Thinko: 64 bytes is the minimum SRQ WQE size (not the maximum).
Signed-off-by: NJack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

sae and sre bits should only be set when setting sra_max.  Further, in
the old code, if the caller specifies max_rd_atomic = 0, the sre and
sae bits are still set, with the result that the QP ends up with
max_rd_atomic = 1 in effect.
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>

This patch corrects some corner cases in managing the RAE/RRE bits in
the mthca qp context.  These bits need to be zero if the user requests
max_dest_rd_atomic of zero.  The bits need to be restored to the value
implied by the qp access flags attribute in a previous (or the
current) modify-qp command if the dest_rd_atomic variable is changed
to non-zero.

In the current implementation, the following scenario will not work:
RESET-to-INIT 	set QP access flags to all disabled (zeroes)
INIT-to-RTR     set max_dest_rd_atomic=10, AND
		set qp_access_flags = IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_ATOMIC

The current code will incorrectly take the access-flags value set in
the RESET-to-INIT transition.

We can simplify, and correct, this IB_QP_ACCESS_FLAGS handling: it is
always safe to set qp access flags in the firmware command if either
of IB_QP_MAX_DEST_RD_ATOMIC or IB_QP_ACCESS_FLAGS is set, so let's
just set it to the correct value, always.
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 cleaning up a CQ for a QP attached to SRQ, need to free an SRQ
WQE only if the CQE is a receive completion.
Signed-off-by: NJack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

break only escapes from the innermost loop, and we want to escape both
loops and return an answer.  Noticed by Ishai Rabinovitch.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Only change the driver's copy of the QP attributes in modify QP after
checking the modify QP command completed successfully.
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>

Fix thinko in rd_atomic calculation: ffs(x) - 1 does not find the next
power of 2 -- it should be fls(x - 1).
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>

Add limit checking on rd_atomic and dest_rd_atomic attributes:
especially for max_dest_rd_atomic, a value that is larger than HCA
capability can cause RDB overflow and corruption of another QP.
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>

Free the memory allocated in mthca_init_user_db_tab() when releasing
the db_tab in mthca_cleanup_user_db_tab().
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>

Don't leak packet if it had a timeout, and don't leak timeout struct
if queue_packet() fails.
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>

Use an increasing local ID to avoid re-using identifiers while
messages may still be outstanding on the old ID.  Without this, a
quick connect-disconnect-connect sequence can fail by matching
messages for the new connection with the old connection.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Change reject code from TIMEOUT to CONSUMER_REJECT when destroying a
cm_id in the process of connecting.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Unlike tavor, the max work queue size is an exact power of 2 for arbel
mode, despite what the documentation (of the QUERY_DEV_LIM firmware
command) says.  Without this patch, on Arbel, we can start with a QP
of a valid size and get above the reported limit after rounding to the
next power of two.
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>

uverbs needs to track which multicast groups is each qp
attached to, in order to properly detach when cleanup
is performed on device file close.
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>

On mem-free HCAs, when posting a long list of send requests, a
doorbell must be rung every 255 requests.  Add code to handle this.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

If ipoib_ib_dev_up() fails after ipoib_ib_dev_open() is called, then
ipoib_ib_dev_stop() needs to be called to clean up.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

race condition: ipoib_ib_dev_flush is accessing child list without locks.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

ipoib_mcast_alloc() uses kzalloc(), so there's no need to zero out
members of the mcast struct after it's allocated.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Make sure mcast->done is initialized to uncompleted value before we
submit a new query, so that it's safe to wait on.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Always set path->query to NULL when the SA path record query
completes, rather than only when we don't have an address handle.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

It's possible that IPoIB will issue multiple SA queries for the same
path struct.  Therefore the struct's completion needs to be
initialized for each query rather than only once when the struct is
allocated, or else we might not wait long enough for later queries to
finish and free the path struct too soon.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

ib_umad_write in user_mad.c is looking at rmpp_hdr field in MAD before
checking that the MAD actually has the RMPP header.  So for a MAD
without RMPP header it looks like we are actually checking a bit
inside M_Key, or something.
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>

last pointer is not updated when QP is modified to reset state.  This
causes data corruption if WQEs are already posted on the queue.
Signed-off-by: NMichael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The Coverity checker spotted this obvious NULL pointer dereference.
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Acked-by: NMark Salyzyn <mark_salyzyn@adaptec.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The Coverity checker spotted this obvious use-after-release bug caused
by a wrong order of the cleanups.
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The Coverity checker spotted this obvious NULL pointer dereference.
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Acked-by: NMarkus Lidel <Markus.Lidel@shadowconnect.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

 In __rpc_purge_upcall (net/sunrpc/rpc_pipe.c), the newer code to clean up
 the in_upcall list has a typo.
 Thanks to Vince Busam <vbusam@google.com> for spotting this!
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

 In cases where the server has gone insane, nfs_update_inode() may end
 up calling nfs_invalidate_inode(), which again calls stuff that takes
 the inode->i_lock that we're already holding.

 In addition, given the sort of things we have in NFS these days that
 need to be cleaned up on inode release, I'm not sure we should ever
 be calling make_bad_inode().

 Fix up spinlock recursion, and limit nfs_invalidate_inode() to clearing
 the caches, and marking the inode as being stale.

 Thanks to Steve Dickson <SteveD@redhat.com> for spotting this.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

 When caching locks due to holding a file delegation, we must always
 check against local locks before sending anything to the server.
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>

Blah.  The patch [0] I recently sent fixing errors with
in_hugepage_area() and prepare_hugepage_range() for powerpc itself has
an off-by-one bug.  Furthermore, the related functions
touches_hugepage_*_range() and within_hugepage_*_range() are also
buggy.  Some of the bugs, like those addressed in [0] originated with
commit 7d24f0b8 where we tweaked the
semantics of where hugepages are allowed.  Other bugs have been there
essentially forever, and are due to the undefined behaviour of '<<'
with shift counts greater than the type width (LOW_ESID_MASK could
return non-zero for high ranges with the right congruences).

The good news is that I now have a testsuite which should pick up
things like this if they creep in again.

[0] "powerpc-fix-for-hugepage-areas-straddling-4gb-boundary"
Signed-off-by: NDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

With the removal of include/asm-powerpc, we no longer need
arch/powerpc/include/asm for the 64 bit build.  We also do not need
-Iarch/powerpc for the 64 bit build either.
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

SGI-PV: 946205
SGI-Modid: xfs-linux-melb:xfs-kern:24567a
Signed-off-by: NNathan Scott <nathans@sgi.com>

SGI-PV: 941645
SGI-Modid: xfs-linux-melb:xfs-kern:24566a
Signed-off-by: NNathan Scott <nathans@sgi.com>

its queue of IO completion callbacks, thus creating the deadlock between
umount and xfslogd. Breaking the loop solves the problem.

SGI-PV: 943821
SGI-Modid: xfs-linux-melb:xfs-kern:202363a
Signed-off-by: NFelix Blyakher <felixb@sgi.com>
Signed-off-by: NNathan Scott <nathans@sgi.com>

direct write.

SGI-PV: 944820
SGI-Modid: xfs-linux-melb:xfs-kern:24351a
Signed-off-by: NNathan Scott <nathans@sgi.com>