Add a driver for IBM GX bus InfiniBand adapters, which are usable with
some pSeries/System p systems.

Signed-off-by: Heiko J Schick <schickhj.ibm.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Add local_ib_device and local_ib_port attributes to srp scsi_host.
These are needed when we want to connect to the same target through
multiple distinct ports.
Signed-off-by: NIshai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Signed-off-by: NJames Lentini <jlentini@netapp.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Lockdep warns when userspace creates a QP that uses different CQs for
send completions and receive completions, because both CQs are locked
and their mutexes belong to the same lock class.  However, we know
that the mutexes are distinct and the nesting is safe (there is no
possibility of AB-BA deadlock because the mutexes are locked with
down_read()), so annotate the situation with SINGLE_DEPTH_NESTING to
get rid of the lockdep warning.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

There were two functions that open-coded idr_read_cq() in terms of
idr_read_uobj() rather than using the helper.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Prevent flush task from freeing the ipoib_neigh pointer, while
ipoib_start_xmit() is accessing the ipoib_neigh through the pointer it
has loaded from the skb's hardware address.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Make kernel use UAR2 instead of UAR1 for hardware access: this adds
sanity checking from the hardware side, without any performance cost.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The SM LID used to send traps to is incorrectly set to port LID.  This
is a regression from 2.6.17 -- after a PortInfo MAD is received, no
traps are sent to the SM LID.  The traps go to the loopback interface
instead, and are dropped there.  The SM LID should be taken from the
sm_lid of the PortInfo response.

The bug was introduced by commit 12bbb2b7:
	IB/mthca: Add client reregister event generation
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

3 seems like a low number of IB Communication Manager retries to set;
we see connections failing under stress, and in any case 3 just looks
like an arbitrary number.  15 is the max value allowed by the
InfiniBand spec.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Acked-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

When a send-only multicast group join fails, mcast->query must be set
to NULL.  Otherwise, IPoIB will never retry the join and the multicast
group will never be reachable.
Signed-off-by: NEli Cohen <eli@mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

If there is a problem in the connection, the SCSI mid-layer will
eventually call srp_reset_host(), which will call srp_reconnect(), so
we do not need to schedule a call to srp_reconnect_work() from
srp_completion().

Removing this prevents srp_reset_host() from failing if a reconnect
scheduled from srp_completion() is already in progress, which in turn
was causing crashes as both SCSI midlayer and srp_reconnect() were
cancelling commands.
Signed-off-by: NIshai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

It is supposed to be OK to call mthca_create_ah() and mthca_destroy_ah()
from any context.  However, for mem-full HCAs, these functions use the
mthca_alloc() and mthca_free() bitmap helpers, and those helpers use
non-IRQ-safe spin_lock() internally.  Lockdep correctly warns that
this could lead to a deadlock.  Fix this by changing mthca_alloc() and
mthca_free() to use spin_lock_irqsave().
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Update the driver's list of HCA firmware revisions to make sure people
running Sinai firmware older than 1.1.0 get a message suggesting a
firmware upgrade.  Update the Arbel versions as well while we are at it.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Leave all SRQ methods out of the device's uverbs_cmd_mask if the
device doesn't have SRQ support (because of ancient firmware) so that
we don't allow userspace to call the driver's create_srq method.  This
fixes a userspace-triggerable oops caused by ib_uverbs_create_srq()
following the device's ->create_srq function pointer, which will be
NULL if the device doesn't support SRQs.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

After commit 12bbb2b7, when SM LID
change or LID change MAD also has a client reregistration bit set,
only CLIENT_REREGISTER event is generated.

As a result, the sa_query module and the cache module don't update the
port information, and ULPs (e.g. IPoIB) stop working.  This is the
regression we observe as compared to 2.6.17.

Rather than generate multiple events (which would have negative
performance impact), let us simply let cache and SA query respond to
reregister event in the same way as to LID and SM change events.
Signed-off-by: NJack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

When destroying a QP, mthca locks both the QP's send CQ and receive
CQ.  However, the following scenario is perfectly valid:

    QP_a: send_cq == CQ_x, recv_cq == CQ_y
    QP_b: send_cq == CQ_y, recv_cq == CQ_x

The old mthca code simply locked send_cq and then recv_cq, which in
this case could lead to an AB-BA deadlock if QP_a and QP_b were
destroyed simultaneously.

We can fix this by changing the locking code to lock the CQ with the
lower CQ number first, which will create a consistent lock ordering.
Also, the second CQ is locked with spin_lock_nested() to tell lockdep
that we know what we're doing with the lock nesting.

This bug was found by lockdep.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The fence bit needs to be set in the doorbell too, not just the WQE.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Wait until all users have closed their device context before allowing
device unregistration to complete.  This prevents a crash caused by
referring to stale data structures.

A better solution would be to have a way to revoke contexts rather
than waiting for userspace to close the context, but that's a much
bigger change that will have to wait.  For now let's at least avoid
the crash.
Signed-off-by: NJack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Remove references to the IPoIB IETF working group as it has been closed.
Signed-off-by: NOr Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Data corruption has been seen with Mellanox SRP targets when FMRs
create a memory region with I/O virtual address != 0.  Add a
workaround that disables FMR merging for Mellanox targets (OUI 0002c9).
Signed-off-by: NIshai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Protect against srp_reset_device() clearing the req_queue while
srp_reconnect_target() is in progress (note that state change at
the top of srp_reconnect_target() is not sufficient for this since
srp_reset_device() ignores the state).
Signed-off-by: NIshai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Report error code rather than success (0) on failure allocating
timewait_info in ib_send_cm_req().
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Define a constant MTHCA_ARRAY_MASK to replace repeated uses of
(PAGE_SIZE / sizeof (void *) - 1) in mthca array code.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

mthca_array_clear() does not clear the slot if the used count is
positive. This leads to crashes in mthca_qp_event() since that uses
mthca_array_get() to check that the qp is valid.

Discovered by Ali Ayoub.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Signed-off-by: NTom Tucker <tom@opengridcomputing.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When we enter recovery and flush the running commands
we cannot freee the connection before flushing the commands.
Some commands may have a reference to the connection
that needs to be released before. iscsi_stop was forcing
the term and suspend too early and was causing a oops
in iser, so this patch removes those callbacks all together
and allows the LLD to handle that detail.
Signed-off-by: NMike Christie <michaelc@cs.wisc.edu>
Signed-off-by: NJames Bottomley <James.Bottomley@SteelEye.com>

Read the max_cmds value from the response to the QUERY_FW command
before printing out the value, so that the real value goes into the
debug output.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The neighbour ha field may get updated without destroying the
neighbour.  In this case, the ha field gets out of sync with the
address handle stored in ipoib_neigh->ah, with the result that
the ah field would point to an incorrect path, resulting in all
packets being lost.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Need to set mcast->ah before debug code dereferences it.
Signed-off-by: NOr Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Validate MADs sent by userspace clients for spec compliance with
C13-18.1.1 (prevent duplicate requests and responses sent on the
same port).  Without this, RMPP transactions get aborted because
of duplicate packets.

This patch is similar to that provided by Jack Morgenstein.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NJack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

ipath_skip_sge() doesn't exactly duplicate the side effects of
ipath_copy_sge() if num_sge > 1 since it doesn't decrement ss->num_sge.
This could result in the sg_list being accessed out of bounds.
Since ipath_skip_sge() is almost always called with num_sge == 1,
the original "optimization" is almost never used.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

I am still working on a proposal to remove the phys_to_virt() calls
in the ib_ipath driver.  In the mean time, this patch allows SRP
to work by fixing the R_Key check and conversion from IB address
to kernel virtual address.  It also returns the correct page size
for FMRs.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This patch fixes a problem where certain error packets are passed
to the InfiniBand layer for processing even though the packet
actually was received with an error.
Signed-off-by: NRalph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Mem-free HCAs always keep one spare SRQ WQE, so the SRQ limit cannot
be set beyond srq->max - 1.
Signed-off-by: NDotan Barak <dotanb@mellanox.co.il>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Lockdep warns because uverbs is trying to take uobj->mutex when it
already holds that lock.  This is because there are really multiple
types of uobjs even though all of their locks are initialized in
common code.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

ib_uverbs_create_ah() and ib_uverbs_create_srq() did not release the
PD's read lock in their error paths, which lead to deadlock when
destroying the PD.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Avoid bogus out of memory errors: fix sa_query to actually pass gfp_mask
supplied by the user to idr_pre_get.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Acked-by: N"Sean Hefty" <mshefty@ichips.intel.com>
Acked-by: N"Roland Dreier" <rdreier@cisco.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

ib_fmr_pool_map_phys gets the virtual address by pointer but never writes
there, and users (e.g.  srp) seem to assume this and ignore the value
returned.  This patch cleans up the API to get the VA by value, and updates
all users.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Acked-by: NRoland Dreier <rolandd@cisco.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Set private data length for reject messages to the correct size.  Fix from
openib svn r8483.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

srp_unmap_data assumes req->fmr is NULL if the request is not mapped, so we
must clean it out in case of an error.
Signed-off-by: NVu Pham <vu@mellanox.com>
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Acked-by: NRoland Dreier <rolandd@cisco.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>