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

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

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

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

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

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

Calling arp_send() to initiate neighbour discovery (ND) doesn't do the
full ND protocol.  Namely, it doesn't handle retransmitting the arp
request if it is dropped. The function neigh_event_send() does all
this.  Without doing full ND, RDMA address resolution fails in the
presence of dropped ARP broadcast packets.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Acked-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

During ib_umem_get(), determine whether all pages from the memory
region are hugetlb pages and report this in the "hugetlb" member.
Low-level drivers can use this information if they need it.
Signed-off-by: NJoachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Export the ability to set the type of service to user space.  Model
the interface after setsockopt.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Provide support to specify a type of service for a communication
identifier.  A new function call is used when dealing with IPv4
addresses.  For IPv6 addresses, the ToS is specified through the
traffic class field in the sockaddr_in6 structure.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>

[ The comments Eitan Zahavi and myself have made over the v1 post at 
  <http://lists.openfabrics.org/pipermail/general/2007-August/039247.html>
  were fully addressed. ]
 
Reviewed-by: Or Gerlitz <ogerlitz@voltaire.com> 
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The QoS annex defines new fields for path records.  Add them to the
ib_sa for consumers that want to use them.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Reviewed-by: NOr Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

ib_create_send_mad() returns an error code pointer on error, not NULL.
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

A number of printks in fmr_pool.c dont have newlines, eg:

    fmr_create failed for FMR 0<5>FS-Cache: Loaded

Fix them up.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Fix sparse warning

    drivers/infiniband/core/device.c:142:6: warning: incorrect type in argument 1 (different signedness)
    drivers/infiniband/core/device.c:142:6:    expected unsigned long const *addr
    drivers/infiniband/core/device.c:142:6:    got long *[assigned] inuse

by making the local variable inuse unsigned.  Does not affect generated
code at all.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

After moving the definition of struct ib_umem_chunk from ib_verbs.h to
ib_umem.h there isn't any reason for the macro IB_UMEM_MAX_PAGE_CHUNK
to stay in ib_verbs.h.  Move the macro to umem.c, the only place where
it is used.
Signed-off-by: NDotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The address handle associated with dual-sided RMPP direction switch
ACKs is never destroyed.  Free the AH for ACKs which fall into this
category.

Problem was reported by Dotan Barak <dotanb@dev.mellanox.co.il>.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Nothing looks at the return value of agent_send_response(), so there's
no point in returning anything.
Signed-off-by: NHal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

If agent_send_response() returns an error, we shouldn't do anything
differently than if it succeeds; setting response to NULL just means
that the response buffer gets leaked.
Signed-off-by: NSuresh Shelvapille <suri@baymicrosystems.com>
Signed-off-by: NHal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

If ib_mad_recv_done_handler() fails to allocate response, then it just
printed a warning and continued, which leads to an oops if the MAD is
being handled for a switch device, because the switch code uses
response without checking for NULL.  Fix this by bailing out of the
function if the allocation fails.
Signed-off-by: NSuresh Shelvapille <suri@baymicrosystems.com>
Signed-off-by: NHal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Now that ib_find_pkey() ignores the membership bit of P_Keys, there's no
need for ib_sa to look for both 0x7fff and 0xffff in a port's P_Key table.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

ib_find_pkey() is used as a replacement for ib_find_cached_pkey(), and
the original function ignored the membership bit when searching for a
P_Key, so ib_find_pkey() should ignore the bit too.

In particular, IPoIB turns on the P_Key membership bit of limited
membership P_Keys when creating a child interface and looks for the
full membership P_key.  This broke if a port was a partial member of a
partition when IPoIB switched from ib_find_cached_pkey() to
ib_find_pkey(), and this change fixes things again.
Signed-off-by: NMoni Shoua <monis@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Slab destructors were no longer supported after Christoph's
c59def9f change. They've been
BUGs for both slab and slub, and slob never supported them
either.

This rips out support for the dtor pointer from kmem_cache_create()
completely and fixes up every single callsite in the kernel (there were
about 224, not including the slab allocator definitions themselves,
or the documentation references).
Signed-off-by: NPaul Mundt <lethal@linux-sh.org>

Transform some calls to kmalloc/memset to a single kzalloc (or kcalloc).

Here is a short excerpt of the semantic patch performing
this transformation:

@@
type T2;
expression x;
identifier f,fld;
expression E;
expression E1,E2;
expression e1,e2,e3,y;
statement S;
@@

 x =
- kmalloc
+ kzalloc
  (E1,E2)
  ...  when != \(x->fld=E;\|y=f(...,x,...);\|f(...,x,...);\|x=E;\|while(...) S\|for(e1;e2;e3) S\)
- memset((T2)x,0,E1);

@@
expression E1,E2,E3;
@@

- kzalloc(E1 * E2,E3)
+ kcalloc(E1,E2,E3)

[akpm@linux-foundation.org: get kcalloc args the right way around]
Signed-off-by: NYoann Padioleau <padator@wanadoo.fr>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Acked-by: NRussell King <rmk@arm.linux.org.uk>
Cc: Bryan Wu <bryan.wu@analog.com>
Acked-by: NJiri Slaby <jirislaby@gmail.com>
Cc: Dave Airlie <airlied@linux.ie>
Acked-by: NRoland Dreier <rolandd@cisco.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Acked-by: NDmitry Torokhov <dtor@mail.ru>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: NMauro Carvalho Chehab <mchehab@infradead.org>
Acked-by: NPierre Ossman <drzeus-list@drzeus.cx>
Cc: Jeff Garzik <jeff@garzik.org>
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: NGreg KH <greg@kroah.com>
Cc: James Bottomley <James.Bottomley@steeleye.com>
Cc: "Antonino A. Daplas" <adaplas@pol.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Local write permission makes no sense as part of the QP access flags,
since the access flags only control what the remote end of the
connection is allowed to do.  Remove the code in the RDMA CM that
initializes qp_access_flags with IB_ACCESS_LOCAL_WRITE.
Signed-off-by: NDotan Barak <dotanb@mellanox.co.il>
Acked-by: NSean Hefty <sean.hefty@intel.com>
Acked-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Signed-off-by: NRoland Dreier <rolandd@cisco.com>

sysfs is now completely out of driver/module lifetime game.  After
deletion, a sysfs node doesn't access anything outside sysfs proper,
so there's no reason to hold onto the attribute owners.  Note that
often the wrong modules were accounted for as owners leading to
accessing removed modules.

This patch kills now unnecessary attribute->owner.  Note that with
this change, userland holding a sysfs node does not prevent the
backing module from being unloaded.

For more info regarding lifetime rule cleanup, please read the
following message.

  http://article.gmane.org/gmane.linux.kernel/510293

(tweaked by Greg to not delete the field just yet, to make it easier to
merge things properly.)
Signed-off-by: NTejun Heo <htejun@gmail.com>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

If a SIDR REQ does not match a listen, we should reply with status
value 1 (service ID not supported), rather than dropping through to
the default case of status 2 (rejected by service provider).

Doing this also fixes a bug where the cm_id_priv is removed from the
remote_sidr_table twice.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Fix handling to duplicate SIDR REQs to avoid sending a reject if a
duplicate is detected.  Duplicates should just be silently discarded.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

cm_msgs.h uses definitions from ib_cm.h.  Include it directly, rather
than depending on a specific include order.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The IB CM should include the HCA ACK delay when calculating the local
ACK timeout value to use for RC QPs.  If the HCA ACK delay is large
enough relative to the packet life time, then if it is not taken into
account, the calculated timeout value ends up being too small, which
can result in "retry exceeded" errors.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The ib_cm is a little over zealous about using spin_lock_irqsave,
when spin_lock_irq would do.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

MADs sent to the SA should use the the default P_Key (0x7fff/0xffff).
There's no requirement that the default P_Key is stored at index 0 in
the local P_Key table, so add code to the sa_query module to look up
the index of the default P_Key when creating an address handle for the
SA (which is done any time the P_Key table might change), and use this
index for all SA queries.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

When allocating out_mad in show_pma_counter(), take sizeof *out_mad
instead of sizeof *in_mad.  It is true that today the type of in_mad
and out_mad are the same, but this patch will give us a cleaner code.
Signed-off-by: NDotan Barak <dotanb@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

gcc correctly warned:

drivers/infiniband/core/umem.c: In function 'ib_umem_get':
drivers/infiniband/core/umem.c:78: warning: 'ret' may be used uninitialized in this function

Set ret to 0 in case npages == 0 and the loop isn't entered at all.
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

A few files had 0xa0 characters in comments.  Remove them so that the 
files are clean ASCII text.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Extend the SMI with switch (intermediate hop) support. Care has been
taken to ensure that the CA (and router) code paths are changed as
little as possible.
Signed-off-by: NSuresh Shelvapille <suri@baymicrosystems.com>
Signed-off-by: NHal Rosenstock <halr@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

If ib_umem_release() is called after ib_uverbs_close() sets context->closing,
then a process can get stuck in a D state, because the code boils down to

	if (down_write_trylock(&mm->mmap_sem))
		down_write(&mm->mmap_sem);

which is obviously a stupid instant deadlock.  Fix the code so that we
only try to take the lock once.

This bug was introduced in commit f7c6a7b5 ("IB/uverbs: Export
ib_umem_get()/ib_umem_release() to modules") which fortunately never
made it into a release, and was reported by Pete Wyckoff <pw@osc.edu>.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

next_port should be between sysctl_local_port_range[0] and [1].
However, it is initially set to a random value with get_random_bytes().  
If the value is negative when treated as a signed integer, next_port
can end up outside the expected range because of the result of the % 
operator being negative.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The ib_cm can incorrectly detect a stale connection (a new connection
request for a QPN that is already connected) as a duplicate connection
request.  Separate the handling of potential duplicate REQs from stale
connections.
Signed-off-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

The IB CM uses an idr for local id allocations, with a running counter
as start_id.  This fails to generate distinct ids if

1. An id is constantly created and destroyed
2. A chunk of ids just beyond the current next_id value is occupied

This in turn leads to an increased chance of connection request being
mis-detected as a duplicate, sometimes for several retries, until
next_id gets past the block of allocated ids. This has been observed
in practice.

As a fix, remember the last id allocated and start immediately above it.
This also fixes a problem with the old code, where next_id might
overflow and become negative.
Signed-off-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Acked-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.

This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
   getting them indirectly

Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
   they don't need sched.h
b) sched.h stops being dependency for significant number of files:
   on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
   after patch it's only 3744 (-8.3%).

Cross-compile tested on

	all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
	alpha alpha-up
	arm
	i386 i386-up i386-defconfig i386-allnoconfig
	ia64 ia64-up
	m68k
	mips
	parisc parisc-up
	powerpc powerpc-up
	s390 s390-up
	sparc sparc-up
	sparc64 sparc64-up
	um-x86_64
	x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig

as well as my two usual configs.
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Clean up ib_query_port() and ib_modify_port() slightly by using the 
just-added start_port() and end_port() helpers.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Add ib_find_gid() and ib_find_pkey() functions that use uncached device
queries.  The calls might block but the returns are always up-to-date.
Cache P_Key and GID table lengths in core to avoid extra port info queries.
Signed-off-by: NYosef Etigin <yosefe@voltaire.com>
Acked-by: NMichael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Free umem when task's mm is already destroyed by the time
ib_umem_release gets called.

Found by Dotan Barak at Mellanox.
Signed-off-by: NEli Cohen <eli@mellanox.co.il>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>