linux-stable.git/drivers/infiniband, branch linux-5.17.y

RDMA/rxe: Generate a completion for unsupported/invalid opcode

2022-06-09T08:26:31+00:00

commit 2f917af777011c88e977b9b9a5d00b280d3a59ce upstream.

Current rxe_requester() doesn't generate a completion when processing an
unsupported/invalid opcode. If rxe driver doesn't support a new opcode
(e.g. RDMA Atomic Write) and RDMA library supports it, an application
using the new opcode can reproduce this issue. Fix the issue by calling
"goto err;".

Fixes: 8700e3e7c485 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20220410113513.27537-1-yangx.jy@fujitsu.com
Signed-off-by: Xiao Yang 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Greg Kroah-Hartman

RDMA/hns: Remove the num_cqc_timer variable

2022-06-09T08:26:31+00:00

commit db5dfbf5b201df65c1f5332c4d9d5e7c2f42396b upstream.

The bt number of cqc_timer of HIP09 increases compared with that of HIP08.
Therefore, cqc_timer_bt_num and num_cqc_timer do not match. As a result,
the driver may fail to allocate cqc_timer. So the driver needs to uniquely
uses cqc_timer_bt_num to represent the bt number of cqc_timer.

Fixes: 0e40dc2f70cd ("RDMA/hns: Add timer allocation support for hip08")
Link: https://lore.kernel.org/r/20220429093545.58070-1-liangwenpeng@huawei.com
Signed-off-by: Yixing Liu 
Signed-off-by: Wenpeng Liang 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Greg Kroah-Hartman

RDMA/hfi1: Fix potential integer multiplication overflow errors

2022-06-09T08:26:25+00:00

commit f93e91a0372c922c20d5bee260b0f43b4b8a1bee upstream.

When multiplying of different types, an overflow is possible even when
storing the result in a larger type. This is because the conversion is
done after the multiplication. So arithmetic overflow and thus in
incorrect value is possible.

Correct an instance of this in the inter packet delay calculation.  Fix by
ensuring one of the operands is u64 which will promote the other to u64 as
well ensuring no overflow.

Cc: stable@vger.kernel.org
Fixes: 7724105686e7 ("IB/hfi1: add driver files")
Link: https://lore.kernel.org/r/20220520183712.48973.29855.stgit@awfm-01.cornelisnetworks.com
Reviewed-by: Mike Marciniszyn 
Signed-off-by: Dennis Dalessandro 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Greg Kroah-Hartman

RDMA/hfi1: Prevent use of lock before it is initialized

2022-06-09T08:26:10+00:00

[ Upstream commit 05c03dfd09c069c4ffd783b47b2da5dcc9421f2c ]

If there is a failure during probe of hfi1 before the sdma_map_lock is
initialized, the call to hfi1_free_devdata() will attempt to use a lock
that has not been initialized. If the locking correctness validator is on
then an INFO message and stack trace resembling the following may be seen:

  INFO: trying to register non-static key.
  The code is fine but needs lockdep annotation, or maybe
  you didn't initialize this object before use?
  turning off the locking correctness validator.
  Call Trace:
  register_lock_class+0x11b/0x880
  __lock_acquire+0xf3/0x7930
  lock_acquire+0xff/0x2d0
  _raw_spin_lock_irq+0x46/0x60
  sdma_clean+0x42a/0x660 [hfi1]
  hfi1_free_devdata+0x3a7/0x420 [hfi1]
  init_one+0x867/0x11a0 [hfi1]
  pci_device_probe+0x40e/0x8d0

The use of sdma_map_lock in sdma_clean() is for freeing the sdma_map
memory, and sdma_map is not allocated/initialized until after
sdma_map_lock has been initialized. This code only needs to be run if
sdma_map is not NULL, and so checking for that condition will avoid trying
to use the lock before it is initialized.

Fixes: 473291b3ea0e ("IB/hfi1: Fix for early release of sdma context")
Fixes: 7724105686e7 ("IB/hfi1: add driver files")
Link: https://lore.kernel.org/r/20220520183701.48973.72434.stgit@awfm-01.cornelisnetworks.com
Reported-by: Zheyu Ma 
Signed-off-by: Douglas Miller 
Signed-off-by: Dennis Dalessandro 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Sasha Levin

RDMA/hns: Add the detection for CMDQ status in the device initialization process

2022-06-09T08:26:06+00:00

[ Upstream commit e8ea058edc2b225a68b307057a65599625daaebf ]

CMDQ may fail during HNS ROCEE initialization. The following is the log
when the execution fails:

  hns3 0000:bd:00.2: In reset process RoCE client reinit.
  hns3 0000:bd:00.2: CMDQ move tail from 840 to 839
  hns3 0000:bd:00.2 hns_2: failed to set gid, ret = -11!
  hns3 0000:bd:00.2: CMDQ move tail from 840 to 839
  <...>
  hns3 0000:bd:00.2: CMDQ move tail from 840 to 839
  hns3 0000:bd:00.2: CMDQ move tail from 840 to 0
  hns3 0000:bd:00.2: [cmd]token 14e mailbox 20 timeout.
  hns3 0000:bd:00.2 hns_2: set HEM step 0 failed!
  hns3 0000:bd:00.2 hns_2: set HEM address to HW failed!
  hns3 0000:bd:00.2 hns_2: failed to alloc mtpt, ret = -16.
  infiniband hns_2: Couldn't create ib_mad PD
  infiniband hns_2: Couldn't open port 1
  hns3 0000:bd:00.2: Reset done, RoCE client reinit finished.

However, even if ib_mad client registration failed, ib_register_device()
still returns success to the driver.

In the device initialization process, CMDQ execution fails because HW/FW
is abnormal. Therefore, if CMDQ fails, the initialization function should
set CMDQ to a fatal error state and return a failure to the caller.

Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver")
Link: https://lore.kernel.org/r/20220429093104.26687-1-liangwenpeng@huawei.com
Signed-off-by: Yangyang Li 
Signed-off-by: Wenpeng Liang 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Sasha Levin

RDMA/hfi1: Prevent panic when SDMA is disabled

2022-06-09T08:25:35+00:00

[ Upstream commit 629e052d0c98e46dde9f0824f0aa437f678d9b8f ]

If the hfi1 module is loaded with HFI1_CAP_SDMA off, a call to
hfi1_write_iter() will dereference a NULL pointer and panic. A typical
stack frame is:

  sdma_select_user_engine [hfi1]
  hfi1_user_sdma_process_request [hfi1]
  hfi1_write_iter [hfi1]
  do_iter_readv_writev
  do_iter_write
  vfs_writev
  do_writev
  do_syscall_64

The fix is to test for SDMA in hfi1_write_iter() and fail the I/O with
EINVAL.

Link: https://lore.kernel.org/r/20220520183706.48973.79803.stgit@awfm-01.cornelisnetworks.com
Signed-off-by: Douglas Miller 
Signed-off-by: Dennis Dalessandro 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Sasha Levin

IB/rdmavt: add missing locks in rvt_ruc_loopback

2022-06-09T08:25:31+00:00

[ Upstream commit 22cbc6c2681a0a4fe76150270426e763d52353a4 ]

The documentation of the function rvt_error_qp says both r_lock and
s_lock need to be held when calling that function.
It also asserts using lockdep that both of those locks are held.
rvt_error_qp is called form rvt_send_cq, which is called from
rvt_qp_complete_swqe, which is called from rvt_send_complete, which is
called from rvt_ruc_loopback in two places. Both of these places do not
hold r_lock. Fix this by acquiring a spin_lock of r_lock in both of
these places.
The r_lock acquiring cannot be added in rvt_qp_complete_swqe because
some of its other callers already have r_lock acquired.

Link: https://lore.kernel.org/r/20220228195144.71946-1-dossche.niels@gmail.com
Signed-off-by: Niels Dossche 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Sasha Levin

RDMA/irdma: Fix deadlock in irdma_cleanup_cm_core()

2022-05-18T08:28:16+00:00

[ Upstream commit 679ab61bf5f5f519377d812afb4fb93634782c74 ]

There is a deadlock in irdma_cleanup_cm_core(), which is shown below:

   (Thread 1)              |      (Thread 2)
                           | irdma_schedule_cm_timer()
irdma_cleanup_cm_core()    |  add_timer()
 spin_lock_irqsave() //(1) |  (wait a time)
 ...                       | irdma_cm_timer_tick()
 del_timer_sync()          |  spin_lock_irqsave() //(2)
 (wait timer to stop)      |  ...

We hold cm_core->ht_lock in position (1) of thread 1 and use
del_timer_sync() to wait timer to stop, but timer handler also need
cm_core->ht_lock in position (2) of thread 2.  As a result,
irdma_cleanup_cm_core() will block forever.

This patch removes the check of timer_pending() in
irdma_cleanup_cm_core(), because the del_timer_sync() function will just
return directly if there isn't a pending timer. As a result, the lock is
redundant, because there is no resource it could protect.

Link: https://lore.kernel.org/r/20220418153322.42524-1-duoming@zju.edu.cn
Signed-off-by: Duoming Zhou 
Reviewed-by: Shiraz Saleem 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Sasha Levin

RDMA/irdma: Fix possible crash due to NULL netdev in notifier

2022-05-12T10:32:34+00:00

commit 1c9043ae0667a43bd87beeebbdd4bed674713629 upstream.

For some net events in irdma_net_event notifier, the netdev can be NULL
which will cause a crash in rdma_vlan_dev_real_dev.  Fix this by moving
all processing to the NETEVENT_NEIGH_UPDATE case where the netdev is
guaranteed to not be NULL.

Fixes: 6702bc147448 ("RDMA/irdma: Fix netdev notifications for vlan's")
Link: https://lore.kernel.org/r/20220425181703.1634-4-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail 
Signed-off-by: Shiraz Saleem 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Greg Kroah-Hartman

RDMA/irdma: Reduce iWARP QP destroy time

2022-05-12T10:32:33+00:00

commit 2df6d895907b2f5dfbc558cbff7801bba82cb3cc upstream.

QP destroy is synchronous and waits for its refcnt to be decremented in
irdma_cm_node_free_cb (for iWARP) which fires after the RCU grace period
elapses.

Applications running a large number of connections are exposed to high
wait times on destroy QP for events like SIGABORT.

The long pole for this wait time is the firing of the call_rcu callback
during a CM node destroy which can be slow. It holds the QP reference
count and blocks the destroy QP from completing.

call_rcu only needs to make sure that list walkers have a reference to the
cm_node object before freeing it and thus need to wait for grace period
elapse. The rest of the connection teardown in irdma_cm_node_free_cb is
moved out of the grace period wait in irdma_destroy_connection. Also,
replace call_rcu with a simple kfree_rcu as it just needs to do a kfree on
the cm_node

Fixes: 146b9756f14c ("RDMA/irdma: Add connection manager")
Link: https://lore.kernel.org/r/20220425181703.1634-3-shiraz.saleem@intel.com
Signed-off-by: Shiraz Saleem 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Greg Kroah-Hartman