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 e112373f
("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
ec5f0615 ("net: Kill link between CSUM and SG features.")
Signed-off-by: NYuval Shaia <yuval.shaia@oracle.com>
Acked-by: NChristian Marie <christian@ponies.io>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

__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: [<ffffffffa0791e2a>] __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]

 but task is already holding lock:
  (&priv->vlan_rwsem){.+.+..}, at: [<ffffffffa0791e2a>] __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: [<ffffffff810827cc>] process_one_work+0x15c/0x760
  #1:  ((&priv->flush_heavy)){+.+...}, at: [<ffffffff810827cc>] process_one_work+0x15c/0x760
  #2:  (&priv->vlan_rwsem){.+.+..}, at: [<ffffffffa0791e2a>] __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:
  [<ffffffff81665238>] dump_stack+0x4f/0x6f
  [<ffffffff810bba51>] __lock_acquire+0x741/0x1820
  [<ffffffff810bcbf8>] lock_acquire+0xc8/0x240
  [<ffffffffa0791e2a>] ? __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]
  [<ffffffff81669d2c>] down_read+0x4c/0x70
  [<ffffffffa0791e2a>] ? __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]
  [<ffffffffa0791e2a>] __ipoib_ib_dev_flush+0x3a/0x2b0 [ib_ipoib]
  [<ffffffffa0791e4a>] __ipoib_ib_dev_flush+0x5a/0x2b0 [ib_ipoib]
  [<ffffffffa07920ba>] ipoib_ib_dev_flush_heavy+0x1a/0x20 [ib_ipoib]
  [<ffffffff81082871>] process_one_work+0x201/0x760
  [<ffffffff810827cc>] ? process_one_work+0x15c/0x760
  [<ffffffff81082ef0>] worker_thread+0x120/0x4d0
  [<ffffffff81082dd0>] ? process_one_work+0x760/0x760
  [<ffffffff81082dd0>] ? process_one_work+0x760/0x760
  [<ffffffff81088b7e>] kthread+0xfe/0x120
  [<ffffffff81088a80>] ? __init_kthread_worker+0x70/0x70
  [<ffffffff8166c6e2>] ret_from_fork+0x42/0x70
  [<ffffffff81088a80>] ? __init_kthread_worker+0x70/0x70
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

As the result of a completion error the QP can moved to SQE state by
the hardware. Since it's not the Error state, there are no flushes
and hence the driver doesn't know about that.

The fix creates a task that after completion with error which is not a
flush tracks the QP state and if it is in SQE state moves it back to RTS.
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The current code in the RX flow uses two sg entries for each incoming
packet, the first one was for the IB headers and the second for the rest
of the data, that causes two  dma map/unmap and two allocations, and few
more actions that were done at the data path.

Use only one linear skb on each incoming packet, for the data (IB
headers and payload), that reduces the packet processing in the
data-path (only one skb, no frags, the first frag was not used anyway,
less memory allocations) and the dma handling (only one dma map/unmap
over each incoming packet instead of two map/unmap per each incoming packet).

After commit 73d3fe6d ("gro: fix aggregation for skb using frag_list") from
Eric Dumazet, we will get full aggregation for large packets.

When running bandwidth tests before and after the (over the card's numa node),
using "netperf -H 1.1.1.3 -T -t TCP_STREAM", the results before are ~12Gbs before
and after ~16Gbs on my setup (Mellanox's ConnectX3).
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Various places in the IPoIB code had a deadlock related to flushing
the ipoib workqueue.  Now that we have per device workqueues and a
specific flush workqueue, there is no longer a deadlock issue with
flushing the device specific workqueues and we can do so unilaterally.
Signed-off-by: NDoug Ledford <dledford@redhat.com>

During my recent work on the rtnl lock deadlock in the IPoIB driver, I
saw that even once I fixed the apparent races for a single device, as
soon as that device had any children, new races popped up.  It turns
out that this is because no matter how well we protect against races
on a single device, the fact that all devices use the same workqueue,
and flush_workqueue() flushes *everything* from that workqueue means
that we would also have to prevent all races between different devices
(for instance, ipoib_mcast_restart_task on interface ib0 can race with
ipoib_mcast_flush_dev on interface ib0.8002, resulting in a deadlock on
the rtnl_lock).

There are several possible solutions to this problem:

Make carrier_on_task and mcast_restart_task try to take the rtnl for
some set period of time and if they fail, then bail.  This runs the
real risk of dropping work on the floor, which can end up being its
own separate kind of deadlock.

Set some global flag in the driver that says some device is in the
middle of going down, letting all tasks know to bail.  Again, this can
drop work on the floor.

Or the method this patch attempts to use, which is when we bring an
interface up, create a workqueue specifically for that interface, so
that when we take it back down, we are flushing only those tasks
associated with our interface.  In addition, keep the global
workqueue, but now limit it to only flush tasks.  In this way, the
flush tasks can always flush the device specific work queues without
having deadlock issues.
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Create a an ipoib_flush_ah and ipoib_stop_ah routines to use at
appropriate times to flush out all remaining ah entries before we shut
the device down.

Because neighbors and mcast entries can each have a reference on any
given ah, we must make sure to free all of those first before our ah
will actually have a 0 refcount and be able to be reaped.

This factoring is needed in preparation for having per-device work
queues.  The original per-device workqueue code resulted in the following
error message:

<ibdev>: ib_dealloc_pd failed

That error was tracked down to this issue.  With the changes to which
workqueues were flushed when, there were no flushes of the per device
workqueue after the last ah's were freed, resulting in an attempt to
dealloc the pd with outstanding resources still allocated.  This code
puts the explicit flushes in the needed places to avoid that problem.
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This reverts commit 5141861c.

The series of IPoIB bug fixes that went into 3.19-rc1 introduce
regressions, and after trying to sort things out, we decided to revert
to 3.18's IPoIB driver and get things right for 3.20.
Signed-off-by: NRoland Dreier <roland@purestorage.com>

This reverts commit bb42a6dd.

The series of IPoIB bug fixes that went into 3.19-rc1 introduce
regressions, and after trying to sort things out, we decided to revert
to 3.18's IPoIB driver and get things right for 3.20.
Signed-off-by: NRoland Dreier <roland@purestorage.com>

This reverts commit ce347ab9.

The series of IPoIB bug fixes that went into 3.19-rc1 introduce
regressions, and after trying to sort things out, we decided to revert
to 3.18's IPoIB driver and get things right for 3.20.
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Various places in the IPoIB code had a deadlock related to flushing
the ipoib workqueue.  Now that we have per device workqueues and a
specific flush workqueue, there is no longer a deadlock issue with
flushing the device specific workqueues and we can do so unilaterally.
Signed-off-by: NDoug Ledford <dledford@redhat.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

We used to pass a flush variable to mcast_stop_thread to indicate if
we should flush the workqueue or not.  This was due to some code
trying to flush a workqueue that it was currently running on which is
a no-no.  Now that we have per-device work queues, and now that
ipoib_mcast_restart_task has taken the fact that it is queued on a
single thread workqueue with all of the ipoib_mcast_join_task's and
therefore has no need to stop the join task while it runs, we can do
away with the flush parameter and unilaterally flush always.
Signed-off-by: NDoug Ledford <dledford@redhat.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

During my recent work on the rtnl lock deadlock in the IPoIB driver, I
saw that even once I fixed the apparent races for a single device, as
soon as that device had any children, new races popped up.  It turns
out that this is because no matter how well we protect against races
on a single device, the fact that all devices use the same workqueue,
and flush_workqueue() flushes *everything* from that workqueue, we can
have one device in the middle of a down and holding the rtnl lock and
another totally unrelated device needing to run mcast_restart_task,
which wants the rtnl lock and will loop trying to take it unless is
sees its own FLAG_ADMIN_UP flag go away.  Because the unrelated
interface will never see its own ADMIN_UP flag drop, the interface
going down will deadlock trying to flush the queue.  There are several
possible solutions to this problem:

Make carrier_on_task and mcast_restart_task try to take the rtnl for
some set period of time and if they fail, then bail.  This runs the
real risk of dropping work on the floor, which can end up being its
own separate kind of deadlock.

Set some global flag in the driver that says some device is in the
middle of going down, letting all tasks know to bail.  Again, this can
drop work on the floor.  I suppose if our own ADMIN_UP flag doesn't go
away, then maybe after a few tries on the rtnl lock we can queue our
own task back up as a delayed work and return and avoid dropping work
on the floor that way.  But I'm not 100% convinced that we won't cause
other problems.

Or the method this patch attempts to use, which is when we bring an
interface up, create a workqueue specifically for that interface, so
that when we take it back down, we are flushing only those tasks
associated with our interface.  In addition, keep the global
workqueue, but now limit it to only flush tasks.  In this way, the
flush tasks can always flush the device specific work queues without
having deadlock issues.
Signed-off-by: NDoug Ledford <dledford@redhat.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Currently, the parent interface keeps sending broadcast group join
requests even if p_key index 0 is invalid, which is possible/common in
virtualized environments where a VF has been probed to VM but the
actual P_key configuration has not yet been assigned by the management
software. This creates unnecessary noise on the fabric and in the
kernel logs:

    ib0: multicast join failed for ff12:401b:8000:0000:0000:0000:ffff:ffff, status -22

The original code run the multicast task regardless of the actual
P_key value, which can be avoided. The fix is to re-init resources and
bring interface up only if P_key index 0 is valid either when starting
up or on PKEY_CHANGE event.

Fixes: c2904141 ("IPoIB: Fix pkey change flow for virtualization environments")
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Signed-off-by: NAlex Estrin <alex.estrin@intel.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The error flow of ipoib_ib_dev_open() invokes ipoib_ib_dev_stop() with
workqueue flushing enabled, which deadlocks if the open procedure
itself was called by a worker thread.

Fix this by adding a flush enabled flag to ipoib_ib_dev_open() and set
it accordingly from the locations where such a call is made.

The call trace was the following:

 [<ffffffff81095bc4>] ? flush_workqueue+0x54/0x80
 [<ffffffffa056c657>] ? ipoib_ib_dev_stop+0x447/0x650 [ib_ipoib]
 [<ffffffffa056cc34>] ? ipoib_ib_dev_open+0x284/0x430 [ib_ipoib]
 [<ffffffffa05674a8>] ? ipoib_open+0x78/0x1d0 [ib_ipoib]
 [<ffffffffa05697b8>] ? ipoib_pkey_open+0x38/0x40 [ib_ipoib]
 [<ffffffffa056cf3c>] ? __ipoib_ib_dev_flush+0x15c/0x2c0 [ib_ipoib]
 [<ffffffffa056ce56>] ? __ipoib_ib_dev_flush+0x76/0x2c0 [ib_ipoib]
 [<ffffffffa056d0a0>] ? ipoib_ib_dev_flush_heavy+0x0/0x20 [ib_ipoib]
 [<ffffffffa056d0ba>] ? ipoib_ib_dev_flush_heavy+0x1a/0x20 [ib_ipoib]
 [<ffffffff81094d20>] ? worker_thread+0x170/0x2a0
 [<ffffffff8109b2a0>] ? autoremove_wake_function+0x0/0x40
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Acked-by: NAlex Estrin <alex.estrin@intel.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The current code use a dedicated polling logic to determine when the P_Key
assigned to the ipoib device is present in HCA port table and act accordingly.

Move to use the code which acts upon getting PKEY_CHANGE event to handle this
task and remove the P_Key polling logic/thread as they add extra complexity
which isn't needed.
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Acked-by: NAlex Estrin <alex.estrin@intel.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The path_rec_completion() callback may be invoked asynchronously even
at the middle of "driver uninit" process.  This can lead to scheduling
a task that tries to touch members of the priv object that are no
longer valid.  For example the function cm_create_tx_qp can attempt to
create qp with no valid priv->pd object.

The following crash is one of the results:
RIP: 0010:[<ffffffffa021bb47>]  [<ffffffffa021bb47>] ipoib_cm_create_tx_qp+0x57/0x90 [ib_ipoib]
Process ipoib (pid: 5916, threadinfo ffff8803786e4000, task ffff8804150e1500)
Stack:
Call Trace:
[<ffffffff81309ef0>] ? get_random_bytes+0x20/0x30
[<ffffffffa021be2a>] ipoib_cm_tx_init+0xca/0x340 [ib_ipoib]
[<ffffffffa021f765>] ipoib_cm_tx_start+0x215/0x3f0 [ib_ipoib]
[<ffffffffa021f550>] ? ipoib_cm_tx_start+0x0/0x3f0 [ib_ipoib]
[<ffffffff8108b2b0>] worker_thread+0x170/0x2a0
[<ffffffff81090bf0>] ? autoremove_wake_function+0x0/0x40
[<ffffffff8108b140>] ? worker_thread+0x0/0x2a0
[<ffffffff81090886>] kthread+0x96/0xa0
[<ffffffff8100c14a>] child_rip+0xa/0x20
[<ffffffff810907f0>] ? kthread+0x0/0xa0
[<ffffffff8100c140>] ? child_rip+0x0/0x20

Fix that by flushing all pending path queries at this point.
Signed-off-by: NAlex Markuze <markuze@mellanox.com>
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

The driver should not flush the whole workqueue when only one work (the
pkey poll one) needs to be cancelled.  Use cancel_delayed_work_sync()
instead.
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

When ipoib interface is going down it takes all of its children with
it, under mutex.

For each child, dev_change_flags() is called.  That function calls
ipoib_stop() via the ndo, and causes flush of the workqueue.
Sometimes in the workqueue an __ipoib_dev_flush work() is waiting and
when invoked tries to get the same mutex, which leads to a deadlock,
as seen below.

The solution is to switch to rw-sem instead of mutex.

The deadlock:
[11028.165303]  [<ffffffff812b0977>] ? vgacon_scroll+0x107/0x2e0
[11028.171844]  [<ffffffff814eaac5>] schedule_timeout+0x215/0x2e0
[11028.178465]  [<ffffffff8105a5c3>] ? perf_event_task_sched_out+0x33/0x80
[11028.185962]  [<ffffffff814ea743>] wait_for_common+0x123/0x180
[11028.192491]  [<ffffffff8105fa40>] ? default_wake_function+0x0/0x20
[11028.199504]  [<ffffffff814ea85d>] wait_for_completion+0x1d/0x20
[11028.206224]  [<ffffffff8108b4f1>] flush_cpu_workqueue+0x61/0x90
[11028.212948]  [<ffffffff8108b5a0>] ? wq_barrier_func+0x0/0x20
[11028.219375]  [<ffffffff8108bfc4>] flush_workqueue+0x54/0x80
[11028.225712]  [<ffffffffa05a0576>] ipoib_mcast_stop_thread+0x66/0x90 [ib_ipoib]
[11028.233988]  [<ffffffffa059ccea>] ipoib_ib_dev_down+0x6a/0x100 [ib_ipoib]
[11028.241678]  [<ffffffffa059849a>] ipoib_stop+0x8a/0x140 [ib_ipoib]
[11028.248692]  [<ffffffff8142adf1>] dev_close+0x71/0xc0
[11028.254447]  [<ffffffff8142a631>] dev_change_flags+0xa1/0x1d0
[11028.261062]  [<ffffffffa059851b>] ipoib_stop+0x10b/0x140 [ib_ipoib]
[11028.268172]  [<ffffffff8142adf1>] dev_close+0x71/0xc0
[11028.273922]  [<ffffffff8142a631>] dev_change_flags+0xa1/0x1d0
[11028.280452]  [<ffffffff8148f20b>] devinet_ioctl+0x5eb/0x6a0
[11028.286786]  [<ffffffff814903b8>] inet_ioctl+0x88/0xa0
[11028.292633]  [<ffffffff8141591a>] sock_ioctl+0x7a/0x280
[11028.298576]  [<ffffffff81189012>] vfs_ioctl+0x22/0xa0
[11028.304326]  [<ffffffff81140540>] ? unmap_region+0x110/0x130
[11028.310756]  [<ffffffff811891b4>] do_vfs_ioctl+0x84/0x580
[11028.316897]  [<ffffffff81189731>] sys_ioctl+0x81/0xa0

and

11028.017533]  [<ffffffff8105a5c3>] ? perf_event_task_sched_out+0x33/0x80
[11028.025030]  [<ffffffff8100bb8e>] ? apic_timer_interrupt+0xe/0x20
[11028.031945]  [<ffffffff814eb2ae>] __mutex_lock_slowpath+0x13e/0x180
[11028.039053]  [<ffffffff814eb14b>] mutex_lock+0x2b/0x50
[11028.044910]  [<ffffffffa059f7e7>] __ipoib_ib_dev_flush+0x37/0x210 [ib_ipoib]
[11028.052894]  [<ffffffffa059fa00>] ? ipoib_ib_dev_flush_light+0x0/0x20 [ib_ipoib]
[11028.061363]  [<ffffffffa059fa17>] ipoib_ib_dev_flush_light+0x17/0x20 [ib_ipoib]
[11028.069738]  [<ffffffff8108b120>] worker_thread+0x170/0x2a0
[11028.076068]  [<ffffffff81090990>] ? autoremove_wake_function+0x0/0x40
[11028.083374]  [<ffffffff8108afb0>] ? worker_thread+0x0/0x2a0
[11028.089709]  [<ffffffff81090626>] kthread+0x96/0xa0
[11028.095266]  [<ffffffff8100c0ca>] child_rip+0xa/0x20
[11028.100921]  [<ffffffff81090590>] ? kthread+0x0/0xa0
[11028.106573]  [<ffffffff8100c0c0>] ? child_rip+0x0/0x20
[11028.112423] INFO: task ifconfig:23640 blocked for more than 120 seconds.
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

If napi has never been enabled when calling ipoib_ib_dev_stop, a
kernel crash occurs, because the verbs layer completion handler
(ipoib_ib_completion) calls napi_schedule unconditionally.

If the napi structure passed in the napi_schedule call has not
been initialized, napi will crash.

The cleanest solution is to simply enable napi before calling
ipoib_ib_dev_stop in the dev_open error flow. (dev_stop then
immediately disables napi).
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

IPoIB's required behaviour w.r.t to the pkey used by the device is the following:

- For "parent" interfaces (e.g ib0, ib1, etc) who are created
  automatically as a result of hot-plug events from the IB core, the
  driver needs to take whatever pkey vlaue it finds in index 0, and
  stick to that index.

- For child interfaces (e.g ib0.8001, etc) created by admin directive,
  the driver needs to use and stick to the value provided during its
  creation.

In SR-IOV environment its possible for the VF probe to take place
before the cloud management software provisions the suitable pkey for
the VF in the paravirtualed PKEY table index 0. When this is the case,
the VF IB stack will find in index 0 an invalide pkey, which is all
zeros.

Moreover, the cloud managment can assign the pkey value at index 0 at
any time of the guest life cycle.

The correct behavior for IPoIB to address these requirements for
parent interfaces is to use PKEY_CHANGE event as trigger to optionally
re-init the device pkey value and re-create all the relevant resources
accordingly, if the value of the pkey in index 0 has changed (from
invalid to valid or from valid value X to invalid value Y).

This patch enhances the heavy flushing code which is triggered by pkey
change event, to behave correctly for parent devices. For child
devices, the code remains the same, namely chases pkey value and not
index.
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

After commit b13912bb ("IPoIB: Call skb_dst_drop() once skb is
enqueued for sending"), using connected mode and running multithreaded
iperf for long time, ie

    iperf -c <IP> -P 16 -t 3600

results in a crash.

After the above-mentioned patch, the driver is calling skb_orphan() and
skb_dst_drop() after calling post_send() in ipoib_cm.c::ipoib_cm_send()
(also in ipoib_ib.c::ipoib_send())

The problem with this is, as is written in a comment in both routines,
"it's entirely possible that the completion handler will run before we
execute anything after the post_send()."  This leads to running the
skb cleanup routines simultaneously in two different contexts.

The solution is to always perform the skb_orphan() and skb_dst_drop()
before queueing the send work request.  If an error occurs, then it
will be no different than the regular case where dev_free_skb_any() in
the completion path, which is assumed to be after these two routines.
Signed-off-by: NShlomo Pongratz <shlomop@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Currently, IPoIB delays collecting send completions for TX packets in
order to batch work more efficiently.  It does skb_orphan() right after
queuing the packets so that destructors run early, to avoid problems
like holding socket send buffers for too long (since we might not
collect a send completion until a long time after the packet is
actually sent).

However, IPoIB clears IFF_XMIT_DST_RELEASE because it actually looks
at skb_dst() to update the PMTU when it gets a too-long packet.  This
means that the packets sitting in the TX ring with uncollected send
completions are holding a reference on the dst.  We've seen this lead
to pathological behavior with respect to route and neighbour GC.  The
easy fix for this is to call skb_dst_drop() when we call skb_orphan().

Also, give packets sent via connected mode (CM) the same skb_orphan()
/ skb_dst_drop() treatment that packets sent via datagram mode get.
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Or Gerlitz reported triggering of WARN_ON_ONCE(delta < len); in
skb_try_coalesce()
This warning tracks drivers that incorrectly set skb->truesize

IPoIB indeed allocates a full page to store a fragment, but only
accounts in skb->truesize the used part of the page (frame length)

This patch fixes skb truesize underestimation, and
also fixes a performance issue, because RX skbs have not enough tailroom
to allow IP and TCP stacks to pull their header in skb linear part
without an expensive call to pskb_expand_head()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NOr Gerlitz <ogerlitz@mellanox.com>
Cc: Erez Shitrit <erezsh@mellanox.com>
Cc: Shlomo Pongartz <shlomop@mellanox.com>
Cc: Roland Dreier <roland@purestorage.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use a bit in wc_flags rather then a whole integer to hold the
"checksum OK" flag.  By itself, this change doesn't reduce the size of
struct ib_wc on 64bit machines -- it stays on 56 bytes because of
padding.  However, it will allow to add more fields in the future
without enlarging the struct.  Also, it will let us have a unified
approach with future libibverbs checksum offload reporting, because a
bit flag doesn't break the library ABI.

This patch was suggested during conversation with Liran Liss
<liranl@mellanox.com>.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: NSean Hefty <sean.hefty@intel.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

This following can occur with ipoib when processing a multicast reponse:

    BUG: soft lockup - CPU#0 stuck for 67s! [ib_mad1:982]
    Modules linked in: ...
    CPU 0:
    Modules linked in: ...
    Pid: 982, comm: ib_mad1 Not tainted 2.6.32-131.0.15.el6.x86_64 #1 ProLiant DL160 G5
    RIP: 0010:[<ffffffff814ddb27>]  [<ffffffff814ddb27>] _spin_unlock_irqrestore+0x17/0x20
    RSP: 0018:ffff8802119ed860  EFLAGS: 00000246
    0000000000000004 RBX: ffff8802119ed860 RCX: 000000000000a299
    RDX: ffff88021086c700 RSI: 0000000000000246 RDI: 0000000000000246
    RBP: ffffffff8100bc8e R08: ffff880210ac229c R09: 0000000000000000
    R10: ffff88021278aab8 R11: 0000000000000000 R12: ffff8802119ed860
    R13: ffffffff8100be6e R14: 0000000000000001 R15: 0000000000000003
    FS:  0000000000000000(0000) GS:ffff880028200000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0018 ES: 0018 CR0: 000000008005003b
    CR2: 00000000006d4840 CR3: 0000000209aa5000 CR4: 00000000000406f0
    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
    Call Trace:
    [<ffffffffa032c247>] ? ipoib_mcast_send+0x157/0x480 [ib_ipoib]
    [<ffffffff8100bc8e>] ? apic_timer_interrupt+0xe/0x20
    [<ffffffff8100bc8e>] ? apic_timer_interrupt+0xe/0x20
    [<ffffffffa03283d4>] ? ipoib_path_lookup+0x124/0x2d0 [ib_ipoib]
    [<ffffffffa03286fc>] ? ipoib_start_xmit+0x17c/0x430 [ib_ipoib]
    [<ffffffff8141e758>] ? dev_hard_start_xmit+0x2c8/0x3f0
    [<ffffffff81439d0a>] ? sch_direct_xmit+0x15a/0x1c0
    [<ffffffff81423098>] ? dev_queue_xmit+0x388/0x4d0
    [<ffffffffa032d6b7>] ? ipoib_mcast_join_finish+0x2c7/0x510 [ib_ipoib]
    [<ffffffffa032dab8>] ? ipoib_mcast_sendonly_join_complete+0x1b8/0x1f0 [ib_ipoib]
    [<ffffffffa02a0946>] ? mcast_work_handler+0x1a6/0x710 [ib_sa]
    [<ffffffffa015f01e>] ? ib_send_mad+0xfe/0x3c0 [ib_mad]
    [<ffffffffa00f6c93>] ? ib_get_cached_lmc+0xa3/0xb0 [ib_core]
    [<ffffffffa02a0f9b>] ? join_handler+0xeb/0x200 [ib_sa]
    [<ffffffffa029e4fc>] ? ib_sa_mcmember_rec_callback+0x5c/0xa0 [ib_sa]
    [<ffffffffa029e79c>] ? recv_handler+0x3c/0x70 [ib_sa]
    [<ffffffffa01603a4>] ? ib_mad_completion_handler+0x844/0x9d0 [ib_mad]
    [<ffffffffa015fb60>] ? ib_mad_completion_handler+0x0/0x9d0 [ib_mad]
    [<ffffffff81088830>] ? worker_thread+0x170/0x2a0
    [<ffffffff8108e160>] ? autoremove_wake_function+0x0/0x40
    [<ffffffff810886c0>] ? worker_thread+0x0/0x2a0
    [<ffffffff8108ddf6>] ? kthread+0x96/0xa0
    [<ffffffff8100c1ca>] ? child_rip+0xa/0x20

Coinciding with stack trace is the following message:

    ib0: ib_address_create failed

The code below in ipoib_mcast_join_finish() will note the above
failure in the address handle but otherwise continue:

                ah = ipoib_create_ah(dev, priv->pd, &av);
                if (!ah) {
                        ipoib_warn(priv, "ib_address_create failed\n");
                } else {

The while loop at the bottom of ipoib_mcast_join_finish() will attempt
to send queued multicast packets in mcast->pkt_queue and eventually
end up in ipoib_mcast_send():

        if (!mcast->ah) {
                if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
                        skb_queue_tail(&mcast->pkt_queue, skb);
                else {
                        ++dev->stats.tx_dropped;
                        dev_kfree_skb_any(skb);
                }

My read is that the code will requeue the packet and return to the
ipoib_mcast_join_finish() while loop and the stage is set for the
"hung" task diagnostic as the while loop never sees a non-NULL ah, and
will do nothing to resolve.

There are GFP_ATOMIC allocates in the provider routines, so this is
possible and should be dealt with.

The test that induced the failure is associated with a host SM on the
same server during a shutdown.

This patch causes ipoib_mcast_join_finish() to exit with an error
which will flush the queued mcast packets.  Nothing is done to unwind
the QP attached state so that subsequent sends from above will retry
the join.
Reviewed-by: NRam Vepa <ram.vepa@qlogic.com>
Reviewed-by: NGary Leshner <gary.leshner@qlogic.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

These files were getting the moduleparam infrastructure from the
implicit presence of module.h being everywhere, but that is going
away soon.
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

To ease skb->truesize sanitization, its better to be able to localize
all references to skb frags size.

Define accessors : skb_frag_size() to fetch frag size, and
skb_frag_size_{set|add|sub}() to manipulate it.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Reviewed-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Roland Dreier <roland@kernel.org>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Cc: linux-rdma@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NMichał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NOr Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

As a first step in moving from LRO to GRO, revert commit af40da89
("IPoIB: add LRO support").  Also eliminate the ethtool set_flags
callback which isn't needed anymore.  Finally, we need to include
<linux/sched.h> directly to get the declaration of restart_syscall()
(which used to be included implicitly through <linux/inet_lro.h>).

Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Vladimir Sokolovsky <vlad@mellanox.co.il>
Signed-off-by: NOr Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

IGMP processing is broken because the IPOIB does not set the
skb->pkt_type the right way for multicast traffic.  All incoming
packets are set to PACKET_HOST which means that igmp_recv() will
ignore the IGMP broadcasts/multicasts.

This in turn means that the IGMP timers are firing and are sending
information about multicast subscriptions unnecessarily.  In a large
private network this can cause traffic spikes.
Signed-off-by: NChristoph Lameter <cl@linux.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h

percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: NTejun Heo <tj@kernel.org>
Guess-its-ok-by: NChristoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>

Print the return code of ib_post_send() if it fails to make these
debugging messages more useful.
Signed-off-by: NOr Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

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

The generic packet receive code takes care of setting
netdev->last_rx when necessary, for the sake of the
bonding ARP monitor.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Acked-by: NNeil Horman <nhorman@txudriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If NAPI is enabled while IPoIB's CQ is being drained, it creates a
race on priv->ibwc between ipoib_poll() and ipoib_drain_cq(), leading
to memory corruption.

The solution is to enable/disable NAPI in ipoib_ib_dev_{open/stop}()
instead of in ipoib_{open/stop}(), and sync NAPI on the INITIALIZED
flag instead on the ADMIN_UP flag. This way NAPI will be disabled when
ipoib_drain_cq() is called.

This fixes <https://bugs.openfabrics.org/show_bug.cgi?id=1587>.
Signed-off-by: NYossi Etigin <yosefe@voltaire.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

Following the removal of the unused struct net_device * parameter from
the NAPI functions named *netif_rx_* in commit 908a7a16, they are
exactly equivalent to the corresponding *napi_* functions and are
therefore redundant.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the napi api was changed to separate its 1:1 binding to the net_device
struct, the netif_rx_[prep|schedule|complete] api failed to remove the now
vestigual net_device structure parameter.  This patch cleans up that api by
properly removing it..
Signed-off-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>