Commit Graph

2150 Commits

Author SHA1 Message Date
Roland Dreier
73f526da02 Merge branch 'mad' into for-linus
Conflicts:
	drivers/infiniband/core/mad.c
2009-09-10 21:19:45 -07:00
Roland Dreier
45c448a1c0 Merge branches 'cxgb3', 'ehca', 'ipath', 'ipoib', 'misc', 'mlx4', 'mthca' and 'nes' into for-linus 2009-09-10 21:18:07 -07:00
Steve Wise
cb58160e72 RDMA/iwcm: Reject the connection when the cm_id is destroyed
If the cm_id of a connect request is destroyed prior to the ULP
accepting or rejecting the connection, then the provider never cleans
up the connection.  The iwcm should explicitly reject these
connections if the cm_id is destroyed.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-09 11:37:38 -07:00
Steve Wise
ffc40c6433 RDMA/cxgb3: Clean up properly on FW mismatch failures
FW mismatches can cause a crash in the iw_cxgb3 event handler.

- NULL the t3cdev->ulp pointer on failures in cxio_rdev_open()
- Silently ignore events when the ulp ptr is NULL in iwch_err_handler()

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-09 11:25:56 -07:00
Steve Wise
13a239330a RDMA/cxgb3: Don't ignore insert_handle() failures
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-09 11:25:55 -07:00
Hal Rosenstock
b76aabc395 IB/mad: Allow tuning of QP0 and QP1 sizes
MADs are UD and can be dropped if there are no receives posted, so
allow receive queue size to be set with a module parameter in case the
queue needs to be lengthened.  Send side tuning is done for symmetry
with receive.

Signed-off-by: Hal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-07 08:28:48 -07:00
Roland Dreier
6b2eef8fd7 IB/mad: Fix possible lock-lock-timer deadlock
Lockdep reported a possible deadlock with cm_id_priv->lock,
mad_agent_priv->lock and mad_agent_priv->timed_work.timer; this
happens because the mad module does

	cancel_delayed_work(&mad_agent_priv->timed_work);

while holding mad_agent_priv->lock.  cancel_delayed_work() internally
does del_timer_sync(&mad_agent_priv->timed_work.timer).

This can turn into a deadlock because mad_agent_priv->lock is taken
inside cm_id_priv->lock, so we can get the following set of contexts
that deadlock each other:

 A: holding cm_id_priv->lock, waiting for mad_agent_priv->lock
 B: holding mad_agent_priv->lock, waiting for del_timer_sync()
 C: interrupt during mad_agent_priv->timed_work.timer that takes
    cm_id_priv->lock

Fix this by using the new __cancel_delayed_work() interface (which
internally does del_timer() instead of del_timer_sync()) in all the
places where we are holding a lock.

Addresses: http://bugzilla.kernel.org/show_bug.cgi?id=13757
Reported-by: Bart Van Assche <bart.vanassche@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-07 08:27:50 -07:00
Chien Tung
cd1d3f7abe RDMA/nes: Map MTU to IB_MTU_* and correctly report link state
Old query_port code reports static MTU and link state values.
Instead, map actual MTU to next largest IB_MTU_* constant and
correctly report link state.

Cc: Steve Wise <swise@opengridcomputing.com>
Reported-by: Jeff Squyres <jsquyres@cisco.com>
Signed-off-by: Chien Tung <chien.tin.tung@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:39 -07:00
Don Wood
b29a4fc49b RDMA/nes: Rework the disconn routine for terminate and flushing
The disconn routine has been reworked to acoomodate the terminate and
flushing changes.  The routine has been reorganized to make all the
decisions at the start then it performs all the required operations.
This simplified the lock handling and is easier to follow.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:39 -07:00
Don Wood
320cdfd21d RDMA/nes: Use the flush code to fill in cqe error
Use the flush status to fill in cqe status when a specific error has
been identified.  Subsequent flushed completions still use the flushed
value.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:39 -07:00
Don Wood
6eed5e7c8b RDMA/nes: Make poll_cq return correct number of wqes during flush
When a flush request is given to the hw, it will place one cqe marked
as flushed (unless there is nothing to flush).  An application that is
waiting for all wqe's to complete will be left hanging.  This modifies
poll_cq to return the correct number of flushes for the pending
elements on the wq.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:39 -07:00
Don Wood
4b281faec3 RDMA/nes: Use flush mechanism to set status for wqe in error
When an asynchronous event occurs that requires a terminate, it is
sometimes possible to identify the wqe in error.  This change uses
flush to get this information to the poll routine.  The flush
operation puts the status into the cqe.  If this information is not
available, it continues to use the more generic flush code as before.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:38 -07:00
Don Wood
8b1c9dc4ba RDMA/nes: Implement Terminate Packet
Implement the sending and receiving of Terminate packets.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:38 -07:00
Don Wood
3c28b4457a RDMA/nes: Add CQ error handling
CQ errors are not being handled correctly.  Put in the the upcall for
CQ errors.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:38 -07:00
Don Wood
5ee21fe0ea RDMA/nes: Clean out CQ completions when QP is destroyed
When a QP is destroyed, unprocessed CQ entries could still reference
the QP.  This change zeroes the context value at QP destroy time.  By
skipping over cqe's with a zero context, poll_cq no longer processes a
cqe for a destroyed QP.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:37 -07:00
Don Wood
ba0c5d9a89 RDMA/nes: Change memory allocation for cqp request to GFP_ATOMIC
The routine to allocate a cqp request is not called from process
context code.  Since it is not OK to sleep, it needs to use GFP_ATOMIC
not GFP_KERNEL.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:37 -07:00
Don Wood
873fcdd4bf RDMA/nes: Allocate work item for disconnect event handling
The code currently has a work structure in the QP.  This requires a
lock and a pending flag to ensure there is never more than one request
active.  When two events happen quickly (such as FIN and LLP CLOSE),
it causes unnecessary timeouts since the second one is dropped.

This fix allocates memory for the work request so the second one can
be queued.  A lock is removed since it is no longer needed.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:37 -07:00
Don Wood
c4c3f279cd RDMA/nes: Update refcnt during disconnect
During termination, it is possible for the refcnt to go to zero while
the worker thread is posting events upward.  This fix increments the
refcnt before the request is passed to the worker thread.  The thread
decrements the refcnt when the request is completed.

Signed-off-by: Don Wood <donald.e.wood@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:36 -07:00
Jack Morgenstein
d841064777 IB/mthca: Don't allow userspace open while recovering from catastrophic error
Userspace apps are supposed to release all ib device resources if they
receive a fatal async event (IBV_EVENT_DEVICE_FATAL).  However, the
app has no way of knowing when the device has come back up, except to
repeatedly attempt ibv_open_device() until it succeeds.

However, currently there is no protection against the open succeeding
while the device is in being removed following the fatal event.  In
this case, the open will succeed, but as a result the device waits in
the middle of its removal until the new app releases its resources --
and the new app will not do so, since the open succeeded at a point
following the fatal event generation.

This patch adds an "active" flag to the device. The active flag is set
to false (in the fatal event flow) before the "fatal" event is
generated, so any subsequent ibv_dev_open() call to the device will
fail until the device comes back up, thus preventing the above
deadlock.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:16 -07:00
Arputham Benjamin
d94a868901 IB/mthca: Distinguish multiple devices in /proc/interrupts
When the mthca driver uses the same name for interrupts for every
device in the system.  This can make it very confusing trying to work
out exactly which device MSI-X interrupts are for.  Change the driver
to add the PCI name of the device to the interrupt name.

Signed-off-by: Arputham Benjamin <abenjamin@sgi.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:15 -07:00
Roland Dreier
ffe063f32b IB/mthca: Annotate CQ locking
mthca_ib_lock_cqs()/mthca_ib_unlock_cqs() are helper functions that
lock/unlock both CQs attached to a QP in the proper order to avoid
AB-BA deadlocks.  Annotate this so sparse can understand what's going
on (and warn us if we misuse these functions).

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:15 -07:00
Roland Dreier
deecb5d672 IB/mthca: Remove unnecessary include of <linux/init.h>
mthca_reset.c doesn't have any function annotations, so there's no
reason to include <linux/init.h>.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:15 -07:00
Roland Dreier
fc1285585f IB/mthca: Remove unnecessary include of <asm/page.h>
mthca_config_reg.h was including <asm/page.h> for no reason -- the whole
file is just defines of constants, so it's entirely self-contained.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:36:13 -07:00
Jack Morgenstein
3b4a8cd51e IB/mlx4: Don't allow userspace open while recovering from catastrophic error
Userspace apps are supposed to release all ib device resources if they
receive a fatal async event (IBV_EVENT_DEVICE_FATAL).  However, the
app has no way of knowing when the device has come back up, except to
repeatedly attempt ibv_open_device() until it succeeds.

However, currently there is no protection against the open succeeding
while the device is in being removed following the fatal event.  In
this case, the open will succeed, but as a result the device waits in
the middle of its removal until the new app releases its resources --
and the new app will not do so, since the open succeeded at a point
following the fatal event generation.

This patch adds an "active" flag to the device. The active flag is set
to false (in the fatal event flow) before the "fatal" event is
generated, so any subsequent ibv_dev_open() call to the device will
fail until the device comes back up, thus preventing the above
deadlock.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:50 -07:00
Roland Dreier
338a8fad27 IB/mlx4: Annotate CQ locking
mlx4_ib_lock_cqs()/mlx4_ib_unlock_cqs() are helper functions that
lock/unlock both CQs attached to a QP in the proper order to avoid
AB-BA deadlocks.  Annotate this so sparse can understand what's going
on (and warn us if we misuse these functions).

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:49 -07:00
Roel Kluin
1493ab4083 RDMA/amso1100: Check kmalloc() result in c2_register_device()
dev->ibdev.iwcm allocation may fail, prevent a dereference.

Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:24 -07:00
Jack Morgenstein
b1b8afb833 IB/uverbs: Return ENOSYS for unimplemented commands (not EINVAL)
Since the original commit 883a99c7 ("[IB] uverbs: Add a mask of device
methods allowed for userspace"), the uverbs core returns EINVAL for
commands not implemented by a specific low-level driver.

This creates a problem that there is no way to tell the difference
between an unimplemented command and an implemented one which is
incorrectly invoked (which also returns EINVAL).

The fix is to have unimplemented commands return ENOSYS.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:24 -07:00
Yossi Etigin
e1d7806df3 IB/core: Fix send multicast group leave retry
Until now, retries were only sent when joining a multicast group. This
patch will adds retries when leaving a multicast group as well.

Signed-off-by: Ron Livne <ronli@voltaire.com>
Signed-off-by: Yossi Etigin <yosefe@voltaire.com>
Acked-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:24 -07:00
Marcin Slusarz
f1aa78b26e IB: Use printk_once() for driver versions
Replace open-coded reimplementations with printk_once().

Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:24 -07:00
Tobias Klauser
181c74e87e RDMA/amso1100: Use %pM conversion specifier
Use the %pM conversion specifier to print a MAC address.

Signed-off-by: Tobias Klauser <klto@zhaw.ch>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:23 -07:00
Roland Dreier
6276e08a9b IB: Use DEFINE_SPINLOCK() for static spinlocks
Rather than just defining static spinlock_t variables and then
initializing them later in init functions, simply define them with
DEFINE_SPINLOCK() and remove the calls to spin_lock_init().  This cleans
up the source a tad and also shrinks the compiled code; eg on x86-64:

add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-40 (-40)
function                                     old     new   delta
ib_uverbs_init                               336     326     -10
ib_mad_init_module                           147     137     -10
ib_sa_init                                   123     103     -20

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:23 -07:00
Roland Dreier
60f2b652f5 IB/mad: Check hop count field in directed route MAD to avoid array overflow
The hop count field in a directed route MAD is only allowed to be in the
range 0 to 63 (by spec).  Check that this really is the case to avoid
accessing outside the bounds of the hop array.

Reported-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:24:10 -07:00
Jason Gunthorpe
5e47596bee IPoIB: Check multicast address format
Check that the format of multicast link addresses is correct before
taking them from dev->mc_list to priv->multicast_list.  This way we
never try to send a bogus address to the SA, which prevents badness
from erronous 'ip maddr addr add', broken bonding drivers, etc.

Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:23:40 -07:00
Roland Dreier
721d67cdca IPoIB: Drop priv->lock before calling ipoib_send()
IPoIB currently must use irqsave locking for priv->lock, since it is
taken from interrupt context in one path.  However, ipoib_send() does
skb_orphan(), and the network stack locking is not IRQ-safe.
Therefore we need to make sure we don't hold priv->lock when calling
ipoib_send() to avoid lockdep warnings (the code was almost certainly
safe in practice, since the only code path that takes priv->lock from
interrupt context would never call into the network stack).

Addresses: http://bugzilla.kernel.org/show_bug.cgi?id=13757
Reported-by: Bart Van Assche <bart.vanassche@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:23:40 -07:00
Roland Dreier
cd0bcf4cb9 IPoIB: Remove unused <rdma/ib_cache.h> includes
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:23:38 -07:00
Roel Kluin
286b63d096 IB/ipath: strncpy() doesn't always NUL-terminate
strlcpy() will always null terminate the string.  node_desc is not
guaranteed to be NUL-terminated so just use memcpy().

Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:23:21 -07:00
Joachim Fenkes
6303e74c69 IB/ehca: Fix CQE flags reporting
The driver was reporting CQE flags in the wrong bit positions, causing
consumers to miss incoming immediate data.

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:22:55 -07:00
Joachim Fenkes
d706834d99 IB/ehca: Construct MAD redirect replies from request MAD
The old code used a lot of hard-coded values, which might not be valid
in all environments (especially routed fabrics or partitioned
subnets).  Copy as much information as possible from the incoming
request to correct that.

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:22:55 -07:00
Alexander Schmidt
50d40b8e53 IB/ehca: Make port autodetect mode the default
Make port autodetect mode the default for the ehca driver. The
autodetect code has been in the kernel for several releases now and
has proved to be stable.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:22:54 -07:00
Steve Wise
a52bf98d99 RDMA/cxgb3: Wake up any waiters on peer close/abort
A close/abort while waiting for a wr_ack during connection migration
can cause a hung process in iwch_accept_cr/iwch_reject_cr.

The fix is to set rpl_error/rpl_done and wake up the waiters when we
get a close/abort while in MPA_REQ_RCVD state.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:22:38 -07:00
Steve Wise
6e47fe4350 RDMA/cxgb3: Don't free endpoints early
- Keep ref on connection request endpoints until either accepted or
  rejected so it doesn't get freed early.

- Endpoint flags now need to be set via atomic bitops because they can
  be set on both the iw_cxgb3 workqueue thread and user disconnect
  threads.

- Don't move out of CLOSING too early due to multiple calls to
  iwch_ep_disconnect.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:22:38 -07:00
Steve Wise
fa0d4c11c4 RDMA/cxgb3: Handle port events properly
Massage the err_handler upcall into an event handler upcall, pass
netdev port events to the cxgb3 ULPs and generate RDMA port events
based on LLD port events.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:22:38 -07:00
Steve Wise
b496fe82d4 RDMA/cxgb3: Set the appropriate IO channel in rdma_init work requests
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:22:37 -07:00
Steve Wise
3793d2fc3e RDMA/cxgb3: iwch_unregister_device leaks memory
The iwcm struct mem is never freed.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-09-05 20:22:36 -07:00
Roland Dreier
4a7eca824c Merge branches 'ehca', 'misc', 'mlx4', 'mthca' and 'nes' into for-linus 2009-06-23 10:38:47 -07:00
Peter Huewe
716abb1fdf RDMA: Add __init/__exit macros to addr.c and cma.c
Add __init and __exit annotations to the module_init/module_exit
functions from drivers/infiniband/core/addr.c and cma.c.

Signed-off-by: Peter Huewe <peterhuewe@gmx.de>
Acked-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-06-23 10:38:42 -07:00
Alexander Schmidt
1d4d6da535 IB/ehca: Bump version number
Increment version number for DMEM toleration.

Signed-off-by: Alexander Schmidt <alexs@linux.vnet.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-06-23 10:30:04 -07:00
Roland Dreier
99987bea47 IB/mthca: Replace dma_sync_single() use with proper functions
dma_sync_single() is deprecated now, and the use in mthca is wrong:
there should be a dma_sync_single_for_cpu() before touching the memory
from the CPU, and a dma_sync_single_for_device() afterwards.  Fix
this, prompted by a kick in the pants from a patch from FUJITA
Tomonori <fujita.tomonori@lab.ntt.co.jp>.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-06-22 23:04:13 -07:00
Faisal Latif
68237a0ff8 RDMA/nes: Fix FIN state handling under error conditions
During cluster testing, one QP was not closed, as FIN is not handled
properly when its rexmit count expires or in some cases when RST is is
received after sending FIN.  The reason is that the cm_id does not get
decremented under these conditions.

Signed-off-by: Faisal Latif <faisal.latif@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-06-22 22:53:28 -07:00
Faisal Latif
66388d67a0 RDMA/nes: Fix max_qp_init_rd_atom returned from query device
In nes_query_device(), max_qp_init_rd_atom is incorrectly set to
max_qp_wr.  This was found when a test application had a dapl async
event error.

Signed-off-by: Faisal Latif <faisal.latif@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-06-22 22:52:30 -07:00