Corporation
Category: Standards Track                                 M. Chadalapaka
                                                 Hewlett-Packard Company
                                                              J. Hufferd
                                                           Brocade, Inc.
                                                                U. Elzur
                                                                 H. Shah
                                                               P. Thaler
                                                    Broadcom Corporation
                                                            October 2007


      <span class="h1">Internet Small Computer System Interface (iSCSI) Extensions</span>
                 <span class="h1">for Remote Direct Memory Access (RDMA)</span>

Status of This Memo

   This document specifies an Internet standards track protocol for the
   Internet community, and requests discussion and suggestions for
   improvements.  Please refer to the current edition of the "Internet
   Official Protocol Standards" (STD 1) for the standardization state
   and status of this protocol.  Distribution of this memo is unlimited.

Abstract

   Internet Small Computer System Interface (iSCSI) Extensions for
   Remote Direct Memory Access (RDMA) provides the RDMA data transfer
   capability to iSCSI by layering iSCSI on top of an RDMA-Capable
   Protocol, such as the iWARP protocol suite.  An RDMA-Capable Protocol
   provides RDMA Read and Write services, which enable data to be
   transferred directly into SCSI I/O Buffers without intermediate data
   copies.  This document describes the extensions to the iSCSI protocol
   to support RDMA services as provided by an RDMA-Capable Protocol,
   such as the iWARP protocol suite.
















<span class="grey">Ko, et al.                  Standards Track                     [Page 1]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-2" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


Table of Contents

   <a href="#section-1">1</a>. Introduction ....................................................<a href="#page-5">5</a>
      <a href="#section-1.1">1.1</a>. Motivation .................................................<a href="#page-5">5</a>
      <a href="#section-1.2">1.2</a>. Architectural Goals ........................................<a href="#page-6">6</a>
      <a href="#section-1.3">1.3</a>. Protocol Overview ..........................................<a href="#page-7">7</a>
      <a href="#section-1.4">1.4</a>. RDMA Services and iSER .....................................<a href="#page-8">8</a>
           <a href="#section-1.4.1">1.4.1</a>. STag ................................................<a href="#page-8">8</a>
           <a href="#section-1.4.2">1.4.2</a>. Send ................................................<a href="#page-9">9</a>
           <a href="#section-1.4.3">1.4.3</a>. RDMA Write ..........................................<a href="#page-9">9</a>
           <a href="#section-1.4.4">1.4.4</a>. RDMA Read ...........................................<a href="#page-9">9</a>
      <a href="#section-1.5">1.5</a>. SCSI Read Overview ........................................<a href="#page-10">10</a>
      <a href="#section-1.6">1.6</a>. SCSI Write Overview .......................................<a href="#page-10">10</a>
      <a href="#section-1.7">1.7</a>. iSCSI/iSER Layering .......................................<a href="#page-10">10</a>
   <a href="#section-2">2</a>. Definitions and Acronyms .......................................<a href="#page-11">11</a>
      <a href="#section-2.1">2.1</a>. Definitions ...............................................<a href="#page-11">11</a>
      <a href="#section-2.2">2.2</a>. Acronyms ..................................................<a href="#page-17">17</a>
      <a href="#section-2.3">2.3</a>. Conventions ...............................................<a href="#page-19">19</a>
   <a href="#section-3">3</a>. Upper Layer Interface Requirements .............................<a href="#page-19">19</a>
      <a href="#section-3.1">3.1</a>. Operational Primitives Offered by iSER ....................<a href="#page-20">20</a>
           <a href="#section-3.1.1">3.1.1</a>. Send_Control .......................................<a href="#page-20">20</a>
           <a href="#section-3.1.2">3.1.2</a>. Put_Data ...........................................<a href="#page-20">20</a>
           <a href="#section-3.1.3">3.1.3</a>. Get_Data ...........................................<a href="#page-21">21</a>
           <a href="#section-3.1.4">3.1.4</a>. Allocate_Connection_Resources ......................<a href="#page-21">21</a>
           <a href="#section-3.1.5">3.1.5</a>. Deallocate_Connection_Resources ....................<a href="#page-22">22</a>
           <a href="#section-3.1.6">3.1.6</a>. Enable_Datamover ...................................<a href="#page-22">22</a>
           <a href="#section-3.1.7">3.1.7</a>. Connection_Terminate ...............................<a href="#page-22">22</a>
           <a href="#section-3.1.8">3.1.8</a>. Notice_Key_Values ..................................<a href="#page-23">23</a>
           <a href="#section-3.1.9">3.1.9</a>. Deallocate_Task_Resources ..........................<a href="#page-23">23</a>
      <a href="#section-3.2">3.2</a>. Operational Primitives Used by iSER .......................<a href="#page-23">23</a>
           <a href="#section-3.2.1">3.2.1</a>. Control_Notify .....................................<a href="#page-24">24</a>
           <a href="#section-3.2.2">3.2.2</a>. Data_Completion_Notify .............................<a href="#page-24">24</a>
           <a href="#section-3.2.3">3.2.3</a>. Data_ACK_Notify ....................................<a href="#page-24">24</a>
           <a href="#section-3.2.4">3.2.4</a>. Connection_Terminate_Notify ........................<a href="#page-25">25</a>
      <a href="#section-3.3">3.3</a>. iSCSI Protocol Usage Requirements .........................<a href="#page-25">25</a>
   <a href="#section-4">4</a>. Lower Layer Interface Requirements .............................<a href="#page-26">26</a>
      <a href="#section-4.1">4.1</a>. Interactions with the RCaP Layer ..........................<a href="#page-26">26</a>
      <a href="#section-4.2">4.2</a>. Interactions with the Transport Layer .....................<a href="#page-27">27</a>
   <a href="#section-5">5</a>. Connection Setup and Termination ...............................<a href="#page-27">27</a>
      <a href="#section-5.1">5.1</a>. iSCSI/iSER Connection Setup ...............................<a href="#page-27">27</a>
           <a href="#section-5.1.1">5.1.1</a>. Initiator Behavior .................................<a href="#page-29">29</a>
           <a href="#section-5.1.2">5.1.2</a>. Target Behavior ....................................<a href="#page-30">30</a>
           <a href="#section-5.1.3">5.1.3</a>. iSER Hello Exchange ................................<a href="#page-32">32</a>
      <a href="#section-5.2">5.2</a>. iSCSI/iSER Connection Termination .........................<a href="#page-33">33</a>
           <a href="#section-5.2.1">5.2.1</a>. Normal Connection Termination at the Initiator .....<a href="#page-33">33</a>
           <a href="#section-5.2.2">5.2.2</a>. Normal Connection Termination at the Target ........<a href="#page-34">34</a>
           <a href="#section-5.2.3">5.2.3</a>. Termination without Logout Request/Response PDUs ...<a href="#page-34">34</a>




<span class="grey">Ko, et al.                  Standards Track                     [Page 2]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-3" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   <a href="#section-6">6</a>. Login/Text Operational Keys ....................................<a href="#page-35">35</a>
      <a href="#section-6.1">6.1</a>. HeaderDigest and DataDigest ...............................<a href="#page-35">35</a>
      <a href="#section-6.2">6.2</a>. MaxRecvDataSegmentLength ..................................<a href="#page-36">36</a>
      <a href="#section-6.3">6.3</a>. RDMAExtensions ............................................<a href="#page-36">36</a>
      <a href="#section-6.4">6.4</a>. TargetRecvDataSegmentLength ...............................<a href="#page-37">37</a>
      <a href="#section-6.5">6.5</a>. InitiatorRecvDataSegmentLength ............................<a href="#page-38">38</a>
      <a href="#section-6.6">6.6</a>. OFMarker and IFMarker .....................................<a href="#page-38">38</a>
      <a href="#section-6.7">6.7</a>. MaxOutstandingUnexpectedPDUs ..............................<a href="#page-38">38</a>
   <a href="#section-7">7</a>. iSCSI PDU Considerations .......................................<a href="#page-39">39</a>
      <a href="#section-7.1">7.1</a>. iSCSI Data-Type PDU .......................................<a href="#page-39">39</a>
      <a href="#section-7.2">7.2</a>. iSCSI Control-Type PDU ....................................<a href="#page-40">40</a>
      <a href="#section-7.3">7.3</a>. iSCSI PDUs ................................................<a href="#page-40">40</a>
           <a href="#section-7.3.1">7.3.1</a>. SCSI Command .......................................<a href="#page-40">40</a>
           <a href="#section-7.3.2">7.3.2</a>. SCSI Response ......................................<a href="#page-42">42</a>
           <a href="#section-7.3.3">7.3.3</a>. Task Management Function Request/Response ..........<a href="#page-44">44</a>
           <a href="#section-7.3.4">7.3.4</a>. SCSI Data-Out ......................................<a href="#page-45">45</a>
           <a href="#section-7.3.5">7.3.5</a>. SCSI Data-In .......................................<a href="#page-46">46</a>
           <a href="#section-7.3.6">7.3.6</a>. Ready to Transfer (R2T) ............................<a href="#page-48">48</a>
           <a href="#section-7.3.7">7.3.7</a>. Asynchronous Message ...............................<a href="#page-50">50</a>
           <a href="#section-7.3.8">7.3.8</a>. Text Request and Text Response .....................<a href="#page-50">50</a>
           <a href="#section-7.3.9">7.3.9</a>. Login Request and Login Response ...................<a href="#page-50">50</a>
           <a href="#section-7.3.10">7.3.10</a>. Logout Request and Logout Response ................<a href="#page-51">51</a>
           <a href="#section-7.3.11">7.3.11</a>. SNACK Request .....................................<a href="#page-51">51</a>
           <a href="#section-7.3.12">7.3.12</a>. Reject ............................................<a href="#page-51">51</a>
           <a href="#section-7.3.13">7.3.13</a>. NOP-Out and NOP-In ................................<a href="#page-51">51</a>
   <a href="#section-8">8</a>. Flow Control and STag Management ...............................<a href="#page-52">52</a>
      <a href="#section-8.1">8.1</a>. Flow Control for RDMA Send Message Types ..................<a href="#page-52">52</a>
           8.1.1. Flow Control for Control-Type PDUs from the
                  Initiator ..........................................<a href="#page-52">52</a>
           8.1.2. Flow Control for Control-Type PDUs from the
                  Target .............................................<a href="#page-55">55</a>
      <a href="#section-8.2">8.2</a>. Flow Control for RDMA Read Resources ......................<a href="#page-56">56</a>
      <a href="#section-8.3">8.3</a>. STag Management ...........................................<a href="#page-56">56</a>
           <a href="#section-8.3.1">8.3.1</a>. Allocation of STags ................................<a href="#page-57">57</a>
           <a href="#section-8.3.2">8.3.2</a>. Invalidation of STags ..............................<a href="#page-57">57</a>
   <a href="#section-9">9</a>. iSER Control and Data Transfer .................................<a href="#page-58">58</a>
      <a href="#section-9.1">9.1</a>. iSER Header Format ........................................<a href="#page-58">58</a>
      <a href="#section-9.2">9.2</a>. iSER Header Format for the iSCSI Control-Type PDU .........<a href="#page-59">59</a>
      <a href="#section-9.3">9.3</a>. iSER Header Format for the iSER Hello Message .............<a href="#page-60">60</a>
      <a href="#section-9.4">9.4</a>. iSER Header Format for the iSER HelloReply Message ........<a href="#page-61">61</a>
      <a href="#section-9.5">9.5</a>. SCSI Data Transfer Operations .............................<a href="#page-62">62</a>
           <a href="#section-9.5.1">9.5.1</a>. SCSI Write Operation ...............................<a href="#page-62">62</a>
           <a href="#section-9.5.2">9.5.2</a>. SCSI Read Operation ................................<a href="#page-63">63</a>
           <a href="#section-9.5.3">9.5.3</a>. Bidirectional Operation ............................<a href="#page-64">64</a>
   <a href="#section-10">10</a>. iSER Error Handling and Recovery ..............................<a href="#page-64">64</a>
      <a href="#section-10.1">10.1</a>. Error Handling ...........................................<a href="#page-64">64</a>
           <a href="#section-10.1.1">10.1.1</a>. Errors in the Transport Layer .....................<a href="#page-64">64</a>
           <a href="#section-10.1.2">10.1.2</a>. Errors in the RCaP Layer ..........................<a href="#page-65">65</a>



<span class="grey">Ko, et al.                  Standards Track                     [Page 3]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-4" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


           <a href="#section-10.1.3">10.1.3</a>. Errors in the iSER Layer ..........................<a href="#page-66">66</a>
           <a href="#section-10.1.4">10.1.4</a>. Errors in the iSCSI Layer .........................<a href="#page-67">67</a>
      <a href="#section-10.2">10.2</a>. Error Recovery ...........................................<a href="#page-69">69</a>
           <a href="#section-10.2.1">10.2.1</a>. PDU Recovery ......................................<a href="#page-69">69</a>
           <a href="#section-10.2.2">10.2.2</a>. Connection Recovery ...............................<a href="#page-70">70</a>
   <a href="#section-11">11</a>. Security Considerations .......................................<a href="#page-71">71</a>
   <a href="#section-12">12</a>. References ....................................................<a href="#page-71">71</a>
      <a href="#section-12.1">12.1</a>. Normative References .....................................<a href="#page-71">71</a>
      <a href="#section-12.2">12.2</a>. Informative References ...................................<a href="#page-72">72</a>
   <a href="#appendix-A">Appendix A</a>. iWARP Message Format for iSER .........................<a href="#page-73">73</a>
      <a href="#appendix-A.1">A.1</a>. iWARP Message Format for iSER Hello Message ...............<a href="#page-73">73</a>
      <a href="#appendix-A.2">A.2</a>. iWARP Message Format for iSER HelloReply Message ..........<a href="#page-74">74</a>
      <a href="#appendix-A.3">A.3</a>. iWARP Message Format for SCSI Read Command PDU ............<a href="#page-75">75</a>
      <a href="#appendix-A.4">A.4</a>. iWARP Message Format for SCSI Read Data ...................<a href="#page-76">76</a>
      <a href="#appendix-A.5">A.5</a>. iWARP Message Format for SCSI Write Command PDU ...........<a href="#page-77">77</a>
      <a href="#appendix-A.6">A.6</a>. iWARP Message Format for RDMA Read Request ................<a href="#page-78">78</a>
      <a href="#appendix-A.7">A.7</a>. iWARP Message Format for Solicited SCSI Write Data ........<a href="#page-79">79</a>
      <a href="#appendix-A.8">A.8</a>. iWARP Message Format for SCSI Response PDU ................<a href="#page-80">80</a>
   <a href="#appendix-B">Appendix B</a>. Architectural Discussion of iSER over InfiniBand ......<a href="#page-81">81</a>
      B.1. The Host Side of the iSCSI and iSER Connections
           in InfiniBand .............................................<a href="#page-81">81</a>
      B.2. The Storage Side of the iSCSI and iSER Mixed
           Network Environment .......................................<a href="#page-82">82</a>
      <a href="#appendix-B.3">B.3</a>. Discovery Processes for an InfiniBand Host ................<a href="#page-82">82</a>
      <a href="#appendix-B.4">B.4</a>. IBTA Connection Specifications ............................<a href="#page-83">83</a>
   Acknowledgments ...................................................<a href="#page-83">83</a>

Table of Figures

   Figure 1. Example of iSCSI/iSER Layering in Full Feature Phase ....<a href="#page-11">11</a>
   Figure 2. iSER Header Format ......................................<a href="#page-58">58</a>
   Figure 3. iSER Header Format for iSCSI Control-Type PDU ...........<a href="#page-59">59</a>
   Figure 4. iSER Header Format for iSER Hello Message ...............<a href="#page-60">60</a>
   Figure 5. iSER Header Format for iSER HelloReply Message ..........<a href="#page-61">61</a>
   Figure 6. SendSE Message containing an iSER Hello Message .........<a href="#page-72">72</a>
   Figure 7. SendSE Message containing an iSER HelloReply Message ....<a href="#page-74">74</a>
   Figure 8. SendSE Message containing a SCSI Read Command PDU .......<a href="#page-75">75</a>
   Figure 9. RDMA Write Message containing SCSI Read Data ............<a href="#page-76">76</a>
   Figure 10. SendSE Message containing a SCSI Write Command PDU .....<a href="#page-77">77</a>
   Figure 11. RDMA Read Request Message ..............................<a href="#page-78">78</a>
   Figure 12. RDMA Read Response Message containing SCSI Write Data ..79
   Figure 13. SendInvSE Message containing SCSI Response PDU .........<a href="#page-80">80</a>
   Figure 14. iSCSI and iSER on IB ...................................<a href="#page-81">81</a>
   Figure 15. Storage Controller with TCP, iWARP, and IB Connections .82







<span class="grey">Ko, et al.                  Standards Track                     [Page 4]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-5" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h2"><a class="selflink" id="section-1" href="#section-1">1</a>.  Introduction</span>

<span class="h3"><a class="selflink" id="section-1.1" href="#section-1.1">1.1</a>.  Motivation</span>

   The iSCSI protocol [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] is a mapping of the SCSI Architecture
   Model (see [<a href="#ref-SAM2">SAM2</a>]) over the TCP protocol.  SCSI commands are carried
   by iSCSI requests, and SCSI responses and status are carried by iSCSI
   responses.  Other iSCSI protocol exchanges and SCSI data are also
   transported in iSCSI Protocol Data Units (PDUs).

   Out-of-order TCP segments in the Traditional iSCSI model have to be
   stored and reassembled before the iSCSI protocol layer within an end
   node can place the data in the iSCSI buffers.  This reassembly is
   required because not every TCP segment is likely to contain an iSCSI
   header to enable its placement, and TCP itself does not have a
   built-in mechanism for signaling Upper Level Protocol (ULP) message
   boundaries to aid placement of out-of-order segments.  This TCP
   reassembly at high network speeds is quite counter-productive for the
   following reasons: wasted memory bandwidth in data copying, the need
   for reassembly memory, wasted CPU cycles in data copying, and the
   general store-and-forward latency from an application perspective.
   TCP reassembly was recognized as a serious issue in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>], and
   the notion of a "sync and steering layer" was introduced that is
   optional to implement and use.  One specific sync and steering
   mechanism, called "markers", was defined in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>], which provides
   an application-level way of framing iSCSI Protocol Data Units (PDUs)
   within the TCP data stream even when the TCP segments are not yet
   reassembled to be in-order.

   With these defined techniques in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>], a Network Interface
   Controller customized for iSCSI (SNIC) could offload the TCP/IP
   processing and support direct data placement, but most iSCSI
   implementations do not support iSCSI "markers", making SNIC marker-
   based direct data placement unusable in practice.

   The iWARP protocol stack provides direct data placement functionality
   that is usable in practice.  In addition, there is interest in using
   iSCSI with other Remote Direct Memory Access (RDMA) protocol stacks
   that support direct data placement, such as the one provided by
   InfiniBand.  The generic term RDMA-Capable Protocol (RCaP) is used to
   refer to the RDMA functionality provided by such protocol stacks.

   With the availability of RDMA-Capable Controllers within a host
   system, which does not have SNICs, it is appropriate for iSCSI to be
   able to exploit the direct data placement function of the RDMA-
   Capable Controller like other applications.





<span class="grey">Ko, et al.                  Standards Track                     [Page 5]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-6" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   iSCSI Extensions for RDMA (iSER) is designed precisely to take
   advantage of generic RDMA technologies -- iSER's goal is to permit
   iSCSI to employ direct data placement and RDMA capabilities using a
   generic RDMA-Capable Controller.  In summary, the iSCSI/iSER protocol
   stack is designed to enable scaling to high speeds by relying on a
   generic data placement process and RDMA technologies and products,
   which enable direct data placement of both in-order and out-of-order
   data.

   This document describes iSER as a protocol extension to iSCSI, both
   for convenience of description and because it is true in a very
   strict protocol sense.  However, note that iSER is in reality
   extending the connectivity of the iSCSI protocol defined in
   [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>], and the name iSER reflects this reality.

   When the iSCSI protocol as defined in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] (i.e., without the
   iSER enhancements) is intended in the rest of the document, the term
   "Traditional iSCSI" is used to make the intention clear.

<span class="h3"><a class="selflink" id="section-1.2" href="#section-1.2">1.2</a>.  Architectural Goals</span>

   This section summarizes the architectural goals that guided the
   design of iSER.

   1. Provide an RDMA data transfer model for iSCSI that enables direct
      in-order or out-of-order data placement of SCSI data into pre-
      allocated SCSI buffers while maintaining in-order data delivery.

   2. Not require any major changes to the SCSI Architecture Model
      [<a href="#ref-SAM2">SAM2</a>] and SCSI command set standards.

   3. Utilize existing iSCSI infrastructure (sometimes referred to as
      "iSCSI ecosystem") including but not limited to MIB,
      bootstrapping, negotiation, naming and discovery, and security.

   4. Require a session to operate in the Traditional iSCSI data
      transfer mode if iSER is not supported by either the initiator or
      the target (i.e., not require iSCSI Full Feature Phase
      interoperability between an end node operating in Traditional
      iSCSI mode, and an end node operating in iSER-assisted mode).

   5. Allow initiator and target implementations to utilize generic
      RDMA-Capable Controllers such as RDMA-enabled Network Interface
      Controllers (RNICs), or to implement iSCSI and iSER in software
      (not require iSCSI- or iSER-specific assists in the RCaP
      implementation or RDMA-Capable Controller).





<span class="grey">Ko, et al.                  Standards Track                     [Page 6]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-7" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   6. Require full and only generic RCaP functionality at both the
      initiator and the target.

   7. Implement a lightweight Datamover protocol for iSCSI with minimal
      state maintenance.

<span class="h3"><a class="selflink" id="section-1.3" href="#section-1.3">1.3</a>.  Protocol Overview</span>

   Consistent with the architectural goals stated in <a href="#section-2.2">Section 2.2</a>, the
   iSER protocol does not require changes in the iSCSI ecosystem or any
   related SCSI specifications.  The iSER protocol defines the mapping
   of iSCSI PDUs to RCaP Messages in such a way that it is entirely
   feasible to realize iSCSI/iSER implementations that are based on
   generic RDMA-Capable Controllers.  The iSER protocol layer requires
   minimal state maintenance to assist an iSCSI Full Feature Phase
   connection, besides being oblivious to the notion of an iSCSI
   session.  The crucial protocol aspects of iSER may be summarized
   thus:

   1. iSER-assisted mode is negotiated during the iSCSI login for each
      session, and an entire iSCSI session can only operate in one mode
      (i.e., a connection in a session cannot operate in iSER-assisted
      mode if a different connection of the same session is already in
      Full Feature Phase in the Traditional iSCSI mode).

   2. Once in iSER-assisted mode, all iSCSI interactions on that
      connection use RCaP Messages.

   3. A Send Message Type is used for carrying an iSCSI control-type PDU
      preceded by an iSER header.  See <a href="#section-7.2">Section 7.2</a> for more details on
      iSCSI control-type PDUs.

   4. RDMA Write, RDMA Read Request, and RDMA Read Response Messages are
      used for carrying control and all data information associated with
      the iSCSI data-type PDUs.  See <a href="#section-7.1">Section 7.1</a> for more details on
      iSCSI data-type PDUs.

   5. Target drives all data transfer (with the exception of iSCSI
      unsolicited data) for SCSI writes and SCSI reads, by issuing RDMA
      Read Requests and RDMA Writes, respectively.

   6. RCaP is responsible for ensuring data integrity.  (For example,
      iWARP includes a CRC-enhanced framing layer called Marker PDU
      Aligned Framing for TCP (MPA) on top of TCP; and for InfiniBand,
      the CRCs are included in the Reliable Connection mode).  For this
      reason, iSCSI header and data digests are negotiated to "None" for
      iSCSI/iSER sessions.




<span class="grey">Ko, et al.                  Standards Track                     [Page 7]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-8" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   7. The iSCSI error recovery hierarchy defined in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] is fully
      supported by iSER.  (However, see <a href="#section-7.3.11">Section 7.3.11</a> on the handling
      of SNACK Request PDUs.)

   8. iSER requires no changes to iSCSI authentication, security, and
      text mode negotiation mechanisms.

   Note that Traditional iSCSI implementations may have to be adapted to
   employ iSER.  It is expected that the adaptation when required is
   likely to be centered around the upper layer interface requirements
   of iSER (<a href="#section-3">Section 3</a>).

<span class="h3"><a class="selflink" id="section-1.4" href="#section-1.4">1.4</a>.  RDMA Services and iSER</span>

   iSER is designed to work with software and/or hardware protocol
   stacks providing the protocol services defined in RCaP documents such
   as [<a href="#ref-RDMAP" title="&quot;A Remote Direct Memory Access Protocol Specification&quot;">RDMAP</a>], [<a href="#ref-IB">IB</a>], etc.  The following subsections describe the key
   protocol elements of RCaP services that iSER relies on.

<span class="h4"><a class="selflink" id="section-1.4.1" href="#section-1.4.1">1.4.1</a>.  STag</span>

   A Steering Tag (STag) is the identifier of an I/O Buffer unique to an
   RDMA-Capable Controller that the iSER layer Advertises to the remote
   iSCSI/iSER node in order to complete a SCSI I/O.

   In iSER, Advertisement is the act of informing the target by the
   initiator that an I/O Buffer is available at the initiator for RDMA
   Read or RDMA Write access by the target.  The initiator Advertises
   the I/O Buffer by including the STag in the header of an iSER Message
   containing the SCSI Command PDU to the target.  The base Tagged
   Offset is not explicitly specified, but the target must always assume
   it as zero.  The buffer length is as specified in the SCSI Command
   PDU.

   The iSER layer at the initiator Advertises the STag for the I/O
   Buffer of each SCSI I/O to the iSER layer at the target in the iSER
   header of the Send with Solicited Event (SendSE) Message containing
   the SCSI Command PDU, unless the I/O can be completely satisfied by
   unsolicited data alone.

   The iSER layer at the target provides the STag for the I/O Buffer
   that is the Data Sink of an RDMA Read Operation (<a href="#section-2.4.4">Section 2.4.4</a>) to
   the RCaP layer on the initiator node -- i.e., this is completely
   transparent to the iSER layer at the initiator.

   The iSER protocol is defined so that the Advertised STag is
   automatically invalidated upon a normal completion of the associated
   task.  This automatic invalidation is realized via the Send with



<span class="grey">Ko, et al.                  Standards Track                     [Page 8]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-9" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Solicited Event and Invalidate (SendInvSE) Message carrying the SCSI
   Response PDU.  There are two exceptions to this automatic
   invalidation -- bidirectional commands, and abnormal completion of a
   command.  The iSER layer at the initiator is required to explicitly
   invalidate the STag in these cases, in addition to sanity checking
   the automatic invalidation even when that does happen.

<span class="h4"><a class="selflink" id="section-1.4.2" href="#section-1.4.2">1.4.2</a>.  Send</span>

   Send is the RDMA Operation that is not addressed to an Advertised
   buffer by the sending side, and thus uses Untagged buffers on the
   receiving side.

   The iSER layer at the initiator uses the Send Operation to transmit
   any iSCSI control-type PDU to the target.  As an example, the
   initiator uses Send Operations to transfer iSER Messages containing
   SCSI Command PDUs to the iSER layer at the target.

   An iSER layer at the target uses the Send Operation to transmit any
   iSCSI control-type PDU to the initiator.  As an example, the target
   uses Send Operations to transfer iSER Messages containing SCSI
   Response PDUs to the iSER layer at the initiator.

<span class="h4"><a class="selflink" id="section-1.4.3" href="#section-1.4.3">1.4.3</a>.  RDMA Write</span>

   RDMA Write is the RDMA Operation that is used to place data into an
   Advertised buffer on the receiving side.  The sending side addresses
   the Message using an STag and a Tagged Offset that are valid on the
   Data Sink.

   The iSER layer at the target uses the RDMA Write Operation to
   transfer the contents of a local I/O Buffer to an Advertised I/O
   Buffer at the initiator.  The iSER layer at the target uses the RDMA
   Write to transfer whole or part of the data required to complete a
   SCSI read command.

   The iSER layer at the initiator does not employ RDMA Writes.

<span class="h4"><a class="selflink" id="section-1.4.4" href="#section-1.4.4">1.4.4</a>.  RDMA Read</span>

   RDMA Read is the RDMA Operation that is used to retrieve data from an
   Advertised buffer on a remote node.  The sending side of the RDMA
   Read Request addresses the Message using an STag and a Tagged Offset
   that are valid on the Data Source in addition to providing a valid
   local STag and Tagged Offset that identify the Data Sink.

   The iSER layer at the target uses the RDMA Read Operation to transfer
   the contents of an Advertised I/O Buffer at the initiator to a local



<span class="grey">Ko, et al.                  Standards Track                     [Page 9]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-10" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   I/O Buffer at the target.  The iSER layer at the target uses the RDMA
   Read to fetch whole or part of the data required to complete a SCSI
   write command.

   The iSER layer at the initiator does not employ RDMA Reads.

<span class="h3"><a class="selflink" id="section-1.5" href="#section-1.5">1.5</a>.  SCSI Read Overview</span>

   The iSER layer at the initiator receives the SCSI Command PDU from
   the iSCSI layer.  The iSER layer at the initiator generates an STag
   for the I/O Buffer of the SCSI Read and Advertises the buffer by
   including the STag as part of the iSER header for the PDU.  The iSER
   Message is transferred to the target using a SendSE Message.

   The iSER layer at the target uses one or more RDMA Writes to transfer
   the data required to complete the SCSI Read.

   The iSER layer at the target uses a SendInvSE Message to transfer the
   SCSI Response PDU back to the iSER layer at the initiator.  The iSER
   layer at the initiator notifies the iSCSI layer of the availability
   of the SCSI Response PDU.

<span class="h3"><a class="selflink" id="section-1.6" href="#section-1.6">1.6</a>.  SCSI Write Overview</span>

   The iSER layer at the initiator receives the SCSI Command PDU from
   the iSCSI layer.  If solicited data transfer is involved, the iSER
   layer at the initiator generates an STag for the I/O Buffer of the
   SCSI Write and Advertises the buffer by including the STag as part of
   the iSER header for the PDU.  The iSER Message is transferred to the
   target using a SendSE Message.

   The iSER layer at the initiator may optionally send one or more non-
   immediate unsolicited data PDUs to the target using Send Message
   Types.

   If solicited data transfer is involved, the iSER layer at the target
   uses one or more RDMA Reads to transfer the data required to complete
   the SCSI Write.

   The iSER layer at the target uses a SendInvSE Message to transfer the
   SCSI Response PDU back to the iSER layer at the initiator.  The iSER
   layer at the initiator notifies the iSCSI layer of the availability
   of the SCSI Response PDU.

<span class="h3"><a class="selflink" id="section-1.7" href="#section-1.7">1.7</a>.  iSCSI/iSER Layering</span>

   iSCSI Extensions for RDMA (iSER) is layered between the iSCSI layer
   and the RCaP layer.  Note that the RCaP layer may be composed of one



<span class="grey">Ko, et al.                  Standards Track                    [Page 10]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-11" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   or more distinct protocol layers depending on the specifics of the
   RCaP.  Figure 1 shows an example of the relationship between SCSI,
   iSCSI, iSER, and the different RCaP layers.  For TCP, the RCaP is
   iWARP.  For InfiniBand, the RCaP is the Reliable Connected Transport
   Service.  Note that the iSCSI layer as described here supports the
   RDMA Extensions as used in iSER.

                 +-------------------------------------+
                 |              SCSI                   |
                 +-------------------------------------+
                 |              iSCSI                  |
      DI ------&gt; +-------------------------------------+
                 |              iSER                   |
                 +---------+--------------+------------+
                 |  RDMAP  |              |            |
                 +---------+  InfiniBand  |            |
                 |   DDP   |   Reliable   |   Other    |
                 +---------+  Connected   |   RDMA-    |
                 |   MPA   |  Transport   |  Capable   |
                 +---------+   Service    |  Protocol  |
                 |   TCP   |              |            |
                 +---------+--------------+------------+
                 |         |  InfiniBand  |   Other    |
                 |    IP   |   Network    |  Network   |
                 |         |    Layer     |   Layer    |
                 +---------+--------------+------------+

   Figure 1.  Example of iSCSI/iSER Layering in Full Feature Phase

<span class="h2"><a class="selflink" id="section-2" href="#section-2">2</a>.  Definitions and Acronyms</span>

<span class="h3"><a class="selflink" id="section-2.1" href="#section-2.1">2.1</a>.  Definitions</span>

   Advertisement (Advertised, Advertise, Advertisements, Advertises) -
      The act of informing a remote iSER layer that a local node's
      buffer is available to it.  A Node makes a buffer available for
      incoming RDMA Read Request Message or incoming RDMA Write Message
      access by informing the remote iSER layer of the Tagged Buffer
      identifiers (STag, TO, and buffer length).  Note that this
      Advertisement of Tagged Buffer information is the responsibility
      of the iSER layer on either end and is not defined by the RDMA-
      Capable Protocol.  A typical method would be for the iSER layer to
      embed the Tagged Buffer's STag, TO, and buffer length in a Send
      Message destined for the remote iSER layer.

   Completion (Completed, Complete, Completes) - Completion is defined
      as the process by the RDMA-Capable Protocol layer to inform the




<span class="grey">Ko, et al.                  Standards Track                    [Page 11]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-12" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


      iSER layer, that a particular RDMA Operation has performed all
      functions specified for the RDMA Operation.

   Connection - A connection is a logical circuit between the initiator
      and the target, e.g., a TCP connection.  Communication between the
      initiator and the target occurs over one or more connections.  The
      connections carry control messages, SCSI commands, parameters, and
      data within iSCSI Protocol Data Units (iSCSI PDUs).

   Connection Handle - An information element that identifies the
      particular iSCSI connection and is unique for a given iSCSI-iSER
      pair.  Every invocation of an Operational Primitive is qualified
      with the Connection Handle.

   Data Sink - The peer receiving a data payload.  Note that the Data
      Sink can be required to both send and receive RCaP Messages to
      transfer a data payload.

   Data Source - The peer sending a data payload.  Note that the Data
      Source can be required to both send and receive RCaP Messages to
      transfer a data payload.

   Datamover Interface (DI) - The interface between the iSCSI layer and
      the Datamover layer as described in [<a href="#ref-DA" title="&quot;DA: Datamover Architecture for the Internet Small Computer System Interface (iSCSI)&quot;">DA</a>].

   Datamover Layer - A layer that is directly below the iSCSI layer and
      above the underlying transport layers.  This layer exposes and
      uses a set of transport independent Operational Primitives for the
      communication between the iSCSI layer and itself.  The Datamover
      layer, operating in conjunction with the transport layers, moves
      the control and data information on the iSCSI connection.  In this
      specification, the iSER layer is the Datamover layer.

   Datamover Protocol - A Datamover protocol is the wire-protocol that
      is defined to realize the Datamover layer functionality.  In this
      specification, the iSER protocol is the Datamover protocol.

   Event - An indication provided by the RDMA-Capable Protocol layer to
      the iSER layer to indicate a Completion or other condition
      requiring immediate attention.

   Inbound RDMA Read Queue Depth (IRD) - The maximum number of incoming
      outstanding RDMA Read Requests that the RDMA-Capable Controller
      can handle on a particular RCaP Stream at the Data Source.  For
      some RDMA-Capable Protocol layers, the term "IRD" may be known by
      a different name.  For example, for InfiniBand, the equivalent for
      IRD is the Responder Resources.




<span class="grey">Ko, et al.                  Standards Track                    [Page 12]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-13" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Invalidate STag - A mechanism used to prevent the Remote Peer from
      reusing a previous explicitly Advertised STag, until the iSER
      layer at the local node makes it available through a subsequent
      explicit Advertisement.

   I/O Buffer - A buffer that is used in a SCSI Read or Write operation
      so SCSI data may be sent from or received into that buffer.

   iSCSI - The iSCSI protocol as defined in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] is a mapping of
      the SCSI Architecture Model of SAM-2 over TCP.

   iSCSI control-type PDU - Any iSCSI PDU that is not an iSCSI data-
      type PDU and also not a SCSI Data-out PDU carrying solicited data
      is defined as an iSCSI control-type PDU.  Specifically, it is to
      be noted that SCSI Data-out PDUs for unsolicited data are defined
      as iSCSI control-type PDUs.

   iSCSI data-type PDU - An iSCSI data-type PDU is defined as an iSCSI
      PDU that causes data transfer, transparent to the remote iSCSI
      layer, to take place between the peer iSCSI nodes on a Full
      Feature Phase iSCSI connection.  An iSCSI data-type PDU, when
      requested for transmission by the sender iSCSI layer, results in
      the associated data transfer without the participation of the
      remote iSCSI layer, i.e. the PDU itself is not delivered as-is to
      the remote iSCSI layer.  The following iSCSI PDUs constitute the
      set of iSCSI data-type PDUs - SCSI Data-In PDU and R2T PDU.

   iSCSI Layer - A layer in the protocol stack implementation within an
      end node that implements the iSCSI protocol and interfaces with
      the iSER layer via the Datamover Interface.

   iSCSI PDU (iSCSI Protocol Data Unit) - The iSCSI layer at the
      initiator and the iSCSI layer at the target divide their
      communications into messages.  The term "iSCSI protocol data unit"
      (iSCSI PDU) is used for these messages.

   iSCSI/iSER Connection - An iSER-assisted iSCSI connection.

   iSCSI/iSER Session - An iSER-assisted iSCSI session.

   iSCSI-iSER Pair - The iSCSI layer and the underlying iSER layer.

   iSER - iSCSI Extensions for RDMA, the protocol defined in this
      document.

   iSER-assisted - A term generally used to describe the operation of
      iSCSI when the iSER functionality is also enabled below the iSCSI
      layer for the specific iSCSI/iSER connection in question.



<span class="grey">Ko, et al.                  Standards Track                    [Page 13]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-14" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   iSER-IRD - This variable represents the maximum number of incoming
      outstanding RDMA Read Requests that the iSER layer at the
      initiator declares on a particular RCaP Stream.

   iSER-ORD - This variable represents the maximum number of outstanding
      RDMA Read Requests that the iSER layer can initiate on a
      particular RCaP Stream.  This variable is maintained only by the
      iSER layer at the target.

   iSER Layer - The layer that implements the iSCSI Extensions for RDMA
      (iSER) protocol.

   iWARP - A suite of wire protocols comprising of [<a href="#ref-RDMAP" title="&quot;A Remote Direct Memory Access Protocol Specification&quot;">RDMAP</a>], [<a href="#ref-DDP" title="&quot;Direct Data Placement over Reliable Transports&quot;">DDP</a>], and
      [<a href="#ref-MPA" title="&quot;Marker PDU Aligned Framing for TCP Specification&quot;">MPA</a>] when layered above [<a href="#ref-TCP" title="&quot;Transmission Control Protocol&quot;">TCP</a>].  [<a href="#ref-RDMAP" title="&quot;A Remote Direct Memory Access Protocol Specification&quot;">RDMAP</a>] and [<a href="#ref-DDP" title="&quot;Direct Data Placement over Reliable Transports&quot;">DDP</a>] may be layered
      above SCTP or other transport protocols.

   Local Mapping - A task state record maintained by the iSER layer that
      associates the Initiator Task Tag to the local STag(s).  The
      specifics of the record structure are implementation dependent.

   Local Peer - The implementation of the RDMA-Capable Protocol on the
      local end of the connection.  Used to refer to the local entity
      when describing protocol exchanges or other interactions between
      two Nodes.

   Node - A computing device attached to one or more links of a network.
      A Node in this context does not refer to a specific application or
      protocol instantiation running on the computer.  A Node may
      consist of one or more RDMA-Capable Controllers installed in a
      host computer.

   Operational Primitive - An Operational Primitive is an abstract
      functional interface procedure that requests that another layer
      perform a specific action on the requestor's behalf or notifies
      the other layer of some event.  The Datamover Interface between an
      iSCSI layer and a Datamover layer within an iSCSI end node uses a
      set of Operational Primitives to define the functional interface
      between the two layers.  Note that not every invocation of an
      Operational Primitive may elicit a response from the requested
      layer.  A full discussion of the Operational Primitive types and
      request-response semantics available to iSCSI and iSER can be
      found in [<a href="#ref-DA" title="&quot;DA: Datamover Architecture for the Internet Small Computer System Interface (iSCSI)&quot;">DA</a>].

   Outbound RDMA Read Queue Depth (ORD) - The maximum number of
      outstanding RDMA Read Requests that the RDMA-Capable Controller
      can initiate on a particular RCaP Stream at the Data Sink.  For





<span class="grey">Ko, et al.                  Standards Track                    [Page 14]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-15" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


      some RDMA-Capable Protocol layer, the term "ORD" may be known by a
      different name.  For example, for InfiniBand, the equivalent for
      ORD is the Initiator Depth.

   Phase-Collapse - Refers to the optimization in iSCSI where the SCSI
      status is transferred along with the final SCSI Data-in PDU from a
      target.  See <a href="./rfc3720#section-3.2">Section&nbsp;3.2 in [RFC3720]</a>.

   RCaP Message - One or more packets of the network layer comprising a
      single RDMA Operation or a part of an RDMA Read Operation of the
      RDMA-Capable Protocol.  For iWARP, an RCaP Message is known as an
      RDMAP Message.

   RCaP Stream - A single bidirectional association between the peer
      RDMA-Capable Protocol layers on two Nodes over a single
      transport-level stream.  For iWARP, an RCaP Stream is known as an
      RDMAP Stream, and the association is created when the connection
      transitions to iSER-assisted mode following a successful Login
      Phase during which iSER support is negotiated.

   RDMA-Capable Protocol (RCaP) - The protocol or protocol suite that
      provides a reliable RDMA transport functionality, e.g., iWARP,
      InfiniBand, etc.

   RDMA-Capable Controller - A network I/O adapter or embedded
      controller with RDMA functionality.  For example, for iWARP, this
      could be an RNIC, and for InfiniBand, this could be a HCA (Host
      Channel Adapter) or TCA (Target Channel Adapter).

   RDMA-enabled Network Interface Controller (RNIC) - A network I/O
      adapter or embedded controller with iWARP functionality.

   RDMA Operation - A sequence of RCaP Messages, including control
      Messages, to transfer data from a Data Source to a Data Sink.  The
      following RDMA Operations are defined - RDMA Write Operation, RDMA
      Read Operation, Send Operation, Send with Invalidate Operation,
      Send with Solicited Event Operation, Send with Solicited Event and
      Invalidate Operation, and Terminate Operation.

   RDMA Protocol (RDMAP) - A wire protocol that supports RDMA Operations
      to transfer ULP data between a Local Peer and the Remote Peer as
      described in [<a href="#ref-RDMAP" title="&quot;A Remote Direct Memory Access Protocol Specification&quot;">RDMAP</a>].

   RDMA Read Operation - An RDMA Operation used by the Data Sink to
      transfer the contents of a Data Source buffer from the Remote Peer
      to a Data Sink buffer at the Local Peer.  An RDMA Read operation
      consists of a single RDMA Read Request Message and a single RDMA
      Read Response Message.



<span class="grey">Ko, et al.                  Standards Track                    [Page 15]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-16" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   RDMA Read Request - An RCaP Message used by the Data Sink to request
      that the Data Source transfer the contents of a buffer.  The RDMA
      Read Request Message describes both the Data Source and the Data
      Sink buffers.

   RDMA Read Response - An RCaP Message used by the Data Source to
      transfer the contents of a buffer to the Data Sink, in response to
      an RDMA Read Request.  The RDMA Read Response Message only
      describes the Data Sink buffer.

   RDMA Write Operation - An RDMA Operation used by the Data Source to
      transfer the contents of a Data Source buffer from the Local Peer
      to a Data Sink buffer at the Remote Peer.  The RDMA Write Message
      only describes the Data Sink buffer.

   Remote Direct Memory Access (RDMA) - A method of accessing memory on
      a remote system in which the local system specifies the remote
      location of the data to be transferred.  Employing an RDMA-
      Capable Controller in the remote system allows the access to take
      place without interrupting the processing of the CPU(s) on the
      system.

   Remote Mapping - A task state record maintained by the iSER layer
      that associates the Initiator Task Tag to the Advertised STag(s).
      The specifics of the record structure are implementation
      dependent.

   Remote Peer - The implementation of the RDMA-Capable Protocol on the
      opposite end of the connection.  Used to refer to the remote
      entity when describing protocol exchanges or other interactions
      between two Nodes.

   SCSI Layer - This layer builds/receives SCSI CDBs (Command Descriptor
      Blocks) and sends/receives them with the remaining command execute
      [<a href="#ref-SAM2">SAM2</a>] parameters to/from the iSCSI layer.

   Send - An RDMA Operation that transfers the contents of a Buffer from
      the Local Peer to a Buffer at the Remote Peer.

   Send Message Type - A Send Message, Send with Invalidate Message,
      Send with Solicited Event Message, or Send with Solicited Event
      and Invalidate Message.

   SendInvSE Message - A Send with Solicited Event and Invalidate
      Message.

   SendSE Message - A Send with Solicited Event Message.




<span class="grey">Ko, et al.                  Standards Track                    [Page 16]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-17" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Sequence Number (SN) - DataSN for a SCSI Data-in PDU and R2TSN for an
      R2T PDU.  The semantics for both types of sequence numbers are as
      defined in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>].

   Session, iSCSI Session - The group of connections that link an
      initiator SCSI port with a target SCSI port form an iSCSI session
      (equivalent to a SCSI I-T nexus).  Connections can be added to and
      removed from a session even while the I-T nexus is intact.  Across
      all connections within a session, an initiator sees one and the
      same target.

   Solicited Event (SE) - A facility by which an RDMA Operation sender
      may cause an Event to be generated at the recipient, if the
      recipient is configured to generate such an Event, when a Send
      with Solicited Event or Send with Solicited Event and Invalidate
      Message is received.

   Steering Tag (STag) - An identifier of a Tagged Buffer on a Node
      (Local or Remote) as defined in [<a href="#ref-RDMAP" title="&quot;A Remote Direct Memory Access Protocol Specification&quot;">RDMAP</a>] and [<a href="#ref-DDP" title="&quot;Direct Data Placement over Reliable Transports&quot;">DDP</a>].  For other
      RDMA-Capable Protocols, the Steering Tag may be known by different
      names but will be herein referred to as STags.  For example, for
      InfiniBand, a Remote STag is known as an R-Key, and a local STag
      is known as an L-Key, and both will be considered STags.

   Tagged Buffer - A buffer that is explicitly Advertised to the iSER
      layer at the remote node through the exchange of an STag, Tagged
      Offset, and length.

   Tagged Offset (TO) - The offset within a Tagged Buffer.

   Traditional iSCSI - Refers to the iSCSI protocol as defined in
      [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] (i.e. without the iSER enhancements).

   Untagged Buffer - A buffer that is not explicitly Advertised to the
      iSER layer at the remode node.

<span class="h3"><a class="selflink" id="section-2.2" href="#section-2.2">2.2</a>.  Acronyms</span>

      Acronym        Definition
      --------------------------------------------------------------

      AHS            Additional Header Segment

      BHS            Basic Header Segment

      CO             Connection Only

      CRC            Cyclic Redundancy Check



<span class="grey">Ko, et al.                  Standards Track                    [Page 17]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-18" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


      DDP            Direct Data Placement Protocol

      DI             Datamover Interface

      HCA            Host Channel Adapter

      IANA           Internet Assigned Numbers Authority

      IB             InfiniBand

      IETF           Internet Engineering Task Force

      I/O            Input - Output

      IO             Initialize Only

      IP             Internet Protocol

      IPoIB          IP over InfiniBand

      IPsec          Internet Protocol Security

      iSER           iSCSI Extensions for RDMA

      ITT            Initiator Task Tag

      LO             Leading Only

      MPA            Marker PDU Aligned Framing for TCP

      NOP            No Operation

      NSG            Next Stage (during the iSCSI Login Phase)

      OS             Operating System

      PDU            Protocol Data Unit

      R2T            Ready To Transfer

      R2TSN          Ready To Transfer Sequence Number

      RDMA           Remote Direct Memory Access

      RDMAP          Remote Direct Memory Access Protocol

      RFC            Request For Comments




<span class="grey">Ko, et al.                  Standards Track                    [Page 18]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-19" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


      RNIC           RDMA-enabled Network Interface Controller

      SAM2           SCSI Architecture Model - 2

      SCSI           Small Computer Systems Interface

      SNACK          Selective Negative Acknowledgment - also
                     Sequence Number Acknowledgement for data

      STag           Steering Tag

      SW             Session Wide

      TCA            Target Channel Adapter

      TCP            Transmission Control Protocol

      TMF            Task Management Function

      TTT            Target Transfer Tag

      TO             Tagged Offset

      ULP            Upper Level Protocol

<span class="h3"><a class="selflink" id="section-2.3" href="#section-2.3">2.3</a>.  Conventions</span>

   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
   "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
   document are to be interpreted as described in [<a href="./rfc2119" title="&quot;Key words for use in RFCs to Indicate Requirement Levels&quot;">RFC2119</a>].

<span class="h2"><a class="selflink" id="section-3" href="#section-3">3</a>.  Upper Layer Interface Requirements</span>

   This section discusses the upper layer interface requirements in the
   form of an abstract model of the required interactions between the
   iSCSI layer and the iSER layer.  The abstract model used here is
   derived from the architectural model described in [<a href="#ref-DA" title="&quot;DA: Datamover Architecture for the Internet Small Computer System Interface (iSCSI)&quot;">DA</a>].  [<a href="#ref-DA" title="&quot;DA: Datamover Architecture for the Internet Small Computer System Interface (iSCSI)&quot;">DA</a>] also
   provides a functional overview of the interactions between the iSCSI
   layer and the Datamover layer as intended by the Datamover
   Architecture.

   The interface requirements are specified by Operational Primitives.
   An Operational Primitive is an abstract functional interface
   procedure between the iSCSI layer and the iSER layer that requests
   one layer to perform a specific action on behalf of the other layer
   or notifies the other layer of some event.  Whenever an Operational
   Primitive in invoked, the Connection_Handle qualifier is used to
   identify a particular iSCSI connection.  For some Operational



<span class="grey">Ko, et al.                  Standards Track                    [Page 19]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-20" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Primitives, a Data_Descriptor is used to identify the iSCSI/SCSI data
   buffer associated with the requested or completed operation.

   The abstract model and the Operational Primitives defined in this
   section facilitate the description of the iSER protocol.  In the rest
   of the iSER specification, the compliance statements related to the
   use of these Operational Primitives are only for the purpose of the
   required interactions between the iSCSI layer and the iSER layer.
   Note that the compliance statements related to the Operational
   Primitives in the rest of this specification only mandate functional
   equivalence on implementations, but do not put any requirements on
   the implementation specifics of the interface between the iSCSI layer
   and the iSER layer.

   Each Operational Primitive is invoked with a set of qualifiers that
   specify the information context for performing the specific action
   being requested of the Operational Primitive.  While the qualifiers
   are required, the method of realizing the qualifiers (e.g., by
   passing synchronously with invocation, or by retrieving from task
   context, or by retrieving from shared memory, etc.) is implementation
   dependent.

<span class="h3"><a class="selflink" id="section-3.1" href="#section-3.1">3.1</a>.  Operational Primitives Offered by iSER</span>

   The iSER protocol layer MUST support the following Operational
   Primitives to be used by the iSCSI protocol layer.

<span class="h4"><a class="selflink" id="section-3.1.1" href="#section-3.1.1">3.1.1</a>.  Send_Control</span>

      Input qualifiers:  Connection_Handle, BHS and AHS (if any) of the
      iSCSI PDU, PDU-specific qualifiers

      Return results:  Not specified

   This is used by the iSCSI layers at the initiator and the target to
   request the outbound transfer of an iSCSI control-type PDU (see
   <a href="#section-7.2">Section 7.2</a>).  Qualifiers that only apply for a particular control-
   type PDU are known as PDU-specific qualifiers, e.g.,
   ImmediateDataSize for a SCSI write command.  For details on PDU-
   specific qualifiers, see <a href="#section-7.3">Section 7.3</a>.  The iSCSI layer can only
   invoke the Send_Control Operational Primitive when the connection is
   in iSER-assisted mode.

<span class="h4"><a class="selflink" id="section-3.1.2" href="#section-3.1.2">3.1.2</a>.  Put_Data</span>

      Input qualifiers:  Connection_Handle, content of a SCSI Data-in
      PDU header, Data_Descriptor, Notify_Enable




<span class="grey">Ko, et al.                  Standards Track                    [Page 20]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-21" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


      Return results:  Not specified

   This is used by the iSCSI layer at the target to request the outbound
   transfer of data for a SCSI Data-in PDU from the buffer identified by
   the Data_Descriptor qualifier.  The iSCSI layer can only invoke the
   Put_Data Operational Primitive when the connection is in iSER-
   assisted mode.

   The Notify_Enable qualifier is used to indicate to the iSER layer
   whether or not it should generate an eventual local completion
   notification to the iSCSI layer.  See <a href="#section-3.2.2">Section 3.2.2</a> on
   Data_Completion_Notify for details.

<span class="h4"><a class="selflink" id="section-3.1.3" href="#section-3.1.3">3.1.3</a>.  Get_Data</span>

      Input qualifiers:  Connection_Handle, content of an R2T PDU,
      Data_Descriptor, Notify_Enable

      Return results:  Not specified

   This is used by the iSCSI layer at the target to request the inbound
   transfer of solicited data requested by an R2T PDU into the buffer
   identified by the Data_Descriptor qualifier.  The iSCSI layer can
   only invoke the Get_Data Operational Primitive when the connection is
   in iSER-assisted mode.

   The Notify_Enable qualifier is used to indicate to the iSER layer
   whether or not it should generate the eventual local completion
   notification to the iSCSI layer.  See <a href="#section-3.2.2">Section 3.2.2</a> on
   Data_Completion_Notify for details.

<span class="h4"><a class="selflink" id="section-3.1.4" href="#section-3.1.4">3.1.4</a>.  Allocate_Connection_Resources</span>

      Input qualifiers:  Connection_Handle, Resource_Descriptor
      (optional)

      Return results:  Status

   This is used by the iSCSI layers at the initiator and the target to
   request the allocation of all connection resources necessary to
   support RCaP for an operational iSCSI/iSER connection.  The iSCSI
   layer may optionally specify the implementation-specific resource
   requirements for the iSCSI connection using the Resource_Descriptor
   qualifier.

   A return result of Status=success means that the invocation
   succeeded, and a return result of Status=failure means that the
   invocation failed.  If the invocation is for a Connection_Handle for



<span class="grey">Ko, et al.                  Standards Track                    [Page 21]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-22" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   which an earlier invocation succeeded, the request will be ignored by
   the iSER layer and the result of Status=success will be returned.
   Only one Allocate_Connection_Resources Operational Primitive
   invocation can be outstanding for a given Connection_Handle at any
   time.

<span class="h4"><a class="selflink" id="section-3.1.5" href="#section-3.1.5">3.1.5</a>.  Deallocate_Connection_Resources</span>

      Input qualifiers:  Connection_Handle

      Return results:  Not specified

   This is used by the iSCSI layers at the initiator and the target to
   request the deallocation of all connection resources that were
   allocated earlier as a result of a successful invocation of the
   Allocate_Connection_Resources Operational Primitive.

<span class="h4"><a class="selflink" id="section-3.1.6" href="#section-3.1.6">3.1.6</a>.  Enable_Datamover</span>

      Input qualifiers:  Connection_Handle,
      Transport_Connection_Descriptor, Final Login_Response_PDU
      (optional)

      Return results:  Not specified

   This is used by the iSCSI layers at the initiator and the target to
   request that a specified iSCSI connection be transitioned to iSER-
   assisted mode.  The Transport_Connection_Descriptor qualifier is used
   to identify the specific connection associated with the
   Connection_Handle.  The iSCSI layer can only invoke the
   Enable_Datamover Operational Primitive when there is a corresponding
   prior resource allocation.

   The Final_Login_Response_PDU input qualifier is applicable only for a
   target, and contains the final Login Response PDU that concludes the
   iSCSI Login Phase.  If the underlying transport is TCP, the final
   Login Response PDU must be sent as a byte stream as expected by the
   iSCSI layer at the initiator.  When this qualifier is used, the iSER
   layer at the target MUST transmit this final Login Response PDU
   before transitioning to iSER-assisted mode.

<span class="h4"><a class="selflink" id="section-3.1.7" href="#section-3.1.7">3.1.7</a>.  Connection_Terminate</span>

      Input qualifiers:  Connection_Handle

      Return results:  Not specified





<span class="grey">Ko, et al.                  Standards Track                    [Page 22]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-23" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   This is used by the iSCSI layers at the initiator and the target to
   request that a specified iSCSI/iSER connection be terminated and all
   associated connection and task resources be freed.  When this
   Operational Primitive invocation returns to the iSCSI layer, the
   iSCSI layer may assume full ownership of all iSCSI-level resources,
   e.g., I/O Buffers, associated with the connection.

<span class="h4"><a class="selflink" id="section-3.1.8" href="#section-3.1.8">3.1.8</a>.  Notice_Key_Values</span>

      Input qualifiers:  Connection_Handle, number of keys, list of
      Key-Value pairs

      Return results:  Not specified

   This is used by the iSCSI layers at the initiator and the target to
   request that the iSER layer take note of the specified Key-Value
   pairs that were negotiated by the iSCSI peers for the connection.

<span class="h4"><a class="selflink" id="section-3.1.9" href="#section-3.1.9">3.1.9</a>.  Deallocate_Task_Resources</span>

      Input qualifiers:  Connection_Handle, ITT

      Return results:  Not specified

   This is used by the iSCSI layers at the initiator and the target to
   request the deallocation of all RCaP-specific resources allocated by
   the iSER layer for the task identified by the ITT qualifier.  The
   iSER layer may require a certain number of RCaP-specific resources
   associated with the ITT for each new iSCSI task.  In the normal
   course of execution, these task-level resources in the iSER layer are
   assumed to be transparently allocated on each task initiation and
   deallocated on the conclusion of each task as appropriate.  In
   exception scenarios where the task does not conclude with a SCSI
   Response PDU, the iSER layer needs to be notified of the individual
   task terminations to aid its task-level resource management.  This
   Operational Primitive is used for this purpose, and is not needed
   when a SCSI Response PDU normally concludes a task.  Note that RCaP-
   specific task resources are deallocated by the iSER layer when a SCSI
   Response PDU normally concludes a task, even if the SCSI status was
   not success.

<span class="h3"><a class="selflink" id="section-3.2" href="#section-3.2">3.2</a>.  Operational Primitives Used by iSER</span>

   The iSER layer MUST use the following Operational Primitives offered
   by the iSCSI protocol layer when the connection is in iSER-assisted
   mode.





<span class="grey">Ko, et al.                  Standards Track                    [Page 23]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-24" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-3.2.1" href="#section-3.2.1">3.2.1</a>.  Control_Notify</span>

      Input qualifiers:  Connection_Handle, an iSCSI control-type PDU

      Return results:  Not specified

   This is used by the iSER layers at the initiator and the target to
   notify the iSCSI layer of the availability of an inbound iSCSI
   control-type PDU.  A PDU is described as "available" to the iSCSI
   layer when the iSER layer notifies the iSCSI layer of the reception
   of that inbound PDU, along with an implementation-specific indication
   as to where the received PDU is.

<span class="h4"><a class="selflink" id="section-3.2.2" href="#section-3.2.2">3.2.2</a>.  Data_Completion_Notify</span>

      Input qualifiers:  Connection_Handle, ITT, SN

      Return results:  Not specified

   This is used by the iSER layer to notify the iSCSI layer of the
   completion of outbound data transfer that was requested by the iSCSI
   layer only if the invocation of the Put_Data Operational Primitive
   (see <a href="#section-3.1.2">Section 3.1.2</a>) was qualified with Notify_Enable set.  SN refers
   to the DataSN associated with the SCSI Data-in PDU.

   This is used by the iSER layer to notify the iSCSI layer of the
   completion of inbound data transfer that was requested by the iSCSI
   layer only if the invocation of the Get_Data Operational Primitive
   (see <a href="#section-3.1.3">Section 3.1.3</a>) was qualified with Notify_Enable set.  SN refers
   to the R2TSN associated with the R2T PDU.

<span class="h4"><a class="selflink" id="section-3.2.3" href="#section-3.2.3">3.2.3</a>.  Data_ACK_Notify</span>

      Input qualifier:  Connection_Handle, ITT, DataSN

      Return results:  Not specified

   This is used by the iSER layer at the target to notify the iSCSI
   layer of the arrival of the data acknowledgement (as defined in
   [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>]) requested earlier by the iSCSI layer for the outbound data
   transfer via an invocation of the Put_Data Operational Primitive
   where the A-bit in the SCSI Data-in PDU is set to 1.  See <a href="#section-7.3.5">Section</a>
   <a href="#section-7.3.5">7.3.5</a>.  DataSN refers to the expected DataSN of the next SCSI Data-in
   PDU, which immediately follows the SCSI Data-in PDU with the A-bit
   set to which this notification corresponds, with semantics as defined
   in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>].





<span class="grey">Ko, et al.                  Standards Track                    [Page 24]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-25" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-3.2.4" href="#section-3.2.4">3.2.4</a>.  Connection_Terminate_Notify</span>

      Input qualifiers:  Connection_Handle

      Return results:  Not specified

   This is used by the iSER layers at the initiator and the target to
   notify the iSCSI layer of the unsolicited termination or failure of
   an iSCSI/iSER connection.  The iSER layer MUST deallocate the
   connection and task resources associated with the terminated
   connection before the invocation of this Operational Primitive.  Note
   that the Connection_Terminate_Notify Operational Primitive is not
   invoked when the termination of the connection is earlier requested
   by the local iSCSI layer.

<span class="h3"><a class="selflink" id="section-3.3" href="#section-3.3">3.3</a>.  iSCSI Protocol Usage Requirements</span>

   To operate in an iSER-assisted mode, the iSCSI layers at both the
   initiator and the target MUST negotiate the RDMAExtensions key (see
   <a href="#section-6.3">Section 6.3</a>) to "Yes" on the leading connection.  If the
   RDMAExtensions key is not negotiated to "Yes", then iSER-assisted
   mode MUST NOT be used.  If the RDMAExtensions key is negotiated to
   "Yes" but the invocation of the Allocate_Connection_Resources
   Operational Primitive to the iSER layer fails, the iSCSI layer MUST
   fail the iSCSI Login process or terminate the connection as
   appropriate.  See <a href="#section-10.1.3.1">Section 10.1.3.1</a> for details.

   If the RDMAExtensions key is negotiated to "Yes", the iSCSI layer
   MUST satisfy the following protocol usage requirements from the iSER
   protocol:

   1.  The iSCSI layer at the initiator MUST set ExpDataSN to 0 in Task
       Management Function Requests for Task Allegiance Reassignment for
       read/bidirectional commands, so as to cause the target to send
       all unacknowledged read data.

   2.  The iSCSI layer at the target MUST always return the SCSI status
       in a separate SCSI Response PDU for read commands, i.e., there
       MUST NOT be a "phase collapse" in concluding a SCSI read command.

   3.  The iSCSI layers at both the initiator and the target MUST
       support the keys as defined in <a href="#section-6">Section 6</a> on Login/Text
       Operational Keys.  If used as specified, these keys MUST NOT be
       answered with NotUnderstood, and the semantics as defined MUST be
       followed for each iSER-assisted connection.

   4.  The iSCSI layer at the initiator MUST NOT issue SNACKs for PDUs.




<span class="grey">Ko, et al.                  Standards Track                    [Page 25]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-26" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h2"><a class="selflink" id="section-4" href="#section-4">4</a>.  Lower Layer Interface Requirements</span>

<span class="h3"><a class="selflink" id="section-4.1" href="#section-4.1">4.1</a>.  Interactions with the RCaP Layer</span>

   The iSER protocol layer is layered on top of an RCaP layer (see
   Figure 1) and the following are the key features that are assumed to
   be supported by any RCaP layer:

   *  The RCaP layer supports all basic RDMA operations, including RDMA
      Write Operation, RDMA Read Operation, Send Operation, Send with
      Invalidate Operation, Send with Solicited Event Operation, Send
      with Solicited Event and Invalidate Operation, and Terminate
      Operation.

   *  The RCaP layer provides reliable, in-order message delivery and
      direct data placement.

   *  When the iSER layer initiates an RDMA Read Operation following an
      RDMA Write Operation on one RCaP Stream, the RDMA Read Response
      Message processing on the remote node will be started only after
      the preceding RDMA Write Message payload is placed in the memory
      of the remote node.

   *  The RCaP layer encapsulates a single iSER Message into a single
      RCaP Message on the Data Source side.  The RCaP layer decapsulates
      the iSER Message before delivering it to the iSER layer on the
      Data Sink side.

   *  When the iSER layer provides the STag to be remotely invalidated
      to the RCaP layer for a SendInvSE Message, the RCaP layer uses
      this STag as the STag to be invalidated in the SendInvSE Message.

   *  The RCaP layer uses the STag and Tagged Offset provided by the
      iSER layer for the RDMA Write and RDMA Read Request Messages.

   *  When the RCaP layer delivers the content of an RDMA Send Message
      Type to the iSER layer, the RCaP layer provides the length of the
      RDMA Send message.  This ensures that the iSER layer does not have
      to carry a length field in the iSER header.

   *  When the RCaP layer delivers the SendSE or SendInvSE Message to
      the iSER layer, it notifies the iSER layer with the mechanism
      provided on that interface.

   *  When the RCaP layer delivers a SendInvSE Message to the iSER
      layer, it passes the value of the STag that was invalidated.





<span class="grey">Ko, et al.                  Standards Track                    [Page 26]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-27" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   *  The RCaP layer propagates all status and error indications to the
      iSER layer.

   *  For a transport layer that operates in byte stream mode such as
      TCP, the RCaP implementation supports the enabling of the RDMA
      mode after connection establishment and the exchange of Login
      parameters in byte stream mode.  For a transport layer that
      provides message delivery capability such as [<a href="#ref-IB">IB</a>], the RCaP
      implementation supports the use of the messaging capability by the
      iSCSI layer directly for the Login Phase after connection
      establishment before enabling iSER-assisted mode.

   *  Whenever the iSER layer terminates the RCaP Stream, the RCaP layer
      terminates the associated connection.

<span class="h3"><a class="selflink" id="section-4.2" href="#section-4.2">4.2</a>.  Interactions with the Transport Layer</span>

   The iSER layer does not directly setup the transport layer connection
   (e.g., TCP, or [<a href="#ref-IB">IB</a>]).  During connection setup, the iSCSI layer is
   responsible for setting up the connection.  If the login is
   successful, the iSCSI layer invokes the Enable_Datamover Operational
   Primitive to request the iSER layer to transition to the iSER-
   assisted mode for that iSCSI connection.  See <a href="#section-5.1">Section 5.1</a> on
   iSCSI/iSER connection setup.  After transitioning to iSER-assisted
   mode, the RCaP layer and the underlying transport layer are
   responsible for maintaining the connection and reporting to the iSER
   layer any connection failures.

<span class="h2"><a class="selflink" id="section-5" href="#section-5">5</a>.  Connection Setup and Termination</span>

<span class="h3"><a class="selflink" id="section-5.1" href="#section-5.1">5.1</a>.  iSCSI/iSER Connection Setup</span>

   During connection setup, the iSCSI layer at the initiator is
   responsible for establishing a connection with the target.  After the
   connection is established, the iSCSI layers at the initiator and the
   target enter the Login Phase using the same rules as outlined in
   [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>].  Transition to iSER-assisted mode occurs when the
   connection transitions into the iSCSI Full Feature Phase following a
   successful login negotiation between the initiator and the target in
   which iSER-assisted mode is negotiated and the connection resources
   necessary to support RCaP have been allocated at both the initiator
   and the target.  The same connection MUST be used for both the iSCSI
   Login Phase and the subsequent iSER-assisted Full Feature Phase.

   iSER-assisted mode MUST be enabled only if it is negotiated on the
   leading connection during the LoginOperationalNegotiation stage of
   the iSCSI Login Phase.  iSER-assisted mode is negotiated using the
   RDMAExtensions=&lt;boolean-value&gt; key.  Both the initiator and the



<span class="grey">Ko, et al.                  Standards Track                    [Page 27]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-28" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   target MUST exchange the RDMAExtensions key with the value set to
   "Yes" to enable iSER-assisted mode.  If both the initiator and the
   target fail to negotiate the RDMAExtensions key set to "Yes", then
   the connection MUST continue with the login semantics as defined in
   [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>].  If the RDMAExtensions key is not negotiated to Yes, then
   for some RCaP implementation (such as [<a href="#ref-IB">IB</a>]), the connection may need
   to be re-established in TCP capable mode.  (For InfiniBand this will
   require an [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>] type connection.)

   iSER-assisted mode is defined for a Normal session only and the
   RDMAExtensions key MUST NOT be negotiated for a Discovery session.
   Discovery sessions are always conducted using the transport layer as
   described in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>].

   An iSER enabled node is not required to initiate the RDMAExtensions
   key exchange if its preference is for the Traditional iSCSI mode.
   The RDMAExtensions key, if offered, MUST be sent in the first
   available Login Response or Login Request PDU in the
   LoginOperationalNegotiation stage.  This is due to the fact that the
   value of some login parameters might depend on whether iSER-assisted
   mode is enabled.

   iSER-assisted mode is a session-wide attribute.  If both the
   initiator and the target negotiate RDMAExtensions="Yes" on the
   leading connection of a session, then all subsequent connections of
   the same session MUST enable iSER-assisted mode without having to
   exchange an RDMAExtensions key during the iSCSI Login Phase.

   Conversely, if both the initiator and the target fail to negotiate
   RDMAExtensions to "Yes" on the leading connection of a session, then
   the RDMAExtensions key MUST NOT be negotiated further on any
   additional subsequent connection of the session.

   When the RDMAExtensions key is negotiated to "Yes", the HeaderDigest
   and the DataDigest keys MUST be negotiated to "None" on all
   iSCSI/iSER connections participating in that iSCSI session.  This is
   because, for an iSCSI/iSER connection, RCaP is responsible for
   providing error detection that is at least as good as a 32-bit CRC
   for all iSER Messages.  Furthermore, all SCSI Read data are sent
   using RDMA Write Messages instead of the SCSI Data-in PDUs, and all
   solicited SCSI write data are sent using RDMA Read Response Messages
   instead of the SCSI Data-out PDUs.  HeaderDigest and DataDigest that
   apply to iSCSI PDUs, would not be appropriate for RDMA Read and RDMA
   Write operations used with iSER.







<span class="grey">Ko, et al.                  Standards Track                    [Page 28]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-29" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-5.1.1" href="#section-5.1.1">5.1.1</a>.  Initiator Behavior</span>

   If the outcome of the iSCSI negotiation is to enable iSER-assisted
   mode, then on the initiator side, prior to sending the Login Request
   with the T (Transit) bit set to 1 and the NSG (Next Stage) field set
   to FullFeaturePhase, the iSCSI layer MUST request that the iSER layer
   allocate the connection resources necessary to support RCaP by
   invoking the Allocate_Connection_Resources Operational Primitive.
   The connection resources required are defined by implementation and
   are outside the scope of this specification.  The iSCSI layer may
   invoke the Notice_Key_Values Operational Primitive before invoking
   the Allocate_Connection_Resources Operational Primitive to request
   that the iSER layer take note of the negotiated values of the iSCSI
   keys for the connection.  The specific keys to be passed as input
   qualifiers are implementation dependent.  These may include, but are
   not limited to, MaxOutstandingR2T, ErrorRecoveryLevel, etc.

   To minimize the potential for a denial-of service attack, the iSCSI
   layer MUST NOT request that the iSER layer allocate the connection
   resources necessary to support RCaP until the iSCSI layer is
   sufficiently far along in the iSCSI Login Phase that it is reasonably
   certain that the peer side is not an attacker.  In particular, if the
   Login Phase includes a SecurityNegotiation stage, the iSCSI layer
   MUST defer the connection resource allocation (i.e., invoking the
   Allocate_Connection_Resources Operational Primitive) to the
   LoginOperationalNegotiation stage [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] so that the resource
   allocation occurs after the authentication phase is completed.

   Among the connection resources allocated at the initiator is the
   Inbound RDMA Read Queue Depth (IRD).  As described in <a href="#section-9.5.1">Section 9.5.1</a>,
   R2Ts are transformed by the target into RDMA Read operations.  IRD
   limits the maximum number of simultaneously incoming outstanding RDMA
   Read Requests per an RCaP Stream from the target to the initiator.
   The required value of IRD is outside the scope of the iSER
   specification.  The iSER layer at the initiator MUST set IRD to 1 or
   higher if R2Ts are to be used in the connection.  However, the iSER
   layer at the initiator MAY set IRD to 0 based on implementation
   configuration, which indicates that no R2Ts will be used on that
   connection.  Initially, the iSER-IRD value at the initiator SHOULD be
   set to the IRD value at the initiator and MUST NOT be more than the
   IRD value.

   On the other hand, the Outbound RDMA Read Queue Depth (ORD) MAY be
   set to 0, since the iSER layer at the initiator does not issue RDMA
   Read Requests to the target.






<span class="grey">Ko, et al.                  Standards Track                    [Page 29]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-30" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Failure to allocate the requested connection resources locally
   results in a login failure and its handling is described in <a href="#section-10.1.3.1">Section</a>
   <a href="#section-10.1.3.1">10.1.3.1</a>.

   If the iSER layer at the initiator is successful in allocating the
   connection resources necessary to support RCaP, the following events
   MUST occur in the specified sequence:

   1.  The iSER layer MUST return a success status to the iSCSI layer in
       response to the Allocate_Connection_Resources Operational
       Primitive.

   2.  After the target returns the Login Response with the T bit set to
       1 and the NSG field set to FullFeaturePhase, and a status class
       of 0 (Success), the iSCSI layer MUST request that the iSER layer
       transition to iSER-assisted mode by invoking the Enable_Datamover
       Operational Primitive with the following qualifiers.  (See
       <a href="#section-10.1.4.6">Section 10.1.4.6</a> for the case when the status class is not
       Success.):

       a.  Connection_Handle that identifies the iSCSI connection.

       b.  Transport_Connection_Descriptor that identifies the specific
           transport connection associated with the Connection_Handle.

   3.  If necessary, the iSER layer should enable RCaP and transition
       the connection to iSER-assisted mode.  When the RCaP is iWARP,
       then this step MUST be done.  Not all RCaPs may need it depending
       on the RCaP Stream start-up state.

   4.  The iSER layer MUST send the iSER Hello Message as the first iSER
       Message.  See <a href="#section-5.1.3">Section 5.1.3</a> on iSER Hello Exchange.

<span class="h4"><a class="selflink" id="section-5.1.2" href="#section-5.1.2">5.1.2</a>.  Target Behavior</span>

   If the outcome of the iSCSI negotiation is to enable iSER-assisted
   mode, then on the target side, prior to sending the Login Response
   with the T (Transit) bit set to 1 and the NSG (Next Stage) field set
   to FullFeaturePhase, the iSCSI layer MUST request that the iSER layer
   allocate the resources necessary to support RCaP by invoking the
   Allocate_Connection_Resources Operational Primitive.  The connection
   resources required are defined by implementation and are outside the
   scope of this specification.  Optionally, the iSCSI layer may invoke
   the Notice_Key_Values Operational Primitive before invoking the
   Allocate_Connection_Resources Operational Primitive to request that
   the iSER layer take note of the negotiated values of the iSCSI keys
   for the connection.  The specific keys to be passed as input




<span class="grey">Ko, et al.                  Standards Track                    [Page 30]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-31" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   qualifiers are implementation dependent.  These may include, but are
   not limited to, MaxOutstandingR2T, ErrorRecoveryLevel, etc.

   To minimize the potential for a denial-of-service attack, the iSCSI
   layer MUST NOT request that the iSER layer allocate the connection
   resources necessary to support RCaP until the iSCSI layer is
   sufficiently far along in the iSCSI Login Phase that it is reasonably
   certain that the peer side is not an attacker.  In particular, if the
   Login Phase includes a SecurityNegotiation stage, the iSCSI layer
   MUST defer the connection resource allocation (i.e., invoking the
   Allocate_Connection_Resources Operational Primitive) to the
   LoginOperationalNegotiation stage [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] so that the resource
   allocation occurs after the authentication phase is completed.

   Among the connection resources allocated at the target is the
   Outbound RDMA Read Queue Depth (ORD).  As described in <a href="#section-9.5.1">Section 9.5.1</a>,
   R2Ts are transformed by the target into RDMA Read operations.  The
   ORD limits the maximum number of simultaneously outstanding RDMA Read
   Requests per RCaP Stream from the target to the initiator.
   Initially, the iSER-ORD value at the target SHOULD be set to the ORD
   value at the target.

   On the other hand, the IRD at the target MAY be set to 0 since the
   iSER layer at the target does not expect RDMA Read Requests to be
   issued by the initiator.

   Failure to allocate the requested connection resources locally
   results in a login failure and its handling is described in <a href="#section-10.1.3.1">Section</a>
   <a href="#section-10.1.3.1">10.1.3.1</a>.

   If the iSER layer at the target is successful in allocating the
   connection resources necessary to support RCaP, the following events
   MUST occur in the specified sequence:

   1.  The iSER layer MUST return a success status to the iSCSI layer in
       response to the Allocate_Connection_Resources Operational
       Primitive.

   2.  The iSCSI layer MUST request that the iSER layer transition to
       iSER-assisted mode by invoking the Enable_Datamover Operational
       Primitive with the following qualifiers:

       a.  Connection_Handle that identifies the iSCSI connection.

       b.  Transport_Connection_Descriptor that identifies the specific
           transport connection associated with the Connection_Handle.





<span class="grey">Ko, et al.                  Standards Track                    [Page 31]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-32" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


       c.  The final transport layer (e.g., TCP) message containing the
           Login Response with the T bit set to 1 and the NSG field set
           to FullFeaturePhase.

   3.  The iSER layer MUST send the final Login Response PDU in the
       native transport mode to conclude the iSCSI Login Phase.  If the
       underlying transport is TCP, then the iSER layer MUST send the
       final Login Response PDU in byte stream mode.

   4.  After sending the final Login Response PDU, the iSER layer should
       enable RCaP if necessary and transition the connection to iSER-
       assisted mode.  When the RCaP is iWARP, then this step MUST be
       done.  Not all RCaPs may need it depending on the RCaP Stream
       start-up state.

   5.  After receiving the iSER Hello Message from the initiator, the
       iSER layer MUST respond with the iSER HelloReply Message to be
       sent as the first iSER Message.  See <a href="#section-5.1.3">Section 5.1.3</a> on iSER Hello
       Exchange for more details.

   Note: In the above sequence, the operations as described in bullets 3
   and 4 MUST be performed atomically for iWARP connections.  Failure to
   do this may result in race conditions.

<span class="h4"><a class="selflink" id="section-5.1.3" href="#section-5.1.3">5.1.3</a>.  iSER Hello Exchange</span>

   After the connection transitions into iSER-assisted mode, the first
   iSER Message sent by the iSER layer at the initiator to the target
   MUST be the iSER Hello Message.  The iSER Hello Message is used by
   the iSER layer at the initiator to declare iSER parameters to the
   target.  See <a href="#section-9.3">Section 9.3</a> on iSER Header Format for the iSER Hello
   Message.

   In response to the iSER Hello Message, the iSER layer at the target
   MUST return the iSER HelloReply Message as the first iSER Message
   sent by the target.  The iSER HelloReply Message is used by the iSER
   layer at the target to declare iSER parameters to the initiator.  See
   <a href="#section-9.4">Section 9.4</a> on iSER Header Format for the iSER HelloReply Message.

   In the iSER Hello Message, the iSER layer at the initiator declares
   the iSER-IRD value to the target.

   Upon receiving the iSER Hello Message, the iSER layer at the target
   MUST set the iSER-ORD value to the minimum of the iSER-ORD value at
   the target and the iSER-IRD value declared by the initiator.  The
   iSER layer at the target MAY adjust (lower) its ORD value to match
   the iSER-ORD value if the iSER-ORD value is smaller than the ORD
   value at the target in order to free up the unused resources.



<span class="grey">Ko, et al.                  Standards Track                    [Page 32]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-33" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   In the iSER HelloReply Message, the iSER layer at the target declares
   the iSER-ORD value to the initiator.

   Upon receiving the iSER HelloReply Message, the iSER layer at the
   initiator MAY adjust (lower) its IRD value to match the iSER-ORD
   value in order to free up the unused resources, if the iSER-ORD value
   declared by the target is smaller than the iSER-IRD value declared by
   the initiator.

   It is an iSER level negotiation failure if the iSER parameters
   declared in the iSER Hello Message by the initiator are unacceptable
   to the target.  This includes the following:

   *  The initiator-declared iSER-IRD value is greater than 0 and the
      target-declared iSER-ORD value is 0.

   *  The initiator-supported and the target-supported iSER protocol
      versions do not overlap.

   See <a href="#section-10.1.3.2">Section 10.1.3.2</a> for the handling of the error situation.

<span class="h3"><a class="selflink" id="section-5.2" href="#section-5.2">5.2</a>.  iSCSI/iSER Connection Termination</span>

<span class="h4"><a class="selflink" id="section-5.2.1" href="#section-5.2.1">5.2.1</a>.  Normal Connection Termination at the Initiator</span>

   The iSCSI layer at the initiator terminates an iSCSI/iSER connection
   normally by invoking the Send_Control Operational Primitive qualified
   with the Logout Request PDU.  The iSER layer at the initiator MUST
   use a SendSE Message to send the Logout Request PDU to the target.
   After the iSER layer at the initiator receives the SendSE Message
   containing the Logout Response PDU from the target, it MUST notify
   the iSCSI layer by invoking the Control_Notify Operational Primitive
   qualified with the Logout Response PDU.

   After the iSCSI logout process is complete, the iSCSI layer at the
   target is responsible for closing the iSCSI/iSER connection as
   described in <a href="#section-5.2.2">Section 5.2.2</a>.  After the RCaP layer at the initiator
   reports that the connection has been closed, the iSER layer at the
   initiator MUST deallocate all connection and task resources (if any)
   associated with the connection, and invalidate the Local Mapping(s)
   (if any) that associate the ITT(s) used on that connection to the
   local STag(s) before notifying the iSCSI layer by invoking the
   Connection_Terminate_Notify Operational Primitive.








<span class="grey">Ko, et al.                  Standards Track                    [Page 33]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-34" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-5.2.2" href="#section-5.2.2">5.2.2</a>.  Normal Connection Termination at the Target</span>

   Upon receiving the SendSE Message containing the Logout Request PDU,
   the iSER layer at the target MUST notify the iSCSI layer at the
   target by invoking the Control_Notify Operational Primitive qualified
   with the Logout Request PDU.  The iSCSI layer completes the logout
   process by invoking the Send_Control Operational Primitive qualified
   with the Logout Response PDU.  The iSER layer at the target MUST use
   a SendSE Message to send the Logout Response PDU to the initiator.
   After the iSCSI logout process is complete, the iSCSI layer at the
   target MUST request that the iSER layer at the target terminate the
   RCaP Stream by invoking the Connection_Terminate Operational
   Primitive.

   As part of the termination process, the RCaP layer MUST close the
   connection.  When the RCaP layer notifies the iSER layer after the
   RCaP Stream and the associated connection are terminated, the iSER
   layer MUST deallocate all connection and task resources (if any)
   associated with the connection, and invalidate the Local and Remote
   Mapping(s) (if any) that associate the ITT(s) used on that connection
   to the local STag(s) and the Advertised STag(s) respectively.

<span class="h4"><a class="selflink" id="section-5.2.3" href="#section-5.2.3">5.2.3</a>.  Termination without Logout Request/Response PDUs</span>

<span class="h5"><a class="selflink" id="section-5.2.3.1" href="#section-5.2.3.1">5.2.3.1</a>.  Connection Termination Initiated by the iSCSI Layer</span>

   The Connection_Terminate Operational Primitive MAY be invoked by the
   iSCSI layer to request that the iSER layer terminate the RCaP Stream
   without having previously exchanged the Logout Request and Logout
   Response PDUs between the two iSCSI/iSER nodes.  As part of the
   termination process, the RCaP layer will close the connection.  When
   the RCaP layer notifies the iSER layer after the RCaP Stream and the
   associated connection are terminated, the iSER layer MUST perform the
   following actions.

   If the Connection_Terminate Operational Primitive is invoked by the
   iSCSI layer at the target, then the iSER layer at the target MUST
   deallocate all connection and task resources (if any) associated with
   the connection, and invalidate the Local and Remote Mappings (if any)
   that associate the ITT(s) used on the connection to the local STag(s)
   and the Advertised STag(s), respectively.

   If the Connection_Terminate Operational Primitive is invoked by the
   iSCSI layer at the initiator, then the iSER layer at the initiator
   MUST deallocate all connection and task resources (if any) associated
   with the connection, and invalidate the Local Mapping(s) (if any)
   that associate the ITT(s) used on the connection to the local
   STag(s).



<span class="grey">Ko, et al.                  Standards Track                    [Page 34]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-35" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h5"><a class="selflink" id="section-5.2.3.2" href="#section-5.2.3.2">5.2.3.2</a>.  Connection Termination Notification to the iSCSI Layer</span>

   If the iSCSI/iSER connection is terminated without the invocation of
   Connection_Terminate from the iSCSI layer, the iSER layer MUST notify
   the iSCSI layer that the iSCSI/iSER connection has been terminated by
   invoking the Connection_Terminate_Notify Operational Primitive.

   Prior to invoking Connection_Terminate_Notify, the iSER layer at the
   target MUST deallocate all connection and task resources (if any)
   associated with the connection, and invalidate the Local and Remote
   Mappings (if any) that associate the ITT(s) used on the connection to
   the local STag(s) and the Advertised STag(s), respectively.

   Prior to invoking Connection_Terminate_Notify, the iSER layer at the
   initiator MUST deallocate all connection and task resources (if any)
   associated with the connection, and invalidate the Local Mappings (if
   any) that associate the ITT(s) used on the connection to the local
   STag(s).

   If the remote iSCSI/iSER node initiated the closing of the connection
   (e.g., by sending a TCP FIN or TCP RST), the iSER layer MUST notify
   the iSCSI layer after the RCaP layer reports that the connection is
   closed by invoking the Connection_Terminate_Notify Operational
   Primitive.

   Another example of a connection termination without a preceding
   logout is when the iSCSI layer at the initiator does an implicit
   logout (connection reinstatement).

<span class="h2"><a class="selflink" id="section-6" href="#section-6">6</a>.  Login/Text Operational Keys</span>

   Certain iSCSI login/text operational keys have restricted usage in
   iSER, and additional keys are used to support the iSER protocol
   functionality.  All other keys defined in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] and not discussed
   in this section may be used on iSCSI/iSER connections with the same
   semantics.

<span class="h3"><a class="selflink" id="section-6.1" href="#section-6.1">6.1</a>.  HeaderDigest and DataDigest</span>

   Irrelevant when: RDMAExtensions=Yes

   Negotiations resulting in RDMAExtensions=Yes for a session implies
   HeaderDigest=None and DataDigest=None for all connections in that
   session and overrides both the default and an explicit setting.







<span class="grey">Ko, et al.                  Standards Track                    [Page 35]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-36" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="section-6.2" href="#section-6.2">6.2</a>.  MaxRecvDataSegmentLength</span>

   For an iSCSI connection belonging to a session in which
   RDMAExtensions=Yes was negotiated on the leading connection of the
   session, MaxRecvDataSegmentLength need not be declared in the Login
   Phase.  Instead, InitiatorRecvDataSegmentLength (as described in
   <a href="#section-6.5">Section 6.5</a>) and TargetRecvDataSegmentLength (as described in <a href="#section-6.4">Section</a>
   <a href="#section-6.4">6.4</a>) keys are negotiated.  The values of the local and remote
   MaxRecvDataSegmentLength are derived from the
   InitiatorRecvDataSegmentLength and TargetRecvDataSegmentLength keys
   even if the MaxRecvDataSegmentLength is declared during the Login
   Phase.

   In the Full Feature Phase, the initiator MUST consider the value of
   its local MaxRecvDataSegmentLength (that it would have declared to
   the target) as having the value of InitiatorRecvDataSegmentLength,
   and the value of the remote MaxRecvDataSegmentLength (that would have
   been declared by the target) as having the value of
   TargetRecvDataSegmentLength.  Similarly, the target MUST consider the
   value of its local MaxRecvDataSegmentLength (that it would have
   declared to the initiator) as having the value of
   TargetRecvDataSegmentLength, and the value of the remote
   MaxRecvDataSegmentLength (that would have been declared by the
   initiator) as having the value of InitiatorRecvDataSegmentLength.

   The MaxRecvDataSegmentLength key is applicable only for iSCSI
   control-type PDUs.

<span class="h3"><a class="selflink" id="section-6.3" href="#section-6.3">6.3</a>.  RDMAExtensions</span>

   Use: LO (leading only)

   Senders: Initiator and Target

   Scope: SW (session-wide)

   RDMAExtensions=&lt;boolean-value&gt;

   Irrelevant when: SessionType=Discovery

   Default is No

   Result function is AND

   This key is used by the initiator and the target to negotiate support
   for iSER-assisted mode.  To enable the use of iSER-assisted mode,
   both the initiator and the target MUST exchange RDMAExtensions=Yes.




<span class="grey">Ko, et al.                  Standards Track                    [Page 36]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-37" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   iSER-assisted mode MUST NOT be used if either the initiator or the
   target offers RDMAExtensions=No.

   An iSER-enabled node is not required to initiate the RDMAExtensions
   key exchange if it prefers to operate in the Traditional iSCSI mode.
   However, if the RDMAExtensions key is to be negotiated, an initiator
   MUST offer the key in the first Login Request PDU in the
   LoginOperationalNegotiation stage of the leading connection, and a
   target MUST offer the key in the first Login Response PDU with which
   it is allowed to do so (i.e., the first Login Response PDU issued
   after the first Login Request PDU with the C bit set to 0) in the
   LoginOperationalNegotiation stage of the leading connection.  In
   response to the offered key=value pair of RDMAExtensions=yes, an
   initiator MUST respond in the next Login Request PDU with which it is
   allowed to do so, and a target MUST respond in the next Login
   Response PDU with which it is allowed to do so.

   Negotiating the RDMAExtensions key first enables a node to negotiate
   the optimal value for other keys.  Certain iSCSI keys such as
   MaxBurstLength, MaxOutstandingR2T, ErrorRecoveryLevel, InitialR2T,
   ImmediateData, etc., may be negotiated differently depending on
   whether the connection is in Traditional iSCSI mode or iSER-assisted
   mode.

<span class="h3"><a class="selflink" id="section-6.4" href="#section-6.4">6.4</a>.  TargetRecvDataSegmentLength</span>

   Use: IO (Initialize only)

   Senders: Initiator and Target

   Scope: CO (connection-only)

   Irrelevant when: RDMAExtensions=No

   TargetRecvDataSegmentLength=&lt;numerical-value-512-to-(2**24-1)&gt;

   Default is 8192 bytes

   Result function is minimum

   This key is relevant only for the iSCSI connection of an iSCSI
   session if RDMAExtensions=Yes is negotiated on the leading connection
   of the session.  It is used by the initiator and target to negotiate
   the maximum size of the data segment that an initiator may send to
   the target in an iSCSI control-type PDU in the Full Feature Phase.
   For SCSI Command PDUs and SCSI Data-out PDUs containing non-immediate
   unsolicited data to be sent by the initiator, the initiator MUST send
   all non-Final PDUs with a data segment size of exactly



<span class="grey">Ko, et al.                  Standards Track                    [Page 37]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-38" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   TargetRecvDataSegmentLength whenever the PDUs constitute a data
   sequence whose size is larger than TargetRecvDataSegmentLength.

<span class="h3"><a class="selflink" id="section-6.5" href="#section-6.5">6.5</a>.  InitiatorRecvDataSegmentLength</span>

   Use: IO (Initialize only)

   Senders: Initiator and Target

   Scope: CO (connection-only)

   Irrelevant when: RDMAExtensions=No

   InitiatorRecvDataSegmentLength=&lt;numerical-value-512-to-(2**24-1)&gt;

   Default is 8192 bytes

   Result function is minimum

   This key is relevant only for the iSCSI connection of an iSCSI
   session if RDMAExtensions=Yes is negotiated on the leading connection
   of the session.  It is used by the initiator and target to negotiate
   the maximum size of the data segment that a target may send to the
   initiator in an iSCSI control-type PDU in the Full Feature Phase.

<span class="h3"><a class="selflink" id="section-6.6" href="#section-6.6">6.6</a>.  OFMarker and IFMarker</span>

   Irrelevant when: RDMAExtensions=Yes

   Negotiations resulting in RDMAExtensions=Yes for a session implies
   OFMarker=No and IFMarker=No for all connections in that session and
   overrides both the default and an explicit setting.

<span class="h3"><a class="selflink" id="section-6.7" href="#section-6.7">6.7</a>.  MaxOutstandingUnexpectedPDUs</span>

   Use: LO (leading only), Declarative

   Senders: Initiator and Target

   Scope: SW (session-wide)

   Irrelevant when: RDMAExtensions=No

   MaxOutstandingUnexpectedPDUs=&lt;numerical-value-from-2-to-(2**32-1) |
   0&gt;

   Default is 0




<span class="grey">Ko, et al.                  Standards Track                    [Page 38]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-39" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   This key is used by the initiator and the target to declare the
   maximum number of outstanding "unexpected" iSCSI control-type PDUs
   that it can receive in the Full Feature Phase.  It is intended to
   allow the receiving side to determine the amount of buffer resources
   needed beyond the normal flow control mechanism available in iSCSI.
   An initiator or target should select a value such that it would not
   impose an unnecessary constraint on the iSCSI layer under normal
   circumstances.  The value of 0 is defined to indicate that the
   declarer has no limit on the maximum number of outstanding
   "unexpected" iSCSI control-type PDUs that it can receive.  See
   Sections <a href="#section-8.1.1">8.1.1</a> and <a href="#section-8.1.2">8.1.2</a> for the usage of this key.  Note that iSER
   Hello and HelloReply Messages are not iSCSI control-type PDUs and are
   not affected by this key.

<span class="h2"><a class="selflink" id="section-7" href="#section-7">7</a>.  iSCSI PDU Considerations</span>

   When a connection is in the iSER-assisted mode, two types of message
   transfers are allowed between the iSCSI layer at the initiator and
   the iSCSI layer at the target.  These are known as the iSCSI data-
   type PDUs and the iSCSI control-type PDUs, and these terms are
   described in the following sections.

<span class="h3"><a class="selflink" id="section-7.1" href="#section-7.1">7.1</a>.  iSCSI Data-Type PDU</span>

   An iSCSI data-type PDU is defined as an iSCSI PDU that causes data
   transfer, transparent to the remote iSCSI layer, to take place
   between the peer iSCSI nodes in the full feature phase of an
   iSCSI/iSER connection.  An iSCSI data-type PDU, when requested for
   transmission by the iSCSI layer in the sending node, results in the
   data being transferred without the participation of the iSCSI layers
   at the sending and the receiving nodes.  This is due to the fact that
   the PDU itself is not delivered as-is to the iSCSI layer in the
   receiving node.  Instead, the data transfer operations are
   transformed into the appropriate RDMA operations that are handled by
   the RDMA-Capable Controller.  The set of iSCSI data-type PDUs
   consists of SCSI Data-in PDUs and R2T PDUs.

   If the invocation of the Operational Primitive by the iSCSI layer to
   request that the iSER layer process an iSCSI data-type PDU is
   qualified with Notify_Enable set, then upon completing the RDMA
   operation, the iSER layer at the target MUST notify the iSCSI layer
   at the target by invoking the Data_Completion_Notify Operational
   Primitive qualified with ITT and SN.  There is no data completion
   notification at the initiator since the RDMA operations are
   completely handled by the RDMA-Capable Controller at the initiator
   and the iSER layer at the initiator is not involved with the data
   transfer associated with iSCSI data-type PDUs.




<span class="grey">Ko, et al.                  Standards Track                    [Page 39]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-40" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   If the invocation of the Operational Primitive by the iSCSI layer to
   request that the iSER layer process an iSCSI data-type PDU is
   qualified with Notify_Enable cleared, then upon completing the RDMA
   operation, the iSER layer at the target MUST NOT notify the iSCSI
   layer at the target and MUST NOT invoke the Data_Completion_Notify
   Operational Primitive.

   If an operation associated with an iSCSI data-type PDU fails for any
   reason, the contents of the Data Sink buffers associated with the
   operation are considered indeterminate.

<span class="h3"><a class="selflink" id="section-7.2" href="#section-7.2">7.2</a>.  iSCSI Control-Type PDU</span>

   Any iSCSI PDU that is not an iSCSI data-type PDU and also not a SCSI
   Data-out PDU carrying solicited data is defined as an iSCSI control-
   type PDU.  The iSCSI layer invokes the Send_Control Operational
   Primitive to request that the iSER layer process an iSCSI control-
   type PDU.  iSCSI control-type PDUs are transferred using Send Message
   Types of RCaP.  Specifically, note that SCSI Data-out PDUs carrying
   unsolicited data are defined as iSCSI control-type PDUs.  See <a href="#section-7.3.4">Section</a>
   <a href="#section-7.3.4">7.3.4</a> on the treatment of SCSI Data-out PDUs.

   When the iSER layer receives an iSCSI control-type PDU, it MUST
   notify the iSCSI layer by invoking the Control_Notify Operational
   Primitive qualified with the iSCSI control-type PDU.

<span class="h3"><a class="selflink" id="section-7.3" href="#section-7.3">7.3</a>.  iSCSI PDUs</span>

   This section describes the handling of each of the iSCSI PDU types by
   the iSER layer.  The iSCSI layer requests that the iSER layer process
   the iSCSI PDU by invoking the appropriate Operational Primitive.  A
   Connection_Handle MUST qualify each of these invocations.  In
   addition, BHS and the optional AHS of the iSCSI PDU as defined in
   [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] MUST qualify each of the invocations.  The qualifying
   Connection_Handle, the BHS, and the AHS are not explicitly listed in
   the subsequent sections.

<span class="h4"><a class="selflink" id="section-7.3.1" href="#section-7.3.1">7.3.1</a>.  SCSI Command</span>

      Type:  control-type PDU

      PDU-specific qualifiers (for SCSI Write or bidirectional command):
      ImmediateDataSize, UnsolicitedDataSize, DataDescriptorOut

      PDU-specific qualifiers (for SCSI read or bidirectional command):
      DataDescriptorIn





<span class="grey">Ko, et al.                  Standards Track                    [Page 40]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-41" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   The iSER layer at the initiator MUST send the SCSI command in a
   SendSE Message to the target.

   For a SCSI Write or bidirectional command, the iSCSI layer at the
   initiator MUST invoke the Send_Control Operational Primitive as
   follows:

   *  If there is immediate data to be transferred for the SCSI Write or
      bidirectional command, the qualifier ImmediateDataSize MUST be
      used to define the number of bytes of immediate unsolicited data
      to be sent with the Write or bidirectional command, and the
      qualifier DataDescriptorOut MUST be used to define the initiator's
      I/O Buffer containing the SCSI Write data.

   *  If there is unsolicited data to be transferred for the SCSI Write
      or bidirectional command, the qualifier UnsolicitedDataSize MUST
      be used to define the number of bytes of immediate and non-
      immediate unsolicited data for the command.  The iSCSI layer will
      issue one or more SCSI Data-out PDUs for the non-immediate
      unsolicited data.  See <a href="#section-7.3.4">Section 7.3.4</a> on SCSI Data-out.

   *  If there is solicited data to be transferred for the SCSI write or
      bidirectional command, as indicated by the Expected Data Transfer
      Length in the SCSI Command PDU exceeding the value of
      UnsolicitedDataSize, the iSER layer at the initiator MUST do the
      following:

         a.  It MUST allocate a Write STag for the I/O Buffer defined by
             the qualifier DataDescriptorOut.  The DataDescriptorOut
             describes the I/O buffer starting with the immediate
             unsolicited data (if any), followed by the non-immediate
             unsolicited data (if any) and solicited data.  This means
             that the BufferOffset for the SCSI Data-out for this
             command is equal to the TO.  This implies that a zero TO
             for this STag points to the beginning of this I/O Buffer.

         b.  It MUST establish a Local Mapping that associates the
             Initiator Task Tag (ITT) to the Write STag.

         c.  It MUST Advertise the Write STag to the target by sending
             it as the Write STag in the iSER header of the iSER Message
             (the payload of the SendSE Message of RCaP) containing the
             SCSI write or bidirectional command PDU.  See <a href="#section-9.2">Section 9.2</a>
             on iSER Header Format for the iSCSI Control-Type PDU.

   For a SCSI read or bidirectional command, the iSCSI layer at the
   initiator MUST invoke the Send_Control Operational Primitive
   qualified with DataDescriptorIn, which defines the initiator's I/O



<span class="grey">Ko, et al.                  Standards Track                    [Page 41]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-42" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Buffer for receiving the SCSI Read data.  The iSER layer at the
   initiator MUST do the following:

         a.  It MUST allocate a Read STag for the I/O Buffer.

         b.  It MUST establish a Local Mapping that associates the
             Initiator Task Tag (ITT) to the Read STag.

         c.  It MUST Advertise the Read STag to the target by sending it
             as the Read STag in the iSER header of the iSER Message
             (the payload of the SendSE Message of RCaP) containing the
             SCSI read or bidirectional command PDU.  See <a href="#section-9.2">Section 9.2</a> on
             iSER Header Format for the iSCSI Control-Type PDU.

   If the amount of unsolicited data to be transferred in a SCSI command
   exceeds TargetRecvDataSegmentLength, then the iSCSI layer at the
   initiator MUST segment the data into multiple iSCSI control-type
   PDUs, with the data segment length in all PDUs generated except the
   last one having exactly the size TargetRecvDataSegmentLength.  The
   data segment length of the last iSCSI control-type PDU carrying the
   unsolicited data can be up to TargetRecvDataSegmentLength.

   When the iSER layer at the target receives the SCSI command, it MUST
   establish a Remote Mapping that associates the ITT to the Advertised
   Write STag and the Read STag if present in the iSER header.  The
   Write STag is used by the iSER layer at the target in handling the
   data transfer associated with the R2T PDU(s) as described in <a href="#section-7.3.6">Section</a>
   <a href="#section-7.3.6">7.3.6</a>.  The Read STag is used in handling the SCSI Data-in PDU(s)
   from the iSCSI layer at the target as described in <a href="#section-7.3.5">Section 7.3.5</a>.

<span class="h4"><a class="selflink" id="section-7.3.2" href="#section-7.3.2">7.3.2</a>.  SCSI Response</span>

      Type:  control-type PDU

      PDU-specific qualifiers:  DataDescriptorStatus

   The iSCSI layer at the target MUST invoke the Send_Control
   Operational Primitive qualified with DataDescriptorStatus, which
   defines the buffer containing the sense and response information.
   The iSCSI layer at the target MUST always return the SCSI status for
   a SCSI command in a separate SCSI Response PDU.  "Phase collapse" for
   transferring SCSI status in a SCSI Data-in PDU MUST NOT be used.  The
   iSER layer at the target sends the SCSI Response PDU according to the
   following rules:

   *  If no STags are Advertised by the initiator in the iSER Message
      containing the SCSI command PDU, then the iSER layer at the target
      MUST send a SendSE Message containing the SCSI Response PDU.



<span class="grey">Ko, et al.                  Standards Track                    [Page 42]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-43" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   *  If the initiator Advertised a Read STag in the iSER Message
      containing the SCSI Command PDU, then the iSER layer at the target
      MUST send a SendInvSE Message containing the SCSI Response PDU.
      The header of the SendInvSE Message MUST carry the Read STag to be
      invalidated at the initiator.

   *  If the initiator Advertised only the Write STag in the iSER
      Message containing the SCSI Command PDU, then the iSER layer at
      the target MUST send a SendInvSE Message containing the SCSI
      Response PDU.  The header of the SendInvSE Message MUST carry the
      Write STag to be invalidated at the initiator.

   When the iSCSI layer at the target invokes the Send_Control
   Operational Primitive to send the SCSI Response PDU, the iSER layer
   at the target MUST invalidate the Remote Mapping that associates the
   ITT to the Advertised STag(s) before transferring the SCSI Response
   PDU to the initiator.

   Upon receiving the SendInvSE Message containing the SCSI Response PDU
   from the target, the RCaP layer at the initiator will invalidate the
   STag specified in the header.  The iSER layer at the initiator MUST
   ensure that the correct STag is invalidated.  If both the Read and
   the Write STags are Advertised earlier by the initiator, then the
   iSER layer at the initiator MUST explicitly invalidate the Write STag
   upon receiving the SendInvSE Message because the header of the
   SendInvSE Message can only carry one STag (in this case, the Read
   STag) to be invalidated.

   The iSER layer at the initiator MUST ensure the invalidation of the
   STag(s) used in a command before notifying the iSCSI layer at the
   initiator by invoking the Control_Notify Operational Primitive
   qualified with the SCSI Response.  This precludes the possibility of
   using the STag(s) after the completion of the command, thereby
   causing data corruption.

   When the iSER layer at the initiator receives the SendSE or the
   SendInvSE Message containing the SCSI Response PDU, it SHOULD
   invalidate the Local Mapping that associates the ITT to the local
   STag(s).  The iSER layer MUST ensure that all local STag(s)
   associated with the ITT are invalidated before notifying the iSCSI
   layer of the SCSI Response PDU by invoking the Control_Notify
   Operational Primitive qualified with the SCSI Response PDU.









<span class="grey">Ko, et al.                  Standards Track                    [Page 43]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-44" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-7.3.3" href="#section-7.3.3">7.3.3</a>.  Task Management Function Request/Response</span>

      Type:  control-type PDU

      PDU-specific qualifiers (for TMF Request):  DataDescriptorOut,
      DataDescriptorIn

   The iSER layer MUST use a SendSE Message to send the Task Management
   Function Request/Response PDU.

   For the Task Management Function Request with the TASK REASSIGN
   function, the iSER layer at the initiator MUST do the following:

   *  It MUST use the ITT as specified in the Referenced Task Tag from
      the Task Management Function Request PDU to locate the existing
      STag(s), if any, in the Local Mapping(s) that associates the ITT
      to the local STag(s).

   *  It MUST invalidate the existing STag(s), if any, and the Local
      Mapping(s) that associates the ITT to the local STag(s).

   *  It MUST allocate a Read STag for the I/O Buffer as defined by the
      qualifier DataDescriptorIn if the Send_Control Operational
      Primitive invocation is qualified with DataDescriptorIn.

   *  It MUST allocate a Write STag for the I/O Buffer as defined by the
      qualifier DataDescriptorOut if the Send_Control Operational
      Primitive invocation is qualified with DataDescriptorOut.

   *  If STags are allocated, it MUST establish a new Local Mapping(s)
      that associate the ITT to the allocated STag(s).

   *  It MUST Advertise the STags, if allocated, to the target in the
      iSER header of the SendSE Message carrying the iSCSI PDU, as
      described in <a href="#section-9.2">Section 9.2</a>.

   For the Task Management Function Request with the TASK REASSIGN
   function for a SCSI read or bidirectional command, the iSCSI layer at
   the initiator MUST set ExpDataSN to 0 since the data transfer and
   acknowledgements happen transparently to the iSCSI layer at the
   initiator.  This provides the flexibility to the iSCSI layer at the
   target to request transmission of only the unacknowledged data as
   specified in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>].

   When the iSER layer at the target receives the Task Management
   Function Request with the TASK REASSIGN function, it MUST do the
   following:




<span class="grey">Ko, et al.                  Standards Track                    [Page 44]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-45" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   *  It MUST use the ITT as specified in the Referenced Task Tag from
      the Task Management Function Request PDU to locate the mappings
      that associate the ITT to the Advertised STag(s) and the local
      STag(s), if any.

   *  It MUST invalidate the local STag(s), if any, associated with the
      ITT.

   *  It MUST replace the Advertised STag(s) in the Remote Mapping that
      associates the ITT to the Advertised STag(s) with the Write STag
      and the Read STag if present in the iSER header.  The Write STag
      is used in the handling of the R2T PDU(s) from the iSCSI layer at
      the target as described in <a href="#section-7.3.6">Section 7.3.6</a>.  The Read STag is used
      in the handling of the SCSI Data-in PDU(s) from the iSCSI layer at
      the target as described in <a href="#section-7.3.5">Section 7.3.5</a>.

<span class="h4"><a class="selflink" id="section-7.3.4" href="#section-7.3.4">7.3.4</a>.  SCSI Data-Out</span>

      Type:  control-type PDU

      PDU-specific qualifiers:  DataDescriptorOut

   The iSCSI layer at the initiator MUST invoke the Send_Control
   Operational Primitive qualified with DataDescriptorOut, which defines
   the initiator's I/O Buffer containing unsolicited SCSI Write data.

   If the amount of unsolicited data to be transferred as SCSI Data-out
   exceeds TargetRecvDataSegmentLength, then the iSCSI layer at the
   initiator MUST segment the data into multiple iSCSI control-type
   PDUs, with the DataSegmentLength having the value of
   TargetRecvDataSegmentLength in all PDUs generated except the last
   one.  The DataSegmentLength of the last iSCSI control-type PDU
   carrying the unsolicited data can be up to
   TargetRecvDataSegmentLength.  The iSCSI layer at the target MUST
   perform the reassembly function for the unsolicited data.

   For unsolicited data, if the F bit is set to 0 in a SCSI Data-out
   PDU, the iSER layer at the initiator MUST use a Send Message to send
   the SCSI Data-out PDU.  If the F bit is set to 1, the iSER layer at
   the initiator MUST use a SendSE Message to send the SCSI Data-out
   PDU.

   Note that for solicited data, the SCSI Data-out PDUs are not used
   since R2T PDUs are not delivered to the iSCSI layer at the initiator;
   instead, R2T PDUs are transformed by the iSER layer at the target
   into RDMA Read operations.  (See <a href="#section-7.3.6">Section 7.3.6</a>.)





<span class="grey">Ko, et al.                  Standards Track                    [Page 45]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-46" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-7.3.5" href="#section-7.3.5">7.3.5</a>.  SCSI Data-In</span>

      Type:  data-type PDU

      PDU-specific qualifiers:  DataDescriptorIn

   When the iSCSI layer at the target is ready to return the SCSI Read
   data to the initiator, it MUST invoke the Put_Data Operational
   Primitive qualified with DataDescriptorIn, which defines the SCSI
   Data-in buffer.  See <a href="#section-7.1">Section 7.1</a> on the general requirement on the
   handling of iSCSI data-type PDUs.  SCSI Data-in PDU(s) are used in
   SCSI Read data transfer as described in <a href="#section-9.5.2">Section 9.5.2</a>.

   The iSER layer at the target MUST do the following for each
   invocation of the Put_Data Operational Primitive:

   1.  It MUST use the ITT in the SCSI Data-in PDU to locate the remote
       Read STag in the Remote Mapping that associates the ITT to
       Advertised STag(s).  The Remote Mapping was established earlier
       by the iSER layer at the target when the SCSI read command was
       received from the initiator.

   2.  It MUST generate and send an RDMA Write Message containing the
       read data to the initiator.

       a.  It MUST use the remote Read STag as the Data Sink STag of the
           RDMA Write Message.

       b.  It MUST use the Buffer Offset from the SCSI Data-in PDU as
           the Data Sink Tagged Offset of the RDMA Write Message.

       c.  It MUST use DataSegmentLength from the SCSI Data-in PDU to
           determine the amount of data to be sent in the RDMA Write
           Message.

   3.  It MUST associate DataSN and ITT from the SCSI Data-in PDU with
       the RDMA Write operation.  If the Put_Data Operational Primitive
       invocation was qualified with Notify_Enable set, then when the
       iSER layer at the target receives a completion from the RCaP
       layer for the RDMA Write Message, the iSER layer at the target
       MUST notify the iSCSI layer by invoking the
       Data_Completion_Notify Operational Primitive qualified with
       DataSN and ITT.  Conversely, if the Put_Data Operational
       Primitive invocation was qualified with Notify_Enable cleared,
       then the iSER layer at the target MUST NOT notify the iSCSI layer
       on completion and MUST NOT invoke the Data_Completion_Notify
       Operational Primitive.




<span class="grey">Ko, et al.                  Standards Track                    [Page 46]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-47" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   When the A-bit is set to 1 in the SCSI Data-in PDU, the iSER layer at
   the target MUST notify the iSCSI layer at the target when the data
   transfer is complete at the initiator.  To perform this additional
   function, the iSER layer at the target can take advantage of the
   operational ErrorRecoveryLevel if previously disclosed by the iSCSI
   layer via an earlier invocation of the Notice_Key_Values Operational
   Primitive.  There are two approaches that can be taken:

   1.  If the iSER layer at the target knows that the operational
       ErrorRecoveryLevel is 2, or if the iSER layer at the target does
       not know the operational ErrorRecoveryLevel, then the iSER layer
       at the target MUST issue a zero-length RDMA Read Request Message
       following the RDMA Write Message.  When the iSER layer at the
       target receives a completion for the RDMA Read Request Message
       from the RCaP layer, implying that the RDMA-Capable Controller at
       the initiator has completed processing the RDMA Write Message due
       to the completion ordering semantics of RCaP, the iSER layer at
       the target MUST notify the iSCSI layer at the target by invoking
       the Data_Ack_Notify Operational Primitive qualified with ITT and
       DataSN (see <a href="#section-3.2.3">Section 3.2.3</a>).

   2.  If the iSER layer at the target knows that the operational
       ErrorRecoveryLevel is 1, then the iSER layer at the target MUST
       do one of the following:

       a.  It MUST notify the iSCSI layer at the target by invoking the
           Data_Ack_Notify Operational Primitive qualified with ITT and
           DataSN (see <a href="#section-3.2.3">Section 3.2.3</a>) when it receives the local
           completion from the RCaP layer for the RDMA Write Message.
           This is allowed since digest errors do not occur in iSER (see
           <a href="#section-10.1.4.2">Section 10.1.4.2</a>) and a CRC error will cause the connection
           to be terminated and the task to be terminated anyway.  The
           local RDMA Write completion from the RCaP layer guarantees
           that the RCaP layer will not access the I/O Buffer again to
           transfer the data associated with that RDMA Write operation.

       b.  Alternatively, it MUST use the same procedure for handling
           the data transfer completion at the initiator as for
           ErrorRecoveryLevel 2.

   Note that the iSCSI layer at the target cannot set the A-bit to 1 if
   the ErrorRecoveryLevel=0.

   The SCSI status MUST always be returned in a separate SCSI Response
   PDU.  The S bit in the SCSI Data-in PDU MUST always be set to 0.
   There MUST NOT be a "phase collapse" in the SCSI Data-in PDU.





<span class="grey">Ko, et al.                  Standards Track                    [Page 47]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-48" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Since the RDMA Write Message only transfers the data portion of the
   SCSI Data-in PDU but not the control information in the header, such
   as ExpCmdSN, if timely updates of such information are crucial, the
   iSCSI layer at the initiator MAY issue NOP-Out PDUs to request that
   the iSCSI layer at the target respond with the information using NOP-
   In PDUs.

<span class="h4"><a class="selflink" id="section-7.3.6" href="#section-7.3.6">7.3.6</a>.  Ready to Transfer (R2T)</span>

      Type:  data-type PDU

      PDU-specific qualifiers:  DataDescriptorOut

   In order to send an R2T PDU, the iSCSI layer at the target MUST
   invoke the Get_Data Operational Primitive qualified with
   DataDescriptorOut, which defines the I/O Buffer for receiving the
   SCSI Write data from the initiator.  See <a href="#section-7.1">Section 7.1</a> on the general
   requirements on the handling of iSCSI data-type PDUs.

   The iSER layer at the target MUST do the following for each
   invocation of the Get_Data Operational Primitive:

   1.  It MUST ensure a valid local STag for the I/O Buffer and a valid
       Local Mapping that associates the Initiator Task Tag (ITT) to the
       local STag.  This may involve allocating a valid local STag and
       establishing a Local Mapping.

   2.  It MUST use the ITT in the R2T to locate the remote Write STag in
       the Remote Mapping that associates the ITT to Advertised STag(s).
       The Remote Mapping is established earlier by the iSER layer at
       the target when the iSER Message containing the Advertised Write
       STag and the SCSI Command PDU for a SCSI write or bidirectional
       command is received from the initiator.

   3.  If the iSER-ORD value at the target is set to 0, the iSER layer
       at the target MUST terminate the connection and free up the
       resources associated with the connection (as described in <a href="#section-5.2.3">Section</a>
       <a href="#section-5.2.3">5.2.3</a>) if it receives the R2T PDU from the iSCSI layer at the
       target.  Upon termination of the connection, the iSER layer at
       the target MUST notify the iSCSI layer at the target by invoking
       the Connection_Terminate_Notify Operational Primitive.

   4.  If the iSER-ORD value at the target is set to greater than 0, the
       iSER layer at the target MUST transform the R2T PDU into an RDMA
       Read Request Message.  While transforming the R2T PDU, the iSER
       layer at the target MUST ensure that the number of outstanding
       RDMA Read Request Messages does not exceed the iSER-ORD value.
       To transform the R2T PDU, the iSER layer at the target:



<span class="grey">Ko, et al.                  Standards Track                    [Page 48]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-49" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


       a.  MUST derive the local STag and local Tagged Offset from the
           DataDescriptorOut that qualified the Get_Data invocation.

       b.  MUST use the local STag as the Data Sink STag of the RDMA
           Read Request Message.

       c.  MUST use the local Tagged Offset as the Data Sink Tagged
           Offset of the RDMA Read Request Message.

       d.  MUST use the Desired Data Transfer Length from the R2T PDU as
           the RDMA Read Message Size of the RDMA Read Request Message.

       e.  MUST use the remote Write STag as the Data Source STag of the
           RDMA Read Request Message.

       f.  MUST use the Buffer Offset from the R2T PDU as the Data
           Source Tagged Offset of the RDMA Read Request Message.

   5.  It MUST associate R2TSN and ITT from the R2T PDU with the RDMA
       Read operation.  If the Get_Data Operational Primitive invocation
       is qualified with Notify_Enable set, then when the iSER layer at
       the target receives a completion from the RCaP layer for the RDMA
       Read operation, the iSER layer at the target MUST notify the
       iSCSI layer by invoking the Data_Completion_Notify Operational
       Primitive qualified with R2TSN and ITT.  Conversely, if the
       Get_Data Operational Primitive invocation is qualified with
       Notify_Enable cleared, then the iSER layer at the target MUST NOT
       notify the iSCSI layer on completion and MUST NOT invoke the
       Data_Completion_Notify Operational Primitive.

   When the RCaP layer at the initiator receives a valid RDMA Read
   Request Message, it will return an RDMA Read Response Message
   containing the solicited write data to the target.  When the RCaP
   layer at target receives the RDMA Read Response Message from the
   initiator, it will place the solicited data in the I/O Buffer
   referenced by the Data Sink STag in the RDMA Read Response Message.

   Since the RDMA Read Request Message from the target does not transfer
   the control information in the R2T PDU, such as ExpCmdSN, if timely
   updates of such information are crucial, the iSCSI layer at the
   initiator MAY issue NOP-Out PDUs to request that the iSCSI layer at
   the target respond with the information using NOP-In PDUs.

   Similarly, since the RDMA Read Response Message from the initiator
   only transfers the data but not the control information normally
   found in the SCSI Data-out PDU, such as ExpStatSN, if timely updates
   of such information are crucial, the iSCSI layer at the target MAY




<span class="grey">Ko, et al.                  Standards Track                    [Page 49]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-50" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   issue NOP-In PDUs to request that the iSCSI layer at the initiator
   respond with the information using NOP-Out PDUs.

<span class="h4"><a class="selflink" id="section-7.3.7" href="#section-7.3.7">7.3.7</a>.  Asynchronous Message</span>

      Type:  control-type PDU

      PDU-specific qualifiers:  DataDescriptorSense

   The iSCSI layer MUST invoke the Send_Control Operational Primitive
   qualified with DataDescriptorSense, which defines the buffer
   containing the sense and iSCSI Event information.  The iSER layer
   MUST use a SendSE Message to send the Asynchronous Message PDU.

<span class="h4"><a class="selflink" id="section-7.3.8" href="#section-7.3.8">7.3.8</a>.  Text Request and Text Response</span>

      Type:  control-type PDU

      PDU-specific qualifiers:  DataDescriptorTextOut (for Text
      Request), DataDescriptorIn (for Text Response)

   The iSCSI layer MUST invoke the Send_Control Operational Primitive
   qualified with DataDescriptorTextOut (or DataDescriptorIn), which
   defines the Text Request (or Text Response) buffer.  The iSER layer
   MUST use SendSE Messages to send the Text Request (or Text Response
   PDUs).

<span class="h4"><a class="selflink" id="section-7.3.9" href="#section-7.3.9">7.3.9</a>.  Login Request and Login Response</span>

   During the login negotiation, the iSCSI layer interacts with the
   transport layer directly and the iSER layer is not involved.  See
   <a href="#section-5.1">Section 5.1</a> on iSCSI/iSER connection setup.  If the underlying
   transport is TCP, the Login Request PDUs and the Login Response PDUs
   are exchanged when the connection between the initiator and the
   target is still in the byte stream mode.

   The iSCSI layer MUST not send a Login Request (or a Login Response)
   PDU during the Full Feature Phase.  A Login Request (or a Login
   Response) PDU, if used, MUST be treated as an iSCSI protocol error.
   The iSER layer MAY reject such a PDU from the iSCSI layer with an
   appropriate error code.  If a Login Request PDU is received by the
   iSCSI layer at the target, it MUST respond with a Reject PDU with a
   reason code of "protocol error".








<span class="grey">Ko, et al.                  Standards Track                    [Page 50]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-51" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-7.3.10" href="#section-7.3.10">7.3.10</a>.  Logout Request and Logout Response</span>

      Type:  control-type PDU

      PDU-specific qualifiers:  None

   The iSER layer MUST use a SendSE Message to send the Logout Request
   or Logout Response PDU.  Sections <a href="#section-5.2.1">5.2.1</a> and <a href="#section-5.2.2">5.2.2</a> describe the
   handling of the Logout Request and the Logout Response at the
   initiator and the target and the interactions between the initiator
   and the target to terminate a connection.

<span class="h4"><a class="selflink" id="section-7.3.11" href="#section-7.3.11">7.3.11</a>.  SNACK Request</span>

   Since HeaderDigest and DataDigest must be negotiated to "None", there
   are no digest errors when the connection is in iSER-assisted mode.
   Also, since RCaP delivers all messages in the order they were sent,
   there are no sequence errors when the connection is in iSER-assisted
   mode.  Therefore, the iSCSI layer MUST NOT send SNACK Request PDUs.
   A SNCAK Request PDU, if used, MUST be treated as an iSCSI protocol
   error.  The iSER layer MAY reject such a PDU from the iSCSI layer
   with an appropriate error code.  If a SNACK Request PDU is received
   by the iSCSI layer at the target, it MUST respond with a Reject PDU
   with a reason code of "protocol error".

<span class="h4"><a class="selflink" id="section-7.3.12" href="#section-7.3.12">7.3.12</a>.  Reject</span>

      Type:  control-type PDU

      PDU-specific qualifiers:  DataDescriptorReject

   The iSCSI layer MUST invoke the Send_Control Operational Primitive
   qualified with DataDescriptorReject, which defines the Reject buffer.
   The iSER layer MUST use a SendSE Message to send the Reject PDU.

<span class="h4"><a class="selflink" id="section-7.3.13" href="#section-7.3.13">7.3.13</a>.  NOP-Out and NOP-In</span>

      Type:  control-type PDU

      PDU-specific qualifiers:  DataDescriptorNOPOut (for NOP-Out),
      DataDescriptorNOPIn (for NOP-In)

   The iSCSI layer MUST invoke the Send_Control Operational Primitive
   qualified with DataDescriptorNOPOut (or DataDescriptorNOPIn), which
   defines the Ping (or Return Ping) data buffer.  The iSER layer MUST
   use SendSE Messages to send the NOP-Out (or NOP-In) PDU.





<span class="grey">Ko, et al.                  Standards Track                    [Page 51]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-52" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h2"><a class="selflink" id="section-8" href="#section-8">8</a>.  Flow Control and STag Management</span>

<span class="h3"><a class="selflink" id="section-8.1" href="#section-8.1">8.1</a>.  Flow Control for RDMA Send Message Types</span>

   Send Message Types in RCaP are used by the iSER layer to transfer
   iSCSI control-type PDUs.  Each Send Message Type in RCaP consumes an
   Untagged Buffer at the Data Sink.  However, neither the RCaP layer
   nor the iSER layer provides an explicit flow control mechanism for
   the Send Message Types.  Therefore, the iSER layer SHOULD provision
   enough Untagged buffers for handling incoming Send Message Types to
   prevent buffer exhaustion at the RCaP layer.  If buffer exhaustion
   occurs, it may result in the termination of the connection.

   An implementation may choose to satisfy the buffer requirement by
   using a common buffer pool shared across multiple connections, with
   usage limits on a per-connection basis and usage limits on the buffer
   pool itself.  In such an implementation, exceeding the buffer usage
   limit for a connection or the buffer pool itself may trigger
   interventions from the iSER layer to replenish the buffer pool and/or
   to isolate the connection causing the problem.

   iSER also provides the MaxOutstandingUnexpectedPDUs key to be used by
   the initiator and the target to declare the maximum number of
   outstanding "unexpected" control-type PDUs that it can receive.  It
   is intended to allow the receiving side to determine the amount of
   buffer resources needed beyond the normal flow control mechanism
   available in iSCSI.

   The buffer resources required at both the initiator and the target as
   a result of control-type PDUs sent by the initiator is described in
   <a href="#section-8.1.1">Section 8.1.1</a>.  The buffer resources required at both the initiator
   and target as a result of control-type PDUs sent by the target is
   described in <a href="#section-8.1.2">Section 8.1.2</a>.

<span class="h4"><a class="selflink" id="section-8.1.1" href="#section-8.1.1">8.1.1</a>.  Flow Control for Control-Type PDUs from the Initiator</span>

   The control-type PDUs that can be sent by an initiator to a target
   can be grouped into the following categories:

   1.  Regulated:  Control-type PDUs in this category are regulated by
       the iSCSI CmdSN window mechanism and the immediate flag is not
       set.

   2.  Unregulated but Expected:  Control-type PDUs in this category are
       not regulated by the iSCSI CmdSN window mechanism but are
       expected by the target.





<span class="grey">Ko, et al.                  Standards Track                    [Page 52]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-53" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   3.  Unregulated and Unexpected:  Control-type PDUs in this category
       are not regulated by the iSCSI CmdSN window mechanism and are
       "unexpected" by the target.

<span class="h5"><a class="selflink" id="section-8.1.1.1" href="#section-8.1.1.1">8.1.1.1</a>.  Control-Type PDUs from the Initiator in the Regulated Category</span>

   Control-type PDUs that can be sent by the initiator in this category
   are regulated by the iSCSI CmdSN window mechanism and the immediate
   flag is not set.

   The queuing capacity required of the iSCSI layer at the target is
   described in <a href="./rfc3720#section-3.2.2.1">Section&nbsp;3.2.2.1 of [RFC3720]</a>.  For each of the control-
   type PDUs that can be sent by the initiator in this category, the
   initiator MUST provision for the buffer resources required for the
   corresponding control-type PDU sent as a response from the target.
   The following is a list of the PDUs that can be sent by the initiator
   and the PDUs that are sent by the target in response:

       a.  When an initiator sends a SCSI Command PDU, it expects a SCSI
           Response PDU from the target.

       b.  When the initiator sends a Task Management Function Request
           PDU, it expects a Task Management Function Response PDU from
           the target.

       c.  When the initiator sends a Text Request PDU, it expects a
           Text Response PDU from the target.

       d.  When the initiator sends a Logout Request PDU, it expects a
           Logout Response PDU from the target.

       e.  When the initiator sends a NOP-Out PDU as a ping request with
           ITT != 0xffffffff and TTT = 0xffffffff, it expects a NOP-In
           PDU from the target with the same ITT and TTT as in the ping
           request.

   The response from the target for any of the PDUs enumerated here may
   alternatively be in the form of a Reject PDU sent instead before the
   task is active, as described in <a href="./rfc3720#section-6.3">Section&nbsp;6.3 of [RFC3720]</a>.

<span class="h5"><a class="selflink" id="section-8.1.1.2" href="#section-8.1.1.2">8.1.1.2</a>.  Control-Type PDUs from the Initiator in the Unregulated but</span>
<span class="h5">          Expected Category</span>

   For the control-type PDUs in the Unregulated but Expected category,
   the amount of buffering resources required at the target can be
   predetermined.  The following is a list of the PDUs in this category:





<span class="grey">Ko, et al.                  Standards Track                    [Page 53]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-54" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


       a.  SCSI Data-out PDUs are used by the initiator to send
           unsolicited data.  The amount of buffer resources required by
           the target can be determined using FirstBurstLength.  Note
           that SCSI Data-out PDUs are not used for solicited data since
           the R2T PDU that is used for solicitation is transformed into
           RDMA Read operations by the iSER layer at the target.  See
           <a href="#section-7.3.4">Section 7.3.4</a>.

       b.  A NOP-Out PDU with TTT != 0xffffffff is sent as a ping
           response by the initiator to the NOP-In PDU sent as a ping
           request by the target.

<span class="h5"><a class="selflink" id="section-8.1.1.3" href="#section-8.1.1.3">8.1.1.3</a>.  Control-Type PDUs from the Initiator in the Unregulated and</span>
<span class="h5">          Unexpected Category</span>

   PDUs in the Unregulated and Unexpected category are PDUs with the
   immediate flag set.  The number of PDUs in this category that can be
   sent by an initiator is controlled by the value of
   MaxOutstandingUnexpectedPDUs declared by the target (see <a href="#section-6.7">Section</a>
   <a href="#section-6.7">6.7</a>).  After a PDU in this category is sent by the initiator, it is
   outstanding until it is retired.  At any time, the number of
   outstanding unexpected PDUs MUST not exceed the value of
   MaxOutstandingUnexpectedPDUs declared by the target.

   The target uses the value of MaxOutstandingUnexpectedPDUs that it
   declared to determine the amount of buffer resources required for
   control-type PDUs in this category that can be sent by an initiator.
   For the initiator, for each of the control-type PDUs that can be sent
   in this category, the initiator MUST provision for the buffer
   resources if required for the corresponding control-type PDU that can
   be sent as a response from the target.

   An outstanding PDU in this category is retired as follows.  If the
   CmdSN of the PDU sent by the initiator in this category is x, the PDU
   is outstanding until the initiator sends a non-immediate control-type
   PDU on the same connection with CmdSN = y (where y is at least x) and
   the target responds with a control-type PDU on any connection where
   ExpCmdSN is at least y+1.

   When the number of outstanding unexpected control-type PDUs equals
   MaxOutstandingUnexpectedPDUs, the iSCSI layer at the initiator MUST
   NOT generate any unexpected PDUs that otherwise it would have
   generated, even if it is intended for immediate delivery.








<span class="grey">Ko, et al.                  Standards Track                    [Page 54]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-55" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-8.1.2" href="#section-8.1.2">8.1.2</a>.  Flow Control for Control-Type PDUs from the Target</span>

   Control-type PDUs that can be sent by a target and are expected by
   the initiator are listed in the Regulated category (see <a href="#section-8.1.1.1">Section</a>
   <a href="#section-8.1.1.1">8.1.1.1</a>).

   For the control-type PDUs that can be sent by a target and are
   unexpected by the initiator, the number is controlled by
   MaxOutstandingUnexpectedPDUs declared by the initiator (see <a href="#section-6.7">Section</a>
   <a href="#section-6.7">6.7</a>).  After a PDU in this category is sent by a target, it is
   outstanding until it is retired.  At any time, the number of
   outstanding unexpected PDUs MUST not exceed the value of
   MaxOutstandingUnexpectedPDUs declared by the initiator.  The
   initiator uses the value of MaxOutstandingUnexpectedPDUs that it
   declared to determine the amount of buffer resources required for
   control-type PDUs in this category that can be sent by a target.  The
   following is a list of the PDUs in this category and the conditions
   for retiring the outstanding PDU:

       a.  For an Asynchronous Message PDU with StatSN = x, the PDU is
           outstanding until the initiator sends a control-type PDU with
           ExpStatSN set to at least x+1.

       b.  For a Reject PDU with StatSN = x that is sent after a task is
           active, the PDU is outstanding until the initiator sends a
           control-type PDU with ExpStatSN set to at least x+1.

       c.  For a NOP-In PDU with ITT = 0xffffffff and StatSN = x, the
           PDU is outstanding until the initiator responds with a
           control-type PDU on the same connection where ExpStatSN is at
           least x+1.  But if the NOP-In PDU is sent as a ping request
           with TTT != 0xffffffff, the PDU can also be retired when the
           initiator sends a NOP-Out PDU with the same ITT and TTT as in
           the ping request.  Note that when a target sends a NOP-In PDU
           as a ping request, it must provision a buffer for the NOP-Out
           PDU sent as a ping response from the initiator.

   When the number of outstanding unexpected control-type PDUs equals
   MaxOutstandingUnexpectedPDUs, the iSCSI layer at the target MUST NOT
   generate any unexpected PDUs that otherwise it would have generated,
   even if its intent is to indicate an iSCSI error condition (e.g.,
   Asynchronous Message, Reject).  Task timeouts, as in the initiator
   waiting for a command completion or other connection and session
   level exceptions, will ensure that correct operational behavior will
   result in these cases despite not generating the PDU.  This rule
   overrides any other requirements elsewhere that require that a Reject
   PDU MUST be sent.




<span class="grey">Ko, et al.                  Standards Track                    [Page 55]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-56" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   (Implementation note:  A SCSI task timeout and recovery can be a
   lengthy process and hence SHOULD be avoided by proper provisioning of
   resources.)

   (Implementation note:  To ensure that the initiator has a means to
   inform the target that outstanding PDUs have been retired, the target
   should reserve the last unexpected control-type PDU allowable by the
   value of MaxOutstandingUnexpectedPDUs declared by the initiator for
   sending a NOP-In ping request with TTT != 0xffffffff to allow the
   initiator to return the NOP-Out ping response with the current
   ExpStatSN.)

<span class="h3"><a class="selflink" id="section-8.2" href="#section-8.2">8.2</a>.  Flow Control for RDMA Read Resources</span>

   The total number of RDMA Read operations that can be active
   simultaneously on an iSCSI/iSER connection depends on the amount of
   resources allocated as declared in the iSER Hello exchange described
   in <a href="#section-5.1.3">Section 5.1.3</a>.  Exceeding the number of RDMA Read operations
   allowed on a connection will result in the connection being
   terminated by the RCaP layer.  The iSER layer at the target maintains
   the iSER-ORD to keep track of the maximum number of RDMA Read
   Requests that can be issued by the iSER layer on a particular RCaP
   Stream.

   During connection setup (see <a href="#section-5.1">Section 5.1</a>), iSER-IRD is known at the
   initiator and iSER-ORD is known at the target after the iSER layers
   at the initiator and the target have respectively allocated the
   connection resources necessary to support RCaP, as directed by the
   Allocate_Connection_Resources Operational Primitive from the iSCSI
   layer before the end of the iSCSI Login Phase.  In the Full Feature
   Phase, the first message sent by the initiator is the iSER Hello
   Message (see <a href="#section-9.3">Section 9.3</a>), which contains the value of iSER-IRD.  In
   response to the iSER Hello Message, the target sends the iSER
   HelloReply Message (see <a href="#section-9.4">Section 9.4</a>), which contains the value of
   iSER-ORD.  The iSER layer at both the initiator and the target MAY
   adjust (lower) the resources associated with iSER-IRD and iSER-ORD
   respectively to match the iSER-ORD value declared in the HelloReply
   Message.  The iSER layer at the target MUST flow control the RDMA
   Read Request Messages to not exceed the iSER-ORD value at the target.

<span class="h3"><a class="selflink" id="section-8.3" href="#section-8.3">8.3</a>.  STag Management</span>

   An STag, as defined in [<a href="#ref-RDMAP" title="&quot;A Remote Direct Memory Access Protocol Specification&quot;">RDMAP</a>], is an identifier of a Tagged Buffer
   used in an RDMA operation.  The allocation and the subsequent
   invalidation of the STags are specified in this document if the STags
   are exposed on the wire by being Advertised in the iSER header or
   declared in the header of an RCaP Message.




<span class="grey">Ko, et al.                  Standards Track                    [Page 56]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-57" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-8.3.1" href="#section-8.3.1">8.3.1</a>.  Allocation of STags</span>

   When the iSCSI layer at the initiator invokes the Send_Control
   Operational Primitive to request that the iSER layer at the initiator
   process a SCSI command, zero, one, or two STags may be allocated by
   the iSER layer.  See <a href="#section-7.3.1">Section 7.3.1</a> for details.  The number of STags
   allocated depends on whether the command is unidirectional or
   bidirectional and whether or not solicited write data transfer is
   involved.

   When the iSCSI layer at the initiator invokes the Send_Control
   Operational Primitive to request that the iSER layer at the initiator
   process a Task Management Function Request with the TASK REASSIGN
   function, besides allocating zero, one, or two STags, the iSER layer
   MUST invalidate the existing STags, if any, associated with the ITT.
   See <a href="#section-7.3.3">Section 7.3.3</a> for details.

   The iSER layer at the target allocates a local Data Sink STag when
   the iSCSI layer at the target invokes the Get_Data Operational
   Primitive to request that the iSER layer process an R2T PDU.  See
   <a href="#section-7.3.6">Section 7.3.6</a> for details.

<span class="h4"><a class="selflink" id="section-8.3.2" href="#section-8.3.2">8.3.2</a>.  Invalidation of STags</span>

   The invalidation of the STags at the initiator at the completion of a
   unidirectional or bidirectional command when the associated SCSI
   Response PDU is sent by the target is described in <a href="#section-7.3.2">Section 7.3.2</a>.

   When a unidirectional or bidirectional command concludes without the
   associated SCSI Response PDU being sent by the target, the iSCSI
   layer at the initiator MUST request that the iSER layer at the
   initiator invalidate the STags by invoking the
   Deallocate_Task_Resources Operational Primitive qualified with ITT.
   In response, the iSER layer at the initiator MUST locate the STag(s)
   (if any) in the Local Mapping that associates the ITT to the local
   STag(s).  The iSER layer at the initiator MUST invalidate the STag(s)
   (if any) and the Local Mapping.

   For an RDMA Read operation used to realize a SCSI Write data
   transfer, the iSER layer at the target SHOULD invalidate the Data
   Sink STag at the conclusion of the RDMA Read operation referencing
   the Data Sink STag (to permit the immediate reuse of buffer
   resources).

   For an RDMA Write operation used to realize a SCSI Read data
   transfer, the Data Source STag at the target is not declared to the
   initiator and is not exposed on the wire.  Invalidation of the STag
   is thus not specified.



<span class="grey">Ko, et al.                  Standards Track                    [Page 57]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-58" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   When a unidirectional or bidirectional command concludes without the
   associated SCSI Response PDU being sent by the target, the iSCSI
   layer at the target MUST request that the iSER layer at the target
   invalidate the STags by invoking the Deallocate_Task_Resources
   Operational Primitive qualified with ITT.  In response, the iSER
   layer at the target MUST locate the local STag(s) (if any) in the
   Local Mapping that associates the ITT to the local STag(s).  The iSER
   layer at the target MUST invalidate the local STag(s) (if any) and
   the mapping.

<span class="h2"><a class="selflink" id="section-9" href="#section-9">9</a>.  iSER Control and Data Transfer</span>

   For iSCSI data-type PDUs (see <a href="#section-7.1">Section 7.1</a>), the iSER layer uses RDMA
   Read and RDMA Write operations to transfer the solicited data.  For
   iSCSI control-type PDUs (see <a href="#section-7.2">Section 7.2</a>), the iSER layer uses Send
   Message Types of RCaP.

<span class="h3"><a class="selflink" id="section-9.1" href="#section-9.1">9.1</a>.  iSER Header Format</span>

   An iSER header MUST be present in every Send Message Type of RCaP.
   The iSER header is located in the first 12 bytes of the message
   payload of the Send Message Type of RCaP, as shown in Figure 2.

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      | Opcode|                  Opcode Specific Fields               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                    Opcode Specific Fields                     |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                    Opcode Specific Fields                     |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

                       Figure 2.  iSER Header Format

   Opcode - Operation Code: 4 bits

        The Opcode field identifies the type of iSER Messages:

           0001b = iSCSI control-type PDU

           0010b = iSER Hello Message

           0011b = iSER HelloReply Message

           All other opcodes are reserved.





<span class="grey">Ko, et al.                  Standards Track                    [Page 58]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-59" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="section-9.2" href="#section-9.2">9.2</a>.  iSER Header Format for the iSCSI Control-Type PDU</span>

   The iSER layer uses Send Message Types of RCaP to transfer iSCSI
   control-type PDUs (see <a href="#section-7.2">Section 7.2</a>).  The message payload of each of
   the Send Message Types of RCaP used for transferring an iSER Message
   contains an iSER Header followed by an iSCSI control-type PDU.

   The iSER header in a Send Message Type of RCaP carrying an iSCSI
   control-type PDU MUST have the format as described in Figure 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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |       |W|R|                                                   |
      | 0001b |S|S|                  Reserved                         |
      |       |V|V|                                                   |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                        Write STag (or N/A)                    |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                         Read STag (or N/A)                    |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

          Figure 3.  iSER Header Format for iSCSI Control-Type PDU

   WSV - Write STag Valid flag: 1 bit

       This flag indicates the validity of the Write STag field of the
       iSER Header.  If set to one, the Write STag field in this iSER
       Header is valid.  If set to zero, the Write STag field in this
       iSER Header MUST be ignored at the receiver.  The Write STag
       Valid flag is set to one when there is solicited data to be
       transferred for a SCSI write or bidirectional command, or when
       there are non-immediate unsolicited and solicited data to be
       transferred for the referenced task specified in a Task
       Management Function Request with the TASK REASSIGN function.

   RSV - Read STag Valid flag: 1 bit

       This flag indicates the validity of the Read STag field of the
       iSER Header.  If set to one, the Read STag field in this iSER
       Header is valid.  If set to zero, the Read STag field in this
       iSER Header MUST be ignored at the receiver.  The Read STag Valid
       flag is set to one for a SCSI read or bidirectional command, or
       for a Task Management Function Request with the TASK REASSIGN
       function.






<span class="grey">Ko, et al.                  Standards Track                    [Page 59]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-60" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Write STag - Write Steering Tag: 32 bits

       This field contains the Write STag when the Write STag Valid flag
       is set to one.  For a SCSI write or bidirectional command, the
       Write STag is used to Advertise the initiator's I/O Buffer
       containing the solicited data.  For a Task Management Function
       Request with the TASK REASSIGN function, the Write STag is used
       to Advertise the initiator's I/O Buffer containing the non-
       immediate unsolicited data and solicited data.  This Write STag
       is used as the Data Source STag in the resultant RDMA Read
       operation(s).  When the Write STag Valid flag is set to zero,
       this field MUST be set to zero.

   Read STag - Read Steering Tag: 32 bits

       This field contains the Read STag when the Read STag Valid flag
       is set to one.  The Read STag is used to Advertise the
       initiator's Read I/O Buffer of a SCSI read or bidirectional
       command, or of a Task Management Function Request with the TASK
       REASSIGN function.  This Read STag is used as the Data Sink STag
       in the resultant RDMA Write operation(s).  When the Read STag
       Valid flag is zero, this field MUST be set to zero.

   Reserved:

       Reserved fields MUST be set to zero on transmit and MUST be
       ignored on reception.

<span class="h3"><a class="selflink" id="section-9.3" href="#section-9.3">9.3</a>.  iSER Header Format for the iSER Hello Message</span>

   An iSER Hello Message MUST only contain the iSER header, which MUST
   have the format as described in Figure 4.  The iSER Hello Message is
   the first iSER Message sent on the RCaP Stream from the iSER layer at
   the initiator to the iSER layer at the target.

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |       |       |       |       |                               |
      | 0010b | Rsvd  | MaxVer| MinVer|           iSER-IRD            |
      |       |       |       |       |                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           Reserved                            |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           Reserved                            |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

            Figure 4.  iSER Header Format for iSER Hello Message



<span class="grey">Ko, et al.                  Standards Track                    [Page 60]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-61" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   MaxVer - Maximum Version: 4 bits

       This field specifies the maximum version of the iSER protocol
       supported.  It MUST be set to one to indicate the version of the
       specification described in this document.

   MinVer - Minimum Version: 4 bits

       This field specifies the minimum version of the iSER protocol
       supported.  It MUST be set to one to indicate the version of the
       specification described in this document.

   iSER-IRD: 16 bits

       This field contains the value of the iSER-IRD at the initiator.

   Reserved (Rsvd):

       Reserved fields MUST be set to zero on transmit, and MUST be
       ignored on reception.

<span class="h3"><a class="selflink" id="section-9.4" href="#section-9.4">9.4</a>.  iSER Header Format for the iSER HelloReply Message</span>

   An iSER HelloReply Message MUST only contain the iSER header which
   MUST have the format as described in Figure 5.  The iSER HelloReply
   Message is the first iSER Message sent on the RCaP Stream from the
   iSER layer at the target to the iSER layer at the initiator.

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |       |     |R|       |       |                               |
      | 0011b |Rsvd |E| MaxVer| CurVer|           iSER-ORD            |
      |       |     |J|       |       |                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           Reserved                            |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           Reserved                            |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

         Figure 5.  iSER Header Format for iSER HelloReply Message

   REJ - Reject flag: 1 bit

       This flag indicates whether the target is rejecting this
       connection.  If set to one, the target is rejecting the
       connection.




<span class="grey">Ko, et al.                  Standards Track                    [Page 61]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-62" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   MaxVer - Maximum Version: 4 bits

       This field specifies the maximum version of the iSER protocol
       supported.  It MUST be set to one to indicate the version of the
       specification described in this document.

   CurVer - Current Version: 4 bits

       This field specifies the current version of the iSER protocol
       supported.  It MUST be set to one to indicate the version of the
       specification described in this document.

   iSER-ORD: 16 bits

       This field contains the value of the iSER-ORD at the target.

   Reserved (Rsvd):

       Reserved fields MUST be set to zero on transmit, and MUST be
       ignored on reception.

<span class="h3"><a class="selflink" id="section-9.5" href="#section-9.5">9.5</a>.  SCSI Data Transfer Operations</span>

   The iSER layer at the initiator and the iSER layer at the target
   handle each SCSI Write, SCSI Read, and bidirectional operation as
   described below.

<span class="h4"><a class="selflink" id="section-9.5.1" href="#section-9.5.1">9.5.1</a>.  SCSI Write Operation</span>

   The iSCSI layer at the initiator MUST invoke the Send_Control
   Operational Primitive to request that the iSER layer at the initiator
   send the SCSI write command.  The iSER layer at the initiator MUST
   request that the RCaP layer transmit a SendSE Message with the
   message payload consisting of the iSER header followed by the SCSI
   Command PDU and immediate data (if any).  If there is solicited data,
   the iSER layer MUST Advertise the Write STag in the iSER header of
   the SendSE Message, as described in <a href="#section-9.2">Section 9.2</a>.  Upon receiving the
   SendSE Message, the iSER layer at the target MUST notify the iSCSI
   layer at the target by invoking the Control_Notify Operational
   Primitive qualified with the SCSI Command PDU.  See <a href="#section-7.3.1">Section 7.3.1</a> for
   details on the handling of the SCSI write command.

   For the non-immediate unsolicited data, the iSCSI layer at the
   initiator MUST invoke a Send_Control Operational Primitive qualified
   with the SCSI Data-out PDU.  Upon receiving each Send or SendSE
   Message containing the non-immediate unsolicited data, the iSER layer
   at the target MUST notify the iSCSI layer at the target by invoking
   the Control_Notify Operational Primitive qualified with the SCSI



<span class="grey">Ko, et al.                  Standards Track                    [Page 62]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-63" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   Data-out PDU.  See <a href="#section-7.3.4">Section 7.3.4</a> for details on the handling of the
   SCSI Data-out PDU.

   For the solicited data, when the iSCSI layer at the target has an I/O
   Buffer available, it MUST invoke the Get_Data Operational Primitive
   qualified with the R2T PDU.  See <a href="#section-7.3.6">Section 7.3.6</a> for details on the
   handling of the R2T PDU.

   When the data transfer associated with this SCSI Write operation is
   complete, the iSCSI layer at the target MUST invoke the Send_Control
   Operational Primitive when it is ready to send the SCSI Response PDU.
   Upon receiving a SendSE or SendInvSE Message containing the SCSI
   Response PDU, the iSER layer at the initiator MUST notify the iSCSI
   layer at the initiator by invoking the Control_Notify Operational
   Primitive qualified with the SCSI Response PDU.  See <a href="#section-7.3.2">Section 7.3.2</a>
   for details on the handling of the SCSI Response PDU.

<span class="h4"><a class="selflink" id="section-9.5.2" href="#section-9.5.2">9.5.2</a>.  SCSI Read Operation</span>

   The iSCSI layer at the initiator MUST invoke the Send_Control
   Operational Primitive to request that the iSER layer at the initiator
   to send the SCSI read command.  The iSER layer at the initiator MUST
   request that the RCaP layer transmit a SendSE Message with the
   message payload consisting of the iSER header followed by the SCSI
   Command PDU.  The iSER layer at the initiator MUST Advertise the Read
   STag in the iSER header of the SendSE Message, as described in
   <a href="#section-9.2">Section 9.2</a>.  Upon receiving the SendSE Message, the iSER layer at
   the target MUST notify the iSCSI layer at the target by invoking the
   Control_Notify Operational Primitive qualified with the SCSI Command
   PDU.  See <a href="#section-7.3.1">Section 7.3.1</a> for details on the handling of the SCSI read
   command.

   When the requested SCSI data is available in the I/O Buffer, the
   iSCSI layer at the target MUST invoke the Put_Data Operational
   Primitive qualified with the SCSI Data-in PDU.  See <a href="#section-7.3.5">Section 7.3.5</a> for
   details on the handling of the SCSI Data-in PDU.

   When the data transfer associated with this SCSI Read operation is
   complete, the iSCSI layer at the target MUST invoke the Send_Control
   Operational Primitive when it is ready to send the SCSI Response PDU.
   Upon receiving the SendInvSE Message containing the SCSI Response
   PDU, the iSER layer at the initiator MUST notify the iSCSI layer at
   the initiator by invoking the Control_Notify Operational Primitive
   qualified with the SCSI Response PDU.  See <a href="#section-7.3.2">Section 7.3.2</a> for details
   on the handling of the SCSI Response PDU.






<span class="grey">Ko, et al.                  Standards Track                    [Page 63]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-64" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-9.5.3" href="#section-9.5.3">9.5.3</a>.  Bidirectional Operation</span>

   The initiator and the target handle the SCSI Write and the SCSI Read
   portions of this bidirectional operation the same as described in
   Sections <a href="#section-9.5.1">9.5.1</a> and <a href="#section-9.5.2">9.5.2</a>, respectively.

<span class="h2"><a class="selflink" id="section-10" href="#section-10">10</a>.  iSER Error Handling and Recovery</span>

   RCaP provides the iSER layer with reliable in-order delivery.
   Therefore, the error management needs of an iSER-assisted connection
   are somewhat different than those of a Traditional iSCSI connection.

<span class="h3"><a class="selflink" id="section-10.1" href="#section-10.1">10.1</a>.  Error Handling</span>

   iSER error handling is described in the following sections,
   classified loosely based on the sources of errors:

   1.  Those originating at the transport layer (e.g., TCP).

   2.  Those originating at the RCaP layer.

   3.  Those originating at the iSER layer.

   4.  Those originating at the iSCSI layer.

<span class="h4"><a class="selflink" id="section-10.1.1" href="#section-10.1.1">10.1.1</a>.  Errors in the Transport Layer</span>

   If the transport layer is TCP, then TCP packets with detected errors
   are silently dropped by the TCP layer and result in retransmission at
   the TCP layer.  This has no impact on the iSER layer.  However,
   connection loss (e.g., link failure) and unexpected termination
   (e.g., TCP graceful or abnormal close without the iSCSI Logout
   exchanges) at the transport layer will cause the iSCSI/iSER
   connection to be terminated as well.

<span class="h5"><a class="selflink" id="section-10.1.1.1" href="#section-10.1.1.1">10.1.1.1</a>.  Failure in the Transport Layer before RCaP Mode Is Enabled</span>

   If the connection is lost or terminated before the iSCSI layer
   invokes the Allocate_Connection_Resources Operational Primitive, the
   login process is terminated and no further action is required.

   If the connection is lost or terminated after the iSCSI layer has
   invoked the Allocate_Connection_Resources Operational Primitive, then
   the iSCSI layer MUST request that the iSER layer deallocate all
   connection resources by invoking the Deallocate_Connection_Resources
   Operational Primitive.





<span class="grey">Ko, et al.                  Standards Track                    [Page 64]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-65" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h5"><a class="selflink" id="section-10.1.1.2" href="#section-10.1.1.2">10.1.1.2</a>.  Failure in the Transport Layer after RCaP Mode Is Enabled</span>

   If the connection is lost or terminated after the iSCSI layer has
   invoked the Enable_Datamover Operational Primitive, the iSER layer
   MUST notify the iSCSI layer of the connection loss by invoking the
   Connection_Terminate_Notify Operational Primitive.  Prior to invoking
   the Connection_Terminate_Notify Operational Primitive, the iSER layer
   MUST perform the actions described in <a href="#section-5.2.3.2">Section 5.2.3.2</a>.

<span class="h4"><a class="selflink" id="section-10.1.2" href="#section-10.1.2">10.1.2</a>.  Errors in the RCaP Layer</span>

   The RCaP layer does not have error recovery operations built in.  If
   errors are detected at the RCaP layer, the RCaP layer will terminate
   the RCaP Stream and the associated connection.

<span class="h5"><a class="selflink" id="section-10.1.2.1" href="#section-10.1.2.1">10.1.2.1</a>.  Errors Detected in the Local RCaP Layer</span>

   If an error is encountered at the local RCaP layer, the RCaP layer
   MAY send a Terminate Message to the Remote Peer to report the error
   if possible.  (For iWARP, see [<a href="#ref-RDMAP" title="&quot;A Remote Direct Memory Access Protocol Specification&quot;">RDMAP</a>] for the list of errors where a
   Terminate Message is sent.)  The RCaP layer is responsible for
   terminating the connection.  After the RCaP layer notifies the iSER
   layer that the connection is terminated, the iSER layer MUST notify
   the iSCSI layer by invoking the Connection_Terminate_Notify
   Operational Primitive.  Prior to invoking the
   Connection_Terminate_Notify Operational Primitive, the iSER layer
   MUST perform the actions described in <a href="#section-5.2.3.2">Section 5.2.3.2</a>.

<span class="h5"><a class="selflink" id="section-10.1.2.2" href="#section-10.1.2.2">10.1.2.2</a>.  Errors Detected in the RCaP Layer at the Remote Peer</span>

   If an error is encountered at the RCaP layer at the Remote Peer, the
   RCaP layer at the Remote Peer may send a Terminate Message to report
   the error if possible.  If it is unable to send the Terminate
   Message, the connection is terminated.  This is treated the same as a
   failure in the transport layer after RDMA is enabled as described in
   <a href="#section-10.1.1.2">Section 10.1.1.2</a>.

   If an error is encountered at the RCaP layer at the Remote Peer and
   it is able to send a Terminate Message, the RCaP layer at the Remote
   Peer is responsible for terminating the connection.  After the local
   RCaP layer notifies the iSER layer that the connection is terminated,
   the iSER layer MUST notify the iSCSI layer by invoking the
   Connection_Terminate_Notify Operational Primitive.  Prior to invoking
   the Connection_Terminate_Notify Operational Primitive, the iSER layer
   MUST perform the actions described in <a href="#section-5.2.3.2">Section 5.2.3.2</a>.






<span class="grey">Ko, et al.                  Standards Track                    [Page 65]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-66" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h4"><a class="selflink" id="section-10.1.3" href="#section-10.1.3">10.1.3</a>.  Errors in the iSER Layer</span>

   The error handling due to errors at the iSER layer is described in
   the following sections.

<span class="h5"><a class="selflink" id="section-10.1.3.1" href="#section-10.1.3.1">10.1.3.1</a>.  Insufficient Connection Resources to Support RCaP at</span>
<span class="h5">           Connection Setup</span>

   After the iSCSI layer at the initiator invokes the
   Allocate_Connection_Resources Operational Primitive during the iSCSI
   Login Negotiation Phase, if the iSER layer at the initiator fails to
   allocate the connection resources necessary to support RCaP, it MUST
   return a status of failure to the iSCSI layer at the initiator.  The
   iSCSI layer at the initiator MUST terminate the connection as
   described in <a href="#section-5.2.3.1">Section 5.2.3.1</a>.

   After the iSCSI layer at the target invokes the
   Allocate_Connection_Resources Operational Primitive during the iSCSI
   Login Negotiation Phase, if the iSER layer at the target fails to
   allocate the connection resources necessary to support RCaP, it MUST
   return a status of failure to the iSCSI layer at the target.  The
   iSCSI layer at the target MUST send a Login Response with a status
   class of 3 (Target Error), and a status code of "0302" (Out of
   Resources).  The iSCSI layers at the initiator and the target MUST
   terminate the connection as described in <a href="#section-5.2.3.1">Section 5.2.3.1</a>.

<span class="h5"><a class="selflink" id="section-10.1.3.2" href="#section-10.1.3.2">10.1.3.2</a>.  iSER Negotiation Failures</span>

   If the RCaP or iSER related parameters declared by the initiator in
   the iSER Hello Message are unacceptable to the iSER layer at the
   target, the iSER layer at the target MUST set the Reject (REJ) flag,
   as described in <a href="#section-9.4">Section 9.4</a>, in the iSER HelloReply Message.  The
   following are the cases when the iSER layer MUST set the REJ flag to
   one in the HelloReply Message:

   *  The initiator-declared iSER-IRD value is greater than 0 and the
      target-declared iSER-ORD value is 0.

   *  The initiator-supported and the target-supported iSER protocol
      versions do not overlap.

   After requesting that the RCaP layer send the iSER HelloReply
   Message, the handling of the error situation is the same as that for
   iSER format errors as described in <a href="#section-10.1.3.3">Section 10.1.3.3</a>.







<span class="grey">Ko, et al.                  Standards Track                    [Page 66]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-67" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h5"><a class="selflink" id="section-10.1.3.3" href="#section-10.1.3.3">10.1.3.3</a>.  iSER Format Errors</span>

   The following types of errors in an iSER header are considered format
   errors:

   *  Illegal contents of any iSER header field

   *  Inconsistent field contents in an iSER header

   *  Length error for an iSER Hello or HelloReply Message (see <a href="#section-9.3">Section</a>
      <a href="#section-9.3">9.3</a> and 9.4)

   When a format error is detected, the following events MUST occur in
   the specified sequence:

   1.  The iSER layer MUST request that the RCaP layer terminate the
       RCaP Stream.  The RCaP layer MUST terminate the associated
       connection.

   2.  The iSER layer MUST notify the iSCSI layer of the connection
       termination by invoking the Connection_Terminate_Notify
       Operational Primitive.  Prior to invoking the
       Connection_Terminate_Notify Operational Primitive, the iSER layer
       MUST perform the actions described in <a href="#section-5.2.3.2">Section 5.2.3.2</a>.

<span class="h5"><a class="selflink" id="section-10.1.3.4" href="#section-10.1.3.4">10.1.3.4</a>.  iSER Protocol Errors</span>

   The first iSER Message sent by the iSER layer at the initiator after
   transitioning into iSER-assisted mode MUST be the iSER Hello Message
   (see <a href="#section-9.3">Section 9.3</a>).  Likewise, the first iSER Message sent by the iSER
   layer at the target after transitioning into iSER-assisted mode MUST
   be the iSER HelloReply Message (see <a href="#section-9.4">Section 9.4</a>).  Failure to send
   the iSER Hello or HelloReply Message, as indicated by the wrong
   Opcode in the iSER header, is a protocol error.  The handling of this
   error situation is the same as that for iSER format errors as
   described in <a href="#section-10.1.3.3">Section 10.1.3.3</a>.

   If the sending side of an iSER-enabled connection acts in a manner
   not permitted by the negotiated or declared login/text operational
   key values as described in <a href="#section-6">Section 6</a>, this is a protocol error, and
   the receiving side MAY handle this the same as for iSER format errors
   as described in <a href="#section-10.1.3.3">Section 10.1.3.3</a>.

<span class="h4"><a class="selflink" id="section-10.1.4" href="#section-10.1.4">10.1.4</a>.  Errors in the iSCSI Layer</span>

   The error handling due to errors at the iSCSI layer is described in
   the following sections.  For error recovery, see <a href="#section-10.2">Section 10.2</a>.




<span class="grey">Ko, et al.                  Standards Track                    [Page 67]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-68" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h5"><a class="selflink" id="section-10.1.4.1" href="#section-10.1.4.1">10.1.4.1</a>.  iSCSI Format Errors</span>

   When an iSCSI format error is detected, the iSCSI layer MUST request
   that the iSER layer terminate the RCaP Stream by invoking the
   Connection_Terminate Operational Primitive.  For more details on the
   connection termination, see <a href="#section-5.2.3.1">Section 5.2.3.1</a>.

<span class="h5"><a class="selflink" id="section-10.1.4.2" href="#section-10.1.4.2">10.1.4.2</a>.  iSCSI Digest Errors</span>

   In the iSER-assisted mode, the iSCSI layer will not see any digest
   error because both the HeaderDigest and the DataDigest keys are
   negotiated to "None".

<span class="h5"><a class="selflink" id="section-10.1.4.3" href="#section-10.1.4.3">10.1.4.3</a>.  iSCSI Sequence Errors</span>

   For Traditional iSCSI, sequence errors are caused by dropped PDUs due
   to header or data digest errors.  Since digests are not used in
   iSER-assisted mode and the RCaP layer will deliver all messages in
   the order they were sent, sequence errors will not occur in iSER-
   assisted mode.

<span class="h5"><a class="selflink" id="section-10.1.4.4" href="#section-10.1.4.4">10.1.4.4</a>.  iSCSI Protocol Error</span>

   When the iSCSI layer handles certain protocol errors by dropping the
   connection, the error handling is the same as that for iSCSI format
   errors as described in <a href="#section-10.1.4.1">Section 10.1.4.1</a>.

   When the iSCSI layer uses the iSCSI Reject PDU and response codes to
   handle certain other protocol errors, no special handling at the iSER
   layer is required.

<span class="h5"><a class="selflink" id="section-10.1.4.5" href="#section-10.1.4.5">10.1.4.5</a>.  SCSI Timeouts and Session Errors</span>

   SCSI Timeouts and Session Errors are handled at the iSCSI layer and
   no special handling at the iSER layer is required.

<span class="h5"><a class="selflink" id="section-10.1.4.6" href="#section-10.1.4.6">10.1.4.6</a>.  iSCSI Negotiation Failures</span>

   For negotiation failures that happen during the Login Phase at the
   initiator after the iSCSI layer has invoked the
   Allocate_Connection_Resources Operational Primitive and before the
   Enable_Datamover Operational Primitive has been invoked, the iSCSI
   layer MUST request that the iSER layer deallocate all connection
   resources by invoking the Deallocate_Connection_Resources Operational
   Primitive.  The iSCSI layer at the initiator MUST terminate the
   connection.





<span class="grey">Ko, et al.                  Standards Track                    [Page 68]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-69" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   For negotiation failures during the Login Phase at the target, the
   iSCSI layer can use a Login Response with a status class other than 0
   (success) to terminate the Login Phase.  If the iSCSI layer has
   invoked the Allocate_Connection_Resources Operational Primitive
   before the Enable_Datamover Operational Primitive has been invoked,
   the iSCSI layer at the target MUST request that the iSER layer at the
   target deallocate all connection resources by invoking the
   Deallocate_Connection_Resources Operational Primitive.  The iSCSI
   layer at both the initiator and the target MUST terminate the
   connection.

   During the iSCSI Login Phase, if the iSCSI layer at the initiator
   receives a Login Response from the target with a status class other
   than 0 (Success) after the iSCSI layer at the initiator has invoked
   the Allocate_Connection_Resources Operational Primitive, the iSCSI
   layer MUST request the iSER layer to deallocate all connection
   resources by invoking the Deallocate_Connection_Resources Operational
   Primitive.  The iSCSI layer MUST terminate the connection in this
   case.

   For negotiation failures during the Full Feature Phase, the error
   handling is left to the iSCSI layer and no special handling at the
   iSER layer is required.

<span class="h3"><a class="selflink" id="section-10.2" href="#section-10.2">10.2</a>.  Error Recovery</span>

   Error recovery requirements of iSCSI/iSER are the same as that of
   Traditional iSCSI.  All three ErrorRecoveryLevels as defined in
   [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] are supported in iSCSI/iSER.

   *  For ErrorRecoveryLevel 0, session recovery is handled by iSCSI and
      no special handling by the iSER layer is required.

   *  For ErrorRecoveryLevel 1, see <a href="#section-10.2.1">Section 10.2.1</a> on PDU Recovery.

   *  For ErrorRecoveryLevel 2, see <a href="#section-10.2.2">Section 10.2.2</a> on Connection
      Recovery.

   The iSCSI layer may invoke the Notice_Key_Values Operational
   Primitive during connection setup to request that the iSER layer take
   note of the value of the operational ErrorRecoveryLevel, as described
   in Sections <a href="#section-5.1.1">5.1.1</a> and <a href="#section-5.1.2">5.1.2</a>.

<span class="h4"><a class="selflink" id="section-10.2.1" href="#section-10.2.1">10.2.1</a>.  PDU Recovery</span>

   As described in Sections <a href="#section-10.1.4.2">10.1.4.2</a> and <a href="#section-10.1.4.3">10.1.4.3</a>, digest and sequence
   errors will not occur in the iSER-assisted mode.  If the RCaP layer
   detects an error, it will close the iSCSI/iSER connection, as



<span class="grey">Ko, et al.                  Standards Track                    [Page 69]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-70" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   described in <a href="#section-10.1.2">Section 10.1.2</a>.  Therefore, PDU recovery is not useful
   in the iSER-assisted mode.

   The iSCSI layer at the initiator SHOULD disable iSCSI timeout-driven
   PDU retransmissions.

<span class="h4"><a class="selflink" id="section-10.2.2" href="#section-10.2.2">10.2.2</a>.  Connection Recovery</span>

   The iSCSI layer at the initiator MAY reassign connection allegiance
   for non-immediate commands that are still in progress and are
   associated with the failed connection by using a Task Management
   Function Request with the TASK REASSIGN function.  See <a href="#section-7.3.3">Section 7.3.3</a>
   for more details.

   When the iSCSI layer at the initiator does a task reassignment for a
   SCSI write command, it MUST qualify the Send_Control Operational
   Primitive invocation with DataDescriptorOut, which defines the I/O
   Buffer for both the non-immediate unsolicited data and the solicited
   data.  This allows the iSCSI layer at the target to use recovery R2Ts
   to request data originally sent as unsolicited and solicited from the
   initiator.

   When the iSCSI layer at the target accepts a reassignment request for
   a SCSI read command, it MUST request that the iSER layer process SCSI
   Data-in for all unacknowledged data by invoking the Put_Data
   Operational Primitive.  See <a href="#section-7.3.5">Section 7.3.5</a> on the handling of SCSI
   Data-in.

   When the iSCSI layer at the target accepts a reassignment request for
   a SCSI write command, it MUST request that the iSER layer process a
   recovery R2T for any non-immediate unsolicited data and any solicited
   data sequences that have not been received by invoking the Get_Data
   Operational Primitive.  See <a href="#section-7.3.6">Section 7.3.6</a> on the handling of Ready To
   Transfer (R2T).

   The iSCSI layer at the target MUST NOT issue recovery R2Ts on an
   iSCSI/iSER connection for a task for which the connection allegiance
   was never reassigned.  The iSER layer at the target MAY reject such a
   recovery R2T received via the Get_Data Operational Primitive
   invocation from the iSCSI layer at the target, with an appropriate
   error code.

   The iSER layer at the target will process the requests invoked by the
   Put_Data and Get_Data Operational Primitives for a reassigned task in
   the same way as for the original commands.






<span class="grey">Ko, et al.                  Standards Track                    [Page 70]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-71" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h2"><a class="selflink" id="section-11" href="#section-11">11</a>.  Security Considerations</span>

   When iSER is layered on top of an RCaP layer and provides the RDMA
   extensions to the iSCSI protocol, the security considerations of iSER
   are the same as that of the underlying RCaP layer.  For iWARP, this
   is described in [<a href="#ref-RDMAP" title="&quot;A Remote Direct Memory Access Protocol Specification&quot;">RDMAP</a>] and [<a href="#ref-RDDPSEC" title="&quot;Direct Data Placement Protocol (DDP) / Remote Direct Memory Access Protocol (RDMAP) Security&quot;">RDDPSEC</a>].

   Since the iSER-assisted iSCSI protocol is still functionally iSCSI
   from a security considerations perspective, all of the iSCSI security
   requirements as described in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] and [<a href="./rfc3723" title="&quot;Securing Block Storage Protocols over IP&quot;">RFC3723</a>] apply.  If the
   IPsec [<a href="#ref-IPSEC" title="&quot;Security Architecture for the Internet Protocol&quot;">IPSEC</a>] mechanism is used, then it MUST be established before
   the connection transitions to the iSER-assisted mode.  If iSER is
   layered on top of a non-IP based RCaP layer, all the security
   protocol mechanisms applicable to that RCaP layer are also applicable
   to an iSCSI/iSER connection.  If iSER is layered on top of a non-IP
   protocol, the IPsec mechanism as specified in [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>] MUST be
   implemented at any point where the iSER protocol enters the IP
   network (e.g., via gateways), and the non-IP protocol SHOULD
   implement (optional to use) a packet-by packet security protocol
   equal in strength to the IPsec mechanism specified by [<a href="./rfc3720" title="&quot;Internet Small Computer Systems Interface (iSCSI)&quot;">RFC3720</a>].

   To minimize the potential for a denial-of-service attack, the iSCSI
   layer MUST NOT request that the iSER layer allocate the connection
   resources necessary to support RCaP until the iSCSI layer is
   sufficiently far along in the iSCSI Login Phase that it is reasonably
   certain that the peer side is not an attacker, as described in
   Sections <a href="#section-5.1.1">5.1.1</a> and <a href="#section-5.1.2">5.1.2</a>.

   Note that the IPsec requirements for this document are based on the
   version of IPsec specified in <a href="./rfc2401">RFC 2401</a> [<a href="#ref-IPSEC" title="&quot;Security Architecture for the Internet Protocol&quot;">IPSEC</a>] and related RFCs, as
   profiled by <a href="./rfc3723">RFC 3723</a> [<a href="./rfc3723" title="&quot;Securing Block Storage Protocols over IP&quot;">RFC3723</a>], despite the existence of a newer
   version of IPsec specified in <a href="./rfc4301">RFC 4301</a> [<a href="./rfc4301" title="&quot;Security Architecture for the Internet Protocol&quot;">RFC4301</a>] and related RFCs.

<span class="h2"><a class="selflink" id="section-12" href="#section-12">12</a>.  References</span>

<span class="h3"><a class="selflink" id="section-12.1" href="#section-12.1">12.1</a>.  Normative References</span>

   [<a id="ref-RFC3720">RFC3720</a>] Satran, J., Meth, K., Sapuntzakis, C., Chadalapaka, M., and
             E. Zeidner, "Internet Small Computer Systems Interface
             (iSCSI)", <a href="./rfc3720">RFC 3720</a>, April 2004.

   [<a id="ref-RFC3723">RFC3723</a>] Aboba, B., Tseng, J., Walker, J., Rangan, V., and F.
             Travostino, "Securing Block Storage Protocols over IP", <a href="./rfc3723">RFC</a>
             <a href="./rfc3723">3723</a>, April 2004.

   [<a id="ref-RDMAP">RDMAP</a>]   Recio, R., Culley, P., Garcia, D., Hilland, J., and B.
             Metzler, "A Remote Direct Memory Access Protocol
             Specification", <a href="./rfc5040">RFC 5040</a>, October 2007.



<span class="grey">Ko, et al.                  Standards Track                    [Page 71]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-72" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   [<a id="ref-DDP">DDP</a>]     Shah, H., Pinkerton, J., Recio, R., and P. Culley, "Direct
             Data Placement over Reliable Transports", <a href="./rfc5041">RFC 5041</a>, October
             2007.

   [<a id="ref-IPSEC">IPSEC</a>]   Kent, S. and R. Atkinson, "Security Architecture for the
             Internet Protocol", <a href="./rfc2401">RFC 2401</a>, November 1998.

   [<a id="ref-MPA">MPA</a>]     Culley, P., Elzur, U., Recio, R., Bailey, S., and J.
             Carrier, "Marker PDU Aligned Framing for TCP
             Specification", <a href="./rfc5044">RFC 5044</a>, October 2007.

   [<a id="ref-RDDPSEC">RDDPSEC</a>] Pinkerton, J. and E. Deleganes, "Direct Data Placement
             Protocol (DDP) / Remote Direct Memory Access Protocol
             (RDMAP) Security", <a href="./rfc5042">RFC 5042</a>, October 2007.

   [<a id="ref-TCP">TCP</a>]     Postel, J., "Transmission Control Protocol", STD 7, <a href="./rfc793">RFC</a>
             <a href="./rfc793">793</a>, September 1981.

   [<a id="ref-RFC2119">RFC2119</a>] Bradner, S., "Key words for use in RFCs to Indicate
             Requirement Levels", <a href="https://www.rfc-editor.org/bcp/bcp14">BCP 14</a>, <a href="./rfc2119">RFC 2119</a>, March 1997.

<span class="h3"><a class="selflink" id="section-12.2" href="#section-12.2">12.2</a>.  Informative References</span>

   [<a id="ref-SAM2">SAM2</a>]    T10/1157D, SCSI Architecture Model - 2 (SAM-2)

   [<a id="ref-DA">DA</a>]      Chadalapaka, M., Hufferd, J., Satran, J., and H. Shah, "DA:
             Datamover Architecture for the Internet Small Computer
             System Interface (iSCSI)", <a href="./rfc5047">RFC 5047</a>, October 2007.

   [<a id="ref-IB">IB</a>]      InfiniBand Architecture Specification Volume 1 Release 1.2,
             October 2004

   [<a id="ref-IPoIB">IPoIB</a>]   Chu, J. and V. Kashyap, "Transmission of IP over InfiniBand
             (IPoIB)", <a href="./rfc4391">RFC 4391</a>, April 2006.

   [<a id="ref-RFC4301">RFC4301</a>] Kent, S. and K. Seo, "Security Architecture for the
             Internet Protocol", <a href="./rfc4301">RFC 4301</a>, December 2005.














<span class="grey">Ko, et al.                  Standards Track                    [Page 72]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-73" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h2"><a class="selflink" id="appendix-A" href="#appendix-A">Appendix A</a>.  iWARP Message Format for iSER</span>

   This section is for information only and is NOT part of the standard.
   It simply depicts the iWARP Message format for the various iSER
   Messages when the transport layer is TCP.

<span class="h3"><a class="selflink" id="appendix-A.1" href="#appendix-A.1">A.1</a>.  iWARP Message Format for iSER Hello Message</span>

   The following figure depicts an iSER Hello Message encapsulated in an
   iWARP SendSE Message.

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |         MPA Header            |  DDP Control  | RDMA Control  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                        Reserved                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       (Send) Queue Number                     |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                 (Send) Message Sequence Number                |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                      (Send) Message Offset                    |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      | 0010b | Zeros | 0001b | 0001b |           iSER-IRD            |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           All Zeros                           |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           All Zeros                           |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           MPA CRC                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

         Figure 6.  SendSE Message Containing an iSER Hello Message

















<span class="grey">Ko, et al.                  Standards Track                    [Page 73]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-74" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="appendix-A.2" href="#appendix-A.2">A.2</a>.  iWARP Message Format for iSER HelloReply Message</span>

   The following figure depicts an iSER HelloReply Message encapsulated
   in an iWARP SendSE Message.  The Reject (REJ) flag is set to 0.

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |         MPA Header            |  DDP Control  | RDMA Control  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                        Reserved                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       (Send) Queue Number                     |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                 (Send) Message Sequence Number                |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                      (Send) Message Offset                    |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      | 0011b |Zeros|0| 0001b | 0001b |           iSER-ORD            |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           All Zeros                           |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           All Zeros                           |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           MPA CRC                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

       Figure 7.  SendSE Message Containing an iSER HelloReply Message























<span class="grey">Ko, et al.                  Standards Track                    [Page 74]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-75" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="appendix-A.3" href="#appendix-A.3">A.3</a>.  iWARP Message Format for SCSI Read Command PDU</span>

   The following figure depicts a SCSI Read Command PDU embedded in an
   iSER Message encapsulated in an iWARP SendSE Message.  For this
   particular example, in the iSER header, the Write STag Valid flag is
   set to zero, the Read STag Valid flag is set to one, the Write STag
   field is set to all zeros, and the Read STag field contains a valid
   Read STag.

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |         MPA Header            |  DDP Control  | RDMA Control  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                        Reserved                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       (Send) Queue Number                     |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                 (Send) Message Sequence Number                |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                      (Send) Message Offset                    |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      | 0001b |0|1|                  All zeros                        |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                         All Zeros                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                         Read STag                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       SCSI Read Command PDU                   |
      //                                                             //
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           MPA CRC                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

        Figure 8.  SendSE Message Containing a SCSI Read Command PDU















<span class="grey">Ko, et al.                  Standards Track                    [Page 75]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-76" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="appendix-A.4" href="#appendix-A.4">A.4</a>.  iWARP Message Format for SCSI Read Data</span>

   The following figure depicts an iWARP RDMA Write Message carrying
   SCSI Read data in the payload:

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |         MPA Header            |   DDP Control | RDMA Control  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       Data Sink STag                          |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                   Data Sink Tagged Offset                     |
      +                                                               +
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                      SCSI Read data                           |
      //                                                             //
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           MPA CRC                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

           Figure 9.  RDMA Write Message Containing SCSI Read Data



























<span class="grey">Ko, et al.                  Standards Track                    [Page 76]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-77" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="appendix-A.5" href="#appendix-A.5">A.5</a>.  iWARP Message Format for SCSI Write Command PDU</span>

   The following figure depicts a SCSI Write Command PDU embedded in an
   iSER Message encapsulated in an iWARP SendSE Message.  For this
   particular example, in the iSER header, the Write STag Valid flag is
   set to one, the Read STag Valid flag is set to zero, the Write STag
   field contains a valid Write STag, and the Read STag field is set to
   all zeros since it is not used.

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |         MPA Header            |  DDP Control  | RDMA Control  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                        Reserved                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       (Send) Queue Number                     |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                 (Send) Message Sequence Number                |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                      (Send) Message Offset                    |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      | 0001b |1|0|                  All zeros                        |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                        Write STag                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                         All Zeros                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       SCSI Write Command PDU                  |
      //                                                             //
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           MPA CRC                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

       Figure 10.  SendSE Message Containing a SCSI Write Command PDU















<span class="grey">Ko, et al.                  Standards Track                    [Page 77]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-78" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="appendix-A.6" href="#appendix-A.6">A.6</a>.  iWARP Message Format for RDMA Read Request</span>

   An iSCSI R2T is transformed into an iWARP RDMA Read Request Message.
   The following figure depicts an iWARP RDMA Read Request Message:

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |         MPA Header            |  DDP Control  | RDMA Control  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                      Reserved (Not Used)                      |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |              DDP (RDMA Read Request) Queue Number             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |        DDP (RDMA Read Request) Message Sequence Number        |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |             DDP (RDMA Read Request) Message Offset            |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                     Data Sink STag (SinkSTag)                 |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                                                               |
      +                  Data Sink Tagged Offset (SinkTO)             +
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                  RDMA Read Message Size (RDMARDSZ)            |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                     Data Source STag (SrcSTag)                |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                                                               |
      +                 Data Source Tagged Offset (SrcTO)             +
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           MPA CRC                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

                   Figure 11.  RDMA Read Request Message















<span class="grey">Ko, et al.                  Standards Track                    [Page 78]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-79" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="appendix-A.7" href="#appendix-A.7">A.7</a>.  iWARP Message Format for Solicited SCSI Write Data</span>

   The following figure depicts an iWARP RDMA Read Response Message
   carrying the solicited SCSI Write data in the payload:

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |         MPA Header            |  DDP Control  | RDMA Control  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       Data Sink STag                          |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                   Data Sink Tagged Offset                     |
      +                                                               +
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       SCSI Write Data                         |
      //                                                             //
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           MPA CRC                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

      Figure 12.  RDMA Read Response Message Containing SCSI Write Data



























<span class="grey">Ko, et al.                  Standards Track                    [Page 79]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-80" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="appendix-A.8" href="#appendix-A.8">A.8</a>.  iWARP Message Format for SCSI Response PDU</span>

   The following figure depicts a SCSI Response PDU embedded in an iSER
   Message encapsulated in an iWARP SendInvSE Message:

       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
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |         MPA Header            |  DDP Control  | RDMA Control  |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                      Invalidate STag                          |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       (Send) Queue Number                     |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                 (Send) Message Sequence Number                |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                      (Send) Message Offset                    |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      | 0001b |0|0|                  All Zeros                        |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           All Zeros                           |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           All Zeros                           |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                       SCSI Response PDU                       |
      //                                                             //
      |                                                               |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
      |                           MPA CRC                             |
      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

         Figure 13.  SendInvSE Message Containing SCSI Response PDU



















<span class="grey">Ko, et al.                  Standards Track                    [Page 80]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-81" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h2"><a class="selflink" id="appendix-B" href="#appendix-B">Appendix B</a>.  Architectural Discussion of iSER over InfiniBand</span>

   This section explains how an InfiniBand network (with Gateways) would
   be structured.  It is informational only and is intended to provide
   insight on how iSER is used in an InfiniBand environment.

<span class="h3"><a class="selflink" id="appendix-B.1" href="#appendix-B.1">B.1</a>.  The Host Side of the iSCSI and iSER Connections in InfiniBand</span>

   Figure 14 defines the topologies in which iSCSI and iSER will be able
   to operate on an InfiniBand Network.

   +---------+ +---------+ +---------+ +---------+ +--- -----+
   |  Host   | |  Host   | |   Host  | |   Host  | |   Host  |
   |         | |         | |         | |         | |         |
   +---+-+---+ +---+-+---+ +---+-+---+ +---+-+---+ +---+-+---+
   |HCA| |HCA| |HCA| |HCA| |HCA| |HCA| |HCA| |HCA| |HCA| |HCA|
   +-v-+ +-v-+ +-v-+ +-v-+ +-v-+ +-v-+ +-v-+ +-v-+ +-v-+ +-v-+
     |----+------|-----+-----|-----+-----|-----+-----|-----+---&gt; To IB
   IB|        IB |        IB |        IB |        IB |    SubNet2 SWTCH
   +-v-----------v-----------v-----------v-----------v---------+
   |                  InfiniBand Switch for Subnet1            |
   +---+-----+--------+-----+--------+-----+------------v------+
       | TCA |        | TCA |        | TCA |            |
       +-----+        +-----+        +-----+            | IB
      /  IB   \      /  IB   \      /       \     +--+--v--+--+
     |  iSER   |    |  iSER   |    |  IPoIB  |    |  | TCA |  |
     | Gateway |    | Gateway |    | Gateway |    |  +-----+  |
     |   to    |    |   to    |    |   to    |    | Storage   |
     |  iSCSI  |    |  iSER   |    |   IP    |    | Controller|
     |   TCP   |    |  iWARP  |    |Ethernet |    +-----+-----+
     +---v-----|    +---v-----|    +----v----+
         | EN           | EN            | EN
         +--------------+---------------+----&gt; to IP based storage
           Ethernet links that carry iSCSI or iWARP

                   Figure 14.  iSCSI and iSER on IB

   In Figure 14, the Host systems are connected via the InfiniBand Host
   Channel Adapters (HCAs) to the InfiniBand links.  With the use of IB
   switch(es), the InfiniBand links connect the HCA to InfiniBand Target
   Channel Adapters (TCAs) located in gateways or Storage Controllers.
   An iSER-capable IB-IP Gateway converts the iSER Messages encapsulated
   in IB protocols to either standard iSCSI, or iSER Messages for iWARP.
   An [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>] Gateway converts the InfiniBand [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>] protocol to IP
   protocol, and in the iSCSI case, permits iSCSI to be operated on an
   IB Network between the Hosts and the [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>] Gateway.





<span class="grey">Ko, et al.                  Standards Track                    [Page 81]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-82" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


<span class="h3"><a class="selflink" id="appendix-B.2" href="#appendix-B.2">B.2</a>.  The Storage Side of the iSCSI and iSER Mixed Network Environment</span>

   Figure 15 shows a storage controller that has three different portal
   groups: one supporting only iSCSI (TPG-4), one supporting iSER/iWARP
   or iSCSI (TPG-2), and one supporting iSER/IB (TPG-1).

                  |                |                |
                  |                |                |
            +--+--v--+----------+--v--+----------+--v--+--+
            |  | IB  |          |iWARP|          | EN  |  |
            |  |     |          | TCP |          | NIC |  |
            |  |(TCA)|          | RNIC|          |     |  |
            |  +-----|          +-----+          +-----+  |
            |   TPG-1            TPG-2            TPG-4   |
            |  9.1.3.3          9.1.2.4          9.1.2.6  |
            |                                             |
            |                  Storage Controller         |
            |                                             |
            +---------------------------------------------+

   Figure 15.  Storage Controller with TCP, iWARP, and IB Connections

   The normal iSCSI portal group advertising processes (via the Service
   Location Protocol (SLP), the Internet Storage Name Service (iSNS), or
   SendTargets) are available to a Storage Controller.

<span class="h3"><a class="selflink" id="appendix-B.3" href="#appendix-B.3">B.3</a>.  Discovery Processes for an InfiniBand Host</span>

   An InfiniBand Host system can gather portal group IP addresses from
   SLP, iSNS, or the SendTargets discovery processes by using TCP/IP via
   [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>].  After obtaining one or more remote portal IP addresses, the
   Initiator uses the standard IP mechanisms to resolve the IP address
   to a local outgoing interface and the destination hardware address
   (Ethernet MAC or IB GID of the target or a gateway leading to the
   target).  If the resolved interface is an [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>] network interface,
   then the target portal can be reached through an InfiniBand fabric.
   In this case, the Initiator can establish an iSCSI/TCP or iSCSI/iSER
   session with the Target over that InfiniBand interface, using the
   Hardware Address (InfiniBand GID) obtained through the standard
   Address Resolution (ARP) processes.

   If more than one IP address is obtained through the discovery
   process, the Initiator should select a Target IP address that is on
   the same IP subnet as the Initiator, if one exists.  This will avoid
   a potential overhead of going through a gateway when a direct path
   exists.





<span class="grey">Ko, et al.                  Standards Track                    [Page 82]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-83" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


   In addition, a user can configure manual static IP route entries if a
   particular path to the target is preferred.

<span class="h3"><a class="selflink" id="appendix-B.4" href="#appendix-B.4">B.4</a>.  IBTA Connection Specifications</span>

   The InfiniBand Trade Association (IBTA) connection specifications are
   outside the scope of this document, but it is expected that the IBTA
   has or will define:

   *  The iSER ServiceID.

   *  A Means for permitting a Host to establish a connection with a
      peer InfiniBand end-node, and to fall back to iSCSI/TCP over
      [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>] if that peer indicates iSER is not supported.

   *  A Means for permitting the Host to establish connections with IB
      iSER connections on storage controllers or IB iSER connected
      Gateways in preference to [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>] connected Gateways/Bridges or
      connections to Target Storage Controllers that also accept iSCSI
      via [<a href="#ref-IPoIB" title="&quot;Transmission of IP over InfiniBand (IPoIB)&quot;">IPoIB</a>].

   *  A Means for combining the IB ServiceID for iSER and the IP port
      number such that the IB Host can use normal IB connection
      processes, yet ensure that the iSER target peer can actually
      connect to the required IP port number.

Acknowledgments

   This protocol was developed by a design team that, in addition to the
   authors, included Dwight Barron (HP), John Carrier (formerly from
   Adaptec), Ted Compton (EMC), Paul R. Culley (HP), Yaron Haviv
   (Voltaire), Jeff Hilland (HP), Mike Krause (HP), Alex Nezhinsky
   (Voltaire), Jim Pinkerton (Microsoft), Renato J. Recio (IBM), Julian
   Satran (IBM), Tom Talpey (Network Appliance), and Jim Wendt (HP).
   Special thanks to David Black (EMC) for his extensive review
   comments.















<span class="grey">Ko, et al.                  Standards Track                    [Page 83]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-84" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


Author's Address

   Mallikarjun Chadalapaka
   Hewlett-Packard Company
   8000 Foothills Blvd.
   Roseville, CA 95747-5668, USA
   Phone: +1-916-785-5621
   EMail: cbm@rose.hp.com

   Uri Elzur
   Broadcom Corporation
   5300 California Avenue
   Irvine, CA 92617, USA
   Phone: +1-949-926-6432
   EMail: Uri@Broadcom.com

   John Hufferd
   Brocade Communications Systems, Inc.
   1745 Technology Drive
   San Jose, CA 95110, USA
   Phone: +1-408-333-5244
   EMail: jhufferd@brocade.com

   Mike Ko
   IBM Corp.
   650 Harry Rd.
   San Jose, CA 95120, USA
   Phone: +1-408-927-2085
   EMail: mako@us.ibm.com

   Hemal Shah
   Broadcom Corporation
   5300 California Avenue
   Irvine, CA 92617, USA
   Phone: +1-949-926-6941
   EMail: hemal@broadcom.com

   Patricia Thaler
   Broadcom Corporation
   5300 California Avenue
   Irvine, CA 92617, USA
   Phone: +1-916-570-2707
   EMail: pthaler@broadcom.com








<span class="grey">Ko, et al.                  Standards Track                    [Page 84]</span></pre>
<hr class='noprint'/><!--NewPage--><pre class='newpage'><span id="page-85" ></span>
<span class="grey"><a href="./rfc5046">RFC 5046</a>                   iSER Specification               October 2007</span>


Full Copyright Statement

   Copyright (C) The IETF Trust (2007).

   This document is subject to the rights, licenses and restrictions
   contained in <a href="https://www.rfc-editor.org/bcp/bcp78">BCP 78</a>, and except as set forth therein, the authors
   retain all their rights.

   This document and the information contained herein are provided on an
   "AS IS" basis and THE CONTRIBUTOR, THE ORGANIZATION HE/SHE REPRESENTS
   OR IS SPONSORED BY (IF ANY), THE INTERNET SOCIETY, THE IETF TRUST AND
   THE INTERNET ENGINEERING TASK FORCE DISCLAIM ALL WARRANTIES, EXPRESS
   OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF
   THE INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED
   WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.

Intellectual Property

   The IETF takes no position regarding the validity or scope of any
   Intellectual Property Rights or other rights that might be claimed to
   pertain to the implementation or use of the technology described in
   this document or the extent to which any license under such rights
   might or might not be available; nor does it represent that it has
   made any independent effort to identify any such rights.  Information
   on the procedures with respect to rights in RFC documents can be
   found in <a href="https://www.rfc-editor.org/bcp/bcp78">BCP 78</a> and <a href="https://www.rfc-editor.org/bcp/bcp79">BCP 79</a>.

   Copies of IPR disclosures made to the IETF Secretariat and any
   assurances of licenses to be made available, or the result of an
   attempt made to obtain a general license or permission for the use of
   such proprietary rights by implementers or users of this
   specification can be obtained from the IETF on-line IPR repository at
   <a href="http://www.ietf.org/ipr">http://www.ietf.org/ipr</a>.

   The IETF invites any interested party to bring to its attention any
   copyrights, patents or patent applications, or other proprietary
   rights that may cover technology that may be required to implement
   this standard.  Please address the information to the IETF at
   ietf-ipr@ietf.org.












Ko, et al.                  Standards Track                    [Page 85]
</pre>