The issue is in drivers/infiniband/core/uverbs_std_types_cq.c in the
UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE) function.  We check that:

        if (attr.comp_vector >= attrs->ufile->device->num_comp_vectors) {

But we don't check if "attr.comp_vector" is negative.  It could
potentially lead to an array underflow.  My concern would be where
cq->vector is used in the create_cq() function from the cxgb4 driver.

And really "attr.comp_vector" is appears as a u32 to user space so that's
the right type to use.

Fixes: 9ee79fce ("IB/core: Add completion queue (cq) object actions")
Link: https://lore.kernel.org/r/20191011133419.GA22905@mwandaSigned-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Current code tries to derive VLAN ID and compares it with GID
attribute for matching entry. This raw search fails on macvlan
netdevice as its not a VLAN device, but its an upper device of a VLAN
netdevice.

Due to this limitation, incoming QP1 packets fail to match in the
GID table. Such packets are dropped.

Hence, to support it, use the existing rdma_read_gid_l2_fields()
that takes care of diffferent device types.

Fixes: dbf727de ("IB/core: Use GID table in AH creation and dmac resolution")
Signed-off-by: NParav Pandit <parav@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20191002121750.17313-1-leon@kernel.orgSigned-off-by: NDoug Ledford <dledford@redhat.com>

Remove spaces from the reported firmware version string.
Actual value:
$ cat /sys/class/infiniband/qedr0/fw_ver
8. 37. 7. 0

Expected value:
$ cat /sys/class/infiniband/qedr0/fw_ver
8.37.7.0

Fixes: ec72fce4 ("qedr: Add support for RoCE HW init")
Signed-off-by: NKamal Heib <kamalheib1@gmail.com>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Link: https://lore.kernel.org/r/20191007210730.7173-1-kamalheib1@gmail.comSigned-off-by: NDoug Ledford <dledford@redhat.com>

As siw_free_qp() is the last routine to access 'siw_base_qp' structure,
freeing this structure early in siw_destroy_qp() could cause
touch-after-free issue.
Hence, moved kfree(siw_base_qp) from siw_destroy_qp() to siw_free_qp().

Fixes: 303ae1cd ("rdma/siw: application interface")
Signed-off-by: NKrishnamraju Eraparaju <krishna2@chelsio.com>
Link: https://lore.kernel.org/r/20191007104229.29412-1-krishna2@chelsio.comSigned-off-by: NDoug Ledford <dledford@redhat.com>

kref release routines usually perform memory release operations,
hence, they should not be called with spinlocks held.
one such case is: SIW kref release routine siw_free_qp(), which
can sleep via vfree() while freeing queue memory.

Hence, all iw_rem_ref() calls in IWCM are moved out of spinlocks.

Fixes: 922a8e9f ("RDMA: iWARP Connection Manager.")
Signed-off-by: NKrishnamraju Eraparaju <krishna2@chelsio.com>
Reviewed-by: NBernard Metzler <bmt@zurich.ibm.com>
Link: https://lore.kernel.org/r/20191007102627.12568-1-krishna2@chelsio.comSigned-off-by: NDoug Ledford <dledford@redhat.com>

pass_accept_req() is using the same skb for handling accept request and
sending accept reply to HW. Here req and rpl structures are pointing to
same skb->data which is over written by INIT_TP_WR() and leads to
accessing corrupt req fields in accept_cr() while checking for ECN flags.
Reordered code in accept_cr() to fetch correct req fields.

Fixes: 92e7ae71 ("iw_cxgb4: Choose appropriate hw mtu index and ISS for iWARP connections")
Signed-off-by: NPotnuri Bharat Teja <bharat@chelsio.com>
Link: https://lore.kernel.org/r/20191003104353.11590-1-bharat@chelsio.comSigned-off-by: NDoug Ledford <dledford@redhat.com>

There is no reason for a different pad buffer for the two
packet types.

Expand the current buffer allocation to allow for both
packet types.

Fixes: f8195f3b ("IB/hfi1: Eliminate allocation while atomic")
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: NKaike Wan <kaike.wan@intel.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Link: https://lore.kernel.org/r/20191004204934.26838.13099.stgit@awfm-01.aw.intel.comSigned-off-by: NDoug Ledford <dledford@redhat.com>

A TID RDMA READ request could be retried under one of the following
conditions:
- The RC retry timer expires;
- A later TID RDMA READ RESP packet is received before the next
  expected one.
For the latter, under normal conditions, the PSN in IB space is used
for comparison. More specifically, the IB PSN in the incoming TID RDMA
READ RESP packet is compared with the last IB PSN of a given TID RDMA
READ request to determine if the request should be retried. This is
similar to the retry logic for noraml RDMA READ request.

However, if a TID RDMA READ RESP packet is lost due to congestion,
header suppresion will be disabled and each incoming packet will raise
an interrupt until the hardware flow is reloaded. Under this condition,
each packet KDETH PSN will be checked by software against r_next_psn
and a retry will be requested if the packet KDETH PSN is later than
r_next_psn. Since each TID RDMA READ segment could have up to 64
packets and each TID RDMA READ request could have many segments, we
could make far more retries under such conditions, and thus leading to
RETRY_EXC_ERR status.

This patch fixes the issue by removing the retry when the incoming
packet KDETH PSN is later than r_next_psn. Instead, it resorts to
RC timer and normal IB PSN comparison for any request retry.

Fixes: 9905bf06 ("IB/hfi1: Add functions to receive TID RDMA READ response")
Cc: <stable@vger.kernel.org>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NKaike Wan <kaike.wan@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Link: https://lore.kernel.org/r/20191004204035.26542.41684.stgit@awfm-01.aw.intel.comSigned-off-by: NDoug Ledford <dledford@redhat.com>

Before QP is closed it changes to ERROR state, when this happens
the QP was left with old rate limit that was already removed from
the table.

Fixes: 7d29f349 ("IB/mlx5: Properly adjust rate limit on QP state transitions")
Signed-off-by: NRafi Wiener <rafiw@mellanox.com>
Signed-off-by: NOleg Kuporosov <olegk@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20191002120243.16971-1-leon@kernel.orgSigned-off-by: NDoug Ledford <dledford@redhat.com>

While MR uses live as the SRCU 'update', the MW case uses the xarray
directly, xa_erase() causes the MW to become inaccessible to the pagefault
thread.

Thus whenever a MW is removed from the xarray we must synchronize_srcu()
before freeing it.

This must be done before freeing the mkey as re-use of the mkey while the
pagefault thread is using the stale mkey is undesirable.

Add the missing synchronizes to MW and DEVX indirect mkey and delete the
bogus protection against double destroy in mlx5_core_destroy_mkey()

Fixes: 534fd7aa ("IB/mlx5: Manage indirection mkey upon DEVX flow for ODP")
Fixes: 6aec21f6 ("IB/mlx5: Page faults handling infrastructure")
Link: https://lore.kernel.org/r/20191001153821.23621-7-jgg@ziepe.caReviewed-by: NArtemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

live is used to signal to the pagefault thread that the MR is initialized
and ready for use. It should be after the umem is assigned and all other
setup is completed. This prevents races (at least) of the form:

    CPU0                                     CPU1
mlx5_ib_alloc_implicit_mr()
 implicit_mr_alloc()
  live = 1
 imr->umem = umem
                                    num_pending_prefetch_inc()
                                      if (live)
				        atomic_inc(num_pending_prefetch)
 atomic_set(num_pending_prefetch,0) // Overwrites other thread's store

Further, live is being used with SRCU as the 'update' in an
acquire/release fashion, so it can not be read and written raw.

Move all live = 1's to after MR initialization is completed and use
smp_store_release/smp_load_acquire() for manipulating it.

Add a missing live = 0 when an implicit MR child is deleted, before
queuing work to do synchronize_srcu().

The barriers in update_odp_mr() were some broken attempt to create a
acquire/release, but were not even applied consistently and missed the
point, delete it as well.

Fixes: 6aec21f6 ("IB/mlx5: Page faults handling infrastructure")
Link: https://lore.kernel.org/r/20191001153821.23621-6-jgg@ziepe.caReviewed-by: NArtemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

During destroy setting live = 0 and then synchronize_srcu() prevents
num_pending_prefetch from incrementing, and also, ensures that all work
holding that count is queued on the WQ. Testing before causes races of the
form:

    CPU0                                         CPU1
  dereg_mr()
                                          mlx5_ib_advise_mr_prefetch()
            				   srcu_read_lock()
                                            num_pending_prefetch_inc()
					      if (!live)
   live = 0
   atomic_read() == 0
     // skip flush_workqueue()
                                              atomic_inc()
 					      queue_work();
            				   srcu_read_unlock()
   WARN_ON(atomic_read())  // Fails

Swap the order so that the synchronize_srcu() prevents this.

Fixes: a6bc3875 ("IB/mlx5: Protect against prefetch of invalid MR")
Link: https://lore.kernel.org/r/20191001153821.23621-5-jgg@ziepe.caReviewed-by: NArtemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

This fixes a race of the form:
    CPU0                               CPU1
mlx5_ib_invalidate_range()     mlx5_ib_invalidate_range()
				 // This one actually makes npages == 0
				 ib_umem_odp_unmap_dma_pages()
				 if (npages == 0 && !dying)
  // This one does nothing
  ib_umem_odp_unmap_dma_pages()
  if (npages == 0 && !dying)
     dying = 1;
                                    dying = 1;
				    schedule_work(&umem_odp->work);
     // Double schedule of the same work
     schedule_work(&umem_odp->work);  // BOOM

npages and dying must be read and written under the umem_mutex lock.

Since whenever ib_umem_odp_unmap_dma_pages() is called mlx5 must also call
mlx5_ib_update_xlt, and both need to be done in the same locking region,
hoist the lock out of unmap.

This avoids an expensive double critical section in
mlx5_ib_invalidate_range().

Fixes: 81713d37 ("IB/mlx5: Add implicit MR support")
Link: https://lore.kernel.org/r/20191001153821.23621-4-jgg@ziepe.caReviewed-by: NArtemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

mlx5_ib_update_xlt() must be protected against parallel free of the MR it
is accessing, also it must be called single threaded while updating the
HW. Otherwise we can have races of the form:

    CPU0                               CPU1
  mlx5_ib_update_xlt()
   mlx5_odp_populate_klm()
     odp_lookup() == NULL
     pklm = ZAP
                                      implicit_mr_get_data()
 				        implicit_mr_alloc()
 					  <update interval tree>
					mlx5_ib_update_xlt
					  mlx5_odp_populate_klm()
					    odp_lookup() != NULL
					    pklm = VALID
					   mlx5_ib_post_send_wait()

    mlx5_ib_post_send_wait() // Replaces VALID with ZAP

This can be solved by putting both the SRCU and the umem_mutex lock around
every call to mlx5_ib_update_xlt(). This ensures that the content of the
interval tree relavent to mlx5_odp_populate_klm() (ie mr->parent == mr)
will not change while it is running, and thus the posted WRs to update the
KLM will always reflect the correct information.

The race above will resolve by either having CPU1 wait till CPU0 completes
the ZAP or CPU0 will run after the add and instead store VALID.

The pagefault path adding children already holds the umem_mutex and SRCU,
so the only missed lock is during MR destruction.

Fixes: 81713d37 ("IB/mlx5: Add implicit MR support")
Link: https://lore.kernel.org/r/20191001153821.23621-3-jgg@ziepe.caReviewed-by: NArtemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

This code is completely broken, the umem of a ODP MR simply cannot be
discarded without a lot more locking, nor can an ODP mkey be blithely
destroyed via destroy_mkey().

Fixes: 6aec21f6 ("IB/mlx5: Page faults handling infrastructure")
Link: https://lore.kernel.org/r/20191001153821.23621-2-jgg@ziepe.caReviewed-by: NArtemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

rdma_for_each_port is already incrementing the iterator's value it
receives therefore, after the first iteration the iterator is increased by
2 which eventually causing wrong queries and possible traces.

Fix the above by removing the old redundant incrementation that was used
before rdma_for_each_port() macro.

Cc: <stable@vger.kernel.org>
Fixes: ea1075ed ("RDMA: Add and use rdma_for_each_port")
Link: https://lore.kernel.org/r/20191002122127.17571-1-leon@kernel.orgSigned-off-by: NMohamad Heib <mohamadh@mellanox.com>
Reviewed-by: NErez Alfasi <ereza@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Properly unwind QP counter rebinding in case of failure.

Trying to rebind the counter after unbiding it is not going to work
reliably, move the unbind to the end so it doesn't have to be unwound.

Fixes: b389327d ("RDMA/nldev: Allow counter manual mode configration through RDMA netlink")
Link: https://lore.kernel.org/r/20191002115627.16740-1-leon@kernel.orgReviewed-by: NMark Zhang <markz@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Nicolas pointed out that the cxgb4 driver is doing dma off of the stack,
which is generally considered a very bad thing.  On some architectures it
could be a security problem, but odds are none of them actually run this
driver, so it's just a "normal" bug.

Resolve this by allocating the memory for a message off of the heap
instead of the stack.  kmalloc() always will give us a proper memory
location that DMA will work correctly from.

Link: https://lore.kernel.org/r/20191001165611.GA3542072@kroah.comReported-by: NNicolas Waisman <nico@semmle.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: NPotnuri Bharat Teja <bharat@chelsio.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

In the process of moving the debug counters sysfs entries, the commit
mentioned below eliminated the cm_infiniband sysfs directory.

This sysfs directory was tied to the cm_port object allocated in procedure
cm_add_one().

Before the commit below, this cm_port object was freed via a call to
kobject_put(port->kobj) in procedure cm_remove_port_fs().

Since port no longer uses its kobj, kobject_put(port->kobj) was eliminated.
This, however, meant that kfree was never called for the cm_port buffers.

Fix this by adding explicit kfree(port) calls to functions cm_add_one()
and cm_remove_one().

Note: the kfree call in the first chunk below (in the cm_add_one error
flow) fixes an old, undetected memory leak.

Fixes: c87e65cf ("RDMA/cm: Move debug counters to be under relevant IB device")
Link: https://lore.kernel.org/r/20190916071154.20383-2-leon@kernel.orgSigned-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

According to surrounding error paths, it is likely that 'goto err_get;' is
expected here. Otherwise, a call to 'rdma_restrack_put(res);' would be
missing.

Fixes: c5dfe0ea ("RDMA/nldev: Add resource tracker doit callback")
Link: https://lore.kernel.org/r/20190818091044.8845-1-christophe.jaillet@wanadoo.frSigned-off-by: NChristophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

i40iw IB device registration fails with ENODEV.

ib_register_device
 setup_device/setup_port_data
  i40iw_port_immutable
   ib_query_port
     iw_query_port
      ib_device_get_netdev(ENODEV)

ib_device_get_netdev() does not have a netdev associated
with the ibdev and thus fails.
Use ib_device_set_netdev() to associate netdev to ibdev
in i40iw before IB device registration.

Fixes: 4929116b ("RDMA/core: Add common iWARP query port")
Link: https://lore.kernel.org/r/20190925164524.856-1-shiraz.saleem@intel.comSigned-off-by: NShiraz, Saleem <shiraz.saleem@intel.com>
Reviewed-by: NKamal Heib <kamalheib1@gmail.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

This patch fixes the lock inversion complaint:

============================================
WARNING: possible recursive locking detected
5.3.0-rc7-dbg+ #1 Not tainted
--------------------------------------------
kworker/u16:6/171 is trying to acquire lock:
00000000035c6e6c (&id_priv->handler_mutex){+.+.}, at: rdma_destroy_id+0x78/0x4a0 [rdma_cm]

but task is already holding lock:
00000000bc7c307d (&id_priv->handler_mutex){+.+.}, at: iw_conn_req_handler+0x151/0x680 [rdma_cm]

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

       CPU0
       ----
  lock(&id_priv->handler_mutex);
  lock(&id_priv->handler_mutex);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

3 locks held by kworker/u16:6/171:
 #0: 00000000e2eaa773 ((wq_completion)iw_cm_wq){+.+.}, at: process_one_work+0x472/0xac0
 #1: 000000001efd357b ((work_completion)(&work->work)#3){+.+.}, at: process_one_work+0x476/0xac0
 #2: 00000000bc7c307d (&id_priv->handler_mutex){+.+.}, at: iw_conn_req_handler+0x151/0x680 [rdma_cm]

stack backtrace:
CPU: 3 PID: 171 Comm: kworker/u16:6 Not tainted 5.3.0-rc7-dbg+ #1
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
Workqueue: iw_cm_wq cm_work_handler [iw_cm]
Call Trace:
 dump_stack+0x8a/0xd6
 __lock_acquire.cold+0xe1/0x24d
 lock_acquire+0x106/0x240
 __mutex_lock+0x12e/0xcb0
 mutex_lock_nested+0x1f/0x30
 rdma_destroy_id+0x78/0x4a0 [rdma_cm]
 iw_conn_req_handler+0x5c9/0x680 [rdma_cm]
 cm_work_handler+0xe62/0x1100 [iw_cm]
 process_one_work+0x56d/0xac0
 worker_thread+0x7a/0x5d0
 kthread+0x1bc/0x210
 ret_from_fork+0x24/0x30

This is not a bug as there are actually two lock classes here.

Link: https://lore.kernel.org/r/20190930231707.48259-3-bvanassche@acm.org
Fixes: de910bd9 ("RDMA/cma: Simplify locking needed for serialization of callbacks")
Signed-off-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

dump_qp() is wrongly trying to dump SRQ structures as QP when SRQ is used
by the application. This patch matches the QPID before dumping them.  Also
removes unwanted SRQ id addition to QP id xarray.

Fixes: 2f431291 ("cxgb4: Convert qpidr to XArray")
Link: https://lore.kernel.org/r/20190930074119.20046-1-bharat@chelsio.comSigned-off-by: NRahul Kundu <rahul.kundu@chelsio.com>
Signed-off-by: NPotnuri Bharat Teja <bharat@chelsio.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

In sdma_init if rhashtable_init fails the allocated memory for
tmp_sdma_rht should be released.

Fixes: 5a52a7ac ("IB/hfi1: NULL pointer dereference when freeing rhashtable")
Link: https://lore.kernel.org/r/20190925144543.10141-1-navid.emamdoost@gmail.comSigned-off-by: NNavid Emamdoost <navid.emamdoost@gmail.com>
Acked-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

If an iWARP driver is probed and removed while there are no ips set for
the device, it will lead to a reference count leak on the inet device of
the netdevice.

In addition, the netdevice was accessed after already calling netdev_put,
which could lead to using the netdev after already freed.

Fixes: 4929116b ("RDMA/core: Add common iWARP query port")
Link: https://lore.kernel.org/r/20190925123332.10746-1-michal.kalderon@marvell.comSigned-off-by: NAriel Elior <ariel.elior@marvell.com>
Signed-off-by: NMichal Kalderon <michal.kalderon@marvell.com>
Reviewed-by: NShiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: NKamal Heib <kamalheib1@gmail.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

In siw_qp_llp_write_space(), 'sock' members should be accessed with
sk_callback_lock held, otherwise, it could race with
siw_sk_restore_upcalls(). And this could cause "NULL deref" panic.  Below
panic is due to the NULL cep returned from sk_to_cep(sk):

  Call Trace:
   <IRQ>    siw_qp_llp_write_space+0x11/0x40 [siw]
   tcp_check_space+0x4c/0xf0
   tcp_rcv_established+0x52b/0x630
   tcp_v4_do_rcv+0xf4/0x1e0
   tcp_v4_rcv+0x9b8/0xab0
   ip_protocol_deliver_rcu+0x2c/0x1c0
   ip_local_deliver_finish+0x44/0x50
   ip_local_deliver+0x6b/0xf0
   ? ip_protocol_deliver_rcu+0x1c0/0x1c0
   ip_rcv+0x52/0xd0
   ? ip_rcv_finish_core.isra.14+0x390/0x390
   __netif_receive_skb_one_core+0x83/0xa0
   netif_receive_skb_internal+0x73/0xb0
   napi_gro_frags+0x1ff/0x2b0
   t4_ethrx_handler+0x4a7/0x740 [cxgb4]
   process_responses+0x2c9/0x590 [cxgb4]
   ? t4_sge_intr_msix+0x1d/0x30 [cxgb4]
   ? handle_irq_event_percpu+0x51/0x70
   ? handle_irq_event+0x41/0x60
   ? handle_edge_irq+0x97/0x1a0
   napi_rx_handler+0x14/0xe0 [cxgb4]
   net_rx_action+0x2af/0x410
   __do_softirq+0xda/0x2a8
   do_softirq_own_stack+0x2a/0x40
   </IRQ>
   do_softirq+0x50/0x60
   __local_bh_enable_ip+0x50/0x60
   ip_finish_output2+0x18f/0x520
   ip_output+0x6e/0xf0
   ? __ip_finish_output+0x1f0/0x1f0
   __ip_queue_xmit+0x14f/0x3d0
   ? __slab_alloc+0x4b/0x58
   __tcp_transmit_skb+0x57d/0xa60
   tcp_write_xmit+0x23b/0xfd0
   __tcp_push_pending_frames+0x2e/0xf0
   tcp_sendmsg_locked+0x939/0xd50
   tcp_sendmsg+0x27/0x40
   sock_sendmsg+0x57/0x80
   siw_tx_hdt+0x894/0xb20 [siw]
   ? find_busiest_group+0x3e/0x5b0
   ? common_interrupt+0xa/0xf
   ? common_interrupt+0xa/0xf
   ? common_interrupt+0xa/0xf
   siw_qp_sq_process+0xf1/0xe60 [siw]
   ? __wake_up_common_lock+0x87/0xc0
   siw_sq_resume+0x33/0xe0 [siw]
   siw_run_sq+0xac/0x190 [siw]
   ? remove_wait_queue+0x60/0x60
   kthread+0xf8/0x130
   ? siw_sq_resume+0xe0/0xe0 [siw]
   ? kthread_bind+0x10/0x10
   ret_from_fork+0x35/0x40

Fixes: f29dd55b ("rdma/siw: queue pair methods")
Link: https://lore.kernel.org/r/20190923101112.32685-1-krishna2@chelsio.comSigned-off-by: NKrishnamraju Eraparaju <krishna2@chelsio.com>
Reviewed-by: NBernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

An extra kfree cleanup was missed since these are now deallocated by core.

Link: https://lore.kernel.org/r/1568848066-12449-1-git-send-email-aditr@vmware.com
Cc: <stable@vger.kernel.org>
Fixes: 68e326de ("RDMA: Handle SRQ allocations by IB/core")
Signed-off-by: NAdit Ranadive <aditr@vmware.com>
Reviewed-by: NVishnu Dasa <vdasa@vmware.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Pull btrfs fixes from David Sterba:
 "A bunch of fixes that accumulated in recent weeks, mostly material for
  stable.

  Summary:

   - fix for regression from 5.3 that prevents to use balance convert
     with single profile

   - qgroup fixes: rescan race, accounting leak with multiple writers,
     potential leak after io failure recovery

   - fix for use after free in relocation (reported by KASAN)

   - other error handling fixups"

* tag 'for-5.4-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: qgroup: Fix reserved data space leak if we have multiple reserve calls
  btrfs: qgroup: Fix the wrong target io_tree when freeing reserved data space
  btrfs: Fix a regression which we can't convert to SINGLE profile
  btrfs: relocation: fix use-after-free on dead relocation roots
  Btrfs: fix race setting up and completing qgroup rescan workers
  Btrfs: fix missing error return if writeback for extent buffer never started
  btrfs: adjust dirty_metadata_bytes after writeback failure of extent buffer
  Btrfs: fix selftests failure due to uninitialized i_mode in test inodes

Pull csky updates from Guo Ren:
 "This round of csky subsystem just some fixups:

   - Fix mb() synchronization problem

   - Fix dma_alloc_coherent with PAGE_SO attribute

   - Fix cache_op failed when cross memory ZONEs

   - Optimize arch_sync_dma_for_cpu/device with dma_inv_range

   - Fix ioremap function losing

   - Fix arch_get_unmapped_area() implementation

   - Fix defer cache flush for 610

   - Support kernel non-aligned access

   - Fix 610 vipt cache flush mechanism

   - Fix add zero_fp fixup perf backtrace panic

   - Move static keyword to the front of declaration

   - Fix csky_pmu.max_period assignment

   - Use generic free_initrd_mem()

   - entry: Remove unneeded need_resched() loop"

* tag 'csky-for-linus-5.4-rc1' of git://github.com/c-sky/csky-linux:
  csky: Move static keyword to the front of declaration
  csky: entry: Remove unneeded need_resched() loop
  csky: Fixup csky_pmu.max_period assignment
  csky: Fixup add zero_fp fixup perf backtrace panic
  csky: Use generic free_initrd_mem()
  csky: Fixup 610 vipt cache flush mechanism
  csky: Support kernel non-aligned access
  csky: Fixup defer cache flush for 610
  csky: Fixup arch_get_unmapped_area() implementation
  csky: Fixup ioremap function losing
  csky: Optimize arch_sync_dma_for_cpu/device with dma_inv_range
  csky/dma: Fixup cache_op failed when cross memory ZONEs
  csky: Fixup dma_alloc_coherent with PAGE_SO attribute
  csky: Fixup mb() synchronization problem

Pull ARM SoC fixes from Olof Johansson:
 "A few fixes that have trickled in through the merge window:

   - Video fixes for OMAP due to panel-dpi driver removal

   - Clock fixes for OMAP that broke no-idle quirks + nfsroot on DRA7

   - Fixing arch version on ASpeed ast2500

   - Two fixes for reset handling on ARM SCMI"

* tag 'armsoc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc:
  ARM: aspeed: ast2500 is ARMv6K
  reset: reset-scmi: add missing handle initialisation
  firmware: arm_scmi: reset: fix reset_state assignment in scmi_domain_reset
  bus: ti-sysc: Remove unpaired sysc_clkdm_deny_idle()
  ARM: dts: logicpd-som-lv: Fix i2c2 and i2c3 Pin mux
  ARM: dts: am3517-evm: Fix missing video
  ARM: dts: logicpd-torpedo-baseboard: Fix missing video
  ARM: omap2plus_defconfig: Fix missing video
  bus: ti-sysc: Fix handling of invalid clocks
  bus: ti-sysc: Fix clock handling for no-idle quirks

Pull tracing fixes from Steven Rostedt:
 "A few more tracing fixes:

   - Fix a buffer overflow by checking nr_args correctly in probes

   - Fix a warning that is reported by clang

   - Fix a possible memory leak in error path of filter processing

   - Fix the selftest that checks for failures, but wasn't failing

   - Minor clean up on call site output of a memory trace event"

* tag 'trace-v5.4-3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  selftests/ftrace: Fix same probe error test
  mm, tracing: Print symbol name for call_site in trace events
  tracing: Have error path in predicate_parse() free its allocated memory
  tracing: Fix clang -Wint-in-bool-context warnings in IF_ASSIGN macro
  tracing/probe: Fix to check the difference of nr_args before adding probe

Pull more MMC updates from Ulf Hansson:
 "A couple more updates/fixes for MMC:

   - sdhci-pci: Add Genesys Logic GL975x support

   - sdhci-tegra: Recover loss in throughput for DMA

   - sdhci-of-esdhc: Fix DMA bug"

* tag 'mmc-v5.4-2' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc:
  mmc: host: sdhci-pci: Add Genesys Logic GL975x support
  mmc: tegra: Implement ->set_dma_mask()
  mmc: sdhci: Let drivers define their DMA mask
  mmc: sdhci-of-esdhc: set DMA snooping based on DMA coherence
  mmc: sdhci: improve ADMA error reporting

Move the static keyword to the front of declaration of
csky_pmu_of_device_ids, and resolve the following compiler
warning that can be seen when building with warnings
enabled (W=1):

arch/csky/kernel/perf_event.c:1340:1: warning:
  ‘static’ is not at beginning of declaration [-Wold-style-declaration]
Signed-off-by: NKrzysztof Wilczynski <kw@linux.com>
Signed-off-by: NGuo Ren <guoren@kernel.org>

Since the enabling and disabling of IRQs within preempt_schedule_irq()
is contained in a need_resched() loop, we don't need the outer arch
code loop.
Signed-off-by: NValentin Schneider <valentin.schneider@arm.com>
Signed-off-by: NGuo Ren <guoren@kernel.org>

Pull Documentation/process update from Greg KH:
 "Here are two small Documentation/process/embargoed-hardware-issues.rst
  file updates that missed my previous char/misc pull request.

  The first one adds an Intel representative for the process, and the
  second one cleans up the text a bit more when it comes to how the
  disclosure rules work, as it was a bit confusing to some companies"

* tag 'char-misc-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
  Documentation/process: Clarify disclosure rules
  Documentation/process: Volunteer as the ambassador for Intel

Pull more vfs updates from Al Viro:
 "A couple of misc patches"

* 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  afs dynroot: switch to simple_dir_operations
  fs/handle.c - fix up kerneldoc

Pull more cifs updates from Steve French:
 "Fixes from the recent SMB3 Test events and Storage Developer
  Conference (held the last two weeks).

  Here are nine smb3 patches including an important patch for debugging
  traces with wireshark, with three patches marked for stable.

  Additional fixes from last week to better handle some newly discovered
  reparse points, and a fix the create/mkdir path for setting the mode
  more atomically (in SMB3 Create security descriptor context), and one
  for path name processing are still being tested so are not included
  here"

* tag '5.4-rc-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6:
  CIFS: Fix oplock handling for SMB 2.1+ protocols
  smb3: missing ACL related flags
  smb3: pass mode bits into create calls
  smb3: Add missing reparse tags
  CIFS: fix max ea value size
  fs/cifs/sess.c: Remove set but not used variable 'capabilities'
  fs/cifs/smb2pdu.c: Make SMB2_notify_init static
  smb3: fix leak in "open on server" perf counter
  smb3: allow decryption keys to be dumped by admin for debugging

The csky_pmu.max_period has type u64, and BIT() can only return
32 bits unsigned long on C-SKY. The initialization for max_period
will be incorrect when count_width is bigger than 32.

Use BIT_ULL()
Signed-off-by: NMao Han <han_mao@c-sky.com>
Signed-off-by: NGuo Ren <ren_guo@c-sky.com>

We need set fp zero to let backtrace know the end. The patch fixup perf
callchain panic problem, because backtrace didn't know what is the end
of fp.
Signed-off-by: NGuo Ren <ren_guo@c-sky.com>
Reported-by: NMao Han <han_mao@c-sky.com>