summaryrefslogtreecommitdiffstats
path: root/sys/cam
Commit message (Collapse)AuthorAgeFilesLines
* MFC r288458: More aggressively fill WUT read pipeline.mav2015-10-051-5/+4
| | | | On some tests I've measured 5% copy speedup from this.
* MFC r288450: Make zero WUT use WRITE SAME with recently allowed NDOB flag.mav2015-10-051-5/+3
|
* MFC r288449:mav2015-10-051-1/+9
| | | | Implement SPC-3 exceptions to SPC-2 RESERVE and RELEASE behavior.
* MFC r288448: Unify PR variable names to reduce confusion.mav2015-10-052-66/+66
|
* MFC r288427: Use proper STAILQ_* macros where possible.mav2015-10-052-20/+7
|
* MFC r288420: Make pass, sg and targ drivers respect HBA's maxio.mav2015-10-056-8/+35
| | | | Previous limitation of 64K (DFLTPHYS) is quite annoying.
* MFC r288369: Really implement PREVENT ALLOW MEDIUM REMOVAL command.mav2015-10-055-21/+66
|
* MFC r288368: Don't report SYNC_NV bit set in SYNCHRONIZE CACHE as error.mav2015-10-051-2/+2
| | | | | While this bit is obsolete in SBC-3, behavior controlled by it is allowed on device discretion.
* MFC r288367: Fix arguments order.mav2015-10-051-8/+8
|
* MFC r288359: Report that we can read all flavours of DVD. Why not?mav2015-10-051-1/+55
|
* MFC r288358: Add CD/DVD Capabilities and Mechanical Status Page.mav2015-10-053-0/+102
| | | | | | This page is obsolete since MMC-4, but still used by some software. approved by:
* MFC r288348: Umplement media load/eject support for removable devices.mav2015-10-0510-338/+228
| | | | | In case of block backend eject really closes the backing store, while load tries to open it back. Failed store open is reported as no media.
* MFC r288310: Add to CTL initial support for CDROMs and removable devices.mav2015-10-057-131/+699
| | | | Relnotes: yes
* MFC r288264: Allow LOG SENSE command on non-disk devices.mav2015-10-052-2/+5
|
* MFC r288262: Remove concept of control device.mav2015-10-051-62/+24
|
* MFC r288261: Move ioctl frontend defines where they belong.mav2015-10-052-12/+12
|
* MFC r288260: Remove few more unused variables.mav2015-10-052-4/+0
|
* MFC r288259: Remove some duplicate, legacy, dead and questionable code.mav2015-10-058-406/+23
|
* MFC r288247: Pass to sobind() copy of the address, not the original.mav2015-10-051-2/+6
|
* MFC r288239: Properly lock LUN in ctl_failover_lun().mav2015-10-051-7/+25
|
* MFC r288224: Constify ctl_serialize_table.mav2015-10-052-2/+2
|
* MFC r288229: Fix bit masks changed for the wrong commands in r288221.mav2015-10-051-4/+4
|
* MFC r288221: Remove some dead code found by Clang analyzer.mav2015-10-0510-220/+17
|
* MFC r288220: Remove stale comments and some excessive empty lines.mav2015-10-052-84/+10
|
* MFC r288215: Switch I/O time accounting from system time to uptime.mav2015-10-054-24/+24
| | | | While there, make num_dmas accounted independently of CTL_TIME_IO.
* MFC r288214: Collect DMA statistics on secondary HA node.mav2015-10-051-3/+13
|
* MFC r288213:mav2015-10-051-236/+171
| | | | | | | Make HA handle datamove and done in a universal way, using port methods. Now from primary node point of view requests transferred from secondary node should look almost normal and always have valid port.
* MFC r288211: Remove some control_softc references.mav2015-10-056-52/+25
|
* MFC r288175: Allow WRITE SAME with NDOB bit set but without UNMAP.mav2015-10-052-4/+8
| | | | This combination was originally forbidden, but allowed at spc4r3.
* MFC r288170: Add new report types to REPORT LUNS command.mav2015-10-052-4/+7
| | | | This is only for completeness, since we have nothing new to report there.
* MFC r288166: Update WRITE ATOMIC(16) support to sbc4r8 draft.mav2015-10-053-7/+28
| | | | | This is only a cosmetic change. We still don't support atomic boundary field in the CDB, but at least now we do it formally.
* MFC r288165: Add support for READ BUFFER(16) command.mav2015-10-053-15/+55
|
* MFC r288148: Synchronize mode pages between HA peers.mav2015-10-053-2/+106
| | | | | | We allow to modify only few fields in mode pages now, but still it is not good if they unexpectedly change during failover. Also this fixes reporting of "Mode parameters changed" UAs on secondary node.
* MFC r288146: Make HA peers announce their parameters on connect.mav2015-10-054-7/+99
| | | | | | | HA protocol requires strict version, parameters and configuration match. Differences there may cause full set of problems up to kernel panic. To avoid that, validate peer parameters on connect, and abort connection immediately if some mismatch detected.
* MFC r288110: Add support for Control extension mode page.mav2015-10-053-27/+94
|
* MFC r288104: Remove duplicate and incomplete code handling LUN modify.mav2015-10-051-85/+2
| | | | | Instead reuse code from LUN creation. This allows most of LUN media options to be changed live with modify request without full restart.
* MFC r288067: Log iSCSI session reinstatements.mav2015-10-051-0/+10
| | | | | False session reinstatements can be result of misconfiguration, when several initiators use the same initiator name and ISID.
* MFC r288021: Mark with DMA flag I/Os waiting for iSCSI write data after R2T.mav2015-10-051-0/+5
| | | | Reads and immediate writes are not blocking, so don't bother.
* MFC r288020: Remove couple excess SGLIST I/O flags.mav2015-10-056-7/+4
| | | | Those flags duplicated respective (sg_entries > 0) values.
* MFC r287994: Always execute REPORT LUNS and REQUEST SENSE commands locally.mav2015-10-052-5/+8
| | | | | | | | | REPORT LUNS command is more related to target rather then specific LUN. This node may be primary for LUNs for some reason unknown to another, and command forwarded to another node won't be able to report them. REQUEST SENSE is related to LUN, but in our implementation it reports only UAs and CAs, that are stored locally rather then on primary node.
* MFC r287993: Split two command flags with different meaning.mav2015-10-053-11/+13
| | | | This is only a cosmetical change.
* MFC r287991: Pack struct ctl_ha_msg_hdr by 8 bytes.mav2015-10-051-1/+1
|
* MFC r287986: Fix memory corruption when >128K transferred through HA link.mav2015-10-051-20/+6
| | | | While there, do some cleaning.
* MFC r287968: Mark I/Os with DMA flag while moving data through the HA link.mav2015-10-051-0/+3
|
* MFC r287967: Relax serseq option operation for reads.mav2015-10-054-4/+31
| | | | | | | | Previously, with serseq enabled, next command was unblocked only after previous completed. With this change, for read operations, next command is unblocked as soon as last media read completed. This is important for frontends that actually wait for data move completion (like camtgt), or when data are moved through the HA link, or especially when both.
* MFC r287957: Kill HA link and shutdown the threads on shutdown.mav2015-10-053-11/+48
|
* MFC r287956: Update list of opcodes to 5/26/15.mav2015-10-051-8/+13
|
* MFC r287955: Update list of ASC/ASCQ codes from 5/20/12 to 8/12/15.mav2015-10-051-1/+166
|
* MFC r287940: Replicate initiators WWPNs and names between HA peers.mav2015-10-053-1/+91
|
* MFC r287933: Replicate port->init_devid to HA peer.mav2015-10-052-2/+26
|
OpenPOWER on IntegriCloud