Commit Graph

109 Commits

Author SHA1 Message Date
Edward Tomasz Napierala
e553ca4994 Rework the way iSCSI initiator handles system shutdown. This fixes
hangs on shutdown with LUNs with mounted filesystems over a disconnected
iSCSI session.

MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D3052
2015-08-03 11:57:11 +00:00
Alexander Motin
5b157f2144 Close some potential races around socket start/close.
There are some reports about panics on ic->ic_socket NULL derefence.
This kind of races is the only way I can imagine it to happen.

MFC after:	2 weeks
2015-05-15 13:36:50 +00:00
Edward Tomasz Napierala
aca050aaaa Remove icl_conn_connected(); was unused.
MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2015-04-04 22:11:38 +00:00
Edward Tomasz Napierala
7a03d007cf Extend ICL to add receive offload methods. For software ICL backend
they are no-ops.

MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2015-02-08 19:15:14 +00:00
Edward Tomasz Napierala
d4b195d315 Make output of "iscsictl -v" and "ctladm islist -v" a little prettier
by capitalizing "None".

MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2015-02-08 10:58:25 +00:00
Edward Tomasz Napierala
5aabcd7c4e Tidy up; no functional changes.
MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2015-02-07 14:15:17 +00:00
Edward Tomasz Napierala
674074da06 Don't call callout_drain() with iscsi mutex held; this fixes a warning
that was introduced recently.  While here, don't try to access is_terminating
without lock.

MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2015-02-05 07:46:34 +00:00
Edward Tomasz Napierala
09f2b94bf4 Fix error handling.
MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2015-02-05 07:16:45 +00:00
Edward Tomasz Napierala
82babffba9 Make it possible to set (via iscsi.conf(5)) and query (via iscsictl -v)
initiator iSCSI offload.  Pass maximum data segment size supported by
chosen offload module to iscsid(8), and make iscsid(8) not try to negotiate
anything larger than that.

MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2015-02-05 06:37:59 +00:00
Alexander Motin
4b0e5c9ef4 Missed addition to r278098.
MFC after:	1 week
2015-02-02 16:06:23 +00:00
Alexander Motin
bebf6a8572 Add some fields and constants from RFC7144.
MFC after:	1 week
2015-02-02 15:59:17 +00:00
Edward Tomasz Napierala
872d2d9276 Use proper module name in MODULE_VERSION().
Sponsored by:	The FreeBSD Foundation
2015-01-31 15:22:45 +00:00
Edward Tomasz Napierala
a6ad7194e0 Drop unneeded include.
Sponsored by:	The FreeBSD Foundation
2015-01-31 15:21:54 +00:00
Edward Tomasz Napierala
9e46a88722 Add two files missed in r277963.
Sponsored by:	The FreeBSD Foundation
2015-01-31 08:03:56 +00:00
Edward Tomasz Napierala
321b17ec15 Add kobj interface between ICL and the rest of the iSCSI stack.
Review note - icl.c was moved to icl_soft.c.

MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2015-01-31 07:49:50 +00:00
Alexander Motin
3f9e1172b7 Slightly polish iSCSI parameters negotiation.
MFC after:	1 week
2014-12-19 01:12:22 +00:00
Alexander Motin
2124e3b07f Make sequence numbers checks more strict.
While we don't support MCS, hole in received sequence numbers may mean
only PDU loss.  While we don't support lost PDU recovery, terminate the
connection to avoid stuck commands.

While there, improve handling of sequence numbers wrap after 2^32 PDUs.

MFC after:	2 weeks
2014-12-17 15:13:21 +00:00
Alexander Motin
8b94b5836c For both iSCSI initiator and target increase socket buffer sizes before
establishing connection.

This is a workaround for Chelsio TOE driver, that does not update socket
buffer size in hardware after connection established, and unless that is
done beforehand, kernel code will stuck, attempting to send/receive full
PDU at once.

MFC after:	1 week
2014-11-22 15:09:18 +00:00
Alexander Motin
73e2e95d94 Fix use-after-free introduced in r274843.
I've missed that iscsi_outstanding_remove() frees the second pointer,
so it should no longer be used.  And in fact we don't really need to.

MFC after:	2 weeks
2014-11-22 09:45:32 +00:00
Alexander Motin
c215ad3aa8 Move icl_pdu_get_data() and xpt_done() out of initiator's session lock.
During heavy reads data copying in icl_pdu_get_data() may consume large
percent of CPU time.  Moving it out of the lock significantly reduces
lock hold time and respectively lock congestion on read operations.

MFC after:	2 weeks
2014-11-22 09:05:54 +00:00
Gleb Smirnoff
cfa6009e36 In preparation of merging projects/sendfile, transform bare access to
sb_cc member of struct sockbuf to a couple of inline functions:

sbavail() and sbused()

Right now they are equal, but once notion of "not ready socket buffer data",
will be checked in, they are going to be different.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2014-11-12 09:57:15 +00:00
Edward Tomasz Napierala
d2d52b0013 s/icl_pdu_new_bhs/icl_pdu_new/; no functional changes, just a little
nicer code.

Sponsored by:	The FreeBSD Foundation
2014-11-03 11:15:51 +00:00
Edward Tomasz Napierala
08c5dbaeb0 s/icl_pdu_new/icl_pdu_new_empty/g; no functional changes.
Sponsored by:	The FreeBSD Foundation
2014-11-03 11:05:23 +00:00
Edward Tomasz Napierala
6cc1e267f3 When removing an iSCSI session, check whether all conditions match,
not if any of them matches.  This fixes "iscsictl -Rn" removing
unrelated sessions.

PR:		194034
MFC after:	1 month
Sponsored by:	The FreeBSD Foundation
2014-10-16 09:09:43 +00:00
Alexander Motin
259f12da87 Make iSCSI connection close somewhat less aggressive.
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.
2014-10-09 09:12:08 +00:00
Alexander Motin
3b4ae4621f Remove one second wait for threads exit from icl_conn_close().
Switch it from polling with pause() to using cv_wait()/cv_signal().
2014-10-08 19:54:42 +00:00
Edward Tomasz Napierala
17cf3eb152 Fix LUN discovery for targets that don't support REPORT_LUNS, broken
in r263741.  At least with CTL (slightly modified to report SPC2) there
is still some problem: it doesn't seem to find LUNs higher than 7.

Sponsored by:	The FreeBSD Foundation
2014-09-17 07:55:23 +00:00
Edward Tomasz Napierala
2c5b89e54b Make sure we handle less than zero timeouts in iSCSI initiator and target
in a reasonable way.

Sponsored by:	The FreeBSD Foundation
2014-09-10 14:04:10 +00:00
Edward Tomasz Napierala
ddc5fd903d Use proper include paths in kernel iSCSI code.
MFC after:	2 weeks
Sponsored by:	The FreeBSD Foundation
2014-08-21 16:08:17 +00:00
Edward Tomasz Napierala
b7a65e3936 Make the iSCSI stack use __FBSDID() properly.
MFC after:	2 weeks
Sponsored by:	The FreeBSD Foundation
2014-08-21 15:32:38 +00:00
Edward Tomasz Napierala
e403cfdc57 Fix potential double free that could happen after connection error.
MFC after:	3 days
2014-07-28 21:14:41 +00:00
Alexander Motin
aa75114c57 Add XPT_ABORT support to iSCSI initiator.
While CAM does not use it normally, it is useful for targets testing.

MFC after:	2 weeks
2014-07-08 09:37:41 +00:00
Alexander Motin
462cf3ba2a Make XPT_GET_TRAN_SETTINGS to report CAM that command queueing is enabled,
but make couple changes to handle non-queued commands too, if happen.

MFC after:	2 weeks
2014-07-07 17:34:48 +00:00
Alexander Motin
ffe82e05b3 Make iSCSI initiator keep Initiator Session ID (ISID) across reconnects.
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
2014-07-06 17:37:49 +00:00
Hans Petter Selasky
af3b2549c4 Pull in r267961 and r267973 again. Fix for issues reported will follow. 2014-06-28 03:56:17 +00:00
Glen Barber
37a107a407 Revert r267961, r267973:
These changes prevent sysctl(8) from returning proper output,
such as:

 1) no output from sysctl(8)
 2) erroneously returning ENOMEM with tools like truss(1)
    or uname(1)
 truss: can not get etype: Cannot allocate memory
2014-06-27 22:05:21 +00:00
Hans Petter Selasky
3da1cf1e88 Extend the meaning of the CTLFLAG_TUN flag to automatically check if
there is an environment variable which shall initialize the SYSCTL
during early boot. This works for all SYSCTL types both statically and
dynamically created ones, except for the SYSCTL NODE type and SYSCTLs
which belong to VNETs. A new flag, CTLFLAG_NOFETCH, has been added to
be used in the case a tunable sysctl has a custom initialisation
function allowing the sysctl to still be marked as a tunable. The
kernel SYSCTL API is mostly the same, with a few exceptions for some
special operations like iterating childrens of a static/extern SYSCTL
node. This operation should probably be made into a factored out
common macro, hence some device drivers use this. The reason for
changing the SYSCTL API was the need for a SYSCTL parent OID pointer
and not only the SYSCTL parent OID list pointer in order to quickly
generate the sysctl path. The motivation behind this patch is to avoid
parameter loading cludges inside the OFED driver subsystem. Instead of
adding special code to the OFED driver subsystem to post-load tunables
into dynamically created sysctls, we generalize this in the kernel.

Other changes:
- Corrected a possibly incorrect sysctl name from "hw.cbb.intr_mask"
to "hw.pcic.intr_mask".
- Removed redundant TUNABLE statements throughout the kernel.
- Some minor code rewrites in connection to removing not needed
TUNABLE statements.
- Added a missing SYSCTL_DECL().
- Wrapped two very long lines.
- Avoid malloc()/free() inside sysctl string handling, in case it is
called to initialize a sysctl from a tunable, hence malloc()/free() is
not ready when sysctls from the sysctl dataset are registered.
- Bumped FreeBSD version to indicate SYSCTL API change.

MFC after:	2 weeks
Sponsored by:	Mellanox Technologies
2014-06-27 16:33:43 +00:00
Edward Tomasz Napierala
51be90b522 Implement redirection handling in initiator.
Sponsored by:	The FreeBSD Foundation
2014-06-18 17:35:40 +00:00
Alexander Motin
7a0397fc3b Close the race in older code, that caused connection stuck after r264348.
Reviewed by:	trasz
MFC after:	2 weeks
Sponsored by:	iXsystems, Inc.
2014-04-16 19:59:06 +00:00
Edward Tomasz Napierala
57a4f20b8d Make it possible for the initiator side to operate in both proxy
and normal mode; this makes it possible to compile with the former
by default, but use it only when neccessary.  That's especially
important for the userland part.

Sponsored by:	The FreeBSD Foundation
2014-04-16 18:23:36 +00:00
Edward Tomasz Napierala
a67051e9f6 Fix typo.
Sponsored by:	The FreeBSD Foundation
2014-04-16 17:39:59 +00:00
Edward Tomasz Napierala
f1f12e40e6 Add kern.iscsi.fail_on_disconnection; this is required for gmultipath
to work.

Sponsored by:	The FreeBSD Foundation
2014-04-16 17:39:10 +00:00
Edward Tomasz Napierala
0341c3e1c7 Remove useless debug.
Sponsored by:	The FreeBSD Foundation
2014-04-16 11:28:38 +00:00
Edward Tomasz Napierala
2be596ad38 Be more strict with locking for is_waiting_for_iscsid variable.
Sponsored by:	The FreeBSD Foundation
2014-04-16 11:28:05 +00:00
Edward Tomasz Napierala
d24546759e Get rid of ISCSIDCLOSE; it wasn't used and is redundant anyway,
because of ISCSIDFAIL.

Sponsored by:	The FreeBSD Foundation
2014-04-16 11:19:49 +00:00
Edward Tomasz Napierala
8eab95d646 Properly pass the initiator address when running in proxy mode.
Sponsored by:	The FreeBSD Foundation
2014-04-16 11:00:10 +00:00
Edward Tomasz Napierala
8cab2ed4cd Properly identify target portal when running in proxy mode. While here,
remove CTL_ISCSI_CLOSE, it wasn't used or implemented anyway.

Sponsored by:	The FreeBSD Foundation
2014-04-16 10:29:34 +00:00
Edward Tomasz Napierala
2ebde326cb Add some stuff to make it easier to figure out for the system administrator
whether the ICL_KERNEL_PROXY stuff got compiled in correctly.

Sponsored by:	The FreeBSD Foundation
2014-04-16 10:18:44 +00:00
Alexander Motin
1f6b2af297 Remove unused val argument value from SYSCTL_INT() calls. 2014-04-11 20:44:09 +00:00
Alexander Motin
35263d6a48 Improve use of socket buffer upcalls.
Use soreadable()/sowriteable() in socket upcalls to avoid extra wakeups
until we have enough data to read or space to write.

Increase partial receive len from 1K to 128K to not wake up on every
received packet.

This significantly reduces locks congestion and CPU usage and improves
throughput for large I/Os on NICs without TSO and LRO.

Reviewed by:	trasz
Sponsored by:	iXsystems, Inc.
2014-04-11 18:26:08 +00:00