Commit Graph

740 Commits

Author SHA1 Message Date
Michael S. Tsirkin 2cbe19d48a IB/mthca: Fix off-by-one in mthca SRQ creation
All HCAs (not just mem-free) need a spare SRQ entry, so bump srq->max
by 1 in all cases.

Noted by Jack Morgenstein <jackm@mellanox.co.il>

Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 12:50:38 -07:00
Roland Dreier 73fbe8be73 IPoIB: Check for DMA mapping error for TX packets
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 12:50:38 -07:00
Roland Dreier 1031bfb93a RDMA/amso1100: Fix build with debugging off
Since pr_debug() has changed from a macro to an inline function when
DEBUG is not defined, its arguments now need to be defined even when
debugging is off.  Therefore to_event_str() and to_qp_state_str() need
to be moved out of #ifdef DEBUG.  The compiler will throw the
definitions away if DEBUG is not defined, but it needs to be able to
see that the functions exist.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 12:50:38 -07:00
Sean Hefty 82a9c16a10 IB/cm: Send DREP in response to unmatched DREQ
Currently a DREP is only sent in response to a DREQ if a connection
has been found matching the DREQ, and it is in the proper state.  Once
a DREP is sent, the local connection moves into timewait.  Duplicate
DREQs received while in this state result in re-sending the DREP.

However, it's likely that the local connection will enter and exit
timewait before the remote side times out a lost DREP and resends a DREQ.
To handle this, we send a DREP in response to a DREQ, even if a local
connection is not found.  This avoids maintaining disconnected
id's in timewait states for excessively long times, just to handle a
lost DREP.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 12:50:38 -07:00
Sean Hefty 8575329d4f IB/cm: Fix timewait crash after module unload
If the ib_cm module is unloaded while id's are still in timewait, the
CM will destroy the work queue used to process timewait.  Once the
id's exit timewait, their timers will fire, leading to a crash trying
to access the destroyed work queue.

We need to track id's that are in timewait, and cancel their deferred
work on module unload.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 12:50:38 -07:00
Jack Morgenstein a8bf4e7717 IB/mthca: Query port fix
Fill in "max_vl_num" (encoded according to VLCap field in the PortInfo MAD)
and "init_type_reply" values in the ib_query_port() verb.

Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 12:50:36 -07:00
Ishai Rabinovitz 01cb9bcbd3 IB/srp: Enable multiple connections to the same target
Enable multiple concurrent connections to the same SRP target:

1) Use port GUID instead of node GUID in the initiator port
   identifier.  This allows connections to be made from multiple HCA
   ports at the same time.
2) Let the user specify the identifier extention when adding the
   device.  This allows userspace to make multiple connections even
   from the same port, if it wants too.

Without this, only one connection can be made from any given HCA, even
if it has multiple ports, because we don't use multi-channel mode, so
targets will only allow one connection from a given initiator port ID.

Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 12:49:05 -07:00
Ishai Rabinovitz 9b0af401aa IB/srp: Remove redundant memset()
scsi_host_alloc() already allocates with kzalloc(), so the struct Scsi_Host
is zeroed out, including the private data portion.  Remove the redundant
memset that zeros this out again in the SRP initiator.

Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 09:51:14 -07:00
Tom Tucker e52e6080ca RDMA/amso1100: Add spinlocks to serialize ib_post_send/ib_post_recv
The AMSO driver was not thread-safe in the post WR code and had
code that would sleep if the WR post FIFO was full. Since these
functions can be called on interrupt level I changed the sleep to a
udelay.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-10 09:51:13 -07:00
David Howells 7d12e780e0 IRQ: Maintain regs pointer globally rather than passing to IRQ handlers
Maintain a per-CPU global "struct pt_regs *" variable which can be used instead
of passing regs around manually through all ~1800 interrupt handlers in the
Linux kernel.

The regs pointer is used in few places, but it potentially costs both stack
space and code to pass it around.  On the FRV arch, removing the regs parameter
from all the genirq function results in a 20% speed up of the IRQ exit path
(ie: from leaving timer_interrupt() to leaving do_IRQ()).

Where appropriate, an arch may override the generic storage facility and do
something different with the variable.  On FRV, for instance, the address is
maintained in GR28 at all times inside the kernel as part of general exception
handling.

Having looked over the code, it appears that the parameter may be handed down
through up to twenty or so layers of functions.  Consider a USB character
device attached to a USB hub, attached to a USB controller that posts its
interrupts through a cascaded auxiliary interrupt controller.  A character
device driver may want to pass regs to the sysrq handler through the input
layer which adds another few layers of parameter passing.

I've build this code with allyesconfig for x86_64 and i386.  I've runtested the
main part of the code on FRV and i386, though I can't test most of the drivers.
I've also done partial conversion for powerpc and MIPS - these at least compile
with minimal configurations.

This will affect all archs.  Mostly the changes should be relatively easy.
Take do_IRQ(), store the regs pointer at the beginning, saving the old one:

	struct pt_regs *old_regs = set_irq_regs(regs);

And put the old one back at the end:

	set_irq_regs(old_regs);

Don't pass regs through to generic_handle_irq() or __do_IRQ().

In timer_interrupt(), this sort of change will be necessary:

	-	update_process_times(user_mode(regs));
	-	profile_tick(CPU_PROFILING, regs);
	+	update_process_times(user_mode(get_irq_regs()));
	+	profile_tick(CPU_PROFILING);

I'd like to move update_process_times()'s use of get_irq_regs() into itself,
except that i386, alone of the archs, uses something other than user_mode().

Some notes on the interrupt handling in the drivers:

 (*) input_dev() is now gone entirely.  The regs pointer is no longer stored in
     the input_dev struct.

 (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking.  It does
     something different depending on whether it's been supplied with a regs
     pointer or not.

 (*) Various IRQ handler function pointers have been moved to type
     irq_handler_t.

Signed-Off-By: David Howells <dhowells@redhat.com>
(cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 15:10:12 +01:00
Dave Jones 038b0a6d8d Remove all inclusions of <linux/config.h>
kbuild explicitly includes this at build time.

Signed-off-by: Dave Jones <davej@redhat.com>
2006-10-04 03:38:54 -04:00
Matt LaPlante cab00891c5 Still more typo fixes
Signed-off-by: Adrian Bunk <bunk@stusta.de>
2006-10-03 22:36:44 +02:00
Hoang-Nam Nguyen e5a0106901 IB/ehca: Tweak trace message format
Add an extra space to make things more readable.

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-02 14:52:17 -07:00
Hoang-Nam Nguyen 0f248d9cde IB/ehca: Fix device registration
Move the call to ib_register_device() later, since a device should not
be registered until it is completely read to be used.  This fixes
crashes that occur if an upper-layer driver such as IPoIB is loaded
before the ehca module.

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-02 14:52:17 -07:00
Ralph Campbell 13b18c8617 IB/ipath: Fix RDMA reads
The PSN used to generate the request following a RDMA read was
incorrect and some state booking wasn't maintained correctly.  This
patch fixes that.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
2006-10-02 14:52:17 -07:00
Krishna Kumar 3f168d2b66 RDMA/cma: Optimize error handling
Reorganize code relating to cma_get_net_info() and rdam_create_id() to
optimize error case handling (no need to alloc memory/etc. as part of
rdma_create_id() if input parameters are wrong).

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-02 14:52:16 -07:00
Krishna Kumar 94de178ac6 RDMA/cma: Eliminate unnecessary remove_list
Eliminate remove_list by using list_del_init() instead during device
removal handling.

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-02 14:52:16 -07:00
Sean Hefty 8f0472d331 RDMA/cma: Set status correctly on route resolution error
On reporting a route error, also include the status for the error,
rather than indicating a status of 0 when an error has occurred.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-02 14:52:15 -07:00
Krishna Kumar 6e35aabee1 RDMA/cma: Fix device removal race
The race is as follows:

A process : cma_process_remove() calls cma_remove_id_dev(),
	    which sets id state to CMA_DEVICE_REMOVAL and
	    calls wait_event(dev_remove).

B process : cma_req_handler() had incremented dev_remove,
	    and calls cma_acquire_ib_dev() and on failure
	    calls cma_release_remove(), which does a
	    wake_up of cma_process_remove(). Then
	    cma_req_handler() calls rdma_destroy_id();

A Process : cma_remove_id_dev() gets woken and checks the
	    state of id, and since it is still (wrongly)
	    CMA_DEVICE_REMOVAL, it calls notify_user(id)
	    and if that fails, the caller - cma_process_remove()
	    calls rdma_destroy_id(id). Two processes can
	    call rdma_destroy_id(), resulting in one
	    de-referencing kfreed id_priv.

Fix is for process B to set CMA_DESTROYING in cma_req_handler()
so that process A will return instead of doing a rdma_destroy_id().

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-02 14:52:15 -07:00
Krishna Kumar 675a027c3d RDMA/cma: Fix leak of cm_ids in case of failures
cma_connect_ib() and cma_connect_iw() leak cm_id's in failure cases.

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-10-02 14:52:15 -07:00
Serge E. Hallyn 96b644bdec [PATCH] namespaces: utsname: use init_utsname when appropriate
In some places, particularly drivers and __init code, the init utsns is the
appropriate one to use.  This patch replaces those with a the init_utsname
helper.

Changes: Removed several uses of init_utsname().  Hope I picked all the
	right ones in net/ipv4/ipconfig.c.  These are now changed to
	utsname() (the per-process namespace utsname) in the previous
	patch (2/7)

[akpm@osdl.org: CIFS fix]
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Andrey Savochkin <saw@sw.ru>
Cc: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-02 07:57:21 -07:00
Dave Hansen d8c76e6f45 [PATCH] r/o bind mount prepwork: inc_nlink() helper
This is mostly included for parity with dec_nlink(), where we will have some
more hooks.  This one should stay pretty darn straightforward for now.

Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-01 00:39:30 -07:00
Linus Torvalds 9a69d1aecc Merge branch 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband
* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband: (33 commits)
  IB/ipath: Fix lockdep error upon "ifconfig ibN down"
  IB/ipath: Fix races with ib_resize_cq()
  IB/ipath: Support new PCIE device, QLE7142
  IB/ipath: Set CPU affinity early
  IB/ipath: Fix EEPROM read when driver is compiled with -Os
  IB/ipath: Fix and recover TXE piobuf and PBC parity errors
  IB/ipath: Change HT CRC message to indicate how to resolve problem
  IB/ipath: Clean up module exit code
  IB/ipath: Call mtrr_del with correct arguments
  IB/ipath: Flush RWQEs if access error or invalid error seen
  IB/ipath: Improved support for PowerPC
  IB/ipath: Drop unnecessary "(void *)" casts
  IB/ipath: Support multiple simultaneous devices of different types
  IB/ipath: Fix mismatch in shifts and masks for printing debug info
  IB/ipath: Fix compiler warnings and errors on non-x86_64 systems
  IB/ipath: Print more informative parity error messages
  IB/ipath: Ensure that PD of MR matches PD of QP checking the Rkey
  IB/ipath: RC and UC should validate SLID and DLID
  IB/ipath: Only allow complete writes to flash
  IB/ipath: Count SRQs properly
  ...
2006-09-29 15:18:22 -07:00
Al Viro 60cad5da57 [IPV4]: annotate inetdev.h helpers
inet_confirm_addr(), inet_ifa_byprefix(), ip_dev_find(), inet_make_mask() and
inet_ifa_match() annotated, along with inferred net-endian variables

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-09-28 18:01:05 -07:00
Bryan O'Sullivan 3d27b00457 IB/ipath: Fix lockdep error upon "ifconfig ibN down"
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:17:14 -07:00
Bryan O'Sullivan 7a26c47412 IB/ipath: Fix races with ib_resize_cq()
The resize CQ function changes the memory used to store the queue.
Other routines need to honor the lock before accessing the pointer
to the queue and verify that the head and tail are in range.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:17:12 -07:00
Bryan O'Sullivan bf3258ec41 IB/ipath: Support new PCIE device, QLE7142
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:17:10 -07:00
Bryan O'Sullivan c97d27d8a9 IB/ipath: Set CPU affinity early
This change moves around port assignment so that it happens before any
memory is allocated.  This allows memory to be allocated on an appropriate
CPU, which improves performance for users of /dev/ipath.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:17:07 -07:00
Bryan O'Sullivan 1a4e74a087 IB/ipath: Fix EEPROM read when driver is compiled with -Os
The EEPROM is read via programmable I/O pins. When the driver
is compiled -Os, the CPU can speculatively read the I/O
value before it is valid.  This patch fixes the problem.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:17:05 -07:00
Bryan O'Sullivan 89d1e09b6a IB/ipath: Fix and recover TXE piobuf and PBC parity errors
We can sometimes trigger parity errors due to processor speculative
reads to our write-combined memory (mostly seen on Woodcrest).   Add a
stats counter for these.

Factored out the sendbuffererror buffer cancellation code so it can be
used in the new handling; suppress likely subsequent error messages if
within two jiffies of the cancellation.

Also restore 2 dropped TXE lines on hwe_bitsextant noticed while
debugging.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:17:03 -07:00
Bryan O'Sullivan 510847750c IB/ipath: Change HT CRC message to indicate how to resolve problem
The system must be powercycled to clear a HT CRC error; reloading the
driver is not enough.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:17:01 -07:00
Bryan O'Sullivan 7227aac47d IB/ipath: Clean up module exit code
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:59 -07:00
Bryan O'Sullivan 957670a57e IB/ipath: Call mtrr_del with correct arguments
We were passing 0 for base and length, which worked on older kernels,
but it doesn't seem to any longer.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:57 -07:00
Bryan O'Sullivan 8d0208cb59 IB/ipath: Flush RWQEs if access error or invalid error seen
If the receiver goes into the error state, we need to flush the
posted receive WQEs.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:55 -07:00
Bryan O'Sullivan 1fd3b40fde IB/ipath: Improved support for PowerPC
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:53 -07:00
Bryan O'Sullivan 076fafcdee IB/ipath: Drop unnecessary "(void *)" casts
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:51 -07:00
Bryan O'Sullivan f62fe77ad2 IB/ipath: Support multiple simultaneous devices of different types
Prior to this change, the driver was not able to support a HT and PCIE
card simultaneously present in the same machine.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:49 -07:00
Bryan O'Sullivan 5659416207 IB/ipath: Fix mismatch in shifts and masks for printing debug info
Fixed mismatch in linkstate/trainingstate shifts and masks in the
IPATH_IBSTATE_MASK macro.  It kept some linktrainingstates
from being printed correctly in debug; no functionality issue unless
I misread the code.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:47 -07:00
Bryan O'Sullivan 0624b072f2 IB/ipath: Fix compiler warnings and errors on non-x86_64 systems
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:45 -07:00
Bryan O'Sullivan 8d588f8bb7 IB/ipath: Print more informative parity error messages
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:43 -07:00
Bryan O'Sullivan 6a553af286 IB/ipath: Ensure that PD of MR matches PD of QP checking the Rkey
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:41 -07:00
Bryan O'Sullivan 10aeb0e6d8 IB/ipath: RC and UC should validate SLID and DLID
This is required for IB conformance (spec ch. 9.6.1.5).

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:39 -07:00
Bryan O'Sullivan 7dae5bff2e IB/ipath: Only allow complete writes to flash
Don't allow a write to the eeprom from ipathfs unless the write is exactly
128 bytes and starts at offset 0.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:37 -07:00
Bryan O'Sullivan f3e93c7757 IB/ipath: Count SRQs properly
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:35 -07:00
Bryan O'Sullivan aa4eaed702 IB/ipath: Lock and count allocated CQs properly
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:34 -07:00
Bryan O'Sullivan 11b054fe1d IB/ipath: Clean up handling of GUID 0
Respond with an error to the SM if our GUID is 0, and don't allow the
user to set our GUID to 0.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:32 -07:00
Bryan O'Sullivan c78f6415e9 IB/ipath: Unregister from IB core early
This gives upper-level protocols a chance to unregister while the device
is still usable.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:29 -07:00
Bryan O'Sullivan 2c9446a1d6 IB/ipath: Support revision 2 InfiniPath PCIE devices
This also entailed a little GPIO-interrupt general cleanup.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:27 -07:00
Bryan O'Sullivan 9929b0fb0f IB/ipath: Driver support for userspace sharing of HW contexts
This allows multiple userspace processes to share a single hardware
context in a master/slave arrangement.  It is backwards binary compatible
with existing userspace.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:25 -07:00
Bryan O'Sullivan 221e31985b IB/ipath: Fix memory leak if allocation fails
If the second allocation failed, the first structure allocated in this
routine was not freed.

Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2006-09-28 11:16:23 -07:00