linux-toradex.git/drivers/infiniband, branch v4.11

Merge git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending

2017-04-12T06:51:58+00:00

Pull SCSI target fixes from Nicholas Bellinger:

 "There has been work in a number of different areas over the last
  weeks, including:

   - Fix target-core-user (TCMU) back-end bi-directional handling (Xiubo
     Li + Mike Christie + Ilias Tsitsimpis)

   - Fix iscsi-target TMR reference leak during session shutdown (Rob
     Millner + Chu Yuan Lin)

   - Fix target_core_fabric_configfs.c race between LUN shutdown +
     mapped LUN creation (James Shen)

   - Fix target-core unknown fabric callback queue-full errors (Potnuri
     Bharat Teja)

   - Fix iscsi-target + iser-target queue-full handling in order to
     support iw_cxgb4 RNICs. (Potnuri Bharat Teja + Sagi Grimberg)

   - Fix ALUA transition state race between multiple initiator (Mike
     Christie)

   - Drop work-around for legacy GlobalSAN initiator, to allow QLogic
     57840S + 579xx offload HBAs to work out-of-the-box in MSFT
     environments. (Martin Svec + Arun Easi)

  Note that a number are CC'ed for stable, and although the queue-full
  bug-fixes required for iser-target to work with iw_cxgb4 aren't CC'ed
  here, they'll be posted to Greg-KH separately"

* git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending:
  tcmu: Skip Data-Out blocks before gathering Data-In buffer for BIDI case
  iscsi-target: Drop work-around for legacy GlobalSAN initiator
  target: Fix ALUA transition state race between multiple initiators
  iser-target: avoid posting a recv buffer twice
  iser-target: Fix queue-full response handling
  iscsi-target: Propigate queue_data_in + queue_status errors
  target: Fix unknown fabric callback queue-full errors
  tcmu: Fix wrongly calculating of the base_command_size
  tcmu: Fix possible overwrite of t_data_sg's last iov[]
  target: Avoid mappedlun symlink creation during lun shutdown
  iscsi-target: Fix TMR reference leak during session shutdown
  usb: gadget: Correct usb EP argument for BOT status request
  tcmu: Allow cmd_time_out to be set to zero (disabled)

iser-target: avoid posting a recv buffer twice

2017-03-31T03:35:50+00:00

We pre-allocate our send-queues and might overflow them
in case we have multi work-request operations which tend
to occur for large RDMA transfers over devices with limited
allowed sg elements. When we get to a queue-full condition
we might retry again later, so track our receive buffers
so we don't repost them for a retry case.

Reported-by: Potnuri Bharat Teja 
Tested-by: Potnuri Bharat Teja 
Reviewed-by: Potnuri Bharat Teja 
Signed-off-by: Sagi Grimberg 
Signed-off-by: Nicholas Bellinger

iser-target: Fix queue-full response handling

2017-03-31T03:35:07+00:00

This patch addresses two queue-full handling bugs in iser-target.

The first is propagating isert_rdma_rw_ctx_post() return back
to target-core via isert_put_datain() + isert_get_dataout()
callbacks, in order to trigger queue-full logic in target-core.
Note target-core expects -EAGAIN or -ENOMEM error to signal
RDMA WRITE/READ data-transfer callbacks should be retried,
after queue-full logic been invoked.

Other types of errors propagated up from RDMA RW API will result
in target-core generating internal CHECK_CONDITION status,
avoiding subsequent isert_put_datain() and isert_get_dataout()
iscsit_transport callback retry attempts.

The second is to use transport_generic_request_failure()
during T10-PI hw-offload errors in isert_rdma_write_done()
and isert_rdma_read_done(), so CHECK_CONDITION queue-full
is handled internally by target-core.

Also add isert_put_response() T10-PI failure case fixme in
isert_rdma_write_done(), which is currently not internally
retried or released until session reinstatement.

Reported-by: Potnuri Bharat Teja 
Reviewed-by: Potnuri Bharat Teja 
Tested-by: Potnuri Bharat Teja 
Cc: Potnuri Bharat Teja 
Reported-by: Steve Wise 
Cc: Steve Wise 
Cc: Sagi Grimberg 
Signed-off-by: Nicholas Bellinger

IB/qib: fix false-postive maybe-uninitialized warning

2017-03-25T02:44:29+00:00

aarch64-linux-gcc-7 complains about code it doesn't fully understand:

drivers/infiniband/hw/qib/qib_iba7322.c: In function 'qib_7322_txchk_change':
include/asm-generic/bitops/non-atomic.h:105:35: error: 'shadow' may be used uninitialized in this function [-Werror=maybe-uninitialized]

The code is right, and despite trying hard, I could not come up with a version
that I liked better than just adding a fake initialization here to shut up the
warning.

Fixes: f931551bafe1 ("IB/qib: Add new qib driver for QLogic PCIe InfiniBand adapters")
Signed-off-by: Arnd Bergmann 
Acked-by: Ira Weiny 
Signed-off-by: Doug Ledford

RDMA/iser: Fix possible mr leak on device removal event

2017-03-25T02:31:19+00:00

When the rdma device is removed, we must cleanup all
the rdma resources within the DEVICE_REMOVAL event
handler to let the device teardown gracefully. When
this happens with live I/O, some memory regions are
occupied. Thus, track them too and dereg all the mr's.

We are safe with mr access by iscsi_iser_cleanup_task.

Reported-by: Raju Rangoju 
Signed-off-by: Sagi Grimberg 
Reviewed-by: Max Gurtovoy 
Reviewed-by: Max Gurtovoy 
Signed-off-by: Doug Ledford

IB/device: Convert ib-comp-wq to be CPU-bound

2017-03-25T02:24:04+00:00

This workqueue is used by our storage target mode ULPs
via the new CQ API. Recent observations when working
with very high-end flash storage devices reveal that
UNBOUND workqueue threads can migrate between cpu cores
and even numa nodes (although some numa locality is accounted
for).

While this attribute can be useful in some workloads,
it does not fit in very nicely with the normal
run-to-completion model we usually use in our target-mode
ULPs and the block-mq irq<->cpu affinity facilities.

The whole block-mq concept is that the completion will
land on the same cpu where the submission was performed.
The fact that our submitter thread is migrating cpus
can break this locality.

We assume that as a target mode ULP, we will serve multiple
initiators/clients and we can spread the load enough without
having to use unbound kworkers.

Also, while we're at it, expose this workqueue via sysfs which
is harmless and can be useful for debug.

Signed-off-by: Sagi Grimberg 
Reviewed-by: Bart Van Assche --
Signed-off-by: Doug Ledford

IB/cq: Don't process more than the given budget

2017-03-25T02:19:48+00:00

The caller might not want this overhead.

Reviewed-by: Bart Van Assche 
Reviewed-by: Leon Romanovsky 
Signed-off-by: Sagi Grimberg 
Reviewed-by: Yuval Shaia 
Signed-off-by: Doug Ledford

IB/rxe: increment msn only when completing a request

2017-03-25T02:07:27+00:00

According to C9-147, MSN should only be incremented when the last packet of
a multi packet request has been received.

"Logically, the requester associates a sequential Send Sequence Number
(SSN) with each WQE posted to the send queue. The SSN bears a one-
to-one relationship to the MSN returned by the responder in each re-
sponse packet. Therefore, when the requester receives a response, it in-
terprets the MSN as representing the SSN of the most recent request
completed by the responder to determine which send WQE(s) can be
completed."

Fixes: 8700e3e7c485 ("Soft RoCE driver")

Signed-off-by: David Marchand 
Signed-off-by: Doug Ledford

IB/core: Restore I/O MMU, s390 and powerpc support

2017-03-25T01:51:16+00:00

Avoid that the following error message is reported on the console
while loading an RDMA driver with I/O MMU support enabled:

DMAR: Allocating domain for mlx5_0 failed

Ensure that DMA mapping operations that use to_pci_dev() to
access to struct pci_dev see the correct PCI device. E.g. the s390
and powerpc DMA mapping operations use to_pci_dev() even with I/O
MMU support disabled.

This patch preserves the following changes of the DMA mapping updates
patch series:
- Introduction of dma_virt_ops.
- Removal of ib_device.dma_ops.
- Removal of struct ib_dma_mapping_ops.
- Removal of an if-statement from each ib_dma_*() operation.
- IB HW drivers no longer set dma_device directly.

Reported-by: Sebastian Ott 
Reported-by: Parav Pandit 
Fixes: commit 99db9494035f ("IB/core: Remove ib_device.dma_device")
Signed-off-by: Bart Van Assche 
Reviewed-by: parav@mellanox.com
Tested-by: parav@mellanox.com
Reviewed-by: Leon Romanovsky 
Signed-off-by: Doug Ledford

IB/rxe: Update documentation link

2017-03-25T01:15:28+00:00

All Soft-RoCE (rxe) is handled now in rdma-core user space library,
so the documentation. The patch below updates the documentation
link to that new location.

Reported-by: Josh Beavers 
Signed-off-by: Leon Romanovsky 
Reviewed-by: Ira Weiny 
Signed-off-by: Doug Ledford