https://bugzilla.kernel.org/show_bug.cgi?id=191381

            Bug ID: 191381
           Summary: LIO ignores XCOPY source and destination descriptor
                    IDs
           Product: IO/Storage
           Version: 2.5
    Kernel Version: 4.9.0
          Hardware: All
                OS: Linux
              Tree: Mainline
            Status: NEW
          Severity: normal
          Priority: P1
         Component: SCSI
          Assignee: linux-scsi@vger.kernel.org
          Reporter: ddiss....@gmail.com
        Regression: No

The EXTENDED COPY SCSI command (XCOPY) is used extensively by VMware ESX
initiators, to offload to the iSCSI target, the process of copying data between
a source and destination LU region.
XCOPY is also supported by other initiators, such as ddpt
(http://sg.danny.cz/sg/ddpt.html), libiscsi, etc.

The XCOPY specification in SPC-4 (revision 37) states that the XCOPY source and
destination device(s) should be derived from the copy source and copy
destination descriptor (CSCD) IDs in the XCOPY segment descriptor. The CSCD IDs
are generally (for block -> block copies), indexes into the corresponding CSCD
list, i.e.

=================================
XCOPY Header    
=================================
CSCD List
- entry 0
  + LU ID
- entry 2
  + LU ID
=================================
Segment Descriptor List
- segment 0
  + src CSCD ID = (CSCD entry 0)
  + dest CSCD ID = (CSCD entry 1)
  + len
  + src lba
  + dest lba
=================================

Currently LIO completely ignores the src and dest CSCD IDs in the Segment
Descriptor List, and instead assumes that the first entry in the CSCD list
corresponds to the source, and the second to the destination.

This assumption appears to stand true for XCOPY requests from ESXi initiators.
However, deviation from the spec may break other initiators - it causes a
number of libiscsi tests to fail.

-- 
You are receiving this mail because:
You are the assignee for the bug.
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to