A new field is added to qib_qp called timeout_jiffies. It is
initialized upon create and modify.

The field is now used instead of a computation based on qp->timeout.
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Store both the encoded and decoded MTU in the QP structure as a minor
optimization for UC/RC receive routines.
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The memset for zeroing work completions had been unconditional.

This patch removes the memset and moves the zeroing into the work
completion with a more explicit field by field set.  With this patch,
non-ONLY/non-LAST packets will avoid the overhead since they will not
generate a completion.
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

There is a double completion associated with error handling for RC QPs.

The sequence is:

 - The do_rc_ack() routine fields an RNR nack and there are 0
   rnr_retries configured on the QP.
 - qib_error_qp() stops the pending timer
 - qib_rc_send_complete() is called from sdma_complete()
 - qib_rc_send_complete() starts the timer because the msb of the psn
   just completed says an ack is needed.
 - a bunch of flushes occur as ipoib posts WQEs to an error'ed QP
 - rc_timeout() calls qib_restart_rc()
 - qib_restart_rc() calls qib_send_complete() with a
   IB_WC_RETRY_EXC_ERR on a wqe that has already been completed in the
   past

The fix avoids starting the timer since another packet will never
arrive.
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The following panic BUG_ON occurs during qib testing:

    Kernel BUG at include/linux/timer.h:82

    RIP  [<ffffffff881f7109>] :ib_qib:start_timer+0x73/0x89
     RSP <ffffffff80425bd0>
     <0>Kernel panic - not syncing: Fatal exception
     <0>Dumping qib trace buffer from panic
    qib_set_lid INFO: IB0:1 got a lid: 0xf8
    Done dumping qib trace buffer
    BUG: warning at kernel/panic.c:137/panic() (Tainted: G

The flaw is due to a missing state test when processing responses that
results in an add_timer() call when the same timer is already queued.
This code was executing in parallel with a QP destroy on another CPU
that had changed the state to reset, but the missing test caused to
response handling code to run on into the panic.
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Currently on receipt of a response message (ACKs, RDMA Response,
Atomic Responses etc.) if the SDMA completion counter is not advanced
the driver delays the completion of the WQE.  In most cases this is
overly pessimistic as the response (ACK) to a previously transmitted
send implies that the send is complete.  Ensure that SDMA queue is
progressed appropriately before determining if a send has delayed
completions.
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

See table 35 in IBA - the header order for RDMA_WRITE_ONLY_WITH_IMMEDIATE
and SEND_LAST_WITH_IMMEDIATE is different: the RDMA_WRITE_ONLY has
a RETH header before the immediate data, so we need a different code path
to extract the immediate data.

I tested this with a userspace app that does RDMA_WRITE with immediate
on a QLE7140.
Signed-off-by: NJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

When transitioning a QP to the error state, in progress RWQEs need to
be marked complete.  This also involves releasing the reference count
to the memory regions referenced in the SGEs.  The locking in the
receive packet processing wasn't sufficient to prevent qib_error_qp()
from modifying the r_sge state at the same time, thus leading to
kernel panics.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Add a low-level IB driver for QLogic PCIe adapters.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The base versions handle constant folding just fine, use them
directly.  The replacements are OK in the include/ files as they are
not exported to userspace so we don't need the __ prefixed versions.

This patch does not affect code generation at all.
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The PSN of the first packet after an RDMA read is based on the size of
the RDMA read request. This is calculated correctly for the WQE sent
after the first request message but not on subsequent requests if the
RDMA read is resent.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The code to set the source LID in the sent LRH was not setting the low
bits if LMC != 0 for RC/UC QPs.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This patch adds support for the IB "base memory management extension"
(BMME) and the equivalent iWARP operations (which the iWARP verbs
mandates all devices must implement).  The new operations are:

 - Allocate an ib_mr for use in fast register work requests.

 - Allocate/free a physical buffer lists for use in fast register work
   requests.  This allows device drivers to allocate this memory as
   needed for use in posting send requests (eg via dma_alloc_coherent).

 - New send queue work requests:
   * send with remote invalidate
   * fast register memory region
   * local invalidate memory region
   * RDMA read with invalidate local memory region (iWARP only)

Consumer interface details:

 - A new device capability flag IB_DEVICE_MEM_MGT_EXTENSIONS is added
   to indicate device support for these features.

 - New send work request opcodes IB_WR_FAST_REG_MR, IB_WR_LOCAL_INV,
   IB_WR_RDMA_READ_WITH_INV are added.

 - A new consumer API function, ib_alloc_mr() is added to allocate
   fast register memory regions.

 - New consumer API functions, ib_alloc_fast_reg_page_list() and
   ib_free_fast_reg_page_list() are added to allocate and free
   device-specific memory for fast registration page lists.

 - A new consumer API function, ib_update_fast_reg_key(), is added to
   allow the key portion of the R_Key and L_Key of a fast registration
   MR to be updated.  Consumers call this if desired before posting
   a IB_WR_FAST_REG_MR work request.

Consumers can use this as follows:

 - MR is allocated with ib_alloc_mr().

 - Page list memory is allocated with ib_alloc_fast_reg_page_list().

 - MR R_Key/L_Key "key" field is updated with ib_update_fast_reg_key().

 - MR made VALID and bound to a specific page list via
   ib_post_send(IB_WR_FAST_REG_MR)

 - MR made INVALID via ib_post_send(IB_WR_LOCAL_INV),
   ib_post_send(IB_WR_RDMA_READ_WITH_INV) or an incoming send with
   invalidate operation.

 - MR is deallocated with ib_dereg_mr()

 - page lists dealloced via ib_free_fast_reg_page_list().

Applications can allocate a fast register MR once, and then can
repeatedly bind the MR to different physical block lists (PBLs) via
posting work requests to a send queue (SQ).  For each outstanding
MR-to-PBL binding in the SQ pipe, a fast_reg_page_list needs to be
allocated (the fast_reg_page_list is owned by the low-level driver
from the consumer posting a work request until the request completes).
Thus pipelining can be achieved while still allowing device-specific
page_list processing.

The 32-bit fast register memory key/STag is composed of a 24-bit index
and an 8-bit key.  The application can change the key each time it
fast registers thus allowing more control over the peer's use of the
key/STag (ie it can effectively be changed each time the rkey is
rebound to a page list).
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

If an out of sequence RDMA read response middle or last packet is
received, we should only resend the RDMA read request on the first
out of sequence packet and drop subsequent out of sequence packets
otherwise, we get "too many retries".
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The send DMA hardware queue voided a number of prior assumptions about
when a send is complete which led to completions being generated out of
order.  There were also a number of locking issues when switching the QP
to the error or reset states, and we implement the IB_QPS_SQD state.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

When errors are detected in RC, the QP should transition to the
IB_QPS_ERR state, not the IB_QPS_SQE state. Also, when the error is on
the responder side, the receive work completion error was incorrect
(remote vs. local).
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This patch fixes a bug in the RC responder which generates a completion
entry with the wrong opcode when an RDMA WRITE with immediate is received.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Add a new IB_WR_SEND_WITH_INV send opcode that can be used to mark a
"send with invalidate" work request as defined in the iWARP verbs and
the InfiniBand base memory management extensions.  Also put "imm_data"
and a new "invalidate_rkey" member in a new "ex" union in struct
ib_send_wr. The invalidate_rkey member can be used to pass in an
R_Key/STag to be invalidated.  Add this new union to struct
ib_uverbs_send_wr.  Add code to copy the invalidate_rkey field in
ib_uverbs_post_send().

Fix up low-level drivers to deal with the change to struct ib_send_wr,
and just remove the imm_data initialization from net/sunrpc/xprtrdma/,
since that code never does any send with immediate operations.

Also, move the existing IB_DEVICE_SEND_W_INV flag to a new bit, since
the iWARP drivers currently in the tree set the bit.  The amso1100
driver at least will silently fail to honor the IB_SEND_INVALIDATE bit
if passed in as part of userspace send requests (since it does not
implement kernel bypass work request queueing).  Remove the flag from
all existing drivers that set it until we know which ones are OK.

The values chosen for the new flag is not consecutive to avoid clashing
with flags defined in the XRC patches, which are not merged yet but
which are already in use and are likely to be merged soon.

This resurrects a patch sent long ago by Mikkel Hagen <mhagen@iol.unh.edu>.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This reduces the latency for RC ACKs when a PIO buffer is available.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Reset the retry counter when we get a good RDMA_READ_RESPONSE_MIDDLE
packet.  This fix will prevent the requester from reporting a retry
exceeded error too early.
Signed-off-by: NPatrick Marchand Latifi <patrick.latifi@qlogic.com>

This patch fixes a couple of minor problems with RNR NAK handling:
 - The insertion sort was causing extra delay when inserting ahead
   vs. behind an existing entry on the list.
 - A resend of a first packet of a message which is still not ready,
   needs another RNR NAK (i.e., it was suppressed when it shouldn't).
 - Also, the resend tasklet doesn't need to be woken up unless the
   ACK/NAK actually indicates progress has been made.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

When an ACK is received, the QP is removed from the timeout list and
then if there are still pending send WQEs, the QP is put back on the
timeout list. It is possible that another post send has put the QP on
the timeout list thus, a check needs to be made before trying to do it
again or the list is corrupted.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This patch implements the IB_EVENT_QP_LAST_WQE_REACHED event which is
needed by ib_ipoib to destroy the QP when used in connected mode.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The code to post UD sends tried to process work requests at the time
ib_post_send() is called without using a WQE queue.  This was fine as
long as HW resources were available for sending a packet.  This patch
changes UD to be handled more like RC and UC and shares more code.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Now that it's June, it's about time to update
the copyright notices of files that have changed.
Signed-off-by: NJohn Gregor <john.gregor@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The IB specification ch. 9.9.3 table 58 says that a QP which isn't set
up for the operation should return a NAK invalid request.
Signed-off-by: NRobert Walsh <robert.walsh@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

A duplicate RDMA read request can fool the responder into NAKing a new
RDMA read request because the responder wasn't keeping track of
whether the queue of RDMA read requests had been sent at least once.
For example, requester sends 4 2K byte RDMA read requests, times out,
and resends the first, then sees the 4 responses, then sends a 5th
RDMA read or atomic operation.  The responder sees the 4 requests,
sends 4 responses, sees the resent 1st request, rewinds the queue,
then sees the 5th request but thinks the queue is full and that the
requester is invalidly sending a 5th new request.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

A RDMA read response or atomic response can ACK earlier sends and RDMA
writes.  In this case, the wrong work request pointer was being used
to store the read first response or atomic result.  Also, if a RDMA
read request is retried, the code to compute which request to resend
was incorrect.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

According to chapter 17.2.8.1.1, QPs start in the migrated state and
should send packets with the M bit set in the BTH.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Fix a problem where simple ACKs can be sent ahead of RDMA read
responses thus implicitly NAKing the RDMA read.
Signed-off-by: NRalph Campbell <ralph.cambpell@qlogic.com>
Signed-off-by: NRobert Walsh <robert.walsh@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Fix a missing unlock in ipath_rc_rcv_resp() and remove an extra unlock
from ipath_rc_rcv_error().
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This fixes a problem which causes too many RC timeouts and
retransmits.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This patch fixes the problem reported by Bernd Schubert <bs@q-leap.de>
with kernel debug options enabled:

    BUG: at kernel/lockdep.c:1860 trace_hardirqs_on()

This was caused by using spin_lock_irq()/spin_unlock_irq() from
interrupt context.  Fix all the places that might be called from
interrupts to use spin_lock_irqsave()/spin_unlock_irqrestore().
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Fix RDMA read response length checking for RDMA_READ_RESPONSE_ONLY to
allow a zero length response.  RDMA read responses which don't match
the expected length or occur in response to some other operation
should generate a completion queue error (see table 56, ch. 9.9.2.3 in
the IB spec).
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This patch fixes a number of bugs with updating the PSN for retries of
RC requests.
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

When switching to the QP error state, the completion queue entries
(error or flush) were not being generated correctly.
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This patch adds support for multiple RDMA reads and atomics to be sent
before an ACK is required to be seen by the requester.
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

struct ib_wc currently only includes the local QP number: this matches
the IB spec, but seems mostly useless. The following patch replaces
this with the pointer to qp itself, and updates all low level drivers
and all users.

This has the following advantages:
- Ability to get a per-qp context through wc->qp->qp_context
- Existing drivers already have the qp pointer ready in poll cq, so
  this change actually saves a tiny bit (extra memory read) on data path
  (for ehca it would actually be expensive to find the QP pointer when
  polling a CQ, but ehca does not support SRQ so we can leave wc->qp as
  NULL for ehca)
- Users that need the QP number can still get it through wc->qp->qp_num

Use case:

In IPoIB connected mode code, I have a common CQ shared by multiple
QPs.  To track connection usage, I need a way to get at some per-QP
context upon the completion, and I would like to avoid allocating
context object per work request just to stick a QP pointer into it.
With this code, I can just use wc->qp->qp_context.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The PSN used to generate the request following a RDMA read was
incorrect and some state booking wasn't maintained correctly.  This
patch fixes that.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>