summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Use common vt_fb parts in ofwfb as far as we are able without sacrificingnwhitehorn2014-07-071-73/+52
| | | | | | performance. MFC after: 2 weeks
* Use the appropriate IPv6 hashtype defines when looking up the PCBGROUPbryanv2014-07-071-2/+2
| | | | Reviewed by: adrian@
* Remove /usr/share/doc/psd/28.cvs/paper.ps.gz if it exists, as it isgavin2014-07-061-0/+1
| | | | | | | | obsolete since r251794. PR: 191003 Submitted by: Vick Khera MFC after: 3 days
* Make gcc happy, init idlen2.andreast2014-07-061-1/+1
|
* Close race in r268291 between port destruction, delayed by sessionsmav2014-07-064-0/+28
| | | | | | | teardown, and new port creation during `service ctld restart`. Close it by returning iSCSI port internal state, that allows to identify dying ports, which should not be counted as existing, from really alive.
* Introduce pmap_unwire(). It will replace pmap_change_wiring(). There arealc2014-07-067-0/+362
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | several reasons for this change: pmap_change_wiring() has never (in my memory) been used to set the wired attribute on a virtual page. We have always used pmap_enter() to do that. Moreover, it is not really safe to use pmap_change_wiring() to set the wired attribute on a virtual page. The description of pmap_change_wiring() says that it assumes the existence of a mapping in the pmap. However, non-wired mappings may be reclaimed by the pmap at any time. (See pmap_collect().) Many implementations of pmap_change_wiring() will crash if the mapping does not exist. pmap_unwire() accepts a range of virtual addresses, whereas pmap_change_wiring() acts upon a single virtual page. Since we are typically unwiring a range of virtual addresses, pmap_unwire() will be more efficient. Moreover, pmap_unwire() allows us to unwire superpage mappings. Previously, we were forced to demote the superpage mapping, because pmap_change_wiring() only allowed us to express the unwiring of a single base page mapping at a time. This added to the overhead of unwiring for large ranges of addresses, including the implicit unwiring that occurs at process termination. Implementations for arm and powerpc will follow. Discussed with: jeff, marcel Reviewed by: kib Sponsored by: EMC / Isilon Storage Division
* Make iSCSI initiator keep Initiator Session ID (ISID) across reconnects.mav2014-07-066-30/+23
| | | | | | | | | Previously ISID was changed every time, that made impossible correct persistent reservation, because reconnected session was identified as completely new one. Reviewed by: trasz MFC after: 1 week
* In case we ever support little-endian PowerPC (probably userland only),nwhitehorn2014-07-061-0/+12
| | | | avoid hardcoding endianness here.
* Add a new CPU id for a POWER8 variant.nwhitehorn2014-07-062-1/+5
|
* Fix OFED startup order: All SYSINIT()'s and modules should be loadedhselasky2014-07-064-6/+11
| | | | | | | | | prior to starting "/sbin/init" which will run all the "/etc/rc.d/xxx" scripts. Else there can be a race configuring the interfaces via "/etc/rc.conf". MFC after: 4 weeks Sponsored by: Mellanox Technologies
* Fix compile warning.hselasky2014-07-061-1/+1
| | | | | MFC after: 4 weeks Sponsored by: Mellanox Technologies
* Fix some compile warnings.hselasky2014-07-061-12/+12
| | | | | MFC after: 4 weeks Sponsored by: Mellanox Technologies
* Align the stack in _rtld_bind_start. Normally this is called with theandrew2014-07-061-2/+5
| | | | | | | | | | | | | | | | | | | correct stack alignment, however when we have a leaf function that uses thread local storage it calls __aeabi_read_tp to get the thread pointer. Neither GCC or clang see this as a function call so will align the stack to a 4-byte boundary. This may be a problem as _rtld_bind expects to be on an 8-byte boundary. The solution is to store a copy of the stack pointer and force the alignment before calling _rtld_bind. This fixes a problem with armeb where applications would crash in odd ways. It should also remove the need for a local patch to clang to force the stack alignment to an 8-byte boundary, even for leaf functions. Further testing will be needed before reverting this local change to clang as we may rely on it in other places. Reviewed by: jmg@
* Add support for SCSI Ports (88h) VPD page.mav2014-07-062-8/+153
|
* Make REPORT TARGET PORT GROUPS command report realistic data instead ofmav2014-07-062-81/+101
| | | | hardcoded garbage.
* Move lun_map() method from command nexus to port.mav2014-07-065-34/+30
| | | | | Previous implementation made impossible to do some things, such as calling it for ports other then one through which command arrived.
* Relax some bit checks for INQUIRY command.mav2014-07-061-1/+1
| | | | | FreeBSD still tries to put LUN number in second byte until it get device protocol version, even that it was obsoleted about 20 years ago.
* sh: Fix overflow checking on 'ulimit' operand.jilles2014-07-051-10/+14
|
* Add support to asmc(4) for Macmini 3,1.gavin2014-07-052-0/+28
| | | | | | | PR: 190195 Submitted by: fbsdbugs2 sentry.org MFC after: 1 week Relnotes: yes
* Pass through iSCSI session ISID from LOGIN request to the CTL frontend.mav2014-07-056-0/+16
| | | | | ISID is an important part of initiator transport ID for iSCSI. It is not used now, but should be to properly implement persistent reservation.
* Check the number of returned entries before doing any access to ifm_ulist.loos2014-07-051-0/+2
|
* bsd.dep.mk: add support for generating DTrace header files from .d files.rpaulo2014-07-051-0/+12
| | | | MFC after: 3 weeks
* Use %zu not %zd for printing size_t.gavin2014-07-051-1/+1
| | | | | | PR: 185007 Submitted by: saper saper.info MFC after: 3 days
* Correct format string to fix build of uhsoctl when DEBUG is definedgavin2014-07-051-1/+1
| | | | | | PR: 185007 Submitted by: saper saper.info MFC after: 3 days
* Add the DTrace probe definitions for plockstat support.rpaulo2014-07-051-0/+46
| | | | | | This will be connected to the system later. Sponsored by: The FreeBSD Foundation
* Fix equation and limerick to be correct. NetBSD fixed this 14 years agogavin2014-07-051-2/+2
| | | | | | | | | (src/games/fortune/datfiles/fortunes2 1.7). PR: 188714 Submitted by: ksmakoto dd.iij4u.or.jp Reviewed by: Wolfram Alpha MFC after: 3 days
* Allow the PVID setting on CPU port.loos2014-07-051-2/+8
| | | | | | Return our static list of supported media for the CPU port. Tested on TP-Link 1043ND.
* Burry devid port method, which was a gross hack.mav2014-07-059-340/+196
| | | | | | | | | | | Instead make ports provide wanted port and target IDs, and LUNs provide wanted LUN IDs. After that core Device ID VPD code only had to link all of them together and add relative port and port group numbers. LUN ID for iSCSI LUNs no longer created by CTL, but by ctld, and passed to CTL as "scsiname" LUN option. This makes LUNs to report the same set of IDs, independently from the port through which it is accessed, as required by SCSI specifications.
* Dominion Day became Canada Day in 1982, update the holiday calendar.gavin2014-07-051-1/+1
| | | | | | | PR: 191533 Submitted by: db Obtained from: http://www.pch.gc.ca/eng/1359137387574/1359137429809 MFC after: 3 days
* Create separate CTL port for every iSCSI target (and maybe portal group).mav2014-07-0510-154/+593
| | | | | | | | | | | | | | | Having single port for all iSCSI connections makes problematic implementing some more advanced SCSI functionality in CTL, that require proper ports enumeration and identification. This change extends CTL iSCSI API, making ctld daemon to control list of iSCSI ports in CTL. When new target is defined in config fine, ctld will create respective port in CTL. When target is removed -- port will be also removed after all active commands through that port properly aborted. This change require ctld to be rebuilt to match the kernel. As a minor side effect, this allows to have iSCSI targets without LUNs. While that may look odd and not very useful, that is not incorrect.
* Merge from OpenSolaris (24-Jul-2010):pfg2014-07-051-14/+64
| | | | | | | | | | | 6679140 asymmetric alloc/dealloc activity can induce dynamic variable drops 6679193 dtrace_dynvar walker produces flood of dtrace_dynhash_sink This finishes a set of merges from the older OpenSolaris releases. Still the FreeBSD port has many differences that are difficult to account for but that seems normal given that the kernels are different. MFC after: 1 week
* Fix minor copy-paste bug in r268284.mav2014-07-051-1/+1
|
* Improve CTL_BEARG_* flags support, including optional values copyout.mav2014-07-052-25/+43
|
* Implement and use ctl_frontend_find().mav2014-07-053-7/+23
|
* Fix compile-time errors when NO_WERROR and WITHOUT_INET6_SUPPORTcy2014-07-054-4/+4
| | | | | | | (NO_INET6) are specified. Approved by: glebius MFC after: 1 week
* When getting the initial value of numeric tunables use thehselasky2014-07-051-12/+20
| | | | | | getenv_xxx() functions instead of strtoq(), because the getenv_xxx() functions include wrappers for various postfixes like G/M/K, which strtoq() doesn't do.
* Introduce new IOCTL CTL_PORT_LIST reporting in more flexible XML format.mav2014-07-053-1/+369
| | | | Leave old CTL_GET_PORT_LIST in place so far. Garbage-collect it later.
* Improve readability of XML generated by CTL_LUN_LIST.mav2014-07-052-9/+10
|
* units(1): Clean upeadler2014-07-051-18/+14
| | | | Remove unused constant. Add 'static' where able.
* Make options KPI more generic to allow it to be used for ports too,mav2014-07-057-50/+58
| | | | not only for LUNs.
* units(1): Convert units.lib to use '#' instead of '/'.eadler2014-07-051-31/+31
| | | | | This allows us to run GNU units against our data files and compare the output. In addition, current units(1) does not support '/' as a comment at all.
* units: Support start of line comments with '#'eadler2014-07-052-2/+2
| | | | Modern GNU units(1) supports comments anywhere with '#' but take the easy route for now and at least support start of line # comments.
* units(1): Add 'terse' supporteadler2014-07-052-11/+24
| | | | terse output is used when calling units from another script.
* Extend capabilities to 64-bits in preparation for some API changes.grehan2014-07-051-1/+1
| | | | | The v1.0 virtio spec supports an extended size for guest/host caps, but in practice 64-bits should last for a long time.
* Use proper links field for ports linking.mav2014-07-051-1/+1
|
* The new NFSv3 server did not generate directory postop attributes forrmacklem2014-07-041-2/+4
| | | | | | | | | | | | | | | the reply to ReaddirPlus when the server failed within the loop that calls VFS_VGET(). This failure is most likely an error return from VFS_VGET() caused by a bogus d_fileno that was truncated to 32bits. This patch fixes the server so that it will return directory postop attributes for the failure. It does not fix the underlying issue caused by d_fileno being uint32_t when a file system like ZFS generates a fileno that is greater than 32bits. Reported by: jpaetzel Reviewed by: jpaetzel MFC after: 1 month
* minor perf enhancement for UTF-8pfg2014-07-041-19/+10
| | | | | | | | | | Reduce some duplicate code. Reference: https://www.illumos.org/issues/628 Obtained from: Illumos MFC after: 1 week
* units(1): Add 'help' flageadler2014-07-042-2/+8
| | | | | - Add support for --help for compatibility - Make usage() static
* units(1): Fix man pageeadler2014-07-041-3/+5
| | | | | | Igor walks one way. I walked the other. Reported by: wblock
* units(1): add long optionseadler2014-07-042-7/+17
| | | | | | Things brings additional compatibility with units 2.10 Discussed with: wblock (man page)
OpenPOWER on IntegriCloud