xa_alloc_cyclic() is a SMP release to be paired with some later acquire
during xa_load() as part of cm_acquire_id().

As such, xa_alloc_cyclic() must be done after the cm_id is fully
initialized, in particular, it absolutely must be after the
refcount_set(), otherwise the refcount_inc() in cm_acquire_id() may not
see the set.

As there are several cases where a reader will be able to use the
id.local_id after cm_acquire_id in the IB_CM_IDLE state there needs to be
an unfortunate split into a NULL allocate and a finalizing xa_store.

Fixes: a977049d ("[PATCH] IB: Add the kernel CM implementation")
Link: https://lore.kernel.org/r/20200310092545.251365-2-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

These judgments were used to keep the compatibility with older versions of
userspace that don't have the field named "cap_flags" in structure
hns_roce_ib_create_cq_resp. But it will be wrong to compare outlen with
the size of resp if another new field were added in resp. oulen should be
compared with the end offset of cap_flags in resp.

Fixes: 4f8f0d5e ("RDMA/hns: Package the flow of creating cq")
Link: https://lore.kernel.org/r/1583845569-47257-1-git-send-email-liweihang@huawei.comSigned-off-by: NWeihang Li <liweihang@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

If the cache is completely out of MRs, and we are running in cache mode,
then directly, and synchronously, create an MR that is compatible with the
cache bucket using a sleeping mailbox command. This ensures that the
thread that is waiting for the MR absolutely will get one.

When a MR allocated in this way becomes freed then it is compatible with
the cache bucket and will be recycled back into it.

Deletes the very buggy ent->compl scheme to create a synchronous MR
allocation.

Link: https://lore.kernel.org/r/20200310082238.239865-13-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Currently if the work queue is running then it is in 'hysteresis' mode and
will fill until the cache reaches the high water mark. This implicit state
is very tricky and doesn't interact with pending very well.

Instead of self re-scheduling the work queue after the add_keys() has
started to create the new MR, have the queue scheduled from
reg_mr_callback() only after the requested MR has been added.

This avoids the bad design of an in-rush of queue'd work doing back to
back add_keys() until EAGAIN then sleeping. The add_keys() will be paced
one at a time as they complete, slowly filling up the cache.

Also, fix pending to be only manipulated under lock.

Link: https://lore.kernel.org/r/20200310082238.239865-12-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

All of the members of mlx5_cache_ent must be accessed while holding the
spinlock, add the missing spinlock in the __cache_work_func().

Using cache->stopped and flush_workqueue() is an inherently racy way to
shutdown self-scheduling work on a queue. Replace it with ent->disabled
under lock, and always check disabled before queuing any new work. Use
cancel_work_sync() to shutdown the queue.

Use READ_ONCE/WRITE_ONCE for dev->last_add to manage concurrency as
coherency is less important here.

Split fill_delay from the bitfield. C bitfield updates are not atomic and
this is just a mess. Use READ_ONCE/WRITE_ONCE, but this could also use
test_bit()/set_bit().

Link: https://lore.kernel.org/r/20200310082238.239865-11-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Accesses to these members needs to be locked. There is no reason not to
hold a spinlock while calling queue_work(), so move the tests into a
helper and always call it under lock.

The helper should be called when available_mrs is adjusted.

Link: https://lore.kernel.org/r/20200310082238.239865-10-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The size_write function is supposed to adjust the total_mr's to match the
user's request, but lacks locking and safety checking.

total_mrs can only be adjusted by at most available_mrs. mrs already
assigned to users cannot be revoked. Ensure that the user provides a
target value within the range of available_mrs and within the high/low
water mark.

limit_write has confusing and wrong sanity checking, and doesn't have the
ability to deallocate on limit reduction.

Since both functions use the same algorithm to adjust the available_mrs,
consolidate it into one function and write it correctly. Fix the locking
and by holding the spinlock for all accesses to ent->X.

Always fail if the user provides a malformed string.

Fixes: e126ba97 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Link: https://lore.kernel.org/r/20200310082238.239865-9-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The cache bucket tracks the total number of MRs that exists, both inside
and outside of the cache. Removing a MR from the cache (by setting
cache_ent to NULL) without updating total_mrs will cause the tracking to
leak and be inflated.

Further fix the rereg_mr path to always destroy the MR. reg_create will
always overwrite all the MR data in mlx5_ib_mr, so the MR must be
completely destroyed, in all cases, before this function can be
called. Detach the MR from the cache and unconditionally destroy it to
avoid leaking HW mkeys.

Fixes: afd14174 ("IB/mlx5: Use direct mkey destroy command upon UMR unreg failure")
Fixes: 56e11d62 ("IB/mlx5: Added support for re-registration of MRs")
Link: https://lore.kernel.org/r/20200310082238.239865-8-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

There are many bad APIs here that are accepting a cache bucket index
instead of a bucket pointer. Many of the callers already have a bucket
pointer, so this results in a lot of confusing uses of order2idx().

Pass the struct mlx5_cache_ent into add_keys(), remove_keys(), and
alloc_cached_mr().

Once the MR is in the cache, store the cache bucket pointer directly in
the MR, replacing the 'bool allocated_from cache'.

In the end there is only one place that needs to form index from order,
alloc_mr_from_cache(). Increase the safety of this function by disallowing
it from accessing cache entries in the ODP special area.

Link: https://lore.kernel.org/r/20200310082238.239865-7-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The old names do not clearly indicate the intent.

Link: https://lore.kernel.org/r/20200310082238.239865-6-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

mkey variant calculation was spinlock protected to make it atomic, replace
that with one atomic variable.

Link: https://lore.kernel.org/r/20200310082238.239865-4-leon@kernel.orgSigned-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

As mlx5_ib is the only user of the mlx5_core_create_mkey_cb, move the
logic inside mlx5_ib and cleanup the code in mlx5_core.
Signed-off-by: NMichael Guralnik <michaelgur@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>

mkey variant is not required for mlx5_core use, move the mkey variant
counter to mlx5_ib.
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>

On reg_mr_callback() mlx5_ib is recalculating the mkey variant which is
wrong and will lead to using a different key variant than the one
submitted to firmware on create mkey command invocation.

To fix this, we store the mkey variant before invoking the firmware
command and use it later on completion (reg_mr_callback).
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Reviewed-by: NEli Cohen <eli@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>

Peer to peer support was never implemented, so delete it to make code less
clutter.

Link: https://lore.kernel.org/r/20200310091438.248429-6-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: NMark Zhang <markz@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Convert mlx5 driver to use offsetofend() instead of its duplicated
variant.

Link: https://lore.kernel.org/r/20200310091438.248429-5-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Convert mlx4 to use in-kernel offsetofend() instead
of its duplicated implementation.

Link: https://lore.kernel.org/r/20200310091438.248429-3-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Until now the flex parser capability was used in ib_query_device() to
indicate tunnel_offloads_caps support for mpls_over_gre/mpls_over_udp.

Newer devices and firmware will have configurations with the flexparser
but without mpls support.

Testing for the flex parser capability was a mistake, the tunnel_stateless
capability was intended for detecting mpls and was introduced at the same
time as the flex parser capability.

Otherwise userspace will be incorrectly informed that a future device
supports MPLS when it does not.

Link: https://lore.kernel.org/r/20200305123841.196086-1-leon@kernel.org
Cc: <stable@vger.kernel.org> # 4.17
Fixes: e818e255 ("IB/mlx5: Expose MPLS related tunneling offloads")
Signed-off-by: NAlex Vesker <valex@mellanox.com>
Reviewed-by: NAriel Levkovich <lariel@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Those macros are already defined in include/linux/mlx5/driver.h, so delete
their duplicate variants.

Link: https://lore.kernel.org/r/20200310075706.238592-1-leon@kernel.orgSigned-off-by: NAriel Levkovich <lariel@mellanox.com>
Signed-off-by: NYevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: NErez Shitrit <erezsh@mellanox.com>
Reviewed-by: NAlex Vesker <valex@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The header file rdma_core.h is duplicate, so let's remove it.

Fixes: 622db5b6 ("RDMA/core: Add trace points to follow MR allocation")
Link: https://lore.kernel.org/r/20200310091656.249696-1-leon@kernel.orgSigned-off-by: NZhu Yanjun <yanjunz@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

'wqe' is already zeroed at the top of the 'while' loop, just a few lines
below, and is not used outside of the loop.

So there is no need to zero it again, or for the variable to be declared
outside the loop.

Link: https://lore.kernel.org/r/20200308065442.5415-1-christophe.jaillet@wanadoo.frSigned-off-by: NChristophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

This lock ordering only happens when bonding is enabled and a certain
bonding related event fires. However, since it can happen this is a global
restriction on lock ordering.

Teach lockdep about the order directly and unconditionally so bugs here
are found quickly.

See https://syzkaller.appspot.com/bug?extid=55de90ab5f44172b0c90

Link: https://lore.kernel.org/r/20200227203651.GA27185@ziepe.caSigned-off-by: NJason Gunthorpe <jgg@mellanox.com>

Since RDMA rw API support operations with P2P memory sg list, make sure to
map/unmap the scatter list for signature operation correctly.

Link: https://lore.kernel.org/r/20200220100819.41860-2-maxg@mellanox.comSigned-off-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Introduce packet pacing uobject and its alloc and destroy
methods.

This uobject holds mlx5 packet pacing context according to the device
specification and enables managing packet pacing device entries that are
needed by DEVX applications.

Link: https://lore.kernel.org/r/20200219190518.200912-3-leon@kernel.orgSigned-off-by: NYishai Hadas <yishaih@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

There is a spelling mistake in an error message. Fix it.

Link: https://lore.kernel.org/r/20200304081045.81164-1-colin.king@canonical.comSigned-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The dealloc_work_entries() function must update the work_free_list pointer
while freeing its entries, since potentially called again on same list. A
second iteration of the work list caused system crash. This happens, if
work allocation fails during cma_iw_listen() and free_cm_id() tries to
free the list again during cleanup.

Fixes: 922a8e9f ("RDMA: iWARP Connection Manager.")
Link: https://lore.kernel.org/r/20200302181614.17042-1-bmt@zurich.ibm.com
Reported-by: syzbot+cb0c054eabfba4342146@syzkaller.appspotmail.com
Signed-off-by: NBernard Metzler <bmt@zurich.ibm.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

A failing call to ib_device_set_netdev() during device creation caused
system crash due to xa_destroy of uninitialized xarray hit by device
deallocation. Fixed by moving xarray initialization before potential
device deallocation.

Fixes: bdcf26bf ("rdma/siw: network and RDMA core interface")
Link: https://lore.kernel.org/r/20200302155814.9896-1-bmt@zurich.ibm.com
Reported-by: syzbot+2e80962bedd9559fe0b3@syzkaller.appspotmail.com
Signed-off-by: NBernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Holding the rtnl_lock while iterating a devices interface address list
potentially causes deadlocks with the cma_netdev_callback. While this was
implemented to limit the scope of a wildcard listen to addresses of the
current device only, a better solution limits the scope of the socket to
the device. This completely avoiding locking, and also results in
significant code simplification.

Fixes: c421651f ("RDMA/siw: Add missing rtnl_lock around access to ifa")
Link: https://lore.kernel.org/r/20200228173534.26815-1-bmt@zurich.ibm.com
Reported-by: syzbot+55de90ab5f44172b0c90@syzkaller.appspotmail.com
Suggested-by: NJason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: NBernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Cited commit missed to include low level congestion control related
debugfs stage initialization.  This resulted in missing debugfs entries
for cc_params of a RDMA device.

Add them back.

Fixes: b5ca15ad ("IB/mlx5: Add proper representors support")
Link: https://lore.kernel.org/r/20200227125407.99803-1-leon@kernel.orgSigned-off-by: NParav Pandit <parav@mellanox.com>
Reviewed-by: NMark Bloch <markb@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Add two debugfs parameters described below.

np_min_time_between_cnps - Minimum time between sending CNPs from the
                           port.
                           Unit = microseconds.
                           Default = 0 (no min wait time; generated
                           based on incoming ECN marked packets).

rp_max_rate - Maximum rate at which reaction point node can transmit.
              Once this limit is reached, RP is no longer rate limited.
              Unit = Mbits/sec
              Default = 0 (full speed)

Link: https://lore.kernel.org/r/20200227125246.99472-1-leon@kernel.orgSigned-off-by: NParav Pandit <parav@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

This fixes the kernel crash when a RDMA_NLDEV_CMD_STAT_SET command is
received, but the QP number parameter is not available.

  iwpm_register_pid: Unable to send a nlmsg (client = 2)
  infiniband syz1: RDMA CMA: cma_listen_on_dev, error -98
  general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN
  KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
  CPU: 0 PID: 9754 Comm: syz-executor069 Not tainted 5.6.0-rc2-syzkaller #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
  RIP: 0010:nla_get_u32 include/net/netlink.h:1474 [inline]
  RIP: 0010:nldev_stat_set_doit+0x63c/0xb70 drivers/infiniband/core/nldev.c:1760
  Code: fc 01 0f 84 58 03 00 00 e8 41 83 bf fb 4c 8b a3 58 fd ff ff 48 b8 00 00 00 00 00 fc ff df 49 8d 7c 24 04 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 6d
  RSP: 0018:ffffc900068bf350 EFLAGS: 00010247
  RAX: dffffc0000000000 RBX: ffffc900068bf728 RCX: ffffffff85b60470
  RDX: 0000000000000000 RSI: ffffffff85b6047f RDI: 0000000000000004
  RBP: ffffc900068bf750 R08: ffff88808c3ee140 R09: ffff8880a25e6010
  R10: ffffed10144bcddc R11: ffff8880a25e6ee3 R12: 0000000000000000
  R13: ffff88809acb0000 R14: ffff888092a42c80 R15: 000000009ef2e29a
  FS:  0000000001ff0880(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f4733e34000 CR3: 00000000a9b27000 CR4: 00000000001406f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
    rdma_nl_rcv_msg drivers/infiniband/core/netlink.c:195 [inline]
    rdma_nl_rcv_skb drivers/infiniband/core/netlink.c:239 [inline]
    rdma_nl_rcv+0x5d9/0x980 drivers/infiniband/core/netlink.c:259
    netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
    netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1329
    netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1918
    sock_sendmsg_nosec net/socket.c:652 [inline]
    sock_sendmsg+0xd7/0x130 net/socket.c:672
    ____sys_sendmsg+0x753/0x880 net/socket.c:2343
    ___sys_sendmsg+0x100/0x170 net/socket.c:2397
    __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
    __do_sys_sendmsg net/socket.c:2439 [inline]
    __se_sys_sendmsg net/socket.c:2437 [inline]
    __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
    do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
    entry_SYSCALL_64_after_hwframe+0x49/0xbe
  RIP: 0033:0x4403d9
  Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00
  RSP: 002b:00007ffc0efbc5c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
  RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9
  RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000004
  RBP: 00000000006ca018 R08: 0000000000000008 R09: 00000000004002c8
  R10: 000000000000004a R11: 0000000000000246 R12: 0000000000401c60
  R13: 0000000000401cf0 R14: 0000000000000000 R15: 0000000000000000

Fixes: b389327d ("RDMA/nldev: Allow counter manual mode configration through RDMA netlink")
Link: https://lore.kernel.org/r/20200227125111.99142-1-leon@kernel.org
Reported-by: syzbot+bd4af81bc51ee0283445@syzkaller.appspotmail.com
Signed-off-by: NMark Zhang <markz@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Registration of a mmu_notifier requires the caller to hold a mmget() on
the mm as registration is not permitted to race with exit_mmap(). There is
a BUG_ON inside the mmu_notifier to guard against this.

Normally creating a umem is done against current which implicitly holds
the mmget(), however an implicit ODP child is created from a pagefault
work queue and is not guaranteed to have a mmget().

Call mmget() around this registration and abort faulting if the MM has
gone to exit_mmap().

Before the patch below the notifier was registered when the implicit ODP
parent was created, so there was no chance to register a notifier outside
of current.

Fixes: c571feca ("RDMA/odp: use mmu_notifier_get/put for 'struct ib_ucontext_per_mm'")
Link: https://lore.kernel.org/r/20200227114118.94736-1-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Fix NULL pointer dereference in the error flow of ib_create_qp_user
when accessing to uninitialized list pointers - rdma_mrs and sig_mrs.
The following crash from syzkaller revealed it.

  kasan: GPF could be caused by NULL-ptr deref or user memory access
  general protection fault: 0000 [#1] SMP KASAN PTI
  CPU: 1 PID: 23167 Comm: syz-executor.1 Not tainted 5.5.0-rc5 #2
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
  rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
  RIP: 0010:ib_mr_pool_destroy+0x81/0x1f0
  Code: 00 00 fc ff df 49 c1 ec 03 4d 01 fc e8 a8 ea 72 fe 41 80 3c 24 00
  0f 85 62 01 00 00 48 8b 13 48 89 d6 4c 8d 6a c8 48 c1 ee 03 <42> 80 3c
  3e 00 0f 85 34 01 00 00 48 8d 7a 08 4c 8b 02 48 89 fe 48
  RSP: 0018:ffffc9000951f8b0 EFLAGS: 00010046
  RAX: 0000000000040000 RBX: ffff88810f268038 RCX: ffffffff82c41628
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffc9000951f850
  RBP: ffff88810f268020 R08: 0000000000000004 R09: fffff520012a3f0a
  R10: 0000000000000001 R11: fffff520012a3f0a R12: ffffed1021e4d007
  R13: ffffffffffffffc8 R14: 0000000000000246 R15: dffffc0000000000
  FS:  00007f54bc788700(0000) GS:ffff88811b100000(0000)
  knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000000 CR3: 0000000116920002 CR4: 0000000000360ee0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   rdma_rw_cleanup_mrs+0x15/0x30
   ib_destroy_qp_user+0x674/0x7d0
   ib_create_qp_user+0xb01/0x11c0
   create_qp+0x1517/0x2130
   ib_uverbs_create_qp+0x13e/0x190
   ib_uverbs_write+0xaa5/0xdf0
   __vfs_write+0x7c/0x100
   vfs_write+0x168/0x4a0
   ksys_write+0xc8/0x200
   do_syscall_64+0x9c/0x390
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  RIP: 0033:0x465b49
  Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89
  f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01
  f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007f54bc787c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
  RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000465b49
  RDX: 0000000000000040 RSI: 0000000020000540 RDI: 0000000000000003
  RBP: 00007f54bc787c70 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 00007f54bc7886bc
  R13: 00000000004ca2ec R14: 000000000070ded0 R15: 0000000000000005

Fixes: a060b562 ("IB/core: generic RDMA READ/WRITE API")
Link: https://lore.kernel.org/r/20200227112708.93023-1-leon@kernel.orgSigned-off-by: NMaor Gottlieb <maorg@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>

Following race may occur because of the call_srcu and the placement of
the synchronize_srcu vs the xa_erase.

CPU0				   CPU1

mlx5_ib_free_implicit_mr:	   destroy_unused_implicit_child_mr:
 xa_erase(odp_mkeys)
 synchronize_srcu()
				    xa_lock(implicit_children)
				    if (still in xarray)
				       atomic_inc()
				       call_srcu()
				    xa_unlock(implicit_children)
 xa_erase(implicit_children):
   xa_lock(implicit_children)
   __xa_erase()
   xa_unlock(implicit_children)

 flush_workqueue()
				   [..]
				    free_implicit_child_mr_rcu:
				     (via call_srcu)
				      queue_work()

 WARN_ON(atomic_read())
				   [..]
				    free_implicit_child_mr_work:
				     (via wq)
				      free_implicit_child_mr()
 mlx5_mr_cache_invalidate()
				     mlx5_ib_update_xlt() <-- UMR QP fail
				     atomic_dec()

The wait_event() solves the race because it blocks until
free_implicit_child_mr_work() completes.

Fixes: 5256edcb ("RDMA/mlx5: Rework implicit ODP destroy")
Link: https://lore.kernel.org/r/20200227113918.94432-1-leon@kernel.orgSigned-off-by: NArtemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: NJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Commit f164be8c ("IB/mlx5: Extend caps stage to handle VAR
capabilities") introduced a straight "/" division of the u64 variable
"bar_size".

This was fixed with commit 685eff51 ("IB/mlx5: Use div64_u64 for
num_var_hw_entries calculation"). However, div64_u64() is redundant here
as mlx5_var_table::stride_size is of type u32.  Make the actual code way
more optimized on 32-bit kernels using div_u64() and fix 80 chars
break-through by the way.

Fixes: 685eff51 ("IB/mlx5: Use div64_u64 for num_var_hw_entries calculation")
Link: https://lore.kernel.org/r/20200217073629.8051-1-alobakin@dlink.ruSigned-off-by: NAlexander Lobakin <alobakin@dlink.ru>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

The proper return code is "-EOPNOTSUPP" when the requested QP type is
not supported by the provider.

Link: https://lore.kernel.org/r/20200130082049.463-1-kamalheib1@gmail.comSigned-off-by: NKamal Heib <kamalheib1@gmail.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Relaxed ordering is not supported in UMR so we are disabling UMR usage
when user passes relaxed ordering access flag.

Enable using UMR when user requested relaxed ordering but there are no
relaxed ordering capabilities.

This will prevent user from unnecessarily registering a new mkey.

Fixes: d6de0bb1 ("RDMA/mlx5: Set relaxed ordering when requested")
Link: https://lore.kernel.org/r/20200227113834.94233-1-leon@kernel.orgSigned-off-by: NMichael Guralnik <michaelgur@mellanox.com>
Reviewed-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/infiniband/hw/bnxt_re/qplib_rcfw.c: In function '__send_message':
drivers/infiniband/hw/bnxt_re/qplib_rcfw.c:101:10: warning:
 variable 'idx' set but not used [-Wunused-but-set-variable]
drivers/infiniband/hw/bnxt_re/qplib_rcfw.c:101:6: warning:
 variable 'pg' set but not used [-Wunused-but-set-variable]

commit cee0c7bb ("RDMA/bnxt_re: Refactor command queue management
code") involved this, but not used.

Link: https://lore.kernel.org/r/20200227064900.92255-1-yuehaibing@huawei.comSigned-off-by: NYueHaibing <yuehaibing@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/infiniband/hw/bnxt_re/ib_verbs.c: In function 'bnxt_re_create_gsi_qp':
drivers/infiniband/hw/bnxt_re/ib_verbs.c:1283:30: warning:
 variable 'dev_attr' set but not used [-Wunused-but-set-variable]

commit 8dae419f ("RDMA/bnxt_re: Refactor queue pair creation code")
involved this, but not used, so remove it.

Link: https://lore.kernel.org/r/20200227064542.91205-1-yuehaibing@huawei.comReported-by: NHulk Robot <hulkci@huawei.com>
Signed-off-by: NYueHaibing <yuehaibing@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/infiniband/hw/bnxt_re/qplib_res.c: In function '__alloc_pbl':
drivers/infiniband/hw/bnxt_re/qplib_res.c:109:13: warning:
 variable 'pg_size' set but not used [-Wunused-but-set-variable]

commit 0c4dcd60 ("RDMA/bnxt_re: Refactor hardware queue memory
allocation") involved this, but not used, so remove it.

Link: https://lore.kernel.org/r/20200227064209.87893-1-yuehaibing@huawei.comReported-by: NHulk Robot <hulkci@huawei.com>
Signed-off-by: NYueHaibing <yuehaibing@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>