Driver was not freeing the DMA memory allocated for EQ/CQ in the
 unload path. This patch frees the DMA memory during the driver unload.
Signed-off-by: NJohn Soni Jose <sony.john-n@emulex.com>
Signed-off-by: NJayamohan Kallickal <jayamohan.kallickal@emulex.com>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

 Reserve device PCI I/O and Memory resources.
Signed-off-by: NJohn Soni Jose <sony.john-n@emulex.com>
Signed-off-by: NJayamohan Kallickal <jayamohan.kallickal@emulex.com>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

 Increment the retry count to get the boot target info when
 port async event is received by the driver. Update sysfs enteries
 with the boot target  parameters.
Signed-off-by: NMinh Tran <minhduc.tran@emulex.com>
Signed-off-by: NJohn Soni Jose <sony.john-n@emulex.com>
Signed-off-by: NJayamohan Kallickal <jayamohan.kallickal@emulex.com>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Swap the whole 32 bits we read from the hardware instead of swapping
just the 16bits we care about in place later.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

The fusion HBAs don't really use the instance template like the other
variants, as it branches off at a much higher level.  So instead of
trying to squeeze megasas_fire_cmd_fusion into the wrong calling
convention call it locally with argument data types that match what
is passed.

[jejb: fix up 32 bit compile failure]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Converting structure fields in place is always a bad idea, and in this case
by moving it into the only caller we also only have to do a single byte
swap as most fields of this structure are never used.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Add noop conversions for all ones to make sparse happy.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This adds endianness annotations to all data structures, and a few
variables directly referencing them.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

drivers/scsi/megaraid/megaraid_sas_base.c:1701:6: sparse: symbol 'megasas_complete_outstanding_ioctls' was not declared. Should it be static?
From: Christoph Hellwig <hch@lst.de>
Signed-off-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This patch will add support for Single Server High Availability(SSHA) cluster
support.  Here is the short decsription of changes done to add support for
SSHA-

1) Host will send system's Unique ID based on DMI_PRODUCT_UUID to firmware.
2) Toggle the devhandle in LDIO path for Remote LDs.
Signed-off-by: NKashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This patch will upgrade the driver version and add back the release date and
sysfs hook for the same.  Some internal applications uses sysfs parameter for
release date, so they were broken because of removal of release date from
sysfs.
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

megaraid_sas driver will use block layer provided tag for indexing internal
MPT frames to get any unique MPT frame tied with tag.  Each IO request
submitted from SCSI mid layer will get associated MPT frame from MPT framepool
(retrieved and return back using spinlock inside megaraid_sas driver's
submission/completion call back). Getting MPT frame from MPT Frame pool is
very expensive operation because of associated spin lock operation (spinlock
overhead increase on multi NUMA node). This type of locking in driver is very
expensive call considering each IO request need - Acquire and Release of the
same lock.

With this support, in IO path driver will directly provide the unique command
index(which is based on block layer tag) and will get the MPT frame tied to
the tag and this way driver can get rid off lock, which synchronizes the
access to MPT frame pool while fetching and returning MPT frame from the pool.

This support in driver provides siginificant performance improvement(on multi
NUMA node system)on latest upstream with SCSI.MQ as well as on existing linux
distributions.

Here is the data for test executed at Avago-
- IO Tool- FIO
- 4 Socket SMC server. (4 NUMA node server)
- 12 SSDs in JBOD mode .
- 4K Rand READ, QD=32
- SCSI MQ x86_64 (Latest Upstream kernel)
- upto 300% Performance Improvement.

If IOs are running on single Node, perfromance gain is less, but as soon as
increase number of nodes, performance improvement is significant. IOs running
on all 4 NUMA nodes, with this patch applied IOPs observed was 1170K vs 344K
IOPs seen without this patch.

Logically, there are two parts of this patch- 1) Block layer tag support 2)
changes in calling convention of return_cmd.  part 2 will revert the changes
done by patch- 90dc9d98 megaraid_sas : MFI MPT linked list corruption fix
because changes done in part 1 has fixed the problem of MFI MPT linked list
corruption. part 2 is very much dependent on part 1, so we decided to have
single patch for these two logical changes.

[jejb: remove chatty printk pointed out by hch]
Signed-off-by: NKashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NKashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NKashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This patch will add separate function for refiring MFI commands in Fusion
adapters's OCR code.
Signed-off-by: NKashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This patch will create separate functions for- 1) setting up IRQs for MSI-x
interrupts 2) setting up IRQs for legacy interrupts 3) freeing up IRQs.  and
enable interrupts after adapter's initialization. The reason behind
initialising adapter earlier is: by that time firmware is operational and can
send interrupts, so better to use interrupt based interface to send internal
DCMD to firmware instead of using polling method, since MFI frames' pool size
is reduced and polling method does not free up MFI frame for fusion adapters,
so sending more DCMDs with polled method may cause MFI frames's pool go out of
frames and end up failing DCMD.
Signed-off-by: NKashyap Desai <kashyap.desai@avagotech.com>
Signed-off-by: NSumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

We should return -ENOMEM if kzalloc() fails here instead of returning
success.
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This device only exists on platforms under ARCH_QCOM, not
ARCH_MSM.
Signed-off-by: NStephen Boyd <sboyd@codeaurora.org>
Reviewed-by: NYaniv Gardi <ygardi@codeaurora.org>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NFengguang Wu <fengguang.wu@intel.com>
Acked-by: NMahesh Rajashekhara <Mahesh.Rajashekhara@pmcs.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

set the initial sequence number so the 1st byte of payload is aligned on
the 8-byte boundary.
Signed-off-by: NKaren Xie <kxie@chelsio.com>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Change driver version to follow the same format as other Chelsio drivers.
Added missing release date back to cxgb4i and version string back to libcxgbi.
Signed-off-by: NKaren Xie <kxie@chelsio.com>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Signed-off-by: NKaren Xie <kxie@chelsio.com>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

For adapters supporting both 10G and 40G use per-connection send/recv window
and calculate the size based on the link speed.
Signed-off-by: NKaren Xie <kxie@chelsio.com>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

If device_add() fails then it should return the error code but instead
the current code returns success.
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: NTomas Henzl <thenzl@redhat.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Currently we blindly use the value of cmd_per_lun as the initial setting for
queue_depth.  This fails miserably (hangs the system) if it is zero, which is
the default value for anything uninitialised in the template.  The net result
is that every host template has to set a value for cmd_per_lun.  Instead, use
a default value of 1 if the actual value is unset.  This should pave the way
for removing cmd_per_lun from all the templates and eventually from SCSI
itself.
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

be2iscsi change of ownership from Emulex to Avago Technologies recently. We
like to get the following updates in: changed "Emulex" to "Avago
Technologies", changed email addresses from "emulex.com" to "avagotech.com",
updated MAINTAINER list for be2iscsi driver.
Signed-off-by: NMinh Tran <minh.tran@avagotech.com>
Signed-off-by: NJayamohan Kallickal <jayamohan.kallickal@avagotech.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

256 bytes per sector support has been broken since 2.6.X,
and no-one stepped up to fix this.
So disable support for it.
Signed-off-by: NMark Hounschell <dmarkh@cfl.rr.com>
Signed-off-by: NHannes Reinecke <hare@suse.de>
Cc: stable@vger.kernel.org
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This reverts 4fbdf9cb it breaks LPFC on POWER7 machine, big endian kernel.
Without this, the kernel enters an infinite oops loop.

This is the hardware used for verification:
0005:01:00.0 Fibre Channel [0c04]: Emulex Corporation Saturn-X: LightPulse Fibre Channel Host Adapter [10df:f100] (rev 03)
0005:01:00.1 Fibre Channel [0c04]: Emulex Corporation Saturn-X: LightPulse Fibre Channel Host Adapter [10df:f100] (rev 03)
Signed-off-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: NJames Smart <james.smart@emulex.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Set the SRB flags correctly when there is no data transfer.  Without this
change some IHV drivers will fail valid commands such as TEST_UNIT_READY.

Cc: <stable@vger.kernel.org>
Signed-off-by: NK. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: NLong Li <longli@microsoft.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

The 3w-9xxx driver needs to tear down the dma mappings before returning
the command to the midlayer, as there is no guarantee the sglist and
count are valid after that point.  Also remove the dma mapping helpers
which have another inherent race due to the request_id index.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Acked-by: NAdam Radford <aradford@gmail.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

The 3w-xxxx driver needs to tear down the dma mappings before returning
the command to the midlayer, as there is no guarantee the sglist and
count are valid after that point.  Also remove the dma mapping helpers
which have another inherent race due to the request_id index.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Acked-by: NAdam Radford <aradford@gmail.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

The 3w-sas driver needs to tear down the dma mappings before returning
the command to the midlayer, as there is no guarantee the sglist and
count are valid after that point.  Also remove the dma mapping helpers
which have another inherent race due to the request_id index.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reported-by: NTorsten Luettgert <ml-lkml@enda.eu>
Tested-by: NBernd Kardatzki <Bernd.Kardatzki@med.uni-tuebingen.de>
Cc: stable@vger.kernel.org
Acked-by: NAdam Radford <aradford@gmail.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

The driver currently calls kmalloc with GFP_KERNEL while holding a lock.
Fix it by doing the allocation earlier, before taking the lock.

Tested on AHA-1542B.
Signed-off-by: NOndrej Zary <linux@rainbow-software.org>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

This works around a issue with qnap iscsi targets not handling large IOs
very well.

The target returns:

VPD INQUIRY: Block limits page (SBC)
  Maximum compare and write length: 1 blocks
  Optimal transfer length granularity: 1 blocks
  Maximum transfer length: 4294967295 blocks
  Optimal transfer length: 4294967295 blocks
  Maximum prefetch, xdread, xdwrite transfer length: 0 blocks
  Maximum unmap LBA count: 8388607
  Maximum unmap block descriptor count: 1
  Optimal unmap granularity: 16383
  Unmap granularity alignment valid: 0
  Unmap granularity alignment: 0
  Maximum write same length: 0xffffffff blocks
  Maximum atomic transfer length: 0
  Atomic alignment: 0
  Atomic transfer length granularity: 0

and it is *sometimes* able to handle at least one IO of size up to 8 MB. We
have seen in traces where it will sometimes work, but other times it
looks like it fails and it looks like it returns failures if we send
multiple large IOs sometimes. Also it looks like it can return 2 different
errors. It will sometimes send iscsi reject errors indicating out of
resources or it will send invalid cdb illegal requests check conditions.
And then when it sends iscsi rejects it does not seem to handle retries
when there are command sequence holes, so I could not just add code to
try and gracefully handle that error code.

The problem is that we do not have a good contact for the company,
so we are not able to determine under what conditions it returns
which error and why it sometimes works.

So, this patch just adds a new black list flag to set targets like this to
the old max safe sectors of 1024. The max_hw_sectors changes added in 3.19
caused this regression, so I also ccing stable.
Reported-by: NChristian Hesse <list@eworm.de>
Signed-off-by: NMike Christie <michaelc@cs.wisc.edu>
Cc: stable@vger.kernel.org
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

mvsas is giving a General protection fault when it encounters an expander
attached ATA device.  Analysis of mvs_task_prep_ata() shows that the driver is
assuming all ATA devices are locally attached and obtaining the phy mask by
indexing the local phy table (in the HBA structure) with the phy id.  Since
expanders have many more phys than the HBA, this is causing the index into the
HBA phy table to overflow and returning rubbish as the pointer.

mvs_task_prep_ssp() instead does the phy mask using the port properties.
Mirror this in mvs_task_prep_ata() to fix the panic.
Reported-by: NAdam Talbot <ajtalbot1@gmail.com>
Tested-by: NAdam Talbot <ajtalbot1@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>