A couple of chip bugs in the iba6110 and in the iba6120 are not in more
recent chips.  This first bug swaps two of the pioavail register
locations.  In the second bug, the chip can sometimes forget to dma the
pio avail register to memory.  We indicate the presence of these bugs
with runtime flags and we indicate the presence of the flags by bumping
the SWMINOR.
Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

iba6110 rev3 and earlier had a chip bug where the chip could overrun the
recv header queue. rev4 fixed this chip bug so userspace no longer needs
to workaround it.  Now we only set the workaround flag for older chip
versions.
Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

ipath_poll() suffered from a couple subtle bugs.  Under the right
conditions we could leave recv interrupts enabled on an ipath user
context on close, thereby taking potentially unwanted interrupts on the
next open -- this is fixed by unconditionally turning off recv
interrupts on close.  Also, we now use counters rather than set/clear
bits which allows us to make sure we catch all interrupts at the cost of
changing the semantics slightly (it's now give me all events since the
last time I called poll() rather than give me all events since I called
_this_ poll routine).  We also added some memory barriers which may help
ensure we get all notifications in a timely manner.
Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

The LMC value was being saved by the SMA in two places. This patch
cleans it up so only one copy is kept.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

This patch adds the ability to set the LMC via a sysfs file as if the SM
sent a SubnSet(PortInfo) MAD.  It is useful for debugging when no SM is
running.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

The code to add an entry to the completion queue stored the QPN which is
needed for the user level verbs view of the completion queue entry but
the kernel struct ib_wc contains a pointer to the QP instead of a QPN.
When the kernel polled for a completion queue entry, the QPN was lookup
up and the QP pointer recovered. This patch stores the CQE differently
based on whether the CQ is a kernel CQ or a user CQ thus avoiding the
QPN to QP lookup overhead.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland 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: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Follow the IB spec. (C10-96) for post send which states that a flushed 
completion event should be generated for work requests posted when a QP
is in the error state.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

This patch removes some redundant initialization code.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

In an earlier change, the amount of data read from the flash was
mistakenly limited to the size known to the current driver.  This causes
problems when the length is increased, and written with the new longer
version; the checksum would fail because not enough data was read.
Always read the full 128 byte length to prevent this.
Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

This patch fixes a bug in the receive processing for UC RDMA WRITE with
immediate which caused the last packet to be dropped.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

This is a comment change, only, correcting the comment to match the
implemented workaround, rather than the original workaround, and
clarifying why it's needed.
Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

The ipathfs file system is used to export binary data verses ASCII data
such as through /sys. This patch removes some unneeded files since the
data is available through other /sys files.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

There have been a number of issues where host bandwidth via HT or PCIe
to the InfiniPath chip has been limited in some fashion (BIOS,
configuration, etc.), resulting in user confusion.  This check gives a
clear warning that something is wrong and needs to be resolved.
Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland 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: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Different processors have different ordering restrictions for write
combining.  By taking advantage of this, we can eliminate some write
barriers when writing to the send buffers.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

On iba6110 rev4, support for three more IB counters were added.  The
LocalLinkIntegrityError counter, the ExcessiveBufferOverrunErrors
counter and support for error counting of flow control packets on an
invalid VL.  These counters trigger GPIO interrupts and the sw keeps
track of the counts.  Since we also use GPIO interrupts to signal packet
reception, we need to turn off the fast interrupts, or we risk losing a
GPIO interrupt.
Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Doing min_t(int, foo, INT_MAX) doesn't work correctly, because if foo
is bigger than INT_MAX, then when treated as a signed integer, it will
become negative and hence such an expression is just an elaborate NOP.

Fix such cases in ehca to do min_t(unsigned, foo, INT_MAX) instead.
This fixes negative reported values for max_cqe, max_pd and max_ah:

Before:

        max_cqe:                        -64
        max_pd:                         -1
        max_ah:                         -1

After:
        max_cqe:                        2147483647
        max_pd:                         2147483647
        max_ah:                         2147483647

Based on a bug report and fix from Anton Blanchard <anton@samba.org>.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Make the way QP is being created in ipoib_cm_create_tx_qp()
consistent with ipoib_cm_create_rx_qp().
Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Firmware commands are sent to the HCA by writing multiple words to a
command register block.  Access to this block of registers is
serialized with a mutex.  However, on large SGI systems writes to the
register block may be reordered within the system interconnect and
reach the HCA in a different order than they were issued (even with
the mutex).  Fix this by adding an mmiowb() before dropping the mutex.

This bug was observed with real workloads with the similar FW command
code in the mthca driver, and adding the mmiowb() as in commit
66547550 ("IB/mthca: Use mmiowb() to avoid firmware commands getting
jumbled up") was confirmed to fix the problems, so we should add the
same fix to mlx4.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Firmware commands are sent to the HCA by writing multiple words to a
command register block.  Access to this block of registers is
serialized with a mutex.  However, on large SGI systems, problems were
seen with multiple CPUs issuing FW commands at the same time, because
the writes to the register block may be reordered within the system
interconnect and reach the HCA in a different order than they were
issued (even with the mutex).  Fix this by adding an mmiowb() before
dropping the mutex.
Tested-by: Arthur Kepner <akepner@sgi.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Automatically queue MRA message to decrease the number of retries sent
by the remote side during connection establishment.  This also has the
effect of increasing the overall connection timeout without using a
longer retry time in the case of dropped packets.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

The IB CM provides a message received acknowledged (MRA) message that
can be sent to indicate that a REQ or REP message has been received, but
will require more time to process than the timeout specified by those
messages.  In many cases, the application may not know how long it will
take to respond to a CM message, but the majority of the time, it will
usually respond before a retry has been sent.  Rather than sending an
MRA in response to all messages just to handle the case where a longer
timeout is needed, it is more efficient to queue the MRA for sending in
case a duplicate message is received.

This avoids sending an MRA when it is not needed, but limits the number
of times that a REQ or REP will be resent.  It also provides for a
simpler implementation than generating the MRA based on a timer event.
(That is, trying to send the MRA after receiving the first REQ or REP if
a response has not been generated, so that it is received at the remote
side before a duplicate REQ or REP has been received)
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Increase the number of QPs allowed per multicast group from 8 to 56.
This allows for one QP per core on 16-core systems, which are now
quite common, and allows some space for future growth.

This is basically the same patch that Jack Morgenstein
<jackm@dev.mellanox.co.il> just supplied for mlx4.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Increase the number of QPs allowed per multicast group from 8 to 56.
This allows for one QP per core on 16-core systems, which are now
quite common, and allows some space for future growth.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Implement FMRs for mlx4.  This is an adaptation of code from mthca.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Write MTT entries directly to ICM from the driver (eliminating use of
WRITE_MTT command).  This reduces the number of FW commands needed to
register an MR by at least a factor of 2 and speeds up memory
registration significantly.  This code will also be used to implement
FMRs.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Everything that uses caps.reserved_mtts expects it to be a count of MTT
segments, not MTT entries.  So convert the value that the FW gives us to
a count of segments.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Taking ilog2(dev->caps.reserved_mtts) to find out the order to pass to
the MTT buddy allocator will do the wrong thing if reserved_mtts is ever
not a power of 2.  Be safe and use fls(dev->caps.reserved_mtts - 1).
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Enable having ICM tables in coherent memory, and use coherent memory
for the dMPT table.  This will allow writing MPT entries for MRs both
via the SW2HW_MPT command and also directly by the driver for FMR
remapping without needing to flush or worry about cacheline boundaries.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

ib_uverbs_release_event_file() is only used in uverbs_main.c, so make it
static to that file.  Also move the definition before the first use, so
a forward declaration is not needed.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

The declaration of struct ib_user_mad_reg_req.method_mask[] exported
to userspace was an array of __u32, but the kernel internally treated
it as a bitmap made up of longs.  This makes a difference for 64-bit
big-endian kernels, where numbering the bits in an array of__u32 gives:

    |31.....0|63....31|95....64|127...96|

while numbering the bits in an array of longs gives:

    |63..............0|127............64|

64-bit userspace can handle this by just treating method_mask[] as an
array of longs, but 32-bit userspace is really stuck: the meaning of
the bits in method_mask[] depends on whether the kernel is 32-bit or
64-bit, and there's no sane way for userspace to know that.

Fix this by updating <rdma/ib_user_mad.h> to make it clear that
method_mask[] is an array of longs, and using a compat_ioctl method to
convert to an array of 64-bit longs to handle the 32-on-64 problem.
This fixes the interface description to match existing behavior (so
working binaries continue to work) in almost all situations, and gives
consistent semantics in the case of 32-bit userspace that can run on
either a 32-bit or 64-bit kernel, so that the same binary can work for
both 32-on-32 and 32-on-64 systems.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Add support for setting the P_Key index of sent MADs and getting the
P_Key index of received MADs.  This requires a change to the layout of
the ABI structure struct ib_user_mad_hdr, so to avoid breaking
compatibility, we default to the old (unchanged) ABI and add a new
ioctl IB_USER_MAD_ENABLE_PKEY that allows applications that are aware
of the new ABI to opt into using it.

We plan on switching to the new ABI by default in a year or so, and
this patch adds a warning that is printed when an application uses the
old ABI, to push people towards converting to the new ABI.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Reviewed-by: Hal Rosenstock <hal@xsigo.com>

Totally forgot this.
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

display the following device information under /sys/class/infiniband/mlx4_X:
board_id, fw_ver, hw_rev, hca_type.

This patch makes this information available to userspace utilities
such as ibstat and ibv_devinfo.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

I was looking at the code for multicast.c and noticed that
ib_sa_join_multicast() calls queue_join() which puts the
request at the front of the group->pending_list.  If this
is a second request, it seems like it would interfere with
process_join_error() since group->last_join won't point
to the member at the head of the pending_list. The sequence
would thus be:

1. ib_sa_join_multicast()
   puts member1 on head of pending_list and starts work thread
2. mcast_work_handler()
   calls send_join() which sets group->last_join to member1
3. ib_sa_join_multicast()
   puts member2 on head of pending_list
4. join operation for member1 receives failures response from SA.
5. join_handler() is called with error status
6. process_join_error() fails to process member1 since
   it doesn't match the first entry in the group->pending_list.

The impact is that the failed join request is tossed.  The second
request is processed, and after it completes, the original request ends
up being retried.

This change also results in join requests being processed in FIFO
order.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

* Replace {un}register_cpu_notifier with {un}register_hotcpu_notifier
  thereby losing a couple of #ifdef HOTPLUG_CPU pairs.
* Move comp_pool_callback_nb declaration to below that of callback
  function so that initialization of .notifier_call and .priority can
  occur at build time itself and not runtime.
* Mark the notifier_block (and callback function, and another static
  function used by it) as __cpuinit{data} for the sake of consistency
  and remove enclosing #ifdef. (This may increase size for modular
  build of this module, however, because these are no longer dropped
  unconditionally now.)
Signed-off-by: Satyam Sharma <satyam@infradead.org>
Acked-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

The SRC ("scalable RC") transport has been renamed to XRC ("extended 
RC"), to avoid having an abbreviation that is so easily confused with an 
abbreviation for "source."  Update the HCA capability decoding output to 
use the new name.
Signed-off-by: Roland Dreier <rolandd@cisco.com>