While doing various error injection testing, such as cable
pulls and target moves, some issues were observed in handling
these events. This patch improves the way these events are handled
by increasing the delay waiting for the fabric to settle and also
changes the behavior of Link Up to break the CRQ to ensure everything
gets cleaned up properly on the VIOS.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
The ibmvscsi driver currently has a bug in it which can result
in it using up all its event structs for commands. If something
results in all those commands timing out, we won't have any resources
left to send aborts or resets. This results in escalating to a host reset
in order to recover, which is a bit heavy handed. This fixes it
by reducing can_queue by two in order to have resources to do EH.
It also changes the max_requests module parameter so that it is not
writable at runtime, since the code really does not handle it changing
at runtime.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
In order to ensure the VIOS sees a consistent command buffer, we
need to add a memory barrier after building the command buffer
but before sending the command.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Adds a delay prior to retrying a failed NPIV login. This fixes
a scenario if the backing fibre channel adapter is getting reset
due to an EEH event, NPIV login will fail. Currently, ibmvfc
retries three times very quickly, resets the CRQ and tries one
more time. If the adapter is getting reset due to EEH, this isn't
enough time. This adds a delay prior to retrying a failed NPIV
login and also increments the number of retries.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
The virtual fibre channel stack can return a failure response for a command
indicating the port login has been invalidated without sending the client
an async event. Add code to handle this response and initiate a PLOGI.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
The CRQs used by the ibmvfc driver are read and written by both
the client and the server. Therefore, we need to mark them volatile
so that we do not cache their contents when handling an interrupt.
This fixes a problem which can surface as occasional command timeouts.
No commands were actually timing out, but due to accessing cached data
for the CRQ in the interrupt handler, the interrupt was not processing
all command completions as it should.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Fixes an oops that can occur in the interrupt handler
if we get a lot of async events.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Stops gcc from complaining about a possible uninitialized
variable being used in ibmvfc_reset_device.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
If the ibmvfc driver is in discovery attempting to log into a target
and it encounters an error, the command may get retried one or more
times, depending on the error received. If the retries are
unsuccessful such that the discovery thread gives up on discovery to
that target, the target ends up in a state where, if SCSI core had
previously known about the device, the host will get unblocked but the
host will not be logged into the target, causing any commands sent to
the target to fail. This patch fixes this so that if this occurs, the
target is deleted such that the normal dev_loss processing can occur
instead.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Due to an ambiguity in the VIOS VFC interface specification,
abort/cancel handling is not done correctly and can result in double
completion of commands. In order to cancel all outstanding commands to
a device, a cancel must be sent, followed by an abort task set. After
the responses are received for these commands, there may still be
commands outstanding, in the process of getting flushed back, in which
case, we need to wait for them. This patch removes the assumption that
if the abort and the cancel both complete successfully that the device
queue has been flushed and waits for all the responses to come back.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
If either a "transport fault" or a "general transport" error is received
and no other error information is available, the command is improperly
returned as successful. Fix this to return DID_ERROR in this case.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
The ibmvfc log level filtering logic was reversed. The log_level scsi
host parameter should result in more verbose logs when log_level is
larger, not smaller.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Calling crq_queue_create could lead to the creation of a rport. We
need to set up everything before creating a rport. This moves
crq_queue_create to the end of initialization to avoid a race which
causes an oops if lost.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Reported-by: Olaf Hering <olh@suse.de>
Cc: stable@kernel.org
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
ibmvscsi sets the timeout in its slave configure routine for disk
devices. This now needs to update the request queue timeout in block.
Cc: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
The fc class now calls scsi_target_unblock after calling the
terminate callback, so this patch removes the calls from the
drivers.
Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
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>
Bump driver version to 1.0.2.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
When logging async events, also print the payload in addition to the
event received.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Sanitize the response lengths in order to prevent possible oopses
in the command response path.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
If the client virtual fibre channel adapter is already logged into the
server and does an NPIV Login again, the async queue, which is used for
reporting Link Up/Link Down type of events, does not get reset on the
server side. Fix up the client driver so that we also do not reset it.
This fixes a problem of lost async events following relogins.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
If an ELS is received while the virtual fibre channel adapter is going
through its discovery, a flag is set which causes discovery to get
re-driven. However, the hosts's state does not get set back to
IBMVFC_INITIALIZING and scsi_block_requests does not get called again,
which can result in queuecommand ops getting sent during
discovery. This should not occur and may cause problems. One example
is that we may no longer be logged into the target we send the command
to, resulting in a failure which should not have occurred.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
This fixes a hang on module removal. The module removal code was setting
the hosts's state to IBMVFC_HOST_OFFLINE before tearing down the kernel
thread, but, due to a bug in ibmvfc_wait_while_resetting, was not waiting
for the kernel thread's offlining work to be done prior to destroying
the kernel thread, which left the scsi host in a blocked state which we
never got out of.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
When running ibmvscsi in a shared memory partition, it must provide
a default value for the amount of DMA resources it will need in order to
perform reasonably well. This was being calculated in sectors rather than
bytes, as it should. This patch fixes this.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6: (59 commits)
[SCSI] replace __FUNCTION__ with __func__
[SCSI] extend the last_sector_bug flag to cover more sectors
[SCSI] qla2xxx: Update version number to 8.02.01-k6.
[SCSI] qla2xxx: Additional NPIV corrections.
[SCSI] qla2xxx: suppress uninitialized-var warning
[SCSI] qla2xxx: use memory_read_from_buffer()
[SCSI] qla2xxx: Issue proper ISP callbacks during stop-firmware.
[SCSI] ch: fix ch_remove oops
[SCSI] 3w-9xxx: add MSI support and misc fixes
[SCSI] scsi_lib: use blk_rq_tagged in scsi_request_fn
[SCSI] ibmvfc: Update driver version to 1.0.1
[SCSI] ibmvfc: Add ADISC support
[SCSI] ibmvfc: Miscellaneous fixes
[SCSI] ibmvfc: Fix hang on module removal
[SCSI] ibmvfc: Target refcounting fixes
[SCSI] ibmvfc: Reduce unnecessary log noise
[SCSI] sym53c8xx: free luntbl in sym_hcb_free
[SCSI] scsi_scan.c: Release mutex in error handling code
[SCSI] scsi_eh_prep_cmnd should save scmd->underflow
[SCSI] sd: Support for SCSI disk (SBC) Data Integrity Field
...
[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>
Update driver version to 1.0.1.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Add an ADISC to the target discovery job in order to sanity check whether or
not we need to re-login to the target.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Properly setup the size of the async event queue. This fixes a bug where async events
were not getting processed by the driver.
Setup target_id field in the driver's target struct so that target sysfs attributes
work for multiple targets.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
If certain ELS events are received during module removal, after the kthread
is stopped, the rmmod can hang. This fixes the ibmvfc driver so that ELS
events during rmmod are ignored by stopping all device activity prior to
killing the kthread and also changes reinitialization to not attempt a reinit
if the adapter has been taken offline.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Fix up some refcounting on the ibmvfc drivers internal target struct
when accessed through some sysfs attributes.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Reduces some unnecessary log noise by removing a printk during
host port state query and increasing the log level required to
log received async events.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER
architecture does:
This enables us to cleanly fix the Calgary IOMMU issue that some devices
are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423).
I think that per-device dma_mapping_ops support would be also helpful for
KVM people to support PCI passthrough but Andi thinks that this makes it
difficult to support the PCI passthrough (see the above thread). So I
CC'ed this to KVM camp. Comments are appreciated.
A pointer to dma_mapping_ops to struct dev_archdata is added. If the
pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's
NULL, the system-wide dma_ops pointer is used as before.
If it's useful for KVM people, I plan to implement a mechanism to register
a hook called when a new pci (or dma capable) device is created (it works
with hot plugging). It enables IOMMUs to set up an appropriate
dma_mapping_ops per device.
The major obstacle is that dma_mapping_error doesn't take a pointer to the
device unlike other DMA operations. So x86 can't have dma_mapping_ops per
device. Note all the POWER IOMMUs use the same dma_mapping_error function
so this is not a problem for POWER but x86 IOMMUs use different
dma_mapping_error functions.
The first patch adds the device argument to dma_mapping_error. The patch
is trivial but large since it touches lots of drivers and dma-mapping.h in
all the architecture.
This patch:
dma_mapping_error() doesn't take a pointer to the device unlike other DMA
operations. So we can't have dma_mapping_ops per device.
Note that POWER already has dma_mapping_ops per device but all the POWER
IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device
argument.
[akpm@linux-foundation.org: fix sge]
[akpm@linux-foundation.org: fix svc_rdma]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix bnx2x]
[akpm@linux-foundation.org: fix s2io]
[akpm@linux-foundation.org: fix pasemi_mac]
[akpm@linux-foundation.org: fix sdhci]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix sparc]
[akpm@linux-foundation.org: fix ibmvscsi]
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Muli Ben-Yehuda <muli@il.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Avi Kivity <avi@qumranet.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Adds support to the ibmvfc driver for collaborative memory overcommit.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Robert Jennings <rcj@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Enable the driver to function in a Cooperative Memory Overcommitment (CMO)
environment.
The following changes are made to enable the driver for CMO:
* DMA mapping errors will not result in error messages if entitlement has
been exceeded and resources were not available.
* The driver has a get_desired_dma function defined to function
in a CMO environment. It will indicate how much IO memory it would like
to function.
Signed-off-by: Robert Jennings <rcj@linux.vnet.ibm.com>
Acked by: Brian King <brking@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Acked-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch adds a new device driver to support the Virtual Fibre Channel
interface on IBM Power based servers. The Virtual I/O Server on IBM Power
servers utilizes N-Port ID Virtualization to export a Virtual Fibre Channel
adapter to the client. This driver is the client device driver.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Some versions of the Virtual I/O Server on Power
return 0x99 in the non-SCSI error status field as success,
rather than 0. This fixes the ibmvscsi driver to treat this
response as success.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
- struct scsi_cmnd had a 16 bytes command buffer of its own.
This is an unnecessary duplication and copy of request's
cmd. It is probably left overs from the time that scsi_cmnd
could function without a request attached. So clean that up.
- Once above is done, few places, apart from scsi-ml, needed
adjustments due to changing the data type of scsi_cmnd->cmnd.
- Lots of drivers still use MAX_COMMAND_SIZE. So I have left
that #define but equate it to BLK_MAX_CDB. The way I see it
and is reflected in the patch below is.
MAX_COMMAND_SIZE - means: The longest fixed-length (*) SCSI CDB
as per the SCSI standard and is not related
to the implementation.
BLK_MAX_CDB. - The allocated space at the request level
- I have audit all ISA drivers and made sure none use ->cmnd in a DMA
Operation. Same audit was done by Andi Kleen.
(*)fixed-length here means commands that their size can be determined
by their opcode and the CDB does not carry a length specifier, (unlike
the VARIABLE_LENGTH_CMD(0x7f) command). This is actually not exactly
true and the SCSI standard also defines extended commands and
vendor specific commands that can be bigger than 16 bytes. The kernel
will support these using the same infrastructure used for VARLEN CDB's.
So in effect MAX_COMMAND_SIZE means the maximum size command
scsi-ml supports without specifying a cmd_len by ULD's
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Adds support to the ibmvscsi driver to handle non SCSI error
status. This is needed to support some new VIOS enhancements.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Santiago Leon <santil@us.ibm.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>
drivers/scsi/ibmvscsi/ibmvstgt.c: In function 'ibmvstgt_cmd_done':
drivers/scsi/ibmvscsi/ibmvstgt.c:292: error: 'cmd' undeclared (first use in this function)
drivers/scsi/ibmvscsi/ibmvstgt.c:292: error: (Each undeclared identifier is reported only once
drivers/scsi/ibmvscsi/ibmvstgt.c:292: error: for each function it appears in.)
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Before calling __scsi_alloc_queue, scsi_host->shost_gendev.parent must
be initialized properly.
This patch moves __scsi_alloc_queue after scsi_add_host (like
initiator drivers do).
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
With the sg table code, every SCSI driver is now either chain capable
or broken (or has sg_tablesize set so chaining is never activated), so
there's no need to have a check in the host template.
Also tidy up the code by moving the scatterlist size defines into the
SCSI includes and permit the last entry of the scatterlist pools not
to be a power of two.
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
CRQ send errors that return with H_CLOSED should return with
SCSI_MLQUEUE_HOST_BUSY until firmware alerts the client of a CRQ
transport event. The transport event will either reinitialize and
requeue the requests or fail and return IO with DID_ERROR.
To avoid failing the eh_* functions while re-attaching to the server
adapter this will retry for a period of time while ibmvscsi_send_srp_event
returns SCSI_MLQUEUE_HOST_BUSY.
In ibmvscsi_eh_abort_handler() the loop includes the search of the
event list. The lock on the hostdata is dropped while waiting to try
again after failing ibmvscsi_send_srp_event. The event could have been
purged if a login was in progress when the function was called.
In ibmvscsi_eh_device_reset_handler() the loop includes the call to
get_event_struct() because a failing call to ibmvscsi_send_srp_event()
will have freed the event struct.
Signed-off-by: Robert Jennings <rcj@linux.vnet.ibm.com>
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Set the default command timeout for ibmvscsi disks to 60 seconds
to ensure we don't prematurely timeout commands. This fixes a problem
seen where the default 30 seconds was not long enough due to
congestion on the server.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
- convert to use the new accessors for the sg lists and the
parameters.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
By setting the request_limit in send_srp_login to 1 we allowed login
requests to be sent to the server adapter. If this was not an initial
login, but was a login after a disconnect with the server, other I/O
requests could attempt to be processed before the login occured. These
I/O requests would fail, sometimes resulting in filesystems getting
marked read-only.
To address this we can set the request_limit to 0 while doing the login
and add an exception where login requests, along with task management
events, are always passed to the server.
There is a case where the request_limit had already reached 0 would result
in all events being sent rather than returning SCSI_MLQUEUE_HOST_BUSY; this
has also been fixed by this patch.
Signed-off-by: Robert Jennings <rcj@linux.vnet.ibm.com>
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
This option is true if a low-level driver can support sg
chaining. This will be removed eventually when all the drivers are
converted to support sg chaining. q->max_phys_segments is set to
SCSI_MAX_SG_SEGMENTS if false.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Brian King