linux-stable.git/drivers/infiniband/ulp/ipoib, branch linux-4.2.y

IB/ipoib: Fix CONFIG_INFINIBAND_IPOIB_CM

2015-07-24T15:34:26+00:00

If the above is turned off then ipoib_cm_dev_init unconditionally
returns ENOSYS, and the newly added error handling in
0b3957 prevents ipoib from coming up at all:

kernel: mlx4_0: ipoib_transport_dev_init failed
kernel: mlx4_0: failed to initialize port 1 (ret = -12)

Fixes: 0b39578bcde4 (IB/ipoib: Use dedicated workqueues per interface)
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Doug Ledford

IB/ipoib: Set MTU to max allowed by mode when mode changes

2015-07-14T17:20:13+00:00

When switching between modes (datagram / connected) change the MTU
accordingly.
datagram mode up to 4K, connected mode up to (64K - 0x10).

Signed-off-by: ELi Cohen 
Signed-off-by: Erez Shitrit 
Signed-off-by: Doug Ledford

IB/ipoib: Scatter-Gather support in connected mode

2015-07-14T17:20:13+00:00

By default, IPoIB-CM driver uses 64k MTU. Larger MTU gives better
performance.
This MTU plus overhead puts the memory allocation for IP based packets at
32 4k pages (order 5), which have to be contiguous.
When the system memory under pressure, it was observed that allocating 128k
contiguous physical memory is difficult and causes serious errors (such as
system becomes unusable).

This enhancement resolve the issue by removing the physically contiguous
memory requirement using Scatter/Gather feature that exists in Linux stack.

With this fix Scatter-Gather will be supported also in connected mode.

This change reverts some of the change made in commit e112373fd6aa
("IPoIB/cm: Reduce connected mode TX object size").

The ability to use SG in IPoIB CM is possible because the coupling
between NETIF_F_SG and NETIF_F_CSUM was removed in commit
ec5f06156423 ("net: Kill link between CSUM and SG features.")

Signed-off-by: Yuval Shaia 
Acked-by: Christian Marie 
Signed-off-by: Doug Ledford

IB/ipoib: Prevent lockdep warning in __ipoib_ib_dev_flush

2015-07-14T17:20:12+00:00

__ipoib_ib_dev_flush calls itself recursively on child devices, and lockdep
complains about locking vlan_rwsem twice (see below). Use down_read_nested
instead of down_read to prevent the warning.

 =============================================
 [ INFO: possible recursive locking detected ]
 4.1.0-rc4+ #36 Tainted: G           O
 ---------------------------------------------
 kworker/u20:2/261 is trying to acquire lock:
  (&priv->vlan_rwsem){.+.+..}, at: [] __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]

 but task is already holding lock:
  (&priv->vlan_rwsem){.+.+..}, at: [] __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&priv->vlan_rwsem);
   lock(&priv->vlan_rwsem);

  *** DEADLOCK ***

  May be due to missing lock nesting notation

 3 locks held by kworker/u20:2/261:
  #0:  ("%s""ipoib_flush"){.+.+..}, at: [] process_one_work+0x15c/0x760
  #1:  ((&priv->flush_heavy)){+.+...}, at: [] process_one_work+0x15c/0x760
  #2:  (&priv->vlan_rwsem){.+.+..}, at: [] __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]

 stack backtrace:
 CPU: 3 PID: 261 Comm: kworker/u20:2 Tainted: G           O    4.1.0-rc4+ #36
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2007
 Workqueue: ipoib_flush ipoib_ib_dev_flush_heavy [ib_ipoib]
  ffff8801c6c54790 ffff8801c9927af8 ffffffff81665238 0000000000000001
  ffffffff825b5b30 ffff8801c9927bd8 ffffffff810bba51 ffff880100000000
  ffffffff00000001 ffff880100000001 ffff8801c6c55428 ffff8801c6c54790
 Call Trace:
  [] dump_stack+0x4f/0x6f
  [] __lock_acquire+0x741/0x1820
  [] lock_acquire+0xc8/0x240
  [] ? __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]
  [] down_read+0x4c/0x70
  [] ? __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]
  [] __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]
  [] __ipoib_ib_dev_flush+0x5a/0x2b0 [ib_ipoib]
  [] ipoib_ib_dev_flush_heavy+0x1a/0x20 [ib_ipoib]
  [] process_one_work+0x201/0x760
  [] ? process_one_work+0x15c/0x760
  [] worker_thread+0x120/0x4d0
  [] ? process_one_work+0x760/0x760
  [] ? process_one_work+0x760/0x760
  [] kthread+0xfe/0x120
  [] ? __init_kthread_worker+0x70/0x70
  [] ret_from_fork+0x42/0x70
  [] ? __init_kthread_worker+0x70/0x70

Signed-off-by: Haggai Eran 
Signed-off-by: Doug Ledford

IB/IPoIB: Fix bad error flow in ipoib_add_port()

2015-07-14T17:20:10+00:00

Error values of ib_query_port() and ib_query_device() weren't propagated
correctly. Because of that, ipoib_add_port() could return NULL value,
which escaped the IS_ERR() check in ipoib_add_one() and we crashed.

Signed-off-by: Amir Vadai 
Signed-off-by: Or Gerlitz 
Reviewed-by: Ira Weiny 
Signed-off-by: Doug Ledford

IB: Add rdma_cap_ib_switch helper and use where appropriate

2015-07-14T17:20:08+00:00

Persuant to Liran's comments on node_type on linux-rdma
mailing list:

In an effort to reform the RDMA core and ULPs to minimize use of
node_type in struct ib_device, an additional bit is added to
struct ib_device for is_switch (IB switch). This is needed
to be initialized by any IB switch device driver. This is a
NEW requirement on such device drivers which are all
"out of tree".

In addition, an ib_switch helper was added to ib_verbs.h
based on the is_switch device bit rather than node_type
(although those should be consistent).

The RDMA core (MAD, SMI, agent, sa_query, multicast, sysfs)
as well as (IPoIB and SRP) ULPs are updated where
appropriate to use this new helper. In some cases,
the helper is now used under the covers of using
rdma_[start end]_port rather than the open coding
previously used.

Reviewed-by: Sean Hefty 
Reviewed-By: Jason Gunthorpe 
Reviewed-by: Ira Weiny 
Tested-by: Ira Weiny 
Signed-off-by: Hal Rosenstock 
Signed-off-by: Doug Ledford

IB/core: Change ib_create_cq to use struct ib_cq_init_attr

2015-06-12T18:49:10+00:00

Currently, ib_create_cq uses cqe and comp_vecotr instead
of the extendible ib_cq_init_attr struct.

Earlier patches already changed the vendors to work with
ib_cq_init_attr. This patch changes the consumers too.

Signed-off-by: Matan Barak 
Signed-off-by: Or Gerlitz 
Signed-off-by: Doug Ledford

Merge branch 'for-4.2-misc' into k.o/for-4.2

2015-06-02T13:33:22+00:00

IB/ipoib: Fix RCU annotations in ipoib_neigh_hash_init()

2015-06-02T13:22:31+00:00

Avoid that sparse complains about ipoib_neigh_hash_init(). This
patch does not change any functionality. See also patch "IPoIB:
Fix memory leak in the neigh table deletion flow" (commit ID
66172c09938b).

Signed-off-by: Bart Van Assche 
Cc: Shlomo Pongratz 
Signed-off-by: Doug Ledford

IB/Verbs: Reform IB-ulp ipoib

2015-05-18T17:35:04+00:00

Use raw management helpers to reform IB-ulp ipoib.

Signed-off-by: Michael Wang 
Reviewed-by: Ira Weiny 
Tested-by: Ira Weiny 
Reviewed-by: Sean Hefty 
Reviewed-by: Jason Gunthorpe 
Tested-by: Doug Ledford 
Signed-off-by: Doug Ledford