Improve performance by using multiple RDMA/RC channels per SCSI
host for communication with an SRP target. About the
implementation:
- Introduce a loop over all channels in the code that uses
  target->ch.
- Set the SRP_MULTICHAN_MULTI flag during login for the creation
  of the second and subsequent channels.
- RDMA completion vectors are chosen such that RDMA completion
  interrupts are handled by the CPU socket that submitted the I/O
  request. As one can see in this patch it has been assumed if a
  system contains n CPU sockets and m RDMA completion vectors
  have been assigned to an RDMA HCA that IRQ affinity has been
  configured such that completion vectors [i*m/n..(i+1)*m/n) are
  bound to CPU socket i with 0 <= i < n.
- Modify srp_free_ch_ib() and srp_free_req_data() such that it
  becomes safe to invoke these functions after the corresponding
  allocation function failed.
- Add a ch_count sysfs attribute per target port.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Since the block layer already contains functionality to assign
a tag to each request, use that functionality instead of
reimplementing that functionality in the SRP initiator driver.
This change makes the free_reqs list superfluous. Hence remove
that list.

[hch: updated to use .use_blk_tags instead scsi_activate_tcq]
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Changes in this patch:
- Move channel variables into a new structure (struct srp_rdma_ch).
- Add an srp_target_port pointer, 'lock' and 'comp_vector' members
  in struct srp_rdma_ch.
- Add code to initialize these three new member variables.
- Many boring "target->" into "ch->" changes.
- The cm_id and completion handler context pointers are now of type
  srp_rdma_ch * instead of srp_target_port *.
- Three kzalloc(a * b, f) calls have been changed into kcalloc(a, b, f)
  to avoid that this patch would trigger a checkpatch warning.
- Two casts from u64 into unsigned long long have been left out
  because these are superfluous. Since considerable time u64 is
  defined as unsigned long long for all architectures supported by
  the Linux kernel.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Introduce the srp_target_port member variables 'sgid' and 'pkey'.
Change the type of 'orig_dgid' from __be16[8] into union ib_gid.
This patch does not change any functionality but makes the
"Separate target and channel variables" patch easier to verify.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

If a cable is pulled during LUN scanning it can happen that the
SRP rport and the SCSI host have been created but no LUNs have been
added to the SCSI host. Since multipathd only sends SCSI commands
to a SCSI target if one or more SCSI devices are present and since
there is no keepalive mechanism for IB queue pairs this means that
after a LUN scan failed and after a reconnect has succeeded no
data will be sent over the QP and hence that a subsequent cable
pull will not be detected. Avoid this by not creating an rport or
SCSI host if a cable is pulled during a SCSI LUN scan.

Note: so far the above behavior has only been observed with the
kernel module parameter ch_count set to a value >= 2.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Attempting to connect three times may be insufficient after an
initiator system tries to relogin, especially if the relogin
attempt occurs before the SRP target service ID has been
registered. Since the srp_daemon retries a failed login attempt
anyway, remove the stale connection retry mechanism.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

The patch that adds multichannel support into the SRP initiator
driver introduces an additional call to srp_free_ch_ib(). This
patch helps to keep that later patch simple.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Remove 2 redundant extern inline functions: qla8044_set_qsnt_ready() and
qla8044_need_reset_handler(). At present, within upstream next kernel
source code, they are only used within "drivers/scsi/qla2xxx/qla_nx2.c".

The related error and warnings (with allmodconfig under tile):

    CC [M]  drivers/scsi/qla2xxx/qla_nx2.o
  drivers/scsi/qla2xxx/qla_nx2.c:1633:1: error: static declaration of 'qla8044_need_reset_handler' follows non-static declaration
   qla8044_need_reset_handler(struct scsi_qla_host *vha)
   ^
  In file included from drivers/scsi/qla2xxx/qla_def.h:3706:0,
                   from drivers/scsi/qla2xxx/qla_nx2.c:11:
  drivers/scsi/qla2xxx/qla_gbl.h:756:20: note: previous declaration of 'qla8044_need_reset_handler' was here
   extern inline void qla8044_need_reset_handler(struct scsi_qla_host *vha);
                      ^
  drivers/scsi/qla2xxx/qla_gbl.h:756:20: warning: inline function 'qla8044_need_reset_handler' declared but never defined
  make[3]: *** [drivers/scsi/qla2xxx/qla_nx2.o] Error 1
  make[2]: *** [drivers/scsi/qla2xxx] Error 2
  make[1]: *** [drivers/scsi] Error 2
  make: *** [drivers] Error 2

    CC [M]  drivers/scsi/qla2xxx/qla_tmpl.o
  In file included from drivers/scsi/qla2xxx/qla_def.h:3706:0,
                   from drivers/scsi/qla2xxx/qla_tmpl.c:7:
  drivers/scsi/qla2xxx/qla_gbl.h:755:20: warning: inline function 'qla8044_set_qsnt_ready' declared but never defined
   extern inline void qla8044_set_qsnt_ready(struct scsi_qla_host *vha);
                    ^
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Acked-by: Saurav Kashyap <saurav.kashyap@qlogic.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Use dma_set_mask_and_coherent() to set both the DMA and coherent
DMA mask.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Even though the ipr driver is only used on PCI, convert it
to use the generic DMA API.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

The request (and SCSI command) tag is the tag number assigned
by the generic block-tagging code, not the SCSI-II tag messages.
Those are represented by the device flags 'tagged_supported',
'simple_tags', and 'ordered_tags'.
(The SCSI midlayer doesn't use HEAD_OF_QUEUE tags).
So fixup vmw_pvscsi to assign the correct tag type.

[hch: fixed up to never set MSG_ORDERED_TAG]
Signed-off-by: Hannes Reinecke <hare@suse.de>
Acked-by: Arvind Kumar <arvindkumar@vmware.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Acked-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

This macro is only used in the NCR5380 drivers and they don't include
this header.
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Acked-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>

ufs never looks at the tag type, so there is no need to set it either.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Now that we also get proper values in cmd->request->tag for untagged
commands, there is no need to force tagged_supported to on in drivers
that need host-wide tags.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Remove the tagged argument from scsi_adjust_queue_depth, and just let it
handle the queue depth.  For most drivers those two are fairly separate,
given that most modern drivers don't care about the SCSI "tagged" status
of a command at all, and many old drivers allow queuing of multiple
untagged commands in the driver.

Instead we start out with the ->simple_tags flag set before calling
->slave_configure, which is how all drivers actually looking at
->simple_tags except for one worke anyway.  The one other case looks
broken, but I've kept the behavior as-is for now.

Except for that we only change ->simple_tags from the ->change_queue_type,
and when rejecting a tag message in a single driver, so keeping this
churn out of scsi_adjust_queue_depth is a clear win.

Now that the usage of scsi_adjust_queue_depth is more obvious we can
also remove all the trivial instances in ->slave_alloc or ->slave_configure
that just set it to the cmd_per_lun default.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>

Allow a driver to ask for block layer tags by setting .use_blk_tags in the
host template, in which case it will always see a valid value in
request->tag, similar to the behavior when using blk-mq.  This means even
SCSI "untagged" commands will now have a tag, which is especially useful
when using a host-wide tag map.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>

This function shouldn't change the queue type, just the depth.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Unless we want to build a SPI tag message we should just check SCMD_TAGGED
instead of reverse engineering a tag type through the use of
scsi_populate_tag_msg.

Also rename the function to spi_populate_tag_msg, make it behave like the
other spi message helpers, and move it to the spi transport class.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Remove the ordered_tags field, we haven't been issuing ordered tags based
on it since the big barrier rework in 2010.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>

Currently scsi piggy backs on the block layer to define the concept
of a tagged command.  But we want to be able to have block-level host-wide
tags assigned even for untagged commands like the initial INQUIRY, so add
a new SCSI-level flag for commands that are tagged at the scsi level, so
that even commands without that set can have tags assigned to them.  Note
that this alredy is the case for the blk-mq code path, and this just lets
the old path catch up with it.

We also set this flag based upon sdev->simple_tags instead of the block
queue flag, so that it is entirely independent of the block layer tagging,
and thus always correct even if a driver doesn't use block level tagging
yet.

Also remove the old blk_rq_tagged; it was only used by SCSI drivers, and
removing it forces them to look for the proper replacement.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Most drivers use exactly the same implementation, so provide it as a
library function.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Move all code to set up and tear down sdev->scsi_dh_data to common code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

All drivers now do their own matching, so there is no more need to expose
a device list as part of the interface.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

We need to grab a reference to the module before calling the attach
routines to avoid a small race vs module removal.  It also cleans up
the code significantly as a side effect.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Reviewed-by: Hannes Reinecke <hare@suse.de>

The T10 SBC UNMAP command does not provide any hard guarantees that
blocks will return zeroes on a subsequent READ. This is due to the fact
that the device server is free to silently ignore all or parts of the
request.

The only way to ensure that a block consistently returns zeroes after
being unmapped is to use WRITE SAME with the UNMAP bit set. Should the
device be unable to unmap one or more blocks described by the command it
is required to manually write zeroes to them.

Until now we have preferred UNMAP over the WRITE SAME variants to
accommodate thinly provisioned devices that predated the final SBC-3
spec. This patch changes the heuristic so that we favor WRITE SAME(16)
or (10) over UNMAP if these commands are marked as supported in the
Logical Block Provisioning VPD page.

The patch also disables discard_zeroes_data for devices operating in
UNMAP mode.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

No need to verify the passthrough ioctls, the real handler will
take care of that.  Also make sure not to block for resets on
O_NONBLOCK fds.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

The calling conventions for this function are bad as it could return
-ENODEV both for a device not currently online and a not recognized ioctl.

Add a new scsi_ioctl_block_when_processing_errors function that wraps
scsi_block_when_processing_errors with the a special case for the
SG_SCSI_RESET ioctl command, and handle the SG_SCSI_RESET case itself
in scsi_ioctl.  All callers of scsi_ioctl now must call the above helper
to check for the EH state, so that the ioctl handler itself doesn't
have to.
Reported-by: Robert Elliott <Elliott@hp.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Pull the common code from the two callers into the function,
and rename it to scsi_ioctl_reset.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Modify scsi_find_tag() and scsi_host_find_tag() such that these
functions can translate a tag generated by blk_mq_unique_tag().
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Allow a SCSI LLD to declare how many hardware queues it supports
by setting Scsi_Host.nr_hw_queues before calling scsi_add_host().
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

The queuecommand() callback functions in SCSI low-level drivers
need to know which hardware context has been selected by the
block layer. Since this information is not available in the
request structure, and since passing the hctx pointer directly to
the queuecommand callback function would require modification of
all SCSI LLDs, add a function to the block layer that allows to
query the hardware context index.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>