Commit Graph

1912 Commits

Author SHA1 Message Date
Ingo Molnar
9a13150109 Merge commit 'v2.6.26-rc8' into core/rcu 2008-06-26 09:24:23 +02:00
Eli Cohen
87afd448b1 IB/mthca: Clear ICM pages before handing to FW
Current memfree FW has a bug which in some cases, assumes that ICM
pages passed to it are cleared.  This patch uses __GFP_ZERO to
allocate all ICM pages passed to the FW.  Once firmware with a fix is
released, we can make the workaround conditional on firmware version.

This fixes the bug reported by Arthur Kepner <akepner@sgi.com> here:
http://lists.openfabrics.org/pipermail/general/2008-May/050026.html

Cc: <stable@kernel.org>
Signed-off-by: Eli Cohen <eli@mellanox.co.il>

[ Rewritten to be a one-liner using __GFP_ZERO instead of vmap()ing
  ICM memory and memset()ing it to 0. - Roland ]

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-06-23 09:29:58 -07:00
Ingo Molnar
1e74f9cbbb Merge branch 'linus' into core/rcu 2008-06-23 11:29:11 +02:00
Arnd Bergmann
6b0ee363b2 infiniband-ucma: BKL pushdown
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
2008-06-20 14:05:57 -06:00
Jonathan Corbet
f2b9857eee Add a bunch of cycle_kernel_lock() calls
All of the open() functions which don't need the BKL on their face may
still depend on its acquisition to serialize opens against driver
initialization.  So make those functions acquire then release the BKL to be
on the safe side.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
2008-06-20 14:05:53 -06:00
Jonathan Corbet
057e7c7ff9 infiniband: more BKL pushdown
Be extra-cautious and protect the remaining open() functions.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
2008-06-20 14:05:51 -06:00
Jonathan Corbet
d21c95c569 Add "no BKL needed" comments to several drivers
This documents the fact that somebody looked at the relevant open()
functions and concluded that, due to their trivial nature, no locking was
needed.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
2008-06-20 14:05:50 -06:00
Jack Morgenstein
fb77bcef9f IB/uverbs: Fix check of is_closed flag check in ib_uverbs_async_handler()
Commit 1ae5c187 ("IB/uverbs: Don't store struct file * for event
files") changed the way that closed files are handled in the uverbs
code.  However, after the conversion, is_closed flag is checked
incorrectly in ib_uverbs_async_handler().  As a result, no async
events are ever passed to applications.

Found by: Ronni Zimmerman <ronniz@mellanox.co.il>

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-06-18 15:36:38 -07:00
Ingo Molnar
766d02786e Merge branch 'linus' into core/rcu 2008-06-16 11:23:36 +02:00
Roland Dreier
24797a3442 RDMA/nes: Fix off-by-one in nes_reg_user_mr() error path
nes_reg_user_mr() should fail if page_count becomes >= 1024 * 512
rather than just testing for strict >, because page_count is
essentially used as an index into an array with 1024 * 512 entries, so
allowing the loop to continue with page_count == 1024 * 512 means that
memory after the end of the array is corrupted.  This leads to a crash
triggerable by a userspace application that requests registration of a
too-big region.

Also get rid of the call to pci_free_consistent() here to avoid
corrupting state with a double free, since the same memory will be
freed in the code jumped to at reg_user_mr_err.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-06-10 12:29:49 -07:00
Roland Dreier
4c0283fc56 IB/core: Remove IB_DEVICE_SEND_W_INV capability flag
In 2.6.26, we added some support for send with invalidate work
requests, including a device capability flag to indicate whether a
device supports such requests.  However, the support was incomplete:
the completion structure was not extended with a field for the key
contained in incoming send with invalidate requests.

Full support for memory management extensions (send with invalidate,
local invalidate, fast register through a send queue, etc) is planned
for 2.6.27.  Since send with invalidate is not very useful by itself,
just remove the IB_DEVICE_SEND_W_INV bit before the 2.6.26 final
release; we will add an IB_DEVICE_MEM_MGT_EXTENSIONS bit in 2.6.27,
which makes things simpler for applications, since they will not have
quite as confusing an array of fine-grained bits to check.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-06-09 09:58:42 -07:00
Roland Dreier
8079ffa0e1 IB/umem: Avoid sign problems when demoting npages to integer
On a 64-bit architecture, if ib_umem_get() is called with a size value
that is so big that npages is negative when cast to int, then the
length of the page list passed to get_user_pages(), namely

	min_t(int, npages, PAGE_SIZE / sizeof (struct page *))

will be negative, and get_user_pages() will immediately return 0 (at
least since 900cf086, "Be more robust about bad arguments in
get_user_pages()").  This leads to an infinite loop in ib_umem_get(),
since the code boils down to:

	while (npages) {
		ret = get_user_pages(...);
		npages -= ret;
	}

Fix this by taking the minimum as unsigned longs, so that the value of
npages is never truncated.

The impact of this bug isn't too severe, since the value of npages is
checked against RLIMIT_MEMLOCK, so a process would need to have an
astronomical limit or have CAP_IPC_LOCK to be able to trigger this,
and such a process could already cause lots of mischief.  But it does
let buggy userspace code cause a kernel lock-up; for example I hit
this with code that passes a negative value into a memory registartion
function where it is promoted to a huge u64 value.

Cc: <stable@kernel.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-06-06 21:38:37 -07:00
Ralph Campbell
27676a3e16 IB/ipath: Fix SM trap forwarding
SM/SMA traps received by the ipath driver should be forwarded to the
SM if it is running on the host.  The ib_ipath driver was incorrectly
replying with "bad method."

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-06-06 11:23:29 -07:00
Joachim Fenkes
088af1543c IB/ehca: Reject send WRs only for RESET, INIT and RTR state
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-06-06 11:21:33 -07:00
Ralph Campbell
03031f71c7 IB/ipath: Fix device capability flags
The driver supports a few features (RNR NAK, port active event, SRQ
resize) that were not reported in the device capability flags.  This
patch fixes that.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-26 15:22:17 -07:00
Roland Dreier
e8ffef73c8 IB/ipath: Avoid test_bit() on u64 SDMA status value
Gabriel C <nix.or.die@googlemail.com> pointed out that when the x86
bitops are updated to operate on unsigned long, the code in
sdma_abort_task() will produce warnings:

    drivers/infiniband/hw/ipath/ipath_sdma.c: In function 'sdma_abort_task':
    drivers/infiniband/hw/ipath/ipath_sdma.c:267: warning: passing argument 2 of 'constant_test_bit' from incompatible pointer type

and so on, because it uses test_bit() to operation on a u64 value
(returned by ipath_read_kref64() for a hardware register).

Fix up these warnings by converting the test_bit() operations to &ing
with appropriate symbolic defines of the bits within the hardware
register.  This has the benign side-effect of making the code more
self-documenting as well.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-26 15:20:34 -07:00
Linus Torvalds
c2448278e3 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IB/mad: Fix kernel crash when .process_mad() returns SUCCESS|CONSUMED
  IPoIB: Test for NULL broadcast object in ipiob_mcast_join_finish()
  MAINTAINERS: Add cxgb3 and iw_cxgb3 NIC and iWARP driver entries
  IB/mlx4: Fix creation of kernel QP with max number of send s/g entries
  IB/mthca: Fix max_sge value returned by query_device
  RDMA/cxgb3: Fix uninitialized variable warning in iwch_post_send()
  IB/mlx4: Fix uninitialized-var warning in mlx4_ib_post_send()
  IB/ipath: Fix UC receive completion opcode for RDMA WRITE with immediate
  IB/ipath: Fix printk format for ipath_sdma_status
2008-05-23 11:11:44 -07:00
Dave Olson
5a4f2b6752 IB/mad: Fix kernel crash when .process_mad() returns SUCCESS|CONSUMED
If a low-level driver returns IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED,
handle_outgoing_dr_smp() doesn't clean up properly.  The fix is to
kfree the local data and break, rather than falling through.  This was
observed with the ipath driver, but could happen with any driver.

This fixes <https://bugs.openfabrics.org/show_bug.cgi?id=1027>.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-23 10:52:59 -07:00
Mike Travis
5d7bfd0c4d infiniband: use performance variant for_each_cpu_mask_nr
Change references from for_each_cpu_mask to for_each_cpu_mask_nr
where appropriate

Reviewed-by: Paul Jackson <pj@sgi.com>
Reviewed-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-23 18:39:06 +02:00
Jack Morgenstein
e1d50dce5a IPoIB: Test for NULL broadcast object in ipiob_mcast_join_finish()
We saw a kernel oops in our regression testing when a multicast "join
finish" occurred just after the interface was -- this is
<https://bugs.openfabrics.org/show_bug.cgi?id=1040>.  The test
randomly causes the HCA physical port to go down then up.

The cause of this is that ipoib_mcast_join_finish() processing happen
just after ipoib_mcast_dev_flush() was invoked (in which case the
broadcast pointer is NULL).  This patch tests for and handles the case
where priv->broadcast is NULL.

Cc: <stable@kernel.org>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-20 15:41:09 -07:00
Roland Dreier
cd155c1c7c IB/mlx4: Fix creation of kernel QP with max number of send s/g entries
When creating a kernel QP where the consumer asked for a send queue
with lots of scatter/gater entries, set_kernel_sq_size() incorrectly
returned an error if the send queue stride is larger than the
hardware's maximum send work request descriptor size.  This is not a
problem; the only issue is to make sure that the actual descriptors
used do not overflow the maximum descriptor size, so check this instead.

Clamp the returned max_send_sge value to be no bigger than what
query_device returns for the max_sge to avoid confusing hapless users,
even if the hardware is capable of handling a few more s/g entries.

This bug caused NFS/RDMA mounts to fail when the server adapter used
the mlx4 driver.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-20 14:00:02 -07:00
Greg Kroah-Hartman
6c06aec248 IB: fix race in device_create
There is a race from when a device is created with device_create() and
then the drvdata is set with a call to dev_set_drvdata() in which a
sysfs file could be open, yet the drvdata will be NULL, causing all
sorts of bad things to happen.

This patch fixes the problem by using the new function,
device_create_drvdata().

Cc: Kay Sievers <kay.sievers@vrfy.org>
Reviewed-by: Roland Dreier <rolandd@cisco.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-05-20 13:31:55 -07:00
Franck Bui-Huu
82524746c2 rcu: split list.h and move rcu-protected lists into rculist.h
Move rcu-protected lists from list.h into a new header file rculist.h.

This is done because list are a very used primitive structure all over the
kernel and it's currently impossible to include other header files in this
list.h without creating some circular dependencies.

For example, list.h implements rcu-protected list and uses rcu_dereference()
without including rcupdate.h.  It actually compiles because users of
rcu_dereference() are macros.  Others RCU functions could be used too but
aren't probably because of this.

Therefore this patch creates rculist.h which includes rcupdates without to
many changes/troubles.

Signed-off-by: Franck Bui-Huu <fbuihuu@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Josh Triplett <josh@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-19 10:01:37 +02:00
Roland Dreier
12103dca52 IB/mthca: Fix max_sge value returned by query_device
The mthca driver returns the maximum number of scatter/gather entries
returned by the firmware as the max_sge value when device properties
are queried.  However, the firmware also reports a limit on the
maximum descriptor size allowed, and because mthca takes into account
the worst case send request overhead when checking whether to allow a
QP to be created, the largest number of scatter/gather entries that
can be used with mthca may be limited by the maximum descriptor size
rather than just by the actual s/g entry limit.

This means that applications cannot actually create QPs with
max_send_sge equal to the limit returned by ib_query_device().  Fix
this by checking if the maximum descriptor size imposes a lower limit
and if so returning that lower limit.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-16 14:58:44 -07:00
Roland Dreier
21609ae3ef RDMA/cxgb3: Fix uninitialized variable warning in iwch_post_send()
drivers/infiniband/hw/cxgb3/iwch_qp.c: In function 'iwch_post_send':
    drivers/infiniband/hw/cxgb3/iwch_qp.c:232: warning: 't3_wr_flit_cnt' may be used uninitialized in this function

This is what akpm describes as "the dopey
gcc-doesn't-know-that-foo(&var)-writes-to-var problem."

Signed-off-by: Roland Dreier <rolandd@cisco.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
2008-05-16 14:58:40 -07:00
Andrew Morton
a3d8e1591d IB/mlx4: Fix uninitialized-var warning in mlx4_ib_post_send()
drivers/infiniband/hw/mlx4/qp.c: In function 'mlx4_ib_post_send':
    drivers/infiniband/hw/mlx4/qp.c:1460: warning: 'seglen' may be used uninitialized in this function

This is the dopey gcc-doesn't-know-that-foo(&var)-writes-to-var problem.

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-16 14:28:30 -07:00
Ralph Campbell
df3f0da8db IB/ipath: Fix UC receive completion opcode for RDMA WRITE with immediate
When I fixed the RC receive completion opcode in 2bfc8e9e ("IB/ipath:
Return the correct opcode for RDMA WRITE with immediate"), I forgot to
fix UC, which had the same problem for RDMA write with immediate
returning the wrong opcode.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-15 16:37:25 -07:00
Roland Dreier
cd80ec6f81 IB/ipath: Fix printk format for ipath_sdma_status
Commit f018c7e1 ("IB/ipath: Change ipath_devdata.ipath_sdma_status to be
unsigned long") changed ipath_sdma_status to be unsigned long, but left
a few debug messages that printed it out with a %016llx format, which
generates the warnings

    drivers/infiniband/hw/ipath/ipath_sdma.c:348: warning: format '%016llx' expects type 'long long unsigned int', but argument  3 has type 'long unsigned int'
    drivers/infiniband/hw/ipath/ipath_sdma.c:618: warning: format '%016llx' expects type 'long long unsigned int', but argument  3 has type 'long unsigned int'

Fix this by changing the format used to print out the value to %08lx
(8 hex digits are now sufficient, because the highest bit used is 31).

Warnings reported by Randy Dunlap <randy.dunlap@oracle.com>.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-15 15:28:55 -07:00
Steve Wise
a58e58fafd RDMA/cxgb3: Wrap the software send queue pointer as needed on flush
cxio_flush_sq() was failing to wrap around the software send queue
causing garbage completion entries on a flush operation.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-13 11:52:55 -07:00
Roland Dreier
f018c7e177 IB/ipath: Change ipath_devdata.ipath_sdma_status to be unsigned long
Andrew Morton <akpm@linux-foundation.org> pointed out that bitops
should take an unsigned long * arg.  However, the ipath driver was
doing bitops on struct ipath_devdata.ipath_sdma_status, which is u64.
Change this member to unsigned long to avoid tons of warnings when x86
fixes the bitops to take unsigned long * instead of void *.

Also, change the IPATH_SDMA_RUNNING and IPATH_SDMA_SHUTDOWN bit
numbers to 30 and 31 (instead of 62 and 63) so that we're not setting
another booby trap for someone who tries to make ipath work on a
32-bit architecture.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-13 11:51:23 -07:00
Pavel Emelyanov
40d97692fb IB/ipath: Make ipath_portdata work with struct pid * not pid_t
The official reason is "with the presence of pid namespaces in the
kernel using pid_t-s inside one is no longer safe."

But the reason I fix this right now is the following:

About a month ago (when 2.6.25 was not yet released) there still was a
one last caller of a to-be-deprecated-soon function find_pid() - the
kill_proc() function, which in turn was only used by nfs callback
code.

During the last merge window, this last caller was finally eliminated
by some NFS patch(es) and I was about to finally kill this kill_proc()
and find_pid(), but found, that I was late and the kill_proc is now
called from the ipath driver since commit 58411d1c ("IB/ipath: Head of
Line blocking vs forward progress of user apps").

So here's a patch that fixes this code to use struct pid * and (!)
the kill_pid routine.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-13 11:45:32 -07:00
Ralph Campbell
74116f580b IB/ipath: Fix RDMA read response sequence checking
If an out of sequence RDMA read response middle or last packet is
received, we should only resend the RDMA read request on the first
out of sequence packet and drop subsequent out of sequence packets
otherwise, we get "too many retries".

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-13 11:42:20 -07:00
Ralph Campbell
e509be898d IB/ipath: Fix many locking issues when switching to error state
The send DMA hardware queue voided a number of prior assumptions about
when a send is complete which led to completions being generated out of
order.  There were also a number of locking issues when switching the QP
to the error or reset states, and we implement the IB_QPS_SQD state.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-13 11:41:29 -07:00
Ralph Campbell
53dc1ca194 IB/ipath: Fix RC and UC error handling
When errors are detected in RC, the QP should transition to the
IB_QPS_ERR state, not the IB_QPS_SQE state. Also, when the error is on
the responder side, the receive work completion error was incorrect
(remote vs. local).

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-13 11:40:25 -07:00
Roland Dreier
dd37818dbd RDMA/nes: Fix up nes_lro_max_aggr module parameter
Fix some bugs with the max_aggr module parameter added with LRO support:

 - The module parameter value ignored and not actually used to set
   lro_mgr.max_aggr.
 - MODULE_PARM_DESC had a typo "_mro_" instead of "_lro_" so it didn't
   end up describing the actual module parameter.
 - The nes_lro_max_aggr variable was declared as unsigned, but the
   module_param line said "int" instead of "uint" for the type.
 - The default value for the parameter was stuck in the permissions
   field of module_param, which led to nonsensical permissions for the
   file under /sys/module/iw_nes/param.
 - The parameter was used in only one file but defined in another, which
   led to the variable being global for no good reason.  Move everything
   related to the parameter to the file nes_hw.c where it is actually
   used.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-13 11:27:25 -07:00
Stefan Roscher
12137c593d IB/ehca: Wait for async events to finish before destroying QP
This is necessary because, in a multicore environment, a race between
uverbs async handler and destroy QP could occur.

Signed-off-by: Stefan Roscher <stefan.roscher at de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-07 11:35:06 -07:00
John Gregor
ab69b3cf12 IB/ipath: Fix SDMA error recovery in absence of link status change
What's fixed:

    in ipath_cancel_sends()

        We need to unconditionally set ABORTING.  So, swap the tests
        so the set_bit() isn't shadowed by the &&.

        If we've disarmed the piobufs, then we need to unconditionally
        set DISARMED.  So, move it out from the overly protective if
        at the bottom.

    in sdma_abort_task()

        Abort_task was written knowing that the SDMA engine would always
        be reset (and restarted) on error.  A recent change broke that
        fundamental assumption by taking the restart portion and making
        it conditional on a link status change.  But, SDMA can go boom
        without a link status change in some conditions.

Signed-off-by: John Gregor <john.gregor@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-07 11:01:10 -07:00
Dave Olson
e2ab41cae4 IB/ipath: Need to always request and handle PIO avail interrupts
Now that we always use PIO for vl15 on 7220, we could get stuck forever
if we happened to run out of PIO buffers from the verbs code, because
the setup code wouldn't run; the interrupt was also ignored if SDMA was
supported.  We also have to reduce the pio update threshold if we have
fewer kernel buffers than the existing threshold.

Clean up the initialization a bit to get ordering safer and more
sensible, and use the existing ipath_chg_kernavail call to do init,
rather than doing it separately.

Drop unnecessary clearing of pio buffer on pio parity error.

Drop incorrect updating of pioavailshadow when exitting freeze mode
(software state may not match chip state if buffer has been allocated
and not yet written).

If we couldn't get a kernel buffer for a while, make sure we are
in sync with hardware, mainly to handle the exitting freeze case.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-07 11:00:15 -07:00
Michael Albaugh
2889d1ef12 IB/ipath: Fix count of packets received by kernel
The loop in ipath_kreceive() that processes packets increments the
loop-index 'i' once too often, because the exit condition does not
depend on it, and is checked after the increment. By adding a check for
!last to the iterator in the for loop, we correct that in a way that is
not so likely to be re-broken by changes in the loop body.

Signed-off-by: Michael Albaugh <micheal.albaugh@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-07 10:59:23 -07:00
Ralph Campbell
2bfc8e9edf IB/ipath: Return the correct opcode for RDMA WRITE with immediate
This patch fixes a bug in the RC responder which generates a completion
entry with the wrong opcode when an RDMA WRITE with immediate is received.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-07 10:58:50 -07:00
Dave Olson
b4d390d8d2 IB/ipath: Fix bug that can leave sends disabled after freeze recovery
The semantics of cancel_sends changed, but the code using it was missed.
Don't leave sends and pioavail updates disabled, and add a comment as to
why the force update is needed.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-07 10:57:48 -07:00
Ralph Campbell
6e87d15007 IB/ipath: Only increment SSN if WQE is put on send queue
If a send work request has immediate errors and is not put on the
send queue, we shouldn't update any of the QP state.

The increment of the SSN wasn't obeying this.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-07 10:57:14 -07:00
Michael Albaugh
5f51efc195 IB/ipath: Only warn about prototype chip during init
We warn about prototype chips, but the function that checks for
support is also called as a result of a get_portinfo request, which
can clutter the logs.

Restrict warning to only appear during initialization.

Signed-off-by: Michael Albaugh <michael.albaugh@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-07 10:56:47 -07:00
Roland Dreier
273748cc90 RDMA/cxgb3: Fix severe limit on userspace memory registration size
Currently, iw_cxgb3 is severely limited on the amount of userspace
memory that can be registered in in a single memory region, which
causes big problems for applications that expect to be able to
register 100s of MB.

The problem is that the driver uses a single kmalloc()ed buffer to
hold the physical buffer list (PBL) for the entire memory region
during registration, which means that 8 bytes of contiguous memory are
required for each page of memory being registered.  For example, a 64
MB registration will require 128 KB of contiguous memory with 4 KB
pages, and it unlikely that such an allocation will succeed on a busy
system.

This is purely a driver problem: the temporary page list buffer is not
needed by the hardware, so we can fix this by writing the PBL to the
hardware in page-sized chunks rather than all at once.  We do this by
splitting the memory registration operation up into several steps:

 - Allocate PBL space in adapter memory for the full registration
 - Copy PBL to adapter memory in chunks
 - Allocate STag and enable memory region

This also allows several other cleanups to the __cxio_tpt_op()
interface and related parts of the driver.

This change leaves the reregister memory region and memory window
operations broken, but they already didn't work due to other
longstanding bugs, so fixing them will be left to a later patch.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-06 15:56:22 -07:00
Roland Dreier
0e9913362a RDMA/cxgb3: Don't add PBL memory to gen_pool in chunks
Current iw_cxgb3 code adds PBL memory to the driver's gen_pool in 2 MB
chunks.  This limits the largest single allocation that can be done to
the same size, which means that with 4 KB pages, each of which takes 8
bytes of PBL memory, the largest memory region that can be allocated
is 1 GB (256K PBL entries * 4 KB/entry).

Remove this limit by adding all the PBL memory in a single gen_pool
chunk, if possible.  Add code that falls back to smaller chunks if
gen_pool_add() fails, which can happen if there is not sufficient
contiguous lowmem for the internal gen_pool bitmap.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-06 15:03:38 -07:00
Stefan Roscher
cf04690885 IB/ehca: Fix function return types
Also remove duplicate assignment of local_ca_ack_delay and change
min_t check for local_ca_ack_delay to u8 instead of int.

Signed-off-by: Stefan Roscher <stefan.roscher at de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-05 15:51:49 -07:00
Steve Wise
77a8d5741f RDMA/cxgb3: Bump up the MPA connection setup timeout.
Testing on large clusters shows its way too short at 10 secs.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-02 10:57:09 -07:00
Steve Wise
c4d49776e8 RDMA/cxgb3: Silently ignore close reply after abort.
Remove bad BUG_ON() that can trigger in correct operation from
close_con_rpl().  It is possible to get a close_rpl message on a dead
connection.  The sequence is:

	- host refs ep for close exchange
	- host posts close_req
	- hw posts PEER_ABORT from incoming RST
	- host marks ep DEAD
	- host posts ABORT_RPL and releases ep resources
	- hw posts CLOSE_RPL
	- host derefs ep and ep freed.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-02 10:57:09 -07:00
Steve Wise
c8286944b8 RDMA/cxgb3: QP flush fixes
- Flush the QP only after the HW disables the connection.  Currently
  we flush the QP when transitioning to CLOSING.  This exposes a race
  condition where the HW can complete a RECV WR, for instance, -and-
  the SW can flush that same WR.

- Only call CQ event handlers on flush IFF we actually flushed something.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-02 10:56:57 -07:00
Eli Cohen
57ce41d1d1 IB/ipoib: Fix transmit queue stalling forever
Commit f56bcd80 ("IPoIB: Use separate CQ for UD send completions")
introduced a bug where the transmit queue could get stopped and never
woken up.  The problem is that send completions are only polled at the
end of the xmit function, so if the send queue fills up and the xmit
path stops the queue, then there is no way for send completions to
ever get polled, and so the transmit queue stays stopped forever.

Fix this by arming the send CQ just before posting the last send
request that fills the send queue.  Then, when the completion event
handler is called, drain the send CQ.  Since it is possible that not
enough send completions are in the CQ, verify that the the net queue
has been woken up after draining the send CQ, and if not arm a timer
and drain again at the timer function.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-30 20:02:45 -07:00
Roland Dreier
3ae15e1623 IB/mlx4: Fix off-by-one errors in calls to mlx4_ib_free_cq_buf()
When I merged bbf8eed1 ("IB/mlx4: Add support for resizing CQs") I
changed things around so that mlx4_ib_alloc_cq_buf() and
mlx4_ib_free_cq_buf() were used everywhere they could be.  However, I
screwed up the number of entries passed into mlx4_ib_alloc_cq_buf()
in a couple places -- the function bumps the number of entries
internally, so the caller shouldn't add 1 as well.

Passing a too-big value for the number of entries to mlx4_ib_free_cq_buf()
can cause the cleanup to go off the end of an array and corrupt
allocator state in interesting ways.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-30 19:52:55 -07:00
Glenn Streiff
7495ab6837 RDMA/nes: Formatting cleanup
Various cleanups:
	- Change // to /* .. */
	- Place whitespace around binary operators.
	- Trim down a few long lines.
	- Some minor alignment formatting for better readability.
	- Remove some silly tabs.

Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:54 -07:00
Eric Schneider
0e1de5d62e RDMA/nes: Add support for SFP+ PHY
This patch enables the iw_nes module for NetEffect RNICs to support
additional PHYs including SFP+ (referred to as ARGUS in the code).

Signed-off-by: Eric Schneider <eric.schneider@neteffect.com>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:54 -07:00
Faisal Latif
37dab4112d RDMA/nes: Use LRO
Signed-off-by: Faisal Latif <flatif@neteffect.com.
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:54 -07:00
Eli Cohen
b4132efa1a IPoIB: Copy child MTU from parent
When creating a child interface, copy the MTU information from the
parent.  Otherwise when the child's multicast join completes, the MTU
will not be updated since the code does

	dev->mtu = min(priv->mcast_mtu, priv->admin_mtu);

and priv->admin_mtu will be set to 0.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:53 -07:00
Roland Dreier
baaad380c0 IB/mthca: Avoid changing userspace ABI to handle DMA write barrier attribute
Commit cb9fbc5c ("IB: expand ib_umem_get() prototype") changed the
mthca userspace ABI to provide a way for userspace to indicate which
memory regions need the DMA write barrier attribute.  However, it is
possible to handle this without breaking existing userspace, by having
the mthca kernel driver recognize whether it is talking to old or new
userspace, depending on the size of the register MR structure passed in.

The only potential drawback of this is that is allows old userspace
(which has a bug with DMA ordering on large SGI Altix systems) to
continue to run on new kernels, but the advantage of allowing old
userspace to continue to work on unaffected systems seems to outweigh
this, and we can print a warning to push people to upgrade their
userspace.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:53 -07:00
Olaf Kirch
0bfe151cc4 IB/mthca: Avoid recycling old FMR R_Keys too soon
When a FMR is unmapped, mthca resets the map count to 0, and clears
the upper part of the R_Key which is used as the sequence counter.

This poses a problem for RDS, which uses ib_fmr_unmap as a fence
operation.  RDS assumes that after issuing an unmap, the old R_Keys
will be invalid for a "reasonable" period of time. For instance,
Oracle processes uses shared memory buffers allocated from a pool of
buffers.  When a process dies, we want to reclaim these buffers -- but
we must make sure there are no pending RDMA operations to/from those
buffers.  The only way to achieve that is by using unmap and sync the
TPT.

However, when the sequence count is reset on unmap, there is a high
likelihood that a new mapping will be given the same R_Key that was
issued a few milliseconds ago.

To prevent this, don't reset the sequence count when unmapping a FMR.

Signed-off-by: Olaf Kirch <olaf.kirch@oracle.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:53 -07:00
Stefan Roscher
d227fa7288 IB/ehca: Allocate event queue size depending on max number of CQs and QPs
If a lot of QPs fall into Error state at once and the EQ of the
respective HCA is too small, it might overrun, causing the eHCA driver
to stop processing completion events and calling the application's
completion handlers, effectively causing traffic to stop.

Fix this by limiting available QPs and CQs to a customizable max
count, and determining EQ size based on these counts and a worst-case
assumption.

Signed-off-by: Stefan Roscher <stefan.roscher@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:53 -07:00
Eli Cohen
f56bcd8013 IPoIB: Use separate CQ for UD send completions
Use a dedicated CQ for UD send completions. Also, do not arm the UD
send CQ, which reduces the number of interrupts generated.  This patch
farther reduces overhead by not calling poll CQ for every posted send
WR -- it does polls only when there 16 or more outstanding work requests.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:53 -07:00
Eli Dorfman
87528227df IB/iser: Count FMR alignment violations per session
Count FMR alignment violations per session as part of the iscsi
statistics.

Signed-off-by: Eli Dorfman <elid@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:52 -07:00
Eli Dorfman
6f735e36ba IB/iser: Move high-volume debug output to higher debug level
Add another level for debug.

Signed-off-by: Eli Dorfman <elid@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:52 -07:00
Hoang-Nam Nguyen
7df109d917 IB/ehca: handle negative return value from ibmebus_request_irq() properly
ehca_create_eq() was assigning a signed return value to an unsiged
local variable and then checking if the variable was < 0, which meant
that errors were always ignored.  Fix this by using one variable for
signed integer return values and another for u64 hcall return values.

Bug originally found by Roel Kluin <12o3l@tiscali.nl>.

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:52 -07:00
Steve Wise
f8b0dfd152 RDMA/cxgb3: Support peer-2-peer connection setup
Open MPI, Intel MPI and other applications don't respect the iWARP
requirement that the client (active) side of the connection send the
first RDMA message.  This class of application connection setup is
called peer-to-peer.  Typically once the connection is setup, _both_
sides want to send data.

This patch enables supporting peer-to-peer over the chelsio RNIC by
enforcing this iWARP requirement in the driver itself as part of RDMA
connection setup.

Connection setup is extended, when the peer2peer module option is 1,
such that the MPA initiator will send a 0B Read (the RTR) just after
connection setup.  The MPA responder will suspend SQ processing until
the RTR message is received and reply-to.

In the longer term, this will be handled in a standardized way by
enhancing the MPA negotiation so peers can indicate whether they
want/need the RTR and what type of RTR (0B read, 0B write, or 0B send)
should be sent.  This will be done by standardizing a few bits of the
private data in order to negotiate all this.  However this patch
enables peer-to-peer applications now and allows most of the required
firmware and driver changes to be done and tested now.

Design:

 - Add a module option, peer2peer, to enable this mode.

 - New firmware support for peer-to-peer mode:

	- a new bit in the rdma_init WR to tell it to do peer-2-peer
	  and what form of RTR message to send or expect.

	- process _all_ preposted recvs before moving the connection
	  into rdma mode.

	- passive side: defer completing the rdma_init WR until all
	  pre-posted recvs are processed.  Suspend SQ processing until
	  the RTR is received.

	- active side: expect and process the 0B read WR on offload TX
	  queue. Defer completing the rdma_init WR until all
	  pre-posted recvs are processed.  Suspend SQ processing until
	  the 0B read WR is processed from the offload TX queue.

 - If peer2peer is set, driver posts 0B read request on offload TX
   queue just after posting the rdma_init WR to the offload TX queue.

 - Add CQ poll logic to ignore unsolicitied read responses.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:52 -07:00
Steve Wise
ccaf10d0ad RDMA/cxgb3: Set the max_mr_size device attribute correctly
cxgb3 only supports 4GB memory regions.  The lustre RDMA code uses
this attribute and currently has to code around our bad setting.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:52 -07:00
Steve Wise
989a178069 RDMA/cxgb3: Correctly serialize peer abort path
Open MPI and other stress testing exposed a few bad bugs in handling
aborts in the middle of a normal close.  Fix these by:

 - serializing abort reply and peer abort processing with disconnect
   processing

 - warning (and ignoring) if ep timer is stopped when it wasn't running

 - cleaning up disconnect path to correctly deal with aborting and
   dead endpoints

 - in iwch_modify_qp(), taking a ref on the ep before releasing the qp
   lock if iwch_ep_disconnect() will be called.  The ref is dropped
   after calling disconnect.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:51 -07:00
Yevgeny Petrilin
e463c7b197 mlx4_core: Add a way to set the "collapsed" CQ flag
Extend the mlx4_cq_resize() API with a way to set the "collapsed" flag
for the CQ being created.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:50 -07:00
Arthur Kepner
cb9fbc5c37 IB: expand ib_umem_get() prototype
Add a new parameter, dmasync, to the ib_umem_get() prototype.  Use dmasync = 1
when mapping user-allocated CQs with ib_umem_get().

Signed-off-by: Arthur Kepner <akepner@sgi.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Jes Sorensen <jes@sgi.com>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Roland Dreier <rdreier@cisco.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: David Miller <davem@davemloft.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Grant Grundler <grundler@parisc-linux.org>
Cc: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 08:06:12 -07:00
Roland Dreier
31d1e340f0 RDMA/nes: Remove volatile qualifier from struct nes_hw_cq.cq_vbase
Remove the volatile qualifier from the cq_vbase member of struct
nes_hw_cq, and add an rmb() in the one place where it looks like
access order might make a difference.  As usual, removing a volatile
qualifier in a declaration is actually a bug fix, since a volatile
qualifier is not sufficient to make sure that aggressively
out-of-order CPUs don't reorder things and cause incorrect results.

For example, a CPU might speculatively execute reads of other cqe
fields before the NIC hardware has written those fields and before it
has set the NES_CQE_VALID bit (even though those reads come after the
test of the NES_CQE_VALID bit in program order), but then when the CPU
actually executes the conditional test of the NES_CQE_VALID, the bit
has been set, and the CPU will proceed with the results of the earlier
speculative execution and end up using bogus data.

This also gets rid of the warning:

    drivers/infiniband/hw/nes/nes_verbs.c: In function 'nes_destroy_cq':
    drivers/infiniband/hw/nes/nes_verbs.c:1978: warning: passing argument 3 of 'pci_free_consistent' discards qualifiers from pointer target type

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Yevgeny Petrilin
6296883ca4 mlx4_core: Move kernel doorbell management into core
In addition to mlx4_ib, there will be ethernet and FC consumers of
mlx4_core, so move the code for managing kernel doorbells into the
core module to avoid having to duplicate this multiple times.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Joachim Fenkes
14fb05b349 IB/ehca: Bump version number to 0026
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Joachim Fenkes
0455e36d81 IB/ehca: Make some module parameters bool, update descriptions
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Joachim Fenkes
a7607c9b11 IB/ehca: Remove mr_largepage parameter
Always enable large page support; didn't seem to cause problems for anyone.

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Joachim Fenkes
4da27d6d5b IB/ehca: Move high-volume debug output to higher debug levels
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Joachim Fenkes
863fb09fbf IB/ehca: Prevent posting of SQ WQEs if QP not in RTS
...as required by IB Spec, C10-29.

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Shirley Ma
bc7b3a36ba IPoIB: Handle 4K IB MTU for UD (datagram) mode
This patch enables IPoIB to use 4K UD messages (when the underlying
device and fabrics support a 4K MTU) by using two scatter buffers when
PAGE_SIZE is less than or equal to thhe HCA IB MTU size.  The first
buffer is for IPoIB header + GRH header, and the second buffer is the
IPoIB payload, which is 4K-4.

Signed-off-by: Shirley Ma <xma@us.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Chien Tung
bc5698f3ec RDMA/nes: Fix adapter reset after PXE boot
After PXE boot, the iw_nes driver does a full reset to ensure the card
is in a clean state.  However, it doesn't wait for firmware to
complete its work before issuing a port reset to enable the ports,
which leads to problems bringing up the ports.

The solution is to wait for firmware to complete its work before
proceeding with port reset.

This bug was flagged by Roland Dreier <rolandd@cisco.com>.

Cc: <stable@kernel.org>
Signed-off-by: Chien Tung <ctung@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Roland Dreier
e447703123 RDMA/nes: Print IPv4 addresses in a readable format
Use NIPQUAD_FMT instead of printing raw 32-bit hex quantities in
debugging output.

Acked-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:43 -07:00
Roland Dreier
2bd01c5d2e RDMA/nes: Use print_mac() to format ethernet addresses for printing
Removing open-coded MAC formats shrinks the source and the generated
code too, eg on x86-64:

add/remove: 0/0 grow/shrink: 0/4 up/down: 0/-103 (-103)
function                                     old     new   delta
make_cm_node                                 932     912     -20
nes_netdev_set_mac_address                   427     406     -21
nes_netdev_set_multicast_list               1148    1124     -24
nes_probe                                   2349    2311     -38

Acked-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:52:18 -07:00
Roland Dreier
bc751fe6ff IB/ipath: Correct capitalization "IntX" -> "INTx"
Match what the PCI specification uses.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-21 18:19:15 -07:00
Roland Dreier
44957572cc IB/ipath: Remove tests of PCI_MSI in ipath_iba7220.c
The PCI MSI interface is stubbed out properly so that all the
functions just return failure if PCI_MSI=n, so there's no reason to
have "#ifdef CONFIG_PCI_MSI" blocks in ipath_iba7220.c.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-21 18:19:15 -07:00
Roland Dreier
480f58e614 IB/ipath: Remove dependency on PCI_MSI || HT_IRQ
Before IBA7220 support was added, the ipath driver didn't support any
hardware unless PCI_MSI and/or HT_IRQ was enabled.  However, the
IBA7220 can generate INTx interrupts, so it makes sense to allow the
driver to be build even if PCI_MSI=n and HT_IRQ=n.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-21 18:19:14 -07:00
Roland Dreier
37a6ab5227 IB/ipath: Build IBA7220 code unconditionally
The new IBA7220 code added a call to ipath_init_iba7220_funcs() that
is compiled unconditionally, but only built the IBA7220 code if
PCI_MSI is enabled.  Fix this by building the IBA7220 file
unconditonally.

This fixes build breakage when PCI_MSI=n, HT_IRQ=y and
INFINIBAND_IPATH=y reported by Ingo Molnar <mingo@elte.hu>:

 drivers/built-in.o: In function `ipath_init_one':
 ipath_driver.c:(.devinit.text+0x1e5bc): undefined reference to `ipath_init_iba7220_funcs'

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-21 18:19:14 -07:00
Roland Dreier
88a8317bcd IB/ipath: Remove reference to dev->class_dev
Commit 124b4dcb ("IB/ipath: add calls to new 7220 code and enable in                                
build") inadvertently added core to set dev->class_dev.dev back into                                
ib_ipath.  This is completely redundant since commit 1912ffbb ("IB: Set                             
class_dev->dev in core for nice device symlink"), which removed                                     
class_dev setting from low-level drivers, and also will break the build
when class_dev is removed completely from struct ib_device.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-21 18:19:14 -07:00
Paul Bolle
9862874d21 IB/ipath: Fix module parameter description for disable_sma
Describe disable_sma parameter with its name rather than the internal
ib_ipath_disable_sma variable name, so that the description shows up
properly in modinfo.

Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Acked-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-21 18:19:13 -07:00
Roland Dreier
6a5546e76c RDMA/nes: Remove unneeded function declarations
Remove redundant static declarations of functions that are defined
before they are used in the source.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-21 18:19:12 -07:00
Linus Torvalds
e80ab411e5 Merge git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-2.6: (36 commits)
  SCSI: convert struct class_device to struct device
  DRM: remove unused dev_class
  IB: rename "dev" to "srp_dev" in srp_host structure
  IB: convert struct class_device to struct device
  memstick: convert struct class_device to struct device
  driver core: replace remaining __FUNCTION__ occurrences
  sysfs: refill attribute buffer when reading from offset 0
  PM: Remove destroy_suspended_device()
  Firmware: add iSCSI iBFT Support
  PM: Remove legacy PM (fix)
  Kobject: Replace list_for_each() with list_for_each_entry().
  SYSFS: Explicitly include required header file slab.h.
  Driver core: make device_is_registered() work for class devices
  PM: Convert wakeup flag accessors to inline functions
  PM: Make wakeup flags available whenever CONFIG_PM is set
  PM: Fix misuse of wakeup flag accessors in serial core
  Driver core: Call device_pm_add() after bus_add_device() in device_add()
  PM: Handle device registrations during suspend/resume
  block: send disk "change" event for rescan_partitions()
  sysdev: detect multiple driver registrations
  ...

Fixed trivial conflict in include/linux/memory.h due to semaphore header
file change (made irrelevant by the change to mutex).
2008-04-21 15:49:58 -07:00
Tony Jones
ee959b00c3 SCSI: convert struct class_device to struct device
It's big, but there doesn't seem to be a way to split it up smaller...

Signed-off-by: Tony Jones <tonyj@suse.de>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Cc: Roland Dreier <rolandd@cisco.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-04-19 19:10:33 -07:00
Greg Kroah-Hartman
0532193746 IB: rename "dev" to "srp_dev" in srp_host structure
This sets us up to be able to convert the srp_host to use a struct
device instead of a class_device.

Based on a original patch from Tony Jones, but split up into this piece
by Greg.

Signed-off-by: Tony Jones <tonyj@suse.de>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Reviewed-by: Roland Dreier <rolandd@cisco.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-04-19 19:10:30 -07:00
Tony Jones
f4e91eb4a8 IB: convert struct class_device to struct device
This converts the main ib_device to use struct device instead of struct
class_device as class_device is going away.

Signed-off-by: Tony Jones <tonyj@suse.de>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Cc: Roland Dreier <rolandd@cisco.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-04-19 19:10:30 -07:00
Matthew Wilcox
6188e10d38 Convert asm/semaphore.h users to linux/semaphore.h
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
2008-04-18 22:22:54 -04:00
Matthew Wilcox
d3135846f6 drivers: Remove unnecessary inclusions of asm/semaphore.h
None of these files use any of the functionality promised by
asm/semaphore.h.  It's possible that they rely on it dragging in some
unrelated header file, but I can't build all these files, so we'll have
fix any build failures as they come up.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
2008-04-18 22:16:32 -04:00
Erez Zilber
0a22ab92f5 IB/iser: Don't change itt endianness
The itt field in struct iscsi_data is not defined with any particular
endianness.  open-iscsi should use it as-is without byte-swapping it.
This fixes sparse warnings coming from doing ntohl(hdr->itt).

Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:35 -07:00
Jack Morgenstein
068c4ea1bb IB/mlx4: Update module version and release date
The mlx4_ib driver is stable enough for production use, so bump the
version number to 1.0 to indicate this.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:35 -07:00
Roland Dreier
9fdd5e5bf6 IPoIB: Handle case when P_Key is deleted and re-added at same index
If a P_Key is deleted and then re-added at the same index, then IPoIB
gets confused because __ipoib_ib_dev_flush() only checks whether the
index is the same without checking whether the P_Key was present, so
the interface is stopped when the P_Key is deleted, but the event when
the P_Key is re-added gets ignored and the interface never gets
restarted.

Also, switch to using ib_find_pkey() instead of ib_find_cached_pkey()
everywhere in IPoIB, since none of the places that look for P_Keys are
in a fast path or in non-sleeping context, and in general we want to
kill off the whole caching infrastructure eventually.  This also fixes
consistency problems caused because some IPoIB queries were cached and
some were uncached during the window where the cache was not updated.

Thanks to Venkata Subramonyam <vsubramo@cisco.com> for debugging this
problem and testing this fix.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:35 -07:00
Erez Zilber
d97c51707d IB/iser: Release connection resources on RDMA_CM_EVENT_DEVICE_REMOVAL event
When a RDMA_CM_EVENT_DEVICE_REMOVAL event is raised, iSER should
release the connection resources.

This is necessary when the IB HCA module is unloaded while open-iscsi
is still running.  Currently, iSER just BUG()s.

Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:35 -07:00
Stefan Roscher
c83b5b1cb2 IB/ehca: Support all ibv_devinfo values in query_device() and query_port()
Also, introduce a few inline helper functions to make the code more readable.

Signed-off-by: Stefan Roscher <stefan.roscher@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:35 -07:00
Roland Dreier
4cd1e5eb3c RDMA/nes: Free IRQ before killing tasklet
Move the free_irq() call in nes_remove() to before the tasklet_kill();
otherwise there is a window after tasklet_kill() where a new interrupt
can be handled and reschedule the tasklet, leading to a use-after-free
crash.

Cc: <stable@kernel.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:34 -07:00
Jack Morgenstein
940801b27e IB/mthca: Update module version and release date
The ib_mthca driver has been stable for a while, so bump the version
number to 1.0 to indicate this.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:34 -07:00
Dotan Barak
0df6703095 IB/mlx4: Update QP state if query QP succeeds
If the QP was moved to another state (such as SQE) by the hardware,
then after this change the user won't have to set the IBV_QP_CUR_STATE
mask in order to execute modify QP in order to recover from this state.

Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:34 -07:00
Dotan Barak
5121df3ae4 IB/mthca: Update QP state if query QP succeeds
If the QP was moved to another state (such as SQE) by the hardware,
then after this change the user won't have to set the IBV_QP_CUR_STATE
mask in order to execute modify QP in order to recover from this state.

Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:34 -07:00
Tom Tucker
9285faa1e7 RDMA/amso1100: Add check for NULL reply_msg in c2_intr()
Fix a place where we might dereference a NULL pointer; this fixes
Coverity CID 1392.  On inspection I also found a place where we could
attempt to kmem_cache_free() a NULL pointer, so fix this too.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:34 -07:00
Vladimir Sokolovsky
bbf8eed1a0 IB/mlx4: Add support for resizing CQs
Signed-off-by: Vladimir Sokolovsky <vlad@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:33 -07:00
Eli Cohen
3fdcb97f0b IB/mlx4: Add support for modifying CQ moderation parameters
Signed-off-by: Eli Cohen <eli@mellnaox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:33 -07:00
Eli Cohen
28d52b3cd8 IPoIB: Support modifying IPoIB CQ event moderation
This can be used to tune at run time the parameters controlling the
event (interrupt) generation rate and thus reduce the overhead
incurred by handling interrupts resulting in better throughput.  Since
IPoIB uses a single CQ for both RX and TX, RX is chosen to dictate
configuration for both RX and TX.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:33 -07:00
Eli Cohen
2dd5716227 IB/core: Add support for modify CQ
Add support for modifying CQ parameters for controlling event
generation moderation.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:33 -07:00
Eli Cohen
82c24c18af IPoIB: Add basic ethtool support
Just add the infrastructure so we can add functionality later.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:32 -07:00
Roland Dreier
139b2db795 RDMA/amso1100: Add support for "send with invalidate" work requests
Handle IB_WR_SEND_WITH_INV work requests.

This resurrects a patch sent long ago by Mikkel Hagen <mhagen@iol.unh.edu>.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:32 -07:00
Roland Dreier
0f39cf3d54 IB/core: Add support for "send with invalidate" work requests
Add a new IB_WR_SEND_WITH_INV send opcode that can be used to mark a
"send with invalidate" work request as defined in the iWARP verbs and
the InfiniBand base memory management extensions.  Also put "imm_data"
and a new "invalidate_rkey" member in a new "ex" union in struct
ib_send_wr. The invalidate_rkey member can be used to pass in an
R_Key/STag to be invalidated.  Add this new union to struct
ib_uverbs_send_wr.  Add code to copy the invalidate_rkey field in
ib_uverbs_post_send().

Fix up low-level drivers to deal with the change to struct ib_send_wr,
and just remove the imm_data initialization from net/sunrpc/xprtrdma/,
since that code never does any send with immediate operations.

Also, move the existing IB_DEVICE_SEND_W_INV flag to a new bit, since
the iWARP drivers currently in the tree set the bit.  The amso1100
driver at least will silently fail to honor the IB_SEND_INVALIDATE bit
if passed in as part of userspace send requests (since it does not
implement kernel bypass work request queueing).  Remove the flag from
all existing drivers that set it until we know which ones are OK.

The values chosen for the new flag is not consecutive to avoid clashing
with flags defined in the XRC patches, which are not merged yet but
which are already in use and are likely to be merged soon.

This resurrects a patch sent long ago by Mikkel Hagen <mhagen@iol.unh.edu>.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:32 -07:00
Ralph Campbell
e7eacd3686 IB/ipath: Update copyright dates for files changed in 2008
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:32 -07:00
Dave Olson
124b4dcb1d IB/ipath: add calls to new 7220 code and enable in build
This patch adds the initialization calls into the new 7220 HCA files,
changes the Makefile to compile and link the new files, and code to
handle send DMA.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:32 -07:00
Arthur Jones
bb9171448d IB/ipath: Misc changes to prepare for IB7220 introduction
The patch adds a number of minor changes to support newer HCAs:
 - New send buffer control bits
 - New error condition bits
 - Locking and initialization changes
 - More send buffers

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:31 -07:00
Arthur Jones
8babfa4fb9 IB/ipath: User mode send DMA
A new file which allows the IBA7220 send DMA engine to be used from
userland.  The routines here are not linked in yet, that will happen in
a follow-on patch...

Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:31 -07:00
Arthur Jones
909c0faa8f IB/ipath: User mode send DMA header file
A new header file which allows the IBA7220 send DMA engine to be used
from userland.  The definitions here are not used yet, that will happen
in a follow-on patch...

Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:31 -07:00
John Gregor
f7a60d71af IB/ipath: Add code for IBA7220 send DMA
The IBA7220 HCA has a new feature to DMA data to the on chip send
buffers instead of or in addition to the host CPU doing the data
transfer.  This patch adds code to support the send DMA queue.

Signed-off-by: John Gregor <john.gregor@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:31 -07:00
Ralph Campbell
2c19643563 IB/ipath: Add IBA7220-specific SERDES initialization data
This patch adds binary data to initialize the IB SERDES.

Signed-off-by: Michael Albaugh <Michael.Albaugh@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:31 -07:00
Michael Albaugh
ab0fb2e049 IB/ipath: Support for SerDes portion of IBA7220
The control and initialization of the SerDes blocks of the IBA7220 is
sufficiently complex to merit a separate file.

Signed-off-by: Michael Albaugh <Michael.Albaugh@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:31 -07:00
Ralph Campbell
843e6ab489 IB/ipath: HCA-specific code to support IBA7220
This patch adds the HCA-specific code for the IBA7220 HCA.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:30 -07:00
Michael Albaugh
dd042d59c1 IB/ipath: Isolate 7220-specific content
This patch adds a new ASIC-specific header file for the HCAs using the IBA7220.

Signed-off-by: Michael Albaugh <Michael.Albaugh@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:30 -07:00
Ralph Campbell
afce688ba9 IB/ipath: Header file changes to support IBA7220
This is part of a patch series to add support for a new HCA.  This patch
adds new fields to the header files.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:30 -07:00
Ralph Campbell
6bb68835d3 IB/ipath: Fix up error handling
This patch makes chip reset more robust and reduces lock contention
between user and kernel TID register updates.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:30 -07:00
Dave Olson
9b436eb4f8 IB/ipath: Fix check for no interrupts to reliably fallback to INTx
Newer HCAs support MSI interrupts and also INTx interrupts.  Fix the
code so that INTx can be reliably enabled if MSI interrupts are not
working.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:30 -07:00
Dave Olson
1d7c2e529f IB/ipath: Enable reduced PIO update for HCAs that support it.
Newer HCAs have a threshold counter to reduce the number of DMAs the
chip makes to update the PIO buffer availability status bits.  This
patch enables the feature.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:30 -07:00
Dave Olson
0ab6b2b9ab IB/ipath: Set LID filtering for HCAs that support it.
Whenever the LID is set, notify the HCA specific code so that the
appropriate HW registers can be updated. Also log the info on the
console at low priority.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:29 -07:00
Dave Olson
b3e8f54107 IB/ipath: Add support for IBTA 1.2 Heartbeat
This patch adds code to enable/disable the IBTA 1.2 heartbeat for testing
if the HCA supports it.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:29 -07:00
Dave Olson
555b203e48 IB/ipath: Make link state transition code ignore (transient) link recovery
The hardware-based recovery doesn't need any intervention, and in a few
cases we can get a bit confused about state and skip steps such as
turning off the link state LED when we consider recovery to be "down".
So ignore this transition, and either we recover in hardware, or we
transition to down, and will handle it then.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:29 -07:00
Ralph Campbell
9355fb6a06 IB/ipath: Add support for 7220 receive queue changes
Newer HCAs have a HW option to write a sequence number to each receive
queue entry and avoid a separate DMA of the tail register to memory.
This patch adds support for these changes.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:29 -07:00
Ralph Campbell
2ba3f56eb4 IB/ipath: Fix some white space and code style issues
This patch makes some white space changes and minor non-functional
changes to more closely match the code in OFED-1.3.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:29 -07:00
Michael Albaugh
afd9970f95 IB/ipath: Allow old and new diagnostic packet formats
This patch checks for old and new format writes to send a packet via the
diagnostic interface.

Signed-off-by: Michael Albaugh <Michael.Albaugh@Qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:28 -07:00
Dotan Barak
7ce5eacb45 IB/core: Check optional verbs before using them
Make sure that a device implements the modify_srq and reg_phys_mr
optional methods before calling them.

Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:28 -07:00
Robert P. J. Day
b3b8128fd3 IB/ipath: Fix time comparison to use time_after_eq()
Raw comparison against jiffies will fail if jiffies wraps, although
since ipath currently only supports 64-bit architectures, this is rather
far-fetched.  Still, it's better to use time_after_eq().

Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:28 -07:00
Roland Dreier
f438000f7a IB/mlx4: Micro-optimize mlx4_ib_post_send()
Rather than have build_mlx_header() return a negative value on failure
and the length of the segments it builds on success, add a pointer
parameter to return the length and return 0 on success.  This matches
the calling convention used for build_lso_seg() and generates slightly
smaller code -- eg, on 64-bit x86:

add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-22 (-22)
function                                     old     new   delta
mlx4_ib_post_send                           2023    2001     -22

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:28 -07:00
Eli Cohen
b832be1e40 IB/mlx4: Add IPoIB LSO support
Add TSO support to the mlx4_ib driver.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:27 -07:00
Eli Cohen
40ca1988e0 IPoIB: Add LSO support
For HCAs that support TCP segmentation offload (IB_DEVICE_UD_TSO), set
NETIF_F_TSO and use HW LSO to offload TCP segmentation.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:27 -07:00
Eli Cohen
b846f25aa2 IB/core: Add creation flags to struct ib_qp_init_attr
Add a create_flags member to struct ib_qp_init_attr that will allow a
kernel verbs consumer to create a pass special flags when creating a QP.
Add a flag value for telling low-level drivers that a QP will be used
for IPoIB UD LSO.  The create_flags member will also be useful for XRC
and ehca low-latency QP support.

Since no create_flags handling is implemented yet, add code to all
low-level drivers to return -EINVAL if create_flags is non-zero.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:27 -07:00
Michael Albaugh
d84e0b28d3 IB/ipath: EEPROM support for 7220 devices, robustness improvements, cleanup
Add support for reading newer card's EEPROMs while continuing to support
older EEPROMs.

Also, add support for the temperature sensor if present.

Signed-off-by: Michael Albaugh <Michael.Albaugh@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:27 -07:00
Ralph Campbell
d98b193776 IB/ipath: Use PIO buffer for RC ACKs
This reduces the latency for RC ACKs when a PIO buffer is available.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:27 -07:00
Ralph Campbell
c4b4d16e09 IB/ipath: Make send buffers available for kernel if not allocated to user
A fixed partitioning of send buffers is determined at driver load time
for user processes and kernel use.  Since send buffers are a scarce
resource, it makes sense to allow the kernel to use the buffers if they
are not in use by a user process.

Also, eliminate code duplication for ipath_force_pio_avail_update().

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:26 -07:00
Michael Albaugh
4330e4dad7 IB/ipath: Prevent link-recovery code from negating admin disable
The link can be put in LINKDOWN_DISABLE state either locally or via a
MAD.  However, the link-recovery code will take it out of that state as
a side-effect of attempts to clear SerDes/XGXS issues.

We add a flag to indicate "link is down on purpose, leave it alone."

Signed-off-by: Michael Albaugh <michael.albaugh@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:26 -07:00
Ralph Campbell
8c641d4b5f IB/ipath: Remove some useless (void) casts
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:26 -07:00
Ralph Campbell
928e3e4bb9 IB/ipath: Change the module author
Update the module author to the current email address.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:26 -07:00
Robert P. J. Day
4e96a77440 RDMA/nes: Use more concise list_for_each_entry()
In list iteration code, you normally wouldn't be calling
"container_of()" directly anyway, you'd be invoking "list_entry()".
But you don't even need that here, "list_for_each_entry()" is fine.

Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Acked-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:26 -07:00
Robert P. J. Day
157de22946 IB: Use shorter list_splice_init() for brevity
Convert list_splice() + INIT_LIST_HEAD() to the equivalent list_splice_init()

Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:26 -07:00
Julia Lawall
10f32065a2 RDMA/iwcm: Test rdma_create_id() for IS_ERR rather than 0
The function rdma_create_id() always returns either a valid pointer or
a value made with ERR_PTR, so its result should be tested with IS_ERR,
not with a test for 0.

The problem was found using the following semantic match.
(http://www.emn.fr/x-info/coccinelle/)

//<smpl>
@a@
expression E, E1;
statement S,S1;
position p;
@@

E = rdma_create_id(...)
... when != E = E1
if@p (E) S else S1

@n@
position a.p;
expression E,E1;
statement S,S1;
@@

E = NULL
... when != E = E1
if@p (E) S else S1

@depends on !n@
expression E;
statement S,S1;
position a.p;
@@

* if@p (E)
  S else S1
//</smpl>

Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:25 -07:00
Roland Dreier
4d43653263 RDMA/nes: Remove session_id from nes_cm stuff
The session_id members of struct nes_cm_listener and struct
nes_cm_node are write-only, so remove them.  This allows the
session_id member of struct nes_cm_core to be removed as well, since
it is only used to write those other session_id values.

This removes the use of current->tgid (which will be deprecated)
pointed out by Pavel Emelyanov <xemul@openvz.org>.

Acked-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:25 -07:00
Roland Dreier
782203884e IB/ipath: Fix PCI config write size used to clear linkctrl error bits
In slave_or_pri_blk(), pci_write_config_byte() is used to write a
16-bit quantity to clear linkctrl CRC error bits.  This is clearly a
bug and also causes the warning

    drivers/infiniband/hw/ipath/ipath_iba6110.c: In function 'slave_or_pri_blk':
    drivers/infiniband/hw/ipath/ipath_iba6110.c:849: warning: overflow in implicit constant conversion

Fix this by using pci_write_config_word() instead.

Acked-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:25 -07:00
Ralph Campbell
10a8c3cd01 IB/ipath: Fix sanity checks on QP number of WRs and SGEs
The receive queue number of WRs and SGEs shouldn't be checked if a
SRQ is specified.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:25 -07:00
Ralph Campbell
69bd74c696 IB/ipath: Remove useless comments
Remove useless comment about list removal since locks are held and
the code checks that the QP is on the list before removing it.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:25 -07:00
Dave Olson
72708a0a2b IB/ipath: HW workaround for case where chip can send but not receive
Workaround a QLE7140 problem that in rare cases causes flow control
problems after link recovery by forcing a link retrain after recovery.
A module parameter is provided to control the behavior in case it causes
problems.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:25 -07:00
Ralph Campbell
a51a2513a8 IB/ipath: Add code to support multiple link speeds and widths
This patch adds code to get/set portinfo to support multiple link speeds
and widths.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:24 -07:00
John Gregor
58411d1c01 IB/ipath: Head of Line blocking vs forward progress of user apps
There's a conflict between our need to quiesce PSM-based applications
to avoid HoL blocking when the IB link goes down and the apps' desire
to remain running so that their quiescence timout mechanism can keep
running.

The compromise is to STOP the processes for a fixed period of time and
then alternate between CONT and STOP until the link is again active.

If there are poor interactions with subnet manager configuration at a
given site, the interval can be adjusted via a module paramter.

Signed-off-by: John Gregor <john.gregor@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:24 -07:00
Ralph Campbell
6be979d71a IB/ipath: Make debug error message match the constraint that is checked for
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:24 -07:00
Ralph Campbell
c1702be20f IB/ipath: Don't try to handle freeze mode HW errors if diagnostic mode
Don't try to handle freeze mode HW errors if the driver is in diagnostic
mode since some tests can cause errors that shouldn't be processed.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:14 -07:00
Arthur Jones
b848882153 IB/ipath: Fix link up LED display
The check for link up was incorrect, thus setting the LED display
inconsistently with the link state.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:13 -07:00
Ralph Campbell
8bae0ff259 IB/ipath: Fix error recovery for send buffer status after chip freeze mode
The error recovery code for updating the driver's cached status information
for which send buffers are busy or free wasn't updated for IBA7220.
It should be similar to the initialization code in enable_chip().

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:13 -07:00
Ralph Campbell
0349d16620 IB/ipath: Fix byte order of pioavail in handle_errors()
Fix byte order of value assigned to pioavailshadow.  This bug was
detected by sparse endianness warnings.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:13 -07:00
Roland Dreier
c263ff65d5 IB/mthca: Avoid integer overflow when allocating huge ICM table
In mthca_alloc_icm_table(), the number of entries to allocate for the
table->icm array is computed by calculating obj_size * nobj and then
dividing by MTHCA_TABLE_CHUNK_SIZE.  If nobj is really large, then
obj_size * nobj may overflow and the division may get the wrong value
(even a negative value).  Fix this by calculating the number of
objects per chunk and then dividing nobj by this value instead.

This patch allows crazy configurations such as loading ib_mthca with
the module parameter num_mtt=33554432 to work properly.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:13 -07:00
Roland Dreier
19773539d6 IB/mthca: Avoid integer overflow when dealing with profile size
mthca_make_profile() returns the size in bytes of the HCA context
layout it creates, or a negative value if an error occurs.  However,
the return value is declared as u64 and the memfree initialization
path casts this value to int to test if it is negative.  This makes it
think incorrectly than an error has occurred if the context size
happens to be bigger than 2GB, since this turns into a negative int.

Fix this by having mthca_make_profile() return an s64 and testing
for an error by checking whether this 64-bit value itself is negative.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:13 -07:00
Hoang-Nam Nguyen
f4f82994d1 IB/ehca: Remove tgid checking
Pavel Emelyanov <xemul@openvz.org> mentioned in <http://lkml.org/lkml/2008/3/17/131>
that the task_struct->tgid field is about to become deprecated, so the
uses in the ehca driver need to be fixed up.

However, all the uses in ehca are for some object ownership checking
that is not really needed, and anyway is implementing a policy that
should be in common code rather than a low-level driver.  So just
remove all the checks.

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:13 -07:00
David Dillow
1e89a1946c IB/srp: Enforce protocol limit on srp_sg_tablesize
The current SRP initiator will allow unlimited s/g entries in the
indirect descriptors lists, but the entry count field in the SRP_CMD
request is 8 bits, so setting srp_sg_tablesize too large will open the
possibility of wrapping the count and generating invalid requests.

Clamp srp_sg_tablesize to the protocol limits to prevent surprises.

Reported by Martin W. Schlining III <mschlining@datadirectnet.com>.

Signed-off-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:12 -07:00
Dave Olson
826d801009 IB/ipath: Enable 4KB MTU
Enable use of 4KB MTU.  Since the driver uses more pinned memory for
receive buffers when the 4KB MTU is enabled, whether or not the fabric
supports that MTU, add a "mtu4096" module parameter that can be used to
limit the MTU to 2KB when it is known that 4KB MTUs can't be used
anyway.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:12 -07:00
Dave Olson
5d1ce03dd3 IB/ipath: Shared context code needs to be sure device is usable
The code was checking if units are present, but not that present units
were usable (link up, etc.)

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:12 -07:00
Arthur Jones
6ca2abf4c0 IB/ipath: Provide I/O bus speeds for diagnostic purposes
Modern I/O buses like PCIe and HT can be configured for multiple speeds
and widths.  When an ipath HCA seems to have lower than expected
performance, it is very useful to be able to display what the driver
thinks the bus speed is.

Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:12 -07:00
Dave Olson
f2ceb4929a IB/ipath: Make some constants chip-specific, related cleanup
This patch makes some constants chip-specific, and makes some related
changes to prepare for supporting another HCA.

Signed-off-by: Dave Olson <dave.olson@qlogic.com
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:12 -07:00
Arthur Jones
3dd59e226e IB/ipath: Misc sparse warning cleanup
Recent sparse versions and kernel cleanups knock down the false positive
rate of the ipath driver code to a point where having it be sparse clean
is worthwhile. Here we fixup the sparse warnings.  Some of these warnings
(and the impetus to run sparse again) are due to work by Roland Dreier.

Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:11 -07:00
Eli Cohen
680b575f6d IB/mthca: Add IPoIB checksum offload support
Arbel and Sinai devices support checksum generation and verification
of TCP and UDP packets for UD IPoIB messages.  This patch checks if
the HCA supports this and sets the IB_DEVICE_UD_IP_CSUM capability
flag if it does.  It implements support for handling the IB_SEND_IP_CSUM
send flag and setting the csum_ok field in receive work completions.

Signed-off-by: Eli Cohen <eli@mellnaox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:11 -07:00
Eli Cohen
8ff095ec4b IB/mlx4: Add IPoIB checksum offload support
ConnectX devices support checksum generation and verification of TCP
and UDP packets for UD IPoIB messages.  This patch checks if the HCA
supports this and sets the IB_DEVICE_UD_IP_CSUM capability flag if it
does.  It implements support for handling the IB_SEND_IP_CSUM send
flag and setting the csum_ok field in receive work completions.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Ali Ayub <ali@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:10 -07:00
Eli Cohen
6046136c74 IPoIB: Use checksum offload support if available
For HCAs that support checksum offload (ie that set IB_DEVICE_UD_IP_CSUM
in the device capabilities flags), have IPoIB set NETIF_F_IP_CSUM and
use the HCA to generate and verify IP checksums.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:10 -07:00
Harvey Harrison
3371836383 IB: Replace remaining __FUNCTION__ occurrences with __func__
__FUNCTION__ is gcc-specific, use __func__ instead.

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:10 -07:00
Roland Dreier
e8e91f6b4d IB/ehca: Make symbols used only in a single source file static
Allow the compiler to optimize better and generate smaller code:

add/remove: 0/6 grow/shrink: 2/0 up/down: 1528/-1864 (-336)
function                                     old     new   delta
.ehca_set_pagebuf                           1344    2172    +828
.ehca_probe                                 2312    3012    +700
ehca_set_pagebuf_phys                         24       -     -24
ehca_set_pagebuf_fmr                          24       -     -24
ehca_init_device                              24       -     -24
.ehca_set_pagebuf_fmr                        480       -    -480
.ehca_set_pagebuf_phys                       512       -    -512
.ehca_init_device                            800       -    -800

Also this fixes warnings like:

    drivers/infiniband/hw/ehca/ehca_mrmw.c:2015:5: warning: symbol 'ehca_set_pagebuf_fmr' was not declared. Should it be static?

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:10 -07:00
Roland Dreier
1a855fbfb6 RDMA/nes: Make symbols used only in a single source file static
Avoid namespace pollution and allow the compiler to optimize better.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:09 -07:00
Roland Dreier
71e0957c62 RDMA/nes: Use proper format and cast to print dma_addr_t
On some platforms, eg sparc64, dma_addr_t is not the same size as a
pointer, so printing dma_addr_t values by casting to void * and using
a %p format generates warnings.  Fix this by casting to unsigned long
and using %lx instead.  This fixes the warnings:

    drivers/infiniband/hw/nes/nes_verbs.c: In function 'nes_setup_virt_qp':
    drivers/infiniband/hw/nes/nes_verbs.c:1047: warning: cast to pointer from integer of different size
    drivers/infiniband/hw/nes/nes_verbs.c:1078: warning: cast to pointer from integer of different size
    drivers/infiniband/hw/nes/nes_verbs.c:1078: warning: cast to pointer from integer of different size
    drivers/infiniband/hw/nes/nes_verbs.c: In function 'nes_reg_user_mr':
    drivers/infiniband/hw/nes/nes_verbs.c:2657: warning: cast to pointer from integer of different size

Reported by Andrew Morton <akpm@linux-foundation.org>.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:09 -07:00
Roland Dreier
9d84ab9c7e RDMA/nes: Remove unused nes_netdev_exit() function
nes_netdev_exit() has no callers, so delete it.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:09 -07:00
Roland Dreier
5bd8341ce2 RDMA/nes: Remove redundant NULL check in nes_unregister_ofa_device()
nes_unregister_ofa_device() dereferences the nesibdev pointer before
testing if it's NULL.  Also, the test is doubly redundant because the
only caller of nes_unregister_ofa_device() is nes_destroy_ofa_device(),
which already tests if nesibdev is NULL.  Remove the unnecessary test.

This was spotted by the Coverity checker (CID 2190).

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:09 -07:00
Roland Dreier
a7dab9e887 IB/uverbs: Use alloc_file() instead of get_empty_filp()
Christoph Hellwig wants to unexport get_empty_filp(), which is an ugly
internal interface.  Change the modular user in ib_uverbs_alloc_event_file()
to use the better alloc_file() interface; this makes the code cleaner too.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:08 -07:00
Roland Dreier
1ae5c187ac IB/uverbs: Don't store struct file * for event files
The file member of struct ib_uverbs_event_file was only used to keep
track of whether the file had been closed or not.  The only thing we
ever did with the value was check if it was NULL or not.  Simplify the
code and get rid of the need to keep track of the struct file * we
allocate by replacing the file member with an is_closed member.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:08 -07:00
Roland Dreier
37608eea86 mlx4_core: Fix confusion between mlx4_event and mlx4_dev_event enums
The struct mlx4_interface.event() method was supposed to get an enum
mlx4_dev_event, but the driver code was actually passing in the
hardware enum mlx4_event values.  Fix up the callers of
mlx4_dispatch_event() so that they pass in the right type of value,
and fix up the event method in mlx4_ib so that it can handle the enum
mlx4_dev_event values.

This eliminates the need for the subtype parameter to the event
method, so remove it.

This also fixes the sparse warning

    drivers/net/mlx4/intf.c:127:48: warning: mixing different enum types
    drivers/net/mlx4/intf.c:127:48:     int enum mlx4_event  versus
    drivers/net/mlx4/intf.c:127:48:     int enum mlx4_dev_event

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:08 -07:00
Roland Dreier
26c4fc26d0 RDMA/amso1100: Endian annotate mqsq allocator
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:08 -07:00
Roland Dreier
dc544bc9cb RDMA/amso1100: Start of endianness annotation
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
2008-04-16 21:01:08 -07:00
Roland Dreier
d23b9d8ff2 RDMA/nes: Delete unused variables
None of the cqp_reqs_XXX counters were ever used anywhere, and neither
was the nics_per_function variable.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:08 -07:00
Roland Dreier
b30db1c186 RDMA/nes: Trivial endianness annotations
Fix a couple of htonl() that should really be ntohl().

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:07 -07:00
Roland Dreier
9cda779cc2 RDMA/ucma: Endian annotation
Add __force cast of node_guid to __u64, since we are sticking it into a
structure whose definition is shared with userspace.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:07 -07:00
Roland Dreier
a88f488857 IB/cm: Endianness annotations
Mostly update the RB tree comparisons to force __be types to normal
integers, but the change to cm_format_sidr_req() is a real fix:
param->path->pkey is already __be16.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
Acked-by: Sean Hefty <sean.hefty@intel.com>
2008-04-16 21:01:07 -07:00
Roland Dreier
d2ae16d576 IB/mlx4: Endianness annotations
Trivial fixes to stamp_send_wqe().

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:07 -07:00
Roland Dreier
6358ae25fd IB/ipath: Fix sparse warning about shadowed symbol
Fix

    drivers/infiniband/hw/ipath/ipath_init_chip.c:526:10: warning: symbol 'val' shadows an earlier one
    drivers/infiniband/hw/ipath/ipath_init_chip.c:473:6: originally declared here

by giving the second val a different name.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
Acked-by: Arthur Jones <arthur.jones@qlogic.com>
2008-04-16 21:01:07 -07:00
Arthur Jones
6ef6aee2f0 IB/ipath: Fix sparse warning about pointer signedness
There's no reason for the third parameter of ipath_count_units() to be
a u32 *, so change it to be an int * instead.  This fixes the sparse
warning:

    drivers/infiniband/hw/ipath/ipath_file_ops.c:1654:47: warning: incorrect type in argument 3 (different signedness)
    drivers/infiniband/hw/ipath/ipath_file_ops.c:1654:47:    expected unsigned int [usertype] *maxportsp
    drivers/infiniband/hw/ipath/ipath_file_ops.c:1654:47:    got int *<noident>

Signed-off-by: Arthur Jones <arthur.jones@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:06 -07:00
Roland Dreier
edba846af9 RDMA/cxgb3: IDR IDs are signed
Fix sparse warnings about pointer signedness by using a signed int when
calling idr_get_new_above().

Signed-off-by: Roland Dreier <rolandd@cisco.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
2008-04-16 21:01:06 -07:00
Roland Dreier
4b29043921 RDMA/amso1100: Don't use 0UL as a NULL pointer
Write tests for NULL pointers as

	if (!ptr)

instead of

	if (ptr == 0UL)

to fix sparse warnings.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
2008-04-16 21:01:06 -07:00
Roland Dreier
5d5e815db9 IB/mlx4: Convert "if(foo)" to "if (foo)"
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:04 -07:00
Roland Dreier
b39993936d IB/mthca: Formatting cleanups
Fix a few whitespace and other coding style problems.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:03 -07:00
Al Viro
1b90c137cc trivial endianness annotations: infiniband core
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-03-30 14:20:24 -07:00
Roland Dreier
1f71f50342 RDMA/cxgb3: Program hardware IRD with correct value
Because of a typo in iwch_accept_cr(), the cxgb3 connection handling
code programs the hardware IRD (incoming RDMA read queue depth) with
the value that is passed in for the ORD (outgoing RDMA read queue
depth).  In particular this means that if an application passes in IRD
> 0 and ORD = 0 (which is a completely sane and valid thing to do for
an app that expects only incoming RDMA read requests), then the
hardware will end up programmed with IRD = 0 and the app will fail in
a mysterious way.

Fix this by using "ep->ird" instead of "ep->ord" in the intended place.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-03-28 10:45:32 -07:00
Chien Tung
f2b2b59b93 RDMA/nes: Fix MSS calculation on RDMA path
Fix the calculation of the MSS for RDMA connections: we need to
allow space in frames for a VLAN tag too.

Signed-off-by: Chien Tung <ctung@neteffect.com>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-21 13:59:28 -07:00
Roland Dreier
10313cbb92 IPoIB: Allocate priv->tx_ring with vmalloc()
Commit 7143740d ("IPoIB: Add send gather support") made struct
ipoib_tx_buf significantly larger, since the mapping member changed
from a single u64 to an array with MAX_SKB_FRAGS + 1 entries.  This
means that allocating tx_rings with kzalloc() may fail because there
is not enough contiguous memory for the new, much bigger size.  Fix
this regression by allocating the rings with vmalloc() instead.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-12 07:51:03 -07:00
Roland Dreier
4200406b8f IPoIB/cm: Set tx_wr.num_sge in connected mode post_send()
Commit 7143740d ("IPoIB: Add send gather support") made it possible
for tx_wr.num_sge to be != 1 -- this happens if send gather support is
enabled.  However, the code in the connected mode post_send() function
assumes the old invariant, namely that tx_wr.num_sge is always 1.  Fix
this by explicitly setting tx_wr.num_sge to 1 in the CM post_send().

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-11 18:35:20 -07:00
Or Gerlitz
b3e2749bf3 IPoIB: Don't drop multicast sends when they can be queued
When set_multicast_list() is called the multicast task is restarted
and the IPOIB_MCAST_STARTED bit is cleared.  As a result for some
window of time, multicast packets are not transmitted nor queued but
rather dropped by ipoib_mcast_send().  These dropped packets are
painful in two cases:

 - bonding fail-over which both calls set_multicast_list() on the new
   active slave and sends Gratuitous ARP through that slave.

 - IP_DROP_MEMBERSHIP code which both calls set_multicast_list() on the
   device and issues IGMP leave.

In both these cases, depending on the scheduling of the IPoIB
multicast task, the packets would be dropped.  As a result, in the
bonding case, the failover would not be detected by the peers until
their neighbour is renewed the neighbour (which takes a few tens of
seconds).  In the IGMP case, the IP router doesn't get an IGMP leave
and would only learn on that from further probes on the group (also a
delay of at least a few tens of seconds).

Fix this by allowing transmission (or queuing) depending on the
IPOIB_FLAG_OPER_UP flag instead of the IPOIB_MCAST_STARTED flag.

Signed-off-by: Olga Shern <olgas@voltaire.com>
Signed-off-by: Or Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-11 14:12:03 -07:00
Patrick Marchand Latifi
450bb3875f IB/ipath: Reset the retry counter for RDMA_READ_RESPONSE_MIDDLE packets
Reset the retry counter when we get a good RDMA_READ_RESPONSE_MIDDLE
packet.  This fix will prevent the requester from reporting a retry
exceeded error too early.

Signed-off-by: Patrick Marchand Latifi <patrick.latifi@qlogic.com>
2008-03-11 14:04:35 -07:00
Patrick Marchand Latifi
2a049e514b IB/ipath: Fix error completion put on send CQ instead of recv CQ
A work completion entry could be placed on the wrong completion
queue when an RC QP is placed in the error state.

Signed-off-by: Patrick Marchand Latifi <patrick.latifi@qlogic.com>
Acked-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-11 14:03:54 -07:00
Patrick Marchand Latifi
4cd5060cf7 IB/ipath: Fix RC QP initialization
This patch fixes the initialization of RC QPs, since we would rely on
the queue pair type (ibqp->qp_type) being set, but this field is only
initialized when we return from ipath_create_qp (it is initialized by
the user-level verbs library).

The fix is to not depend on this field to initialize the send and
the receive state of the RC QP.

Signed-off-by: Patrick Marchand Latifi <patrick.latifi@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-11 14:02:32 -07:00
Patrick Marchand Latifi
87d5aed85b IB/ipath: Fix potentially wrong RNR retry counter returned in ipath_query_qp()
There can be a case where the requester's rnr retry counter
(s_rnr_retry) is less than the number of rnr retries allowed per QP
(s_rnr_retry_cnt).  This can happen if the s_rnr_retry counter is being
decremented and an ipath_query_qp call is issued during that time frame.
The fix is to always return the number of rnr retries allowed per QP
instead of the requester's rnr counter.

Found by code review.

Signed-off-by: Patrick Marchand Latifi <patrick.latifi@qlogic.com>
Acked-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-11 14:01:14 -07:00
Ralph Campbell
140277e9a7 IB/ipath: Fix IB compliance problems with link state vs physical state
Subnet manager SetPortinfo messages distingush between changing the link
state (DOWN, ARM, ACTIVE) and the link physical state (POLL, SLEEP,
DISABLED).  These are somewhat independent commands and affect when link
width and speed changes take effect.  Without this patch, a link DOWN
physical state NOP command was causing the link width and speed settings
to take effect which should only happen when the link physical state is
goes down (either by a SMP or some link physical error like link errors
exceeding the threshold).

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-11 13:58:22 -07:00
Steve Wise
d7c1fbd660 RDMA/iwcm: Don't access a cm_id after dropping reference
cm_work_handler() can access cm_id_priv after it drops its reference
by calling iwch_deref_id(), which might cause it to be freed.  The fix
is to look at whether IWCM_F_CALLBACK_DESTROY is set _before_ dropping
the reference.  Then if it was set, free the cm_id on this thread.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-10 21:22:22 -07:00
Arne Redlich
d33ed425c6 IB/iser: Handle iser_device allocation error gracefully
"iser_device" allocation failure is "handled" with a BUG_ON() right
before dereferencing the NULL-pointer - fix this!

Signed-off-by: Arne Redlich <arne.redlich@xiranet.com>
Signed-off-by: Erez Zilber <erezz@voltaire.com>
2008-03-10 21:17:51 -07:00
Arne Redlich
9a378270c0 IB/iser: Fix list iteration bug
The iteration through the list of "iser_device"s during device
lookup/creation is broken -- it might result in an infinite loop if
more than one HCA is used with iSER.  Fix this by using
list_for_each_entry() instead of the open-coded flawed list iteration
code.

Signed-off-by: Arne Redlich <arne.redlich@xiranet.com>
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-10 21:15:49 -07:00
Jon Mason
4fa45725df RDMA/cxgb3: Fix iwch_create_cq() off-by-one error
The cxbg3 driver is unnecessarily decreasing the number of CQ entries by
one when creating a CQ.  This will cause the CQ not to have as many
entries as requested by the user if the user requests a power of 2 size.

Signed-off-by: Jon Mason <jon@opengridcomputing.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-03-09 13:54:12 -07:00
Jon Mason
1bab74e691 RDMA/cxgb3: Return correct max_inline_data when creating a QP
Set cap.max_inline_data to the actual max inline data that the adapter
support, so that userspace apps see the right value returned.

Signed-off-by: Jon Mason <jon@opengridcomputing.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-29 13:53:18 -08:00
Pete Wyckoff
331552925d IB/fmr_pool: Flush all dirty FMRs from ib_fmr_pool_flush()
Commit a3cd7d90 ("IB/fmr_pool: ib_fmr_pool_flush() should flush all
dirty FMRs") caused a regression for iSER and was reverted in
e5507736.

This change attempts to redo the original patch so that all used FMR
entries are flushed when ib_flush_fmr_pool() is called without
affecting the normal FMR pool cleaning thread.  Simply move used
entries from the clean list onto the dirty list in ib_flush_fmr_pool()
before letting the cleanup thread do its job.

Signed-off-by: Pete Wyckoff <pw@osc.edu>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-29 13:31:48 -08:00
Pete Wyckoff
35fb5340e3 Revert "IB/fmr_pool: ib_fmr_pool_flush() should flush all dirty FMRs"
This reverts commit a3cd7d9070.

The original commit breaks iSER reliably, making it complain:

    iser: iser_reg_page_vec:ib_fmr_pool_map_phys failed: -11

The FMR cleanup thread runs ib_fmr_batch_release() as dirty entries
build up.  This commit causes clean but used FMR entries also to be
purged.  During that process, another thread can see that there are no
free FMRs and fail, even though there should always have been enough
available.

Signed-off-by: Pete Wyckoff <pw@osc.edu>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-29 13:29:19 -08:00
Sean Hefty
84ba284cd7 IB/cm: Flush workqueue when removing device
When a CM MAD is received, it is queued to a CM workqueue for
processing.  The queued work item references the port and device on
which the MAD was received.  If that device is removed from the system
before the work item can execute, the work item will reference freed
memory.

To fix this, flush the workqueue after unregistering to receive MAD,
and before the device is be freed.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-29 13:27:52 -08:00
John Lacombe
4b1cc7e7ca RDMA/nes: Fix interrupt moderation low threshold
Interrupt moderation low threshold value was incorrectly triggering,
indicating that the threshold should be lowered.

The impact was the timer was likely to become 40usecs and get stuck
there.  The biggest side effect was too many interrupts and nonoptimal
performance.

Signed-off-by: John Lacombe <jlacombe@neteffect.com>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-26 16:24:29 -08:00
Faisal Latif
30da7cff87 RDMA/nes: Fix CRC endianness for RDMA connection establishment on big-endian
With commit ef19454b ("[LIB] crc32c: Keep intermediate crc state in
cpu order"), the behavior of crc32c changes on big-endian platforms.

Our algorithm expects the previous behavior; otherwise we have RDMA
connection establishment failure on big-endian platforms like powerpc.
Apply cpu_to_le32() to value returned by crc32c() to get the previous
behavior.

Signed-off-by: Faisal Latif <flatif@neteffect.com>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-26 16:24:29 -08:00
Faisal Latif
a2e9c384ce RDMA/nes: Fix use-after-free in mini_cm_dec_refcnt_listen()
Fix use-after-free spotted by Coverity checker flagged by Adrian Bunk.

Signed-off-by: Faisal Latif <flatif@neteffect.com>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-26 16:24:29 -08:00
Glenn Streiff
f84fba6f96 RDMA/nes: Fix use-after-free in nes_create_cq()
Just delete the debugging statement so we don't use cqp_request after
freeing it.  Adrian Bunk flagged this use-after-free issue spotted by
the Coverity checker.

Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-26 16:24:29 -08:00
Adrian Bunk
a4435febd4 RDMA/nes: Fix a check-after-use in nes_probe()
Fix a check-after-use spotted by the Coverity checker.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-26 16:24:29 -08:00
Adrian Bunk
ed0ba33d64 RDMA/nes: Fix a memory leak in schedule_nes_timer()
Fix a memory leak spotted by the Coverity checker.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-26 16:24:27 -08:00
Adrian Bunk
65b07ec293 RDMA/nes: Fix off-by-one
Fix an off-by-one spotted by the Coverity checker.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-25 16:00:30 -08:00
Chien Tung
9300c0c067 RDMA/nes: Resurrect error path dead code
Adrian Bunk pointed out that a Coverity scan found some apparently
dead code in nes_verbs.c that really shouldn't have been dead.

The function nes_create_cq() was missing the assignment

	err = 1;

just prior to an iteration that conditionally set err = 0 if a PBL was
found for a given virtual CQ.  I also noticed we should have been
returning -EFAULT on a couple related error paths.

Signed-off-by: Chien Tung <ctung@neteffect.com>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-25 16:00:30 -08:00
Bryan Rosenburg
82d416fffb RDMA/cxgb3: Fix shift calc in build_phys_page_list() for 1-entry page lists
A single entry (addr 0x10001000, size 0x2000) will get converted to
page address 0x10000000 with a page size of 0x4000.  The code as it
stands doesn't address the single buffer case, but in fact it allows
the subsequent single-buffer special case to be eliminated entirely.
Because the mask now includes the (page adjusted) starting and ending
addresses, the general case works for the single buffer case as well.

Signed-off-by: Bryan Rosenburg <rosnbrg@us.ibm.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-25 16:00:29 -08:00
Roland Dreier
b7f9c112a5 IB/mthca: Free correct MPT on error exit from mthca_fmr_alloc()
When mthca_fmr_alloc() returns an error, it should free the MPT at the
index key, not mr->ibmr.lkey, since the lkey has been mangled by
hw_index_to_key() and no longer is the real index.  This bug causes
corruption of the MPT table free bitmap when mthca_fmr_alloc() fails.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-19 10:42:50 -08:00
Pradeep Satyanarayana
ec229e5e81 IPoIB/cm: Fix ipoib_cm_dev_stop() cleanup when drain times out
Commit efcd9971 ("IPoIB/cm: Factor out ipoib_cm_free_rx_reap_list()")
introduced a bug in ipoib_cm_dev_stop() when the receive drain times
out.  In that case, the function moves all the pending rx stuff into a
private list but then calls ipoib_cm_free_rx_reap_list(), which
handles a different list.

Fix this by moving everything to the rx_reap_list that will actually
get freed up.

This fixes <https://bugs.openfabrics.org/show_bug.cgi?id=906>.

Signed-off-by: Pradeep Satyanarayana <pradeeps@linux.vnet.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-19 10:25:11 -08:00
Roland Dreier
51af33e8e4 RDMA/nes: Fix possible array overrun
In nes_create_qp(), the test

	if (nesqp->mmap_sq_db_index > NES_MAX_USER_WQ_REGIONS) {

is used to error out if the db_index is too large; however, if the
test doesn't trigger, then the index is used as

	nes_ucontext->mmap_nesqp[nesqp->mmap_sq_db_index] = nesqp;

and mmap_nesqp is declared as

	struct nes_qp      *mmap_nesqp[NES_MAX_USER_WQ_REGIONS];

which leads to an array overrun if the index is exactly equal to
NES_MAX_USER_WQ_REGIONS.  Fix this by bailing out if the index is
greater than or equal to NES_MAX_USER_WQ_REGIONS.

This was spotted by the Coverity checker (CID 2162).

Acked-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-18 10:33:59 -08:00
Chien Tung
edd2fd643c RDMA/nes: Fix VLAN support
We need to account for the VLAN header size in nes_netdev_change_mtu()
and nes_netdev_init().  Also, add spin lock/unlock during VLAN RX
registration so only one process can assign VLAN group for a given
interface at a time.

Signed-off-by: Chien Tung <ctung@neteffect.com>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-16 21:16:33 -08:00
Glenn Streiff
11e0704b7e RDMA/nes: Fix MAC interrupt erroneously masked on ifdown
Only mask out MAC interrupt if necessary and re-enable on ifup.  There
could be multiple netdevs going through the same MAC.  MAC interrupts
should not be masked off until the last netdev is downed.

Signed-off-by: Chien Tung <ctung@neteffect.com>
Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-15 15:05:05 -08:00
Li Zefan
c7482b81c8 IB: Fix return value in ib_device_register_sysfs()
If kobject_create_and_add() fails and returns NULL, the current code
in ib_device_register_sysfs() does not set ret and hence returns 0.
Set ret to -ENOMEM for this failure, so that the caller knows that
ib_device_register_sysfs() actually failed.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-15 15:05:05 -08:00
Sean Hefty
ead595aeb0 RDMA/cma: Do not issue MRA if user rejects connection request
There's an undesirable interaction with issuing MRA requests to
increase connection timeouts and the listen backlog.

When the rdma_cm receives a connection request, it queues an MRA with
the ib_cm.  (The ib_cm will send an MRA if it receives a duplicate
REQ.)  The rdma_cm will then create a new rdma_cm_id and give that to
the user, which in this case is the rdma_user_cm.

If the listen backlog maintained in the rdma_user_cm is full, it
destroys the rdma_cm_id, which in turns destroys the ib_cm_id.  The
ib_cm_id generates a REJ because the state of the ib_cm_id has changed
to MRA sent, versus REQ received.  When the backlog is full, we just
want to drop the REQ so that it is retried later.

Fix this by deferring queuing the MRA until after the user of the
rdma_cm has examined the connection request.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-14 15:30:41 -08:00
Jack Morgenstein
e6028c0e00 IB/mlx4: mlx4_ib_fmr_alloc() should call mlx4_fmr_enable()
Currently mlx4_ib_fmr_alloc() calls mlx4_mr_enable() instead of
mlx4_fmr_enable().  The two functions are equivalent at the moment, but 
this is not really correct (and the change is needed to fix a bug).

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-14 10:39:36 -08:00
Eli Cohen
a9d1884925 IPoIB: Remove unused struct ipoib_cm_tx.ibwc member
struct ipoib_cm_tx.ibwc is unused since commit 1b524963 ("IPoIB/cm:
Use common CQ for CM send completions"), so remove it.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
2008-02-14 10:30:50 -08:00
Jack Morgenstein
167c42655c IPoIB: On P_Key change event, reset state properly
In P_Key event handling, if the old P_Key is no longer available, the
driver must call ipoib_ib_dev_stop() -- just as it does when the P_Key
is still available (see procedure __ipoib_ib_dev_flush()).

When a P_Key becomes available, the driver will perform ipoib_open(),
which assumes that the QP is in RESET, the cm_id has been
destroyed/deleted, etc.  If ipoib_ib_dev_stop() is not called as
described above, then these assumptions will be false, and the attempt
to bring the interface up will fail.

Found by Mellanox QA.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-14 10:15:06 -08:00
Marcin Slusarz
5163dc1a64 IB/mthca: Convert to use be16_add_cpu()
replace:

	big_endian_variable = cpu_to_beX(beX_to_cpu(big_endian_variable) +
						expression_in_cpu_byteorder);

with:

	beX_add_cpu(&big_endian_variable, expression_in_cpu_byteorder);

Generated with a semantic patch.

Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-13 07:47:47 -08:00
Steve Wise
8704e9a879 RDMA/cxgb3: Fail loopback connections
The cxgb3 HW and driver don't support loopback RDMA connections.  So
fail any connection attempt where the destination address is local.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-13 07:47:42 -08:00
Roland Dreier
7c7a9bccd2 IB/cm: Fix infiniband_cm class kobject ref counting
Commit 9af57b7a ("IB/cm: Add basic performance counters") introduced a
bug in how the reference count for cm_class.subsys.kobj was handled:
the path that released a device did a kobject_put() on that kobject, but
there was no kobject_get() in the path the handles adding a device.  So
the reference count ended up too low, which leads to bad things.  Fix up
and simplify the reference counting to avoid this.

(Actually, I introduced the bug when fixing the patch up to match some
of Greg's kobject changes, but who's counting)

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-12 14:38:27 -08:00
Roland Dreier
ab64b96067 IB/cm: Remove debug printk()s that snuck upstream
Pesky little devils, sneaking around...

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-12 14:38:27 -08:00
Roland Dreier
fe174357eb IB/mthca: Add missing sg_init_table() in mthca_map_user_db()
Usually harmless, since the scatterlist is always hard-coded to a length
of 1, but it triggers a BUG() if CONFIG_DEBUG_SG=y, so we better fix it.
This fixes <http://bugzilla.kernel.org/show_bug.cgi?id=9934>.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-12 14:38:22 -08:00
Eli Cohen
7143740d26 IPoIB: Add send gather support
This patch acts as a preparation for using checksum offload for IB
devices capable of inserting/verifying checksum in IP packets.  The
patch does not actaully turn on NETIF_F_SG - we defer that to the
patches adding checksum offload capabilities.

We only add support for send gathers for datagram mode, since existing
HW does not support checksum offload on connected QPs.

Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-08 14:32:37 -08:00
Eli Cohen
eb14032f9e IPoIB: Add high DMA feature flag
All current InfiniBand devices can handle all DMA addresses, and it's
hard to imagine anyone would be silly enough to build a new device
that couldn't.  Therefore, enable the NETIF_F_HIGHDMA feature for IPoIB.

This has no effect for no, but is needed when we enable gather/scatter
support and checksum stateless offloads.

Signed-off-by: Eli Cohen <eli@mellnaox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-08 13:39:26 -08:00
Jack Morgenstein
ea54b10c77 IB/mlx4: Use multiple WQ blocks to post smaller send WQEs
ConnectX HCA supports shrinking WQEs, so that a single work request
can be made of multiple units of wqe_shift.  This way, WRs can differ
in size, and do not have to be a power of 2 in size, saving memory and
speeding up send WR posting.  Unfortunately, if we do this then the
wqe_index field in CQEs can't be used to look up the WR ID anymore, so
our implementation does this only if selective signaling is off.

Further, on 32-bit platforms, we can't use vmap() to make the QP
buffer virtually contigious. Thus we have to use constant-sized WRs to
make sure a WR is always fully within a single page-sized chunk.

Finally, we use WRs with the NOP opcode to avoid wrapping around the
queue buffer in the middle of posting a WR, and we set the
NoErrorCompletion bit to avoid getting completions with error for NOP
WRs.  However, NEC is only supported starting with firmware 2.2.232,
so we use constant-sized WRs for older firmware.  And, since MLX QPs
only support SEND, we use constant-sized WRs in this case.

When stamping during NOP posting, do stamping following setting of the
NOP WQE valid bit.

Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-08 13:30:02 -08:00
Roland Dreier
1c69fc2a90 IB/mlx4: Consolidate code to get an entry from a struct mlx4_buf
We use struct mlx4_buf for kernel QP, CQ and SRQ buffers, and the code
to look up an entry is duplicated in get_cqe_from_buf() and the QP and
SRQ versions of get_wqe().  Factor this out into mlx4_buf_offset().

This will also make it easier to switch over to using vmap() for buffers.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-06 21:07:54 -08:00
Glenn Streiff
3c2d774cad RDMA/nes: Add a driver for NetEffect RNICs
Add a standard NIC and RDMA/iWARP driver for NetEffect 1/10Gb ethernet adapters.

Signed-off-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:45 -08:00
Olaf Kirch
2c78853472 IB/mthca: Return proper error codes from mthca_fmr_alloc()
If the allocation of the MTT or the mailbox failed, mthca_fmr_alloc()
would return 0 (success) no matter what. This leads to crashes a
little down the road, when we try to dereference eg mr->mtt, which was
really ERR_PTR(-Ewhatever).

Signed-off-by: Olaf Kirch <olaf.kirch@oracle.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:44 -08:00
Roland Dreier
f33afc26dc IB: Avoid marking __devinitdata as const
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:44 -08:00
Roland Dreier
68f3948dab IB/mlx4: Actually print out the driver version
The string mlx4_ib_version was defined, but never used.  Print out the
version once when the first device is initialized.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:44 -08:00
Eli Cohen
1d368c5465 IB/ib_mthca: Pre-link receive WQEs in Tavor mode
We have recently discovered that Tavor mode requires each WQE in a
posted list of receive WQEs to have a valid NDA field at all times.
This requirement holds true for regular QPs as well as for SRQs.  This
patch prelinks the receive queue in a regular QP and keeps the free
list in SRQ always properly linked.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Reviewed-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:44 -08:00
Eli Cohen
1203c42e7b IB/mthca: Remove checks for srq->first_free < 0
The SRQ receive posting functions make sure that srq->first_free never
becomes negative, so we can remove tests of whether it is negative.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:44 -08:00
Or Gerlitz
1d96354e61 IB/fmr_pool: Allocate page list for pool FMRs only when caching enabled
Allocate memory for the page_list field of struct ib_pool_fmr only
when caching is enabled for the FMR pool, since the field is not used
otherwise.  This can save significant amounts of memory for large
pools with caching turned off.

Signed-off-by: Or Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:44 -08:00
David Dillow
9fe4bcf45e IB/srp: Retry stale connections
When a host just goes away (crash, power loss, etc.) without tearing
down its IB connections, it can get stale connection errors when it
tries to reconnect to targets upon rebooting.  Retrying the connection
a few times will prevent sysadmins from playing the "which disk(s)
went missing?" game.

This would have made things slightly quicker when tracking down some
of the recent bugs, but it also helps quite a bit when you've got a
large number of targets hanging off a wedged server.

Signed-off-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:43 -08:00
Jack Morgenstein
893da75956 mlx4_core: Don't read reserved fields in mlx4_QUERY_ADAPTER()
The firmware QUERY_ADAPTER command does not return vendor_id,
device_id, and revision_id; eliminate these fields from the query.

Initialize the rev_id field of the mlx4 device via init_node_data (MAD
IFC query), as is done in the query_device verb implementation.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:43 -08:00
Jack Morgenstein
6ccef1de2c IB/mthca: Don't read reserved fields in mthca_QUERY_ADAPTER()
For memfree devices, the firmware QUERY_ADAPTER command does not
return vendor_id, device_id, and revision_id; do not return these
fields in the QUERY_ADAPTER function for memfree devices.

Instead, for memfree devices, initialize the rev_id field of the mthca
device via init_node_data (MAD IFC query), as is done in the
query_device verb implementation.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:43 -08:00
Or Gerlitz
7bc531dd88 IPoIB: Remove a misleading debug print
Commit 732a2170 ("IB/ipoib: Bound the net device to the ipoib_neigh
structue") left a misleading debug print (n->dev would be a bond
device only if boding is used).  Clean it up.

Signed-off-by: Or Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:43 -08:00
Or Gerlitz
bafff97417 IPoIB: Handle bonding failover race for connected neighbours too
Move up the code that checks for a situation where the remote GID
stored in the ipoib_neigh is different than the one present in the
neighbour (handle gratuitous ARP) or that a bonding fail over has
happened but the neighbour still has a pointer to an ipoib_neigh
created by a different device than the current slave.  This will cause
the driver to apply the check also for connected mode neighbours.

Signed-off-by: Or Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:43 -08:00
Roland Dreier
0d89fe2c0c IB/mthca: Fix and simplify page size calculation in mthca_reg_phys_mr()
In mthca_reg_phys_mr(), we calculate the page size for the HCA
hardware to use to map the buffer list passed in by the consumer.
For example, if the consumer passes in

    [0] addr 0x1000, size 0x1000
    [1] addr 0x2000, size 0x1000

then the algorithm would come up with a page size of 0x2000 and a list
of two pages, at 0x0000 and 0x2000.  Usually, this would work fine
since the memory region would start at an offset of 0x1000 and have a
length of 0x2000.

However, the old code did not take into account the alignment of the
IO virtual address passed in.  For example, if the consumer passed in
a virtual address of 0x6000 for the above, then the offset of 0x1000
would not be used correctly because the page mask of 0x1fff would
result in an offset of 0.

We can fix this quite neatly by making sure that the page shift we use
is no bigger than the first bit where the start of the first buffer
and the IO virtual address differ.  Also, we can further simplify the
code by removing the special case for a single buffer by noticing that
it doesn't matter if we use a page size that is too big.  This allows
the loop to compute the page shift to be replaced with __ffs().

Thanks to Bryan S Rosenburg <rosnbrg@us.ibm.com> for pointing out the
original bug and suggesting several ways to improve this patch.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:42 -08:00
Hoang-Nam Nguyen
2b5e6b120e IB/ehca: Add PMA support
This patch enables ehca to redirect any PMA queries to the
actual PMA QP.

Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
Reviewed-by: Joachim Fenkes <fenkes@de.ibm.com>
Reviewed-by: Christoph Raisch <raisch@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:42 -08:00