If the port state is blocked and the fast io fail tmo has
fired then this patch will fail bsg requests immediately.
This is needed if userspace is sending IOs to test the transport
like with fcping, so it will not have to wait for the dev loss tmo.
With this patch he bsg req fast io fail code behaves like the normal
and sg io/passthrough fast io fail.
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Acked-By: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Move the duplicated code from FC LLDs to SCSI FC transport class.
Acked-by: James Smart <james.smart@emulex.com>
Acked-by: Giridhar Malavali <giridhar.malavali@qlogic.com>
Acked-by: Abhijeet Joglekar <abjoglek@cisco.com>
Signed-off-by: Christof Schmitt <christof.schmitt@de.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
I was doing some large lun count testing with 2.6.31 and hit
a BUG_ON() in fc_timeout_deleted_rport(), and it seems like it
should have been just a matter of time before someone did.
It seems invalid to set port_state under lock, then expect it to
remain set after releasing the lock. Another thread called
fc_remote_port_add() when the lock was released, changing the
port_state.
This patch removes the BUG_ON and moves the test of the
port_state to inside the host_lock. It's been running for
several weeks now with no ill effect.
Signed-off-by: Michael Reed <mdr@sgi.com>
Acked-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Add missing kernel-doc notation in scsi_transport_fc.c:
Warning(drivers/scsi/scsi_transport_fc.c:3593): No description found for parameter 'q'
Warning(drivers/scsi/scsi_transport_fc.c:3700): No description found for parameter 'q'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Change function parameter name in kernel-doc to match the function's
actual parameter name, to fix 2 kernel-doc warnings.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
BUS_ID_SIZE is being removed from the kernel.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
The return value from BSG timout function should be based on the state of the
BSG job. This helps block layer to take selective actions to clean up BSG job.
Signed-off-by: Giridhar Malavali <giridhar.malavali@qlogic.com>
Acked-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Registered the softirq_done function, since this is requried iby an request
using block level request timeout functionality. This function will be called
by the block layer as part of time out clean process to release the BSG
request.
Moved some of the BSG request completion activities to softirq_done routine to
take care of both normal and timout completions.
Signed-off-by: Giridhar Malavali <giridhar.malavali@qlogic.com>
Acked-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Attached is the ELS/CT pass-thru patch for the FC Transport. The patch
creates a generic framework that lays on top of bsg and the SGIO v4 ioctl
in order to pass transaction requests to LLDD's.
The interface supports the following operations:
On an fc_host basis:
Request login to the specified N_Port_ID, creating an fc_rport.
Request logout of the specified N_Port_ID, deleting an fc_rport
Send ELS request to specified N_Port_ID w/o requiring a login, and
wait for ELS response.
Send CT request to specified N_Port_ID and wait for CT response.
Login is required, but LLDD is allowed to manage login and decide
whether it stays in place after the request is satisfied.
Vendor-Unique request. Allows a LLDD-specific request to be passed
to the LLDD, and the passing of a response back to the application.
On an fc_rport basis:
Send ELS request to nport and wait for ELS response.
Send CT request to nport and wait for CT response.
The patch also exports several headers from include/scsi such that
they can be available to user-space applications:
include/scsi/scsi.h
include/scsi/scsi_netlink.h
include/scsi/scsi_netlink_fc.h
include/scsi/scsi_bsg_fc.h
For further information, refer to the last RFC:
http://marc.info/?l=linux-scsi&m=123436574018579&w=2
Note: Documentation is still spotty and will be added later.
[bharrosh@panasas.com: update for new block API]
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Currently, netlink_broadcast() reports errors to the caller if no
messages at all were delivered:
1) If, at least, one message has been delivered correctly, returns 0.
2) Otherwise, if no messages at all were delivered due to skb_clone()
failure, return -ENOBUFS.
3) Otherwise, if there are no listeners, return -ESRCH.
With this patch, the caller knows if the delivery of any of the
messages to the listeners have failed:
1) If it fails to deliver any message (for whatever reason), return
-ENOBUFS.
2) Otherwise, if all messages were delivered OK, returns 0.
3) Otherwise, if no listeners, return -ESRCH.
In the current ctnetlink code and in Netfilter in general, we can add
reliable logging and connection tracking event delivery by dropping the
packets whose events were not successfully delivered over Netlink. Of
course, this option would be settable via /proc as this approach reduces
performance (in terms of filtered connections per seconds by a stateful
firewall) but providing reliable logging and event delivery (for
conntrackd) in return.
This patch also changes some clients of netlink_broadcast() that
may report ENOBUFS errors via printk. This error handling is not
of any help. Instead, the userspace daemons that are listening to
those netlink messages should resync themselves with the kernel-side
if they hit ENOBUFS.
BTW, netlink_broadcast() clients include those that call
cn_netlink_send(), nlmsg_multicast() and genlmsg_multicast() since they
internally call netlink_broadcast() and return its error value.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we reworked the transport for the rport lifetimes, in cases where the
rport was reused as a container for tgt id bindings, we inadvertantly
removed the callback to the driver indicating that dev_loss_tmo had fired.
This patch restores that functionality.
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
[jejb: limit ioctl to returning 20 characters to avoid overrun
on long device names and add a few more conversions]
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Pre-emptively terminate i/o on the rport if dev_loss_tmo has fired.
The desire is to terminate everything, so that the i/o is cleaned up
prior to the sdev's being unblocked, thus any outstanding timeouts/aborts
are avoided.
Also, we do this early enough such that the rport's port_id field is
still valid. FCOE libFC code needs this info to find the i/o's to
terminate.
Signed-off-by: James Smart <james.smart@emulex.com>
[michaelc@cs.wisc.edu: remove extra scsi_target_unblock call]
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
When we block a rport and the driver implements the terminate
callback we will fail IO that was running quickly. However
IO that was in the scsi_device/block queue sits there until
the dev_loss_tmo fires, and this can make it look like IO is
lost because new IO will get executed but that IO stuck in
the blocked queue sits there for some time longer.
With this patch when the fast io fail tmo fires, we will
fail the blocked IO and any new IO. This patch also allows
all drivers to partially support the fast io fail tmo. If the
terminate io callback is not implemented, we will still fail blocked
IO and any new IO, so multipath can handle that.
This patch also allows the fc and iscsi classes to implement the
same behavior. The timers are just unfornately named differently.
This patch also fixes the problem where drivers were unblocking
the target in their terminate callback, which was needed for
rport removal, but for fast io fail timeout it would cause
IO to bounce arround the scsi/block layer and the LLD queuecommand.
And it for drivers that could have IO stuck but did not have
a terminate callback the unblock calls in the class will fix
them.
v2.
- fix up bit setting style to meet JamesS's pref.
- Broke out new host byte error changes to make it easier to read.
- added JamesS's ack from list.
v1
- initial patch
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6: (37 commits)
[SCSI] zfcp: fix double dbf id usage
[SCSI] zfcp: wait on SCSI work to be finished before proceeding with init dev
[SCSI] zfcp: fix erp list usage without using locks
[SCSI] zfcp: prevent fc_remote_port_delete calls for unregistered rport
[SCSI] zfcp: fix deadlock caused by shared work queue tasks
[SCSI] zfcp: put threshold data in hba trace
[SCSI] zfcp: Simplify zfcp data structures
[SCSI] zfcp: Simplify get_adapter_by_busid
[SCSI] zfcp: remove all typedefs and replace them with standards
[SCSI] zfcp: attach and release SAN nameserver port on demand
[SCSI] zfcp: remove unused references, declarations and flags
[SCSI] zfcp: Update message with input from review
[SCSI] zfcp: add queue_full sysfs attribute
[SCSI] scsi_dh: suppress comparison warning
[SCSI] scsi_dh: add Dell product information into rdac device handler
[SCSI] qla2xxx: remove the unused SCSI_QLOGIC_FC_FIRMWARE option
[SCSI] qla2xxx: fix printk format warnings
[SCSI] qla2xxx: Update version number to 8.02.01-k8.
[SCSI] qla2xxx: Ignore payload reserved-bits during RSCN processing.
[SCSI] qla2xxx: Additional residual-count corrections during UNDERRUN handling.
...
Right now SCSI and others do their own command timeout handling.
Move those bits to the block layer.
Instead of having a timer per command, we try to be a bit more clever
and simply have one per-queue. This avoids the overhead of having to
tear down and setup a timer for each command, so it will result in a lot
less timer fiddling.
Signed-off-by: Mike Anderson <andmike@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
There's already a fc_vport_termintate() call exported by
the transport. This patch adds a symmetric call to the API to allow
an NPIV-capable LLD to instantiate vports sans user intervention.
Additional comments/updates:
Re: scsi_fc_transport.txt
Add a function prototype for fc_vport_terminate similar to what's
done for fc_vport_create
Re: fc_vport_create
I recommend we pass the channel number in fc_vport_create rather
than fixing it at zero.
Also, ids->vport_type should be set to FC_PORTTYPE_NPIV prior to
calling fc_vport_create. The comment is also meaningless.
Added-by and
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: Andrew Vasquez <andrew.vasquez@qlogic.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
[jejb: fixed up a ton of missed conversions.
All of you are on notice this has happened, driver trees will now
need to be rebased]
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Cc: SCSI List <linux-scsi@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Kobjects do not have a limit in name size since a while, so stop
pretending that they do.
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Way back when, when the fc_user_scan routine was created, it kept some
of its original logic that walked the rport list and kicked off a scan.
Unfortunately, it didn't keep any of the locking around the rport list,
nor did it consider the synchronous nature of the scan invoked. The result,
there are some scan requests where the rport list changes, thus a subsequent
scan is called on a bogus rport structure and the system NMI's.
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
It's big, but there doesn't seem to be a way to split it up smaller...
Signed-off-by: Tony Jones <tonyj@suse.de>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Cc: Roland Dreier <rolandd@cisco.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Add Documentation/DocBook/scsi_midlayer.tmpl, add to Makefile, and update
lots of kerneldoc comments in drivers/scsi/*.
Updated with comments from Stefan Richter, Stephen M. Cameron,
James Bottomley and Randy Dunlap.
Signed-off-by: Rob Landley <rob@landley.net>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
In scsi module I've found some inconsistency between variable type
used in module_param_named and type passed to module_param_named as an
argument. Especially the inconsistency of `max_scsi_luns' parameter is
a bit serious because the description text says "last scsi LUN (should
be between 1 and 2^32-1)".
Signed-off-by: Masatake YAMATO <jet@gyve.org>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This adds minimum target driver support like the srp transport does:
- fc_remote_port_{rolechg,delete} calls
scsi_tgt_it_nexus_{create,destroy} for target drivers.
- add callbacks to notify target drivers of the nexus and tmf
operation results to fc_function_template.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This change has already been discussed on linux-scsi:
http://marc.info/?t=118771096400003http://marc.info/?t=118760913100005
Signed-off-by: Christof Schmitt <christof.schmitt@de.ibm.com>
Signed-off-by: Swen Schillig <swen@vnet.ibm.com>
Acked-by: James Smart <James.Smart@Emulex.Com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This patch contains the following cleanups:
- make needlessly global functions static
- every file should #include the headers containing the prototypes for
it's global functions
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
When a target scan is initiated from sysfs, we should check the
portstate prior to invoke scsi_scan_target().
Otherwise scsi_scan_target() might oops as the rport might already
been removed from the scsi host and the traversal from the rport to
the scsi_host in scsi_scan_target() will fail.
Also the portstate already told us that communication with the target
has failed, so it's quite pointless to try.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Cc: James Smart <James.Smart@Emulex.Com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
When the vport attribute "delete" is used to delete the vport, sysfs
deadlocks waiting for the write to complete, which is waiting for the
sysfs teardown to complete. Moved this effort to a work_q element.
Took the opportunity to make some other cosmetic changes:
- removed tabs in Doc file - replaced with expanded spaces
- minor copyright text and author text updates
- removed a bunch of trailing whitespace
Signed-off-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This patch provides support for FC virtual ports based on NPIV.
For information on the interfaces and design, please read the
Documentation/scsi/scsi_fc_transport.txt file enclosed within
the patch.
The RFC was originally posted here:
http://marc.info/?l=linux-scsi&m=117226959918393&w=2
Changes from the initial RFC:
- Bug fix: needed a transport_class_unregister() for the vport class
- Create a symlink to the vport in the shost device if it is not the
parent of the vport.
- Made symbolic name writable so it can be set after creation
- Made the temporary fc_vport_identifiers struct private to the
transport.
- Deleted the vport_id field from the vport. I couldn't find any good
use for it (and symname is a good replacement).
- Made the vport_state and vport_last_state "private" attributes.
Added the fc_vport_set_state() helper function to manage state
transitions
- Updated vport_create() to allow a vport to be created in a disabled
state.
- Added INITIALIZING and FAILED vport states
- Added VPCERR_xxx defines for errors to be returned from vport_create()
- Created a Documentation/scsi/scsi_fc_transport.txt file that describes
the interfaces and expected LLDD behaviors.
Signed-off-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Per the comment in the change - it's not always prudent to immediately
remove the rport upon first notice of a disconnect. Make all rports
wait dev_loss_tmo before being deleted (and each could have a separate
dev_loss_tmo value).
The original post was:
http://marc.info/?l=linux-scsi&m=117392196006703&w=2
The repost contains the following changes:
- Bug fix in fc_starget_delete(). Dev_loss_tmo_callbk() was called prior to
tearing down the target. The callback is to be the last thing called, as
it tells the LLDD that the rport is completely finished and can be torn
down. Rework so that terminate_rport_io() is called to terminate the
outstanding io. Isolated work so it's is simply "starget" work.
- Fix holes in original patch. There were code paths that did not expect
the dev_loss_tmo timer to be running for the non-fcp rports.
- Bug Fix: the transport wasn't protecting against a LLDD calling
fc_remote_port_delete() back-to-back. Thus, the dev_loss_tmo timer
could be restarted such that it fires after the rport had been deleted.
Validate rport state before starting the timer.
Signed-off-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This patch updates the FC transport for all speeds identified in
SM-HBA. Note: it does not sync the "bit" definitions, as that is
actually insulated from user-space via the sysfs text string. (I could
do it, but it does introduce a potential binary-incompatibility).
Signed-off-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
After Al Viro (finally) succeeded in removing the sched.h #include in module.h
recently, it makes sense again to remove other superfluous sched.h includes.
There are quite a lot of files which include it but don't actually need
anything defined in there. Presumably these includes were once needed for
macros that used to live in sched.h, but moved to other header files in the
course of cleaning it up.
To ease the pain, this time I did not fiddle with any header files and only
removed #includes from .c-files, which tend to cause less trouble.
Compile tested against 2.6.20-rc2 and 2.6.20-rc2-mm2 (with offsets) on alpha,
arm, i386, ia64, mips, powerpc, and x86_64 with allnoconfig, defconfig,
allmodconfig, and allyesconfig as well as a few randconfigs on x86_64 and all
configs in arch/arm/configs on arm. I also checked that no new warnings were
introduced by the patch (actually, some warnings are removed that were emitted
by unnecessarily included header files).
Signed-off-by: Tim Schmielau <tim@physik3.uni-rostock.de>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
nlmsg_multicast now takes an extra allocation flag, so add it to
the use in the fibre channel transport class.
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This patch adds the following functionality to the FC transport:
- dev_loss_tmo LLDD callback :
Called to essentially confirm the deletion of an rport. Thus, it is
called whenever the dev_loss_tmo fires, or when the rport is deleted
due to other circumstances (module unload, etc). It is expected that
the callback will initiate the termination of any outstanding i/o on
the rport.
- fast_io_fail_tmo and LLD callback:
There are some cases where it may take a long while to truly determine
device loss, but the system is in a multipathing configuration that if
the i/o was failed quickly (faster than dev_loss_tmo), it could be
redirected to a different path and completed sooner.
Many thanks to Mike Reed who cleaned up the initial RFC in support
of this post.
The original RFC is at:
http://marc.theaimsgroup.com/?l=linux-scsi&m=115505981027246&w=2
Signed-off-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
During discussions with Mike Christie, I became convinced that we needed
a larger vendor id. This patch extends the id from 32 to 64 bits.
This applies on top of the prior patches that add SCSI transport events
via netlink.
Signed-off-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This patch formally adds support for the posting of FC events via netlink.
It is a followup to the original RFC at:
http://marc.theaimsgroup.com/?l=linux-scsi&m=114530667923464&w=2
and the initial posting at:
http://marc.theaimsgroup.com/?l=linux-scsi&m=115507374832500&w=2
The patch has been updated to optimize the send path, per the discussions
in the initial posting.
Per discussions at the Storage Summit and at OLS, we are to use netlink for
async events from transports. Also per discussions, to avoid a netlink
protocol per transport, I've create a single NETLINK_SCSITRANSPORT protocol,
which can then be used by all transports.
This patch:
- Creates new files scsi_netlink.c and scsi_netlink.h, which contains the
single and shared definitions for the SCSI Transport. It is tied into the
base SCSI subsystem intialization.
Contains a single interface routine, scsi_send_transport_event(), for a
transport to send an event (via multicast to a protocol specific group).
- Creates a new scsi_netlink_fc.h file, which contains the FC netlink event
messages
- Adds 3 new routines to the fc transport:
fc_get_event_number() - to get a FC event #
fc_host_post_event() - to send a simple FC event (32 bits of data)
fc_host_post_vendor_event() - to send a Vendor unique event, with
arbitrary amounts of data.
Note: the separation of event number allows for a LLD to send a standard
event, followed by vendor-specific data for the event.
Note: This patch assumes 2 prior fc transport patches have been installed:
http://marc.theaimsgroup.com/?l=linux-scsi&m=115555807316329&w=2http://marc.theaimsgroup.com/?l=linux-scsi&m=115581614930261&w=2
Sorry - next time I'll do something like making these individual
patches of the same posting when I know they'll be posted closely
together.
Signed-off-by: James Smart <James.Smart@emulex.com>
Tidy up configuration not to make SCSI always select NET
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
This patch updates the fc transport for the following:
- Addition of a new attribute "system_hostname" which can be
used to set the fully qualified hostname that the fc_host
is attached to. The fc_host can then register this string
as the FDMI-based host name attribute.
Note: for NPIV, a fc_host could be associated with a system which
is not the local system.
- Add the inline function u64_to_wwn(), which is the inverse of the
existing wwn_to_u64() function.
- Slight reorg, just to keep dynamic attributes with each other, etc
Signed-off-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Original post was incorrect as it didn't realize that we already had
a self-referenc due to device_initialize(), and we were really only
missing the put on our own reference. This was hidden by the other bug
which had the midlayer reusing stargets after they were already free,
which was doing too many puts on our rport.
Updating FC transport for:
- Add put in fc_rport_final_delete(), to release the rport.
Prior, we were leaving the rport with a reference, thus the shost
with references, etc. If the driver was unloaded, shosts and rports
remained, along with work threads, etc
- Fix fc_rport_create failure path - too many put's on parent
- Add commenting to easily track ref taking.
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Updated patch to address comments from Pat Mansfield and Michael Reed:
Bumped max to 600 (10mins). Set default dev_loss_tmo to a value other
than the max (30s).
Signed-off-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
In a prior posting to linux-scsi on the fc transport and workq
deadlocks, we noted a second error that did not have a patch:
http://marc.theaimsgroup.com/?l=linux-scsi&m=114467847711383&w=2
- There's a deadlock where scsi_remove_target() has to sit behind
scsi_scan_target() due to contention over the scan_lock().
Subsequently we posted a request for comments about the deadlock:
http://marc.theaimsgroup.com/?l=linux-scsi&m=114469358829500&w=2
This posting resolves the second error. Here's what we now understand,
and are implementing:
If the lldd deletes the rport while a scan is active, the sdev's queue
is blocked which stops the issuing of commands associated with the scan.
At this point, the scan stalls, and does so with the shost->scan_mutex held.
If, at this point, if any scan or delete request is made on the host, it
will stall waiting for the scan_mutex.
For the FC transport, we queue all delete work to a single workq.
So, things worked fine when competing with the scan, as long as the
target blocking the scan was the same target at the top of our delete
workq, as the delete workq routine always unblocked just prior to
requesting the delete. Unfortunately, if the top of our delete workq
was for a different target, we deadlock. Additionally, if the target
blocking scan returned, we were unblocking it in the scan workq routine,
which really won't execute until the existing stalled scan workq
completes (e.g. we're re-scheduling it while it is in the midst of its
execution).
This patch moves the unblock out of the workq routines and moves it to
the context that is scheduling the work. This ensures that at some point,
we will unblock the target that is blocking scan. Please note, however,
that the deadlock condition may still occur while it waits for the
transport to timeout an unblock on a target. Worst case, this is bounded
by the transport dev_loss_tmo (default: 30 seconds).
Finally, Michael Reed deserves the credit for the bulk of this patch,
analysis, and it's testing. Thank you for your help.
Note: The request for comments statements about the gross-ness of the
scan_mutex still stand.
Signed-off-by: Michael Reed <mdr@sgi.com>
Signed-off-by: James Smart <james.smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Use ARRAY_SIZE macro instead of sizeof(x)/sizeof(x[0]) and remove
duplicates of the macro.
Signed-off-by: Tobias Klauser <tklauser@nuerscht.ch>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
As previously reported via Michael Reed, the FC transport took a hit
in 2.6.15 (perhaps a little earlier) when we solved a recursion error.
There are 2 deadlocks occurring:
- With scan and the delete items sharing the same workq, flushing the
workq for the delete code was getting it stalled behind a very long
running scan code path.
- There's a deadlock where scsi_remove_target() has to sit behind
scsi_scan_target() due to contention over the scan_lock().
This patch resolves the 1st deadlock and significantly reduces the
odds of the second. So far, we have only replicated the 2nd deadlock
on a highly-parallel SMP system. More on the 2nd deadlock in a following
email.
This patch reworks the transport to:
- Only use the scsi host workq for scanning
- Use 2 other workq's internally. One for deletions, the other for
scheduled deletions. Originally, we tried this with a single workq,
but the occassional flushes of the scheduled queues was hitting the
second deadlock with a slightly higher frequency. In the future, we'll
look at the LLDD's and the transport to see if we can get rid of this
extra overhead.
- When moving to the other workq's we tightened up some object states
and some lock handling.
- Properly syncs adds/deletes
- minor code cleanups
- directly reference fc_host_attrs, rather than through attribute
macros
- flush the right workq on delayed work cancel failures.
Large kudos to Michael Reed who has been working this issue for the last
month.
Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Mike Christie