Store persistent reservation keys as uint64_t instead of uint8_t[8].
This allows to simplify the code and save 512KB of RAM per LUN (8%)
by removing no longer needed "registered" keys flags.
It allows to push out some final data from the send queue to the socket
before its close. In particular, it increases chances for logout response
to be delivered to the initiator.
Add support for WRITE ATOMIC (16) command and report SBC-4 compliance.
Atomic writes are only supported for ZVOLs in "dev" mode. In other cases
atomicity can not be guarantied and so the command is blocked.
Add support for MaxBurstLength and Expected Data transfer Length parameters.
Before this change target could send R2T request for write transfer of any
size, that could violate iSCSI RFC, which allows initiator to limit maximum
R2T size by negotiating MaxBurstLength connection parameter.
Also report an error in case of write underflow, when initiator provides
less data than initiator expects. Previously in such case our target
sent R2T request for non-existing data, violating the RFC, and confusing
some initiators. SCSI specs don't explicitly define how write underflows
should be handled and there are different oppinions, but reporting error
is hopefully better then violating iSCSI RFC with unpredictable results.
devq_openings counter lost its meaning after allocation queues has gone.
held counter is still meaningful, but problematic to update due to separate
locking of CCB allocation and queuing.
To fix that replace devq_openings counter with allocated counter. held is
now calculated on request as difference between number of allocated, queued
and active CCBs.
Always report that we support REPORT TARGET PORT GROUPS command.
Without clustering support we any way have only one group of permanently
active ports, but that gives us one more supported VMWare feature. ;)
Solaris' Comstar also reports it even when only one port is present.
Implement control over command reordering via options and control mode page.
It allows to bypass range checks between UNMAP and READ/WRITE commands,
which may introduce additional delays while waiting for UNMAP parameters.
READ and WRITE commands are always processed in safe order since their
range checks are almost free.
Add "readcache" and "writecache" LUN options to control default behavior.
Default values are "on". Disabling requires backend to support IO_DIRECT
and IO_SYNC flags respectively, or some alternatives.
Before this change UNMAP completely blocked other I/Os while running.
Now it blocks only colliding ones, slowing down others only due to ZFS
locks collisions.
Sponsored by: iXsystems, Inc.
Improve cache control support, including DPO/FUA flags and the mode page.
At this moment it works only for files and ZVOLs in device mode since BIOs
have no respective respective cache control flags (DPO/FUA).
When reporting some major UNIT ATTENTION condition, like POWER ON OCCURRED
or I_T NEXUS LOSS, clear all minor UAs for the LUN, redundant in this case.
All SAM specifications tell that target MAY do it, but libiscsi initiator
seems require it to be done, terminating connection with error if some more
UAs happen to be reported during iSCSI connection.
Approved by: re (gjb)
Using pointer from the cdev directly is dangerous since we have no
reference on it, and it may change any time. That caused panic if
device has gone.
While there, report capacity change only if it really changed.
Approved by: re (dephij)
Fix tpc_create_token() introduced in r269497 to encode CREATOR LOGICAL
UNIT DESCRIPTOR field as Identification Descriptor CSCD descriptor, not
just as Identification Descriptor.
Approved by: re (gjb)
Make it possible to disable NOP-In PDUs by the iSCSI initiator by setting
kern.cam.ctl.iscsi.ping_timeout to 0. This fixes interoperability with
some initiators that don't properly support NOP-Ins, namely iPXE/gPXE.
Approved by: re (kib)
