Some types of packet errors are moderately common with longer IB
cables and large clusters, and are not reported with prints by other
IB HCA drivers.  This suppresses those messages unless the new
__IPATH_ERRPKTDBG bit is set in ipath_debug.  Reporting of temporarily
disabled frequent error interrupts was also made clearer

We also distinguish between chip errors, and bad packets sent or
received in the wording of the messages.
Signed-off-by: NDave Olson <dave.olson@qlogic.com>
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>

ipath_dbg doesn't need the same prefixes that printk does.
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>

If a post send is done in loopback and there is no receive queue
entry, the sending QP is put on a timeout list for a while so the
receiver has a chance to post a receive buffer. If the another post
send is done, the code incorrectly tried to put the QP on the timeout
list again an corrupted the timeout list. This eventually leads to a
spin lock deadlock NMI due to the timer function looping forever with
the lock held.
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

A silly programming error causes a CQ entry to not be generated if a
SRQ limit event is generated.
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

A recent change was made to allocate memory for a port after CPU
affinity is set. That change didn't account for subports and was
trying to allocate memory for the port twice.
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The chip documentation on the expected TID vs eager TID parity error
bits was reversed from what was implemented in the RTL, for both
chips.  This corrects the definitions.
Signed-off-by: NDave Olson <dave.olson@qlogic.com>
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The loop which initializes the user memory region from an array of
pages was using the wrong limit for the array.  This worked OK when
dma_map_sg() returned the same number as the number of pages.  This
patch fixes the problem.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This is a sticky state.  It is useful for diagnosing problems with
boards versus cable/switch problems.
Signed-off-by: NDave Olson <dave.olson@qlogic.com>
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

There's no point in printing the opcode field in the completion
handling debugging output, since the type of completion is already
printed at the beginning of the line.  In fact the opcode field is not
even defined for completions with a status other than success.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The current ib_umad code never accesses bits past IB_UMAD_MAX_PORTS in
dev_map[].  We shouldn't declare it to be twice as big.
Pointed-out-by: NRoland Dreier <rolandd@cisco.com>
Signed-off-by: NHal Rosenstock <halr@voltaire.com>

In mthca_arbel_fmr_unmap(), the high bits of the key are masked off.
This gets rid of the effect of adjust_key(), which makes sure that
bits 3 and 23 of the key are equal when the Sinai throughput
optimization is enabled, and so it may happen that an FMR will end up
with bits 3 and 23 in the key being different.  This causes data
corruption, because when enabling the throughput optimization, the
driver promises the HCA firmware that bits 3 and 23 of all memory keys
will always be equal.

Fix by re-applying adjust_key() after masking the key.

Thanks to Or Gerlitz for reproducing the problem, and Ariel Shahar for
help in debug.
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

As of commit 6cdbd77e ("cxgb3 - missing CPL hanler and register
setting."), the cxgb3 ethernet NIC driver no longer handles SET_TCB
replies, so we need to do it in the iWARP driver.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Acked-by: NDivy Le Ray <divy@chelsio.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Receive buffers need to be mapped with DMA_FROM_DEVICE.  Incorrectly
mapping with DMA_TO_DEVICE causes a hard lock on ppc64 machines with
an IOMMU.

This fixes <https://bugs.openfabrics.org/show_bug.cgi?id=431>
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

When a connection is terminated asynchronously from the iSCSI layer's
perspective, iSER needs to notify the iSCSI layer that the connection
has failed.  This is done using a workqueue (switched to from the iSER
tasklet context).  Meanwhile, the connection object (that holds the
work struct) is released.  If the workqueue function wasn't called
yet, it will be called later with a NULL pointer, which will crash the
kernel.

The context switch (tasklet to workqueue) is not required, and
everything can be done from the iSER tasklet. This eliminates the NULL
work struct bug (and simplifies the code).
Signed-off-by: NErez Zilber <erezz@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The SCSI midlayer may abort a command that was already sent.  If the
initiator is still trying to send the command (or data-out PDUs for
that command), the QP may time out after the midlayer times
out. Therefore, when aborting the command, iSER may still have
references for the command's buffers.  When sending these PDUs, the
sends will complete with an error and their resources will be released
then.
Signed-off-by: NErez Zilber <erezz@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Commit c20e20ab ("IB/mthca: Merge MR and FMR space on 64-bit systems")
swapped the number of MTTs and MPTs when initializing the MR table. As
a result, we get a kernel oops when the number of MTT segments
allocated exceeds 0x20000.

Noted by Troy Benjegerdes <troy@scl.ameslab.gov>, and reproduced by
Dotan Barak <dotanb@mellanox.co.il>.  This fixes
https://bugs.openfabrics.org/show_bug.cgi?id=490Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This was spotted by the Coverity checker (CID 1554).
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

->neigh_destructor() is killed (not used), replaced with
->neigh_cleanup(), which is called when neighbor entry goes to dead
state. At this point everything is still valid: neigh->dev,
neigh->parms etc.

The device should guarantee that dead neighbor entries (neigh->dead !=
0) do not get private part initialized, otherwise nobody will cleanup
it.

I think this is enough for ipoib which is the only user of this thing.
Initialization private part of neighbor entries happens in ipib
start_xmit routine, which is not reached when device is down.  But it
would be better to add explicit test for neigh->dead in any case.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The packet length checks in ipoib are broken: we add 4 bytes (IPoIB
encapsulation header) when sending a packet, not 20 bytes (hardware
address length) to each packet.  Therefore, if connected mode is
enabled so that the interface MTU is larger than the multicast MTU,
IPoIB may end up trying to send too-long multicast packets.  For
example, multicast is broken if a message of size 2048 bytes is sent
on an interface with UD MTU 2048, because 2048 is bigger than the real
limit of 2044 but the code tests against the wrong limit of 2060.

This patch fixes <https://bugs.openfabrics.org/show_bug.cgi?id=418>,
submitted by Scott Weitzenkamp <sweitzen@cisco.com>.
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The connected mode code added the possibility that an neigh struct
gets freed in the list_for_each_entry() loop in path_rec_completion(),
which causes a use-after-free.  Fix this by changing to the _safe
variant of the list walking macro.

This was spotted by the Coverity checker (CID 1567).
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

eHCA scaling code must not depend on register_cpu_notifier() if
CONFIG_HOTPLUG_CPU is not set, so put all related code into #ifdefs.
Signed-off-by: NJoachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

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

This fixes kernel.org bug 8003.
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

There's a race between ipoib_mcast_leave() and ipoib_mcast_join_finish()
where we can try to detach from a multicast group before we've
attached to it.  Fix this by reordering the code in ipoib_mcast_leave
to free the multicast group first, which waits for the multicast
callback thread (which calls ipoib_mcast_join_finish()) to complete
before detaching from the group.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The sense of the time_after_eq() test in ipoib_cm_stale_task() is
reversed so that only non-stale connections are reaped.  Fix this by
changing to time_before_eq().

Noticed by Pradeep Satyanarayana <pradeep@us.ibm.com>.
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

method gets u64, not dma_addr_t
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Do netif_carrier_on() right after the IPv4 broadcast multicast group
is joined, rather than waiting for all of the initial set of multicast
group joins to finish.  This allows at least IPv4 traffic to limp
along on broken fabrics where not all multicast groups can be joined.
Signed-off-by: NShirley Ma <xma@us.ibm.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Change the returned error code to ENOMEM if the connection event
backlog is full.  This prevents the ib_cm from issuing a reject
on the connection, which can allow retries to succeed.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Fix memory region permission problems:

- remove useless and redundant iwch_mem_perms enum.

- create ib_to_tpt_access_rights() for mapping ib access rights
  to T3 TPT permissions.

- create ib_to_mwbind_access_rights() for mapping ib access rights
  to T3 MWBIND WR permissions.

- fix up the mem reg code to utilize the new functions.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

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

Only print one AE error for a given connection in the kernel log.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Stop the endpoint timer when the MPA exchange is aborted by the peer.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Change iwch_destroy_qp() to always move the QP to ERROR and let
iwch_modify_qp() decide what to do.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Fixes for "normal close" failures:

- Start normal close timer when moving to CLOSING state.
- Handle ABORTING state in close_con_rpl().
- Stop timer correctly on abort during a normal close.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

cxgb3 uses dma_alloc_coherent() et al. thus needs linux/dma-mapping.h
include in order to build reliably.

Noticed on sparc64.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
Acked-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The struct rdma_bind_list fields for hlist are not being initialized,
resulting in a corrupted list.  Fix this by using kzalloc() to make
sure all pointers are NULL.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

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