summaryrefslogtreecommitdiffstats
path: root/sys/dev/iscsi
Commit message (Expand)AuthorAgeFilesLines
* Fix LUN discovery for targets that don't support REPORT_LUNS, brokentrasz2014-09-171-1/+6
* Make sure we handle less than zero timeouts in iSCSI initiator and targettrasz2014-09-101-2/+12
* Use proper include paths in kernel iSCSI code.trasz2014-08-213-7/+7
* Make the iSCSI stack use __FBSDID() properly.trasz2014-08-213-3/+9
* Fix potential double free that could happen after connection error.trasz2014-07-281-1/+4
* Add XPT_ABORT support to iSCSI initiator.mav2014-07-081-23/+138
* Make XPT_GET_TRAN_SETTINGS to report CAM that command queueing is enabled,mav2014-07-071-18/+36
* Make iSCSI initiator keep Initiator Session ID (ISID) across reconnects.mav2014-07-063-6/+13
* Pull in r267961 and r267973 again. Fix for issues reported will follow.hselasky2014-06-282-11/+0
* Revert r267961, r267973:gjb2014-06-272-0/+11
* Extend the meaning of the CTLFLAG_TUN flag to automatically check ifhselasky2014-06-272-11/+0
* Implement redirection handling in initiator.trasz2014-06-182-13/+71
* Close the race in older code, that caused connection stuck after r264348.mav2014-04-161-7/+11
* Make it possible for the initiator side to operate in both proxytrasz2014-04-162-12/+24
* Fix typo.trasz2014-04-161-1/+1
* Add kern.iscsi.fail_on_disconnection; this is required for gmultipathtrasz2014-04-161-63/+65
* Remove useless debug.trasz2014-04-161-1/+0
* Be more strict with locking for is_waiting_for_iscsid variable.trasz2014-04-161-1/+4
* Get rid of ISCSIDCLOSE; it wasn't used and is redundant anyway,trasz2014-04-162-31/+0
* Properly pass the initiator address when running in proxy mode.trasz2014-04-162-4/+7
* Properly identify target portal when running in proxy mode. While here,trasz2014-04-162-16/+21
* Add some stuff to make it easier to figure out for the system administratortrasz2014-04-161-0/+4
* Remove unused val argument value from SYSCTL_INT() calls.mav2014-04-112-10/+10
* Improve use of socket buffer upcalls.mav2014-04-111-6/+21
* Remove hack to pass STAILQ to a function and do it properly instead.trasz2014-04-051-3/+4
* Rework the iSCSI PDU transmit code to avoid lock contention and coalescetrasz2014-04-042-37/+169
* All the iSCSI sysctls are also tunables; advertise that.trasz2014-04-042-9/+9
* We don't need TAILQ for iSCSI PDUs; STAILQ is enough.trasz2014-04-044-27/+27
* Fix build, broken by r264025.trasz2014-04-021-2/+2
* Enable a KASSERT.trasz2014-04-011-4/+1
* Get rid of the "autoscaling", instead just set socket buffer sizestrasz2014-04-011-11/+29
* Instead of "icltx" and "iclrx", use thread names with prefix from uppertrasz2014-04-013-5/+9
* Get rid of ICL lock; use upper-layer (initiator or target) lock instead.trasz2014-04-013-13/+20
* Move the ic_outstanding_count under #ifdef DIAGNOSTIC.trasz2014-03-252-0/+10
* Fix harmless warning after reconnecting a session and not doing anythingtrasz2014-03-251-2/+2
* Use newly added extended LUN support in CAM.trasz2014-03-251-40/+5
* Use a less unusual syntax in debug printfs.trasz2014-03-252-24/+34
* Update kernel inclusions of capability.h to use capsicum.h instead; somerwatson2014-03-162-2/+2
* Fix a rare "truncated checksums" problem, which manifested like this:trasz2014-01-071-2/+2
* Fix extremely slow operation with data digests enabled. This was causedtrasz2013-12-301-2/+2
* Properly refuse handoff requests on already connected sessions. Previouslytrasz2013-12-101-0/+12
* Fix hang on reboot with active iSCSI connections.trasz2013-12-011-3/+5
* Don't spin with mutex hold when there is not enough room in the send sockettrasz2013-10-241-14/+12
* Properly handle residual count in Data-In PDUs with S bit set.trasz2013-10-091-12/+33
* Be extra paranoid with values obtained from the target.trasz2013-10-091-8/+26
* Fail connection upon receiving too large data segment.trasz2013-10-091-0/+1
* Fix NOP-In/NOP-Out payload handling. Previous way didn't work at all; fortun...trasz2013-10-091-6/+36
* Don't leak memory when removing an unconnected session, and remove uselesstrasz2013-10-042-3/+4
* As it turns out, when MOD_LOAD handler returns error, kernel calls MOD_UNLOADtrasz2013-09-241-11/+7
* Don't use M_WAITOK when running from context where sleeping is prohibited,trasz2013-09-231-1/+5
OpenPOWER on IntegriCloud