In cases where the cm calls c4iw_modify_rc_qp() with the endpoint
mutex held, they must be called with internal == 1.  rx_data() and
process_mpa_reply() are not doing this.  This causes a deadlock
because c4iw_modify_rc_qp() might call c4iw_ep_disconnect() in some
!internal cases, and c4iw_ep_disconnect() acquires the endpoint mutex.
The design was intended to only do the disconnect for !internal calls.

Change rx_data(), FPDU_MODE case, to call c4iw_modify_rc_qp() with
internal == 1, and then disconnect only after releasing the mutex.

Change process_mpa_reply() to call c4iw_modify_rc_qp(TERMINATE) with
internal == 1 and set a new attr flag telling it to send a TERMINATE
message.  Previously this was implied by !internal.

Change process_mpa_reply() to return whether the caller should
disconnect after releasing the endpoint mutex.  Now rx_data() will do
the disconnect in the cases where process_mpa_reply() wants to
disconnect after the TERMINATE is sent.

Change c4iw_modify_rc_qp() RTS->TERM to only disconnect if !internal,
and to send a TERMINATE message if attrs->send_term is 1.

Change abort_connection() to not aquire the ep mutex for setting the
state, and make all calls to abort_connection() do so with the mutex
held.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Need to get the endpoint reference before calling rdma_fini(), which
might fail causing us to not get the reference.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The max depth of a fastreg mr depends on whether the device supports
DSGL or not.  So compute it dynamically based on the device support
and the module use_dsgl option.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

There is a race when moving a QP from RTS->CLOSING where a SQ work
request could be posted after the FW receives the RDMA_RI/FINI WR.
The SQ work request will never get processed, and should be completed
with FLUSHED status.  Function c4iw_flush_sq(), however was dropping
the oldest SQ work request when in CLOSING or IDLE states, instead of
completing the pending work request. If that oldest pending work
request was actually complete and has a CQE in the CQ, then when that
CQE is proceessed in poll_cq, we'll BUG_ON() due to the inconsistent
SQ/CQ state.

This is a very small timing hole and has only been hit once so far.

The fix is two-fold:

1) c4iw_flush_sq() MUST always flush all non-completed WRs with FLUSHED
   status regardless of the QP state.

2) In c4iw_modify_rc_qp(), always set the "in error" bit on the queue
   before moving the state out of RTS.  This ensures that the state
   transition will not happen while another thread is in
   post_rc_send(), because set_state() and post_rc_send() both aquire
   the qp spinlock.  Also, once we transition the state out of RTS,
   subsequent calls to post_rc_send() will fail because the "in error"
   bit is set.  I don't think this fully closes the race where the FW
   can get a FINI followed a SQ work request being posted (because
   they are posted to differente EQs), but the #1 fix will handle the
   issue by flushing the SQ work request.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Some HW platforms can reorder read operations, so we must rmb() after
we see a valid gen bit in a CQE but before we read any other fields
from the CQE.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

1) timedout endpoint processing can be starved. If there are continual
   CPL messages flowing into the driver, the endpoint timeout
   processing can be starved.  This condition exposed the other bugs
   below.

Solution: In process_work(), call process_timedout_eps() after each CPL
is processed.

2) Connection events can be processed even though the endpoint is on
   the timeout list.  If the endpoint is scheduled for timeout
   processing, then we must ignore MPA Start Requests and Replies.

Solution: Change stop_ep_timer() to return 1 if the ep has already been
queued for timeout processing.  All the callers of stop_ep_timer() need
to check this and act accordingly.  There are just a few cases where
the caller needs to do something different if stop_ep_timer() returns 1:

1) in process_mpa_reply(), ignore the reply and  process_timeout()
   will abort the connection.

2) in process_mpa_request, ignore the request and process_timeout()
   will abort the connection.

It is ok for callers of stop_ep_timer() to abort the connection since
that will leave the state in ABORTING or DEAD, and process_timeout()
now ignores timeouts when the ep is in these states.

3) Double insertion on the timeout list.  Since the endpoint timers
   are used for connection setup and teardown, we need to guard
   against the possibility that an endpoint is already on the timeout
   list.  This is a rare condition and only seen under heavy load and
   in the presense of the above 2 bugs.

Solution: In ep_timeout(), don't queue the endpoint if it is already on
the queue.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NSteve Wise <swise@opengridcomputing.com>

[ Fix cast from u64* to integer.  - Roland ]
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Add support for the block multicast loopback QP creation flag along
the proper firmware API for that.
Signed-off-by: NEli Cohen <eli@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

As result of the deprecation of the MSI-X/MSI enablement functions
pci_enable_msix() and pci_enable_msi_block(), all drivers using these
two interfaces need to be updated to use the new
pci_enable_msi_range() or pci_enable_msi_exact() and
pci_enable_msix_range() or pci_enable_msix_exact() interfaces.
Signed-off-by: NAlexander Gordeev <agordeev@redhat.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

As result of the deprecation of the MSI-X/MSI enablement functions
pci_enable_msix() and pci_enable_msi_block(), all drivers using these
two interfaces need to be updated to use the new pci_enable_msi_range()
and pci_enable_msix_range() interfaces.
Signed-off-by: NAlexander Gordeev <agordeev@redhat.com>
Acked-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Unregister the inet notifier during ocrdma unload to avoid a panic after
driver unload.
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

We should cast pointers to and from unsigned long to turn them into ints.
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Clean up code.  Also modifying GSI QP to error during ocrdma_close is fixed.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Adding a sysfs file for getting the FW version.
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Issue mailbox commands to query ocrdma controller information and phy
information and print them while adding ocrdma device.
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Added a routine to issue non-embedded mailbox commands for handling
large mailbox request/response data.
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

As part of SRQ receive buffers posting we populate a non-zero tag
which will be returned in SRQ receive completions.
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Increment the ABI version count for driver/library interface.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Update the driver vrsion string and node description string
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

While loading RoCE driver be2net driver should check for ABI version
to catch functional incompatibilities.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Allow creating DPP QP even if inline-data is not requested.  This is an
optimization to lower latency.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

ocrdma driver selects execution path based on sli_family and asic
generation number.  This introduces code to read the asic gen number
from pci register instead of obtaining it from the Emulex NIC driver.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Introducing new macros to define SQ and RQ doorbell offset.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Stale entries in the CQ being destroyed causes hardware to generate
EQEs indefinitely for a given CQ.  Thus causing uncontrolled execution
of irq_handler.  This patch fixes this using following sementics:

    * irq_handler will ring EQ doorbell atleast once and implement budgeting scheme.
    * cq_destroy will count number of valid entires during destroy and ring
      cq-db so that hardware does not generate uncontrolled EQE.
    * cq_destroy will synchronize with last running irq_handler instance.
    * arm_cq will always defer arming CQ till poll_cq, except for the first arm_cq call.
    * poll_cq will always ring cq-db with arm=SET if arm_cq was called prior to enter poll_cq.
    * poll_cq will always ring cq-db with arm=UNSET if arm_cq was not called prior to enter poll_cq.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Current hardware doesn't correctly support DSGL.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

To avoid racing with other threads doing close/flush/whatever, rx_data()
should hold the endpoint mutex.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

There is a race between ULP threads doing an accept/reject, and the
ingress processing thread handling close/abort for the same connection.
The accept/reject path needs to hold the lock to serialize these paths.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>

[ Fold in locking fix found by Dan Carpenter <dan.carpenter@oracle.com>.
  - Roland ]
Signed-off-by: NRoland Dreier <roland@purestorage.com>

These methods appear to only mimic the sg_dma_address() and
sg_dma_len() behavior.

They can be safely removed.
Suggested-by: NBart Van Assche <bvanassche@acm.org>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Cc: Christoph Raisch <raisch@de.ibm.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The removal of these methods is compensated for by code changes to
.map_sg to insure that the vanilla sg_dma_address() and sg_dma_len()
will do the same thing as the equivalent former ib_sg_dma_address()
and ib_sg_dma_len() calls into the drivers.

The introduction of this patch required that the struct
ipath_dma_mapping_ops be converted to a C99 initializer.
Suggested-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Remove the overload for .dma_len and .dma_address

The removal of these methods is compensated for by code changes to
.map_sg to insure that the vanilla sg_dma_address() and sg_dma_len()
will do the same thing as the equivalent former ib_sg_dma_address()
and ib_sg_dma_len() calls into the drivers.
Suggested-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Tested-by: NVinod Kumar <vinod.kumar@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

My static checker complains that the sprintf() here can overflow.

	drivers/infiniband/hw/mlx4/main.c:1836 mlx4_ib_alloc_eqs()
	error: format string overflow. buf_size: 32 length: 69

This seems like a valid complaint.  The "dev->pdev->bus->name" string
can be 48 characters long.  I just made the buffer 80 characters instead
of 69 and I changed the sprintf() to snprintf().
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The code was indented too far and also kernel style says we should have
curly braces.
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>