8259 Commits

Author SHA1 Message Date
Parav Pandit
218b9e3eb8 RDMA/cma: Move rdma_cm_state to cma_priv.h
rdma_cm_state enum is internal to rdma_cm kernel module.
It is not required to expose state enums to ULP modules.
So lets keep its scope limited to rdma_cm module in cma_priv.h file.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-29 13:54:21 -06:00
Parav Pandit
fd59015d68 IB/addr: Constify dst_entry pointer
Make dst_entry pointer as const struct dst_entry* to improve code
readablity to make sure that dst structure fields are not modified by
various functions which are using it.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-29 13:54:20 -06:00
Jason Gunthorpe
6f57c933a4 RDMA: Use u64_to_user_ptr everywhere
This is already used in many places, get the rest of them too, only
to make the code a bit clearer & simpler.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-29 13:42:29 -06:00
Leon Romanovsky
5b2cc79de8 RDMA/nldev: Provide netdevice name and index
Export the net device name and index to easily find connection
between IB devices and relevant net devices.

We also updated the comment regarding the devices without FW.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-29 13:32:40 -06:00
Zhu Yanjun
99dae69025 IB/rxe: optimize mcast recv process
In mcast recv process, the function skb_clone is used. In fact,
the refcount can be increased to replace cloning a new skb since
the original skb will not be modified before it is freed.

This can make the performance better and save the memory.

CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-29 13:25:22 -06:00
Colin Ian King
a343e3f89e qedr: Fix spelling mistake: "hanlde" -> "handle"
Trivial fix to spelling mistake in DP_ERR message text

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-29 13:19:23 -06:00
Michal Kalderon
50bc60cb15 qed*: Utilize FW 8.33.11.0
This FW contains several fixes and features

RDMA Features
- SRQ support
- XRC support
- Memory window support
- RDMA low latency queue support
- RDMA bonding support

RDMA bug fixes
- RDMA remote invalidate during retransmit fix
- iWARP MPA connect interop issue with RTR fix
- iWARP Legacy DPM support
- Fix MPA reject flow
- iWARP error handling
- RQ WQE validation checks

MISC
- Fix some HSI types endianity
- New Restriction: vlan insertion in core_tx_bd_data can't be set
  for LB packets

ETH
- HW QoS offload support
- Fix vlan, dcb and sriov flow of VF sending a packet with
  inband VLAN tag instead of default VLAN
- Allow GRE version 1 offloads in RX flow
- Allow VXLAN steering

iSCSI / FcoE
- Fix bd availability checking flow
- Support 256th sge proerly in iscsi/fcoe retransmit
- Performance improvement
- Fix handle iSCSI command arrival with AHS and with immediate
- Fix ipv6 traffic class configuration

DEBUG
- Update debug utilities

Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: Manish Rangankar <Manish.Rangankar@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Acked-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-29 14:18:02 -04:00
David S. Miller
6e2135ce54 mlx5-updates-2018-03-27 (Misc updates & SQ recovery)
This series contains Misc updates and cleanups for mlx5e rx path
 and SQ recovery feature for tx path.
 
 From Tariq: (RX updates)
     - Disable Striding RQ when PCI devices, striding RQ limits the use
       of CQE compression feature, which is very critical for slow PCI
       devices performance, in this change we will prefer CQE compression
       over Striding RQ only on specific "slow"  PCIe links.
     - RX path cleanups
     - Private flag to enable/disable striding RQ
 
 From Eran: (TX fast recovery)
     - TX timeout logic improvements, fast SQ recovery and TX error reporting
       if a HW error occurs while transmitting on a specific SQ, the driver will
       ignore such error and will wait for TX timeout to occur and reset all
       the rings. Instead, the current series improves the resiliency for such
       HW errors by detecting TX completions with errors, which will report them
       and perform a fast recover for the specific faulty SQ even before a TX
       timeout is detected.
 
 Thanks,
 Saeed.
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJauuK/AAoJEEg/ir3gV/o+Ro4IAIBcQl4S/6jPttGDOPwElU4b
 Q8MuQbnB9k36Kf6x3GrhBqwtoS3OYBLvfyOeZsghD8uyzklhnqR/psrCt1YhLXq7
 aI5iFbuQucCUwIYBscuZegXBs+PTJYALoil05hOwSkwhEBZR53ZvdRQ9Jg0G0QiY
 sYEYAl41A1DWQOLET5lwleUpVQnVnNvIcXqNHKBKbS4f8rmLpfsZ6YAxJiiIjeDJ
 gLbsaxUyY3p77594okBk6DuFBWZsEAKwumspdSc92OEMrZSYE5ugNL+UgVEE7I8F
 JgK/4OUarw3K7xwhAg//ZhTM1iRRdJv0Sz2GPhhWRzYB0jWACc3ZG2/M/WmxFIg=
 =Uslu
 -----END PGP SIGNATURE-----

Merge tag 'mlx5-updates-2018-03-27' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2018-03-27 (Misc updates & SQ recovery)

This series contains Misc updates and cleanups for mlx5e rx path
and SQ recovery feature for tx path.

From Tariq: (RX updates)
    - Disable Striding RQ when PCI devices, striding RQ limits the use
      of CQE compression feature, which is very critical for slow PCI
      devices performance, in this change we will prefer CQE compression
      over Striding RQ only on specific "slow"  PCIe links.
    - RX path cleanups
    - Private flag to enable/disable striding RQ

From Eran: (TX fast recovery)
    - TX timeout logic improvements, fast SQ recovery and TX error reporting
      if a HW error occurs while transmitting on a specific SQ, the driver will
      ignore such error and will wait for TX timeout to occur and reset all
      the rings. Instead, the current series improves the resiliency for such
      HW errors by detecting TX completions with errors, which will report them
      and perform a fast recover for the specific faulty SQ even before a TX
      timeout is detected.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-29 14:01:40 -04:00
Kirill Tkhai
f0b07bb151 net: Introduce net_rwsem to protect net_namespace_list
rtnl_lock() is used everywhere, and contention is very high.
When someone wants to iterate over alive net namespaces,
he/she has no a possibility to do that without exclusive lock.
But the exclusive rtnl_lock() in such places is overkill,
and it just increases the contention. Yes, there is already
for_each_net_rcu() in kernel, but it requires rcu_read_lock(),
and this can't be sleepable. Also, sometimes it may be need
really prevent net_namespace_list growth, so for_each_net_rcu()
is not fit there.

This patch introduces new rw_semaphore, which will be used
instead of rtnl_mutex to protect net_namespace_list. It is
sleepable and allows not-exclusive iterations over net
namespaces list. It allows to stop using rtnl_lock()
in several places (what is made in next patches) and makes
less the time, we keep rtnl_mutex. Here we just add new lock,
while the explanation of we can remove rtnl_lock() there are
in next patches.

Fine grained locks generally are better, then one big lock,
so let's do that with net_namespace_list, while the situation
allows that.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-29 13:47:53 -04:00
Steve Wise
2253fc0caa RDMA/CMA: Add rdma_port_space to UAPI
Since the rdma_port_space enum is being passed between user and kernel for
user cm_id setup, we need it in a UAPI header.  So add it to
rdma_user_cm.h.

This also fixes the cm_id restrack changes which pass up the port space
value via the RDMA_NLDEV_ATTR_RES_PS attribute.

Fixes: 00313983cda6 ("RDMA/nldev: provide detailed CM_ID information")
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-28 20:50:45 -06:00
Roland Dreier
84652aefb3 RDMA/ucma: Introduce safer rdma_addr_size() variants
There are several places in the ucma ABI where userspace can pass in a
sockaddr but set the address family to AF_IB.  When that happens,
rdma_addr_size() will return a size bigger than sizeof struct sockaddr_in6,
and the ucma kernel code might end up copying past the end of a buffer
not sized for a struct sockaddr_ib.

Fix this by introducing new variants

    int rdma_addr_size_in6(struct sockaddr_in6 *addr);
    int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr);

that are type-safe for the types used in the ucma ABI and return 0 if the
size computed is bigger than the size of the type passed in.  We can use
these new variants to check what size userspace has passed in before
copying any addresses.

Reported-by: <syzbot+6800425d54ed3ed8135d@syzkaller.appspotmail.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-28 16:13:36 -06:00
Alexei Starovoitov
c105547501 treewide: remove large struct-pass-by-value from tracepoint arguments
- fix trace_hfi1_ctxt_info() to pass large struct by reference instead of by value
- convert 'type array[]' tracepoint arguments into 'type *array',
  since compiler will warn that sizeof('type array[]') == sizeof('type *array')
  and later should be used instead

The CAST_TO_U64 macro in the later patch will enforce that tracepoint
arguments can only be integers, pointers, or less than 8 byte structures.
Larger structures should be passed by reference.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-28 22:55:18 +02:00
Eran Ben Elisha
1acae6b030 mlx5: Move dump error CQE function out of mlx5_ib for code sharing
Move mlx5_ib dump error CQE implementation to mlx5 CQ header file in
order to use it in a downstream patch from mlx5e.

In addition, use print_hex_dump instead of manual dumping of the buffer.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2018-03-27 17:17:28 -07:00
Eran Ben Elisha
2816077127 mlx5_{ib,core}: Add query SQ state helper function
Move query SQ state function from mlx5_ib to mlx5_core in order to
have it in shared code.

It will be used in a downstream patch from mlx5e.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2018-03-27 17:17:28 -07:00
Parav Pandit
190fb9c4d1 IB/core: Refer to RoCE port property to decide building cache
IB core maintains the GID cache entries for the GID table.
This cache table has to be maintained regardless of HCA's
support of GID table.
For IB and iWarp ports, cache is created by querying the HCA.
For RoCE cache is created based on netdev events.

Therefore just refer to the RoCE port property of the {device, port} to
decide whether to build cache by querying HCA or from netdev events.
There is no need to check if HCA support GID table or not.

ib_cache_update() referred to RoCE attribute before validating
port. Though in all current callers port is valid, it is incorrect
to query RoCE port property before validating the port. Therefore,
rdma_protocol_roce() check is done after rdma_is_port_valid() verifies
that port is valid.

Fixes: 115b68aa6ea4 ("IB/ocrdma: Removed GID add/del null routines")
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 16:22:12 -06:00
Parav Pandit
22d24f75a1 IB/core: Search GID only for IB link layer
Even though API is only used by IPoIB driver, its incorrect to refer
RoCE GID table property to search for GID.

Look for only IB link layer to search for the GID.

Fixes: dbb12562f7c2 ("IB/{core, ipoib}: Simplify ib_find_gid to search only for IB link layer")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 16:22:12 -06:00
Parav Pandit
4ab7cb4bf3 IB/core: Refer to RoCE port property instead of GID table property
ib_find_gid_by_filter() searches GID with filter only for RoCE link
layer regardless of HCA's support for GID table.
Therefore, right way to lookup is compare RoCE port property and not
the GID table property.

Fixes: 99b27e3b5da0 ("IB/cache: Add ib_find_gid_by_filter cache API")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 16:22:12 -06:00
Parav Pandit
3401857ea3 IB/core: Generate GID change event regardless of RoCE GID table property
Due to following reasons, GID table event is generated regardless of GID
table property.

1. GID table cache is maintained at ib core layer regardless of link layer.
2. GID change event has no relation with IB link layer.
3. GID change event also doesn't depend on whether HCA supports GID table
or not.

Fixes: f3906bd36087 ("IB/core: Refactor GID cache's ib_dispatch_event")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 16:22:12 -06:00
Parav Pandit
97c45c2c28 IB/cm: Block processing alternate path handling RoCE Rx cm messages
Due to below reasons, it is better to not support alternate path receive
messages for RoCE in near term.

1. Alternate path for RoCE is not supported at rdmacm layer.
2. It is not supported in uverbs/core layer for RoCE.
3. Alternate path for IPv6 for link local address cannot resolve route
determinstically without a valid incoming interface id whose usecase
make sense only with dual port mode.
4. init_av_from_path while processing LAP messages for IB and RoCE can
lead to adding duplicate entry of AV into the port list, leads to list
corruption.
5. rdma-core userspace a well known userspace implementation has removed
support of libucm which use ucm.ko module, which is the only module that
can trigger alternate path related messages.
6. ucm kernel module is requested to be removed from the IB core in
patch [1].

[1] https://patchwork.kernel.org/patch/10268503/

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 16:22:12 -06:00
Mark Bloch
e945130b52 IB/core: Protect against concurrent access to hardware stats
Currently access to hardware stats buffer isn't protected, this can
result in multiple writes and reads at the same time to the same
memory location. This can lead to providing an incorrect value to
the user. Add a mutex to protect against it.

Fixes: b40f4757daa1 ("IB/core: Make device counter infrastructure dynamic")
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 15:07:21 -06:00
Colin Ian King
38759d6175 RDMA/hns: ensure for-loop actually iterates and free's buffers
The current for-loop zeros variable i and only loops once, hence
not all the buffers are free'd.  Fix this by setting i correctly.

Detected by CoverityScan, CID#1463415 ("Operands don't affect result")

Fixes: a5073d6054f7 ("RDMA/hns: Add eq support of hip08")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 15:06:34 -06:00
Majd Dibbiny
c8d75a980f IB/mlx5: Respect new UMR capabilities
In some firmware configuration, UMR usage from Virtual Functions is restricted.
This information is published to the driver using new capability bits.

Avoid using UMRs in these cases and use the Firmware slow-path flow to create
mkeys and populate them with Virtual to Physical address translation.

Older drivers that do not have this patch, will end up using memory keys that
aren't populated with Virtual to Physical address translation that is done
part of the UMR work.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Tested-by: Laurence Oberman <loberman@redhat.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 14:43:10 -06:00
Majd Dibbiny
ea8af0d2f2 IB/mlx5: Enable ECN capable bits for UD RoCE v2 QPs
When working with RC QPs, the FW sets the ECN capable bits for all
the RoCE v2 packets. On the other hand, for UD QPs, the driver needs
to set the the ECN capable bits in the Address Handler since the HW
generates each packet according to the Address Handler and not
the QP context.

If ECN is not enabled in NIC or switch, these bits are ignored.

Fixes: 2811ba51b049 ("IB/mlx5: Add RoCE fields to Address Vector")
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 14:43:10 -06:00
Jason Gunthorpe
f2e9bfac13 RDMA/rxe: Fix uABI structure layouts for 32/64 compat
With 32 bit compilation several of the fields become misaligned here.
Fixing this is an ABI break for 32 bit rxe and it is in well used
portions of the rxe ABI.

To handle this we bump the ABI version, as expected. However the user
space driver doesn't handle it properly today, so all existing user
space continues to work.

Updated userspace will start to require the necessary kernel version.

We don't expect there to be any 32 bit users of rxe. Most likely cases,
such as ARM 32 already generally don't work because rxe does not handle
the CPU cache properly on its shared with userspace pages.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 14:25:09 -06:00
Jason Gunthorpe
611cb92b08 RDMA/ucma: Fix uABI structure layouts for 32/64 compat
The rdma_ucm_event_resp is a different length on 32 and 64 bit compiles.

The kernel requires it to be the expected length or longer so 32 bit
builds running on a 64 bit kernel will not work.

Retain full compat by having all kernels accept a struct with or without
the trailing reserved field.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 14:25:08 -06:00
Leon Romanovsky
c8d3bcbfc5 RDMA/ucma: Check that device exists prior to accessing it
Ensure that device exists prior to accessing its properties.

Reported-by: <syzbot+71655d44855ac3e76366@syzkaller.appspotmail.com>
Fixes: 75216638572f ("RDMA/cma: Export rdma cm interface to userspace")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 14:10:45 -06:00
Leon Romanovsky
4b658d1bbc RDMA/ucma: Check that device is connected prior to access it
Add missing check that device is connected prior to access it.

[   55.358652] BUG: KASAN: null-ptr-deref in rdma_init_qp_attr+0x4a/0x2c0
[   55.359389] Read of size 8 at addr 00000000000000b0 by task qp/618
[   55.360255]
[   55.360432] CPU: 1 PID: 618 Comm: qp Not tainted 4.16.0-rc1-00071-gcaf61b1b8b88 
[   55.361693] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-project.org 04/01/2014
[   55.363264] Call Trace:
[   55.363833]  dump_stack+0x5c/0x77
[   55.364215]  kasan_report+0x163/0x380
[   55.364610]  ? rdma_init_qp_attr+0x4a/0x2c0
[   55.365238]  rdma_init_qp_attr+0x4a/0x2c0
[   55.366410]  ucma_init_qp_attr+0x111/0x200
[   55.366846]  ? ucma_notify+0xf0/0xf0
[   55.367405]  ? _get_random_bytes+0xea/0x1b0
[   55.367846]  ? urandom_read+0x2f0/0x2f0
[   55.368436]  ? kmem_cache_alloc_trace+0xd2/0x1e0
[   55.369104]  ? refcount_inc_not_zero+0x9/0x60
[   55.369583]  ? refcount_inc+0x5/0x30
[   55.370155]  ? rdma_create_id+0x215/0x240
[   55.370937]  ? _copy_to_user+0x4f/0x60
[   55.371620]  ? mem_cgroup_commit_charge+0x1f5/0x290
[   55.372127]  ? _copy_from_user+0x5e/0x90
[   55.372720]  ucma_write+0x174/0x1f0
[   55.373090]  ? ucma_close_id+0x40/0x40
[   55.373805]  ? __lru_cache_add+0xa8/0xd0
[   55.374403]  __vfs_write+0xc4/0x350
[   55.374774]  ? kernel_read+0xa0/0xa0
[   55.375173]  ? fsnotify+0x899/0x8f0
[   55.375544]  ? fsnotify_unmount_inodes+0x170/0x170
[   55.376689]  ? __fsnotify_update_child_dentry_flags+0x30/0x30
[   55.377522]  ? handle_mm_fault+0x174/0x320
[   55.378169]  vfs_write+0xf7/0x280
[   55.378864]  SyS_write+0xa1/0x120
[   55.379270]  ? SyS_read+0x120/0x120
[   55.379643]  ? mm_fault_error+0x180/0x180
[   55.380071]  ? task_work_run+0x7d/0xd0
[   55.380910]  ? __task_pid_nr_ns+0x120/0x140
[   55.381366]  ? SyS_read+0x120/0x120
[   55.381739]  do_syscall_64+0xeb/0x250
[   55.382143]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[   55.382841] RIP: 0033:0x7fc2ef803e99
[   55.383227] RSP: 002b:00007fffcc5f3be8 EFLAGS: 00000217 ORIG_RAX: 0000000000000001
[   55.384173] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fc2ef803e99
[   55.386145] RDX: 0000000000000057 RSI: 0000000020000080 RDI: 0000000000000003
[   55.388418] RBP: 00007fffcc5f3c00 R08: 0000000000000000 R09: 0000000000000000
[   55.390542] R10: 0000000000000000 R11: 0000000000000217 R12: 0000000000400480
[   55.392916] R13: 00007fffcc5f3cf0 R14: 0000000000000000 R15: 0000000000000000
[   55.521088] Code: e5 4d 1e ff 48 89 df 44 0f b6 b3 b8 01 00 00 e8 65 50 1e ff 4c 8b 2b 49
8d bd b0 00 00 00 e8 56 50 1e ff 41 0f b6 c6 48 c1 e0 04 <49> 03 85 b0 00 00 00 48 8d 78 08
48 89 04 24 e8 3a 4f 1e ff 48
[   55.525980] RIP: rdma_init_qp_attr+0x52/0x2c0 RSP: ffff8801e2c2f9d8
[   55.532648] CR2: 00000000000000b0
[   55.534396] ---[ end trace 70cee64090251c0b ]---

Fixes: 75216638572f ("RDMA/cma: Export rdma cm interface to userspace")
Fixes: d541e45500bd ("IB/core: Convert ah_attr from OPA to IB when copying to user")
Reported-by: <syzbot+7b62c837c2516f8f38c8@syzkaller.appspotmail.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 14:10:45 -06:00
Jason Gunthorpe
9137108cc3 RDMA/rdma_cm: Fix use after free race with process_one_req
process_one_req() can race with rdma_addr_cancel():

           CPU0                                 CPU1
           ====                                 ====
 process_one_work()
  debug_work_deactivate(work);
  process_one_req()
                                        rdma_addr_cancel()
	                                  mutex_lock(&lock);
 			    	           set_timeout(&req->work,..);
                                              __queue_work()
				   	       debug_work_activate(work);
	                                  mutex_unlock(&lock);

   mutex_lock(&lock);
[..]
	list_del(&req->list);
   mutex_unlock(&lock);
[..]

   // ODEBUG explodes since the work is still queued.
   kfree(req);

Causing ODEBUG to detect the use after free:

ODEBUG: free active (active state 0) object type: work_struct hint: process_one_req+0x0/0x6c0 include/net/dst.h:165
WARNING: CPU: 0 PID: 79 at lib/debugobjects.c:291 debug_print_object+0x166/0x220 lib/debugobjects.c:288
kvm: emulating exchange as write
Kernel panic - not syncing: panic_on_warn set ...

CPU: 0 PID: 79 Comm: kworker/u4:3 Not tainted 4.16.0-rc6+ 
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: ib_addr process_one_req
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x24d lib/dump_stack.c:53
 panic+0x1e4/0x41c kernel/panic.c:183
 __warn+0x1dc/0x200 kernel/panic.c:547
 report_bug+0x1f4/0x2b0 lib/bug.c:186
 fixup_bug.part.11+0x37/0x80 arch/x86/kernel/traps.c:178
 fixup_bug arch/x86/kernel/traps.c:247 [inline]
 do_error_trap+0x2d7/0x3e0 arch/x86/kernel/traps.c:296
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315
 invalid_op+0x1b/0x40 arch/x86/entry/entry_64.S:986
RIP: 0010:debug_print_object+0x166/0x220 lib/debugobjects.c:288
RSP: 0000:ffff8801d966f210 EFLAGS: 00010086
RAX: dffffc0000000008 RBX: 0000000000000003 RCX: ffffffff815acd6e
RDX: 0000000000000000 RSI: 1ffff1003b2cddf2 RDI: 0000000000000000
RBP: ffff8801d966f250 R08: 0000000000000000 R09: 1ffff1003b2cddc8
R10: ffffed003b2cde71 R11: ffffffff86f39a98 R12: 0000000000000001
R13: ffffffff86f15540 R14: ffffffff86408700 R15: ffffffff8147c0a0
 __debug_check_no_obj_freed lib/debugobjects.c:745 [inline]
 debug_check_no_obj_freed+0x662/0xf1f lib/debugobjects.c:774
 kfree+0xc7/0x260 mm/slab.c:3799
 process_one_req+0x2e7/0x6c0 drivers/infiniband/core/addr.c:592
 process_one_work+0xc47/0x1bb0 kernel/workqueue.c:2113
 worker_thread+0x223/0x1990 kernel/workqueue.c:2247
 kthread+0x33c/0x400 kernel/kthread.c:238
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:406

Fixes: 5fff41e1f89d ("IB/core: Fix race condition in resolving IP to MAC")
Reported-by: <syzbot+3b4acab09b6463472d0a@syzkaller.appspotmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-27 13:19:01 -06:00
Kirill Tkhai
2f635ceeb2 net: Drop pernet_operations::async
Synchronous pernet_operations are not allowed anymore.
All are asynchronous. So, drop the structure member.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-27 13:18:09 -04:00
Kirill Tkhai
070f2d7e26 net: Drop NETDEV_UNREGISTER_FINAL
Last user is gone after bdf5bd7f2132 "rds: tcp: remove
register_netdevice_notifier infrastructure.", so we can
remove this netdevice command. This allows to delete
rtnl_lock() in netdev_run_todo(), which is hot path for
net namespace unregistration.

dev_change_net_namespace() and netdev_wait_allrefs()
have rcu_barrier() before NETDEV_UNREGISTER_FINAL call,
and the source commits say they were introduced to
delemit the call with NETDEV_UNREGISTER, but this patch
leaves them on the places, since they require additional
analysis, whether we need in them for something else.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-26 11:34:00 -04:00
Kirill Tkhai
3e0c2dbfea infiniband: Replace usnic_ib_netdev_event_to_string() with netdev_cmd_to_name()
This function just calls netdev_cmd_to_name().

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-26 11:34:00 -04:00
Kirill Tkhai
ede2762d93 net: Make NETDEV_XXX commands enum { }
This patch is preparation to drop NETDEV_UNREGISTER_FINAL.
Since the cmd is used in usnic_ib_netdev_event_to_string()
to get cmd name, after plain removing NETDEV_UNREGISTER_FINAL
from everywhere, we'd have holes in event2str[] in this
function.

Instead of that, let's make NETDEV_XXX commands names
available for everyone, and to define netdev_cmd_to_name()
in the way we won't have to shaffle names after their
numbers are changed.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-26 11:33:26 -04:00
Steve Wise
f215a3d244 iw_cxgb4: Add ib_device->get_netdev support
This is useful to rdma ULPs.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-23 11:12:51 -06:00
Parav Pandit
114cc9c4b1 IB/cma: Resolve route only while receiving CM requests
Currently CM request for RoCE follows following flow.
rdma_create_id()
rdma_resolve_addr()
rdma_resolve_route()
For RC QPs:
rdma_connect()
->cma_connect_ib()
  ->ib_send_cm_req()
    ->cm_init_av_by_path()
      ->ib_init_ah_attr_from_path()
For UD QPs:
rdma_connect()
->cma_resolve_ib_udp()
  ->ib_send_cm_sidr_req()
    ->cm_init_av_by_path()
      ->ib_init_ah_attr_from_path()

In both the flows, route is already resolved before sending CM requests.
Therefore, code is refactored to avoid resolving route second time in
ib_cm layer.
ib_init_ah_attr_from_path() is extended to resolve route when it is not
yet resolved for RoCE link layer. This is achieved by caller setting
route_resolved field in path record whenever it has route already
resolved.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-23 10:58:05 -06:00
David S. Miller
03fe2debbb Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Fun set of conflict resolutions here...

For the mac80211 stuff, these were fortunately just parallel
adds.  Trivially resolved.

In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the
function phy_disable_interrupts() earlier in the file, whilst in
'net-next' the phy_error() call from this function was removed.

In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the
'rt_table_id' member of rtable collided with a bug fix in 'net' that
added a new struct member "rt_mtu_locked" which needs to be copied
over here.

The mlxsw driver conflict consisted of net-next separating
the span code and definitions into separate files, whilst
a 'net' bug fix made some changes to that moved code.

The mlx5 infiniband conflict resolution was quite non-trivial,
the RDMA tree's merge commit was used as a guide here, and
here are their notes:

====================

    Due to bug fixes found by the syzkaller bot and taken into the for-rc
    branch after development for the 4.17 merge window had already started
    being taken into the for-next branch, there were fairly non-trivial
    merge issues that would need to be resolved between the for-rc branch
    and the for-next branch.  This merge resolves those conflicts and
    provides a unified base upon which ongoing development for 4.17 can
    be based.

    Conflicts:
            drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f9524
            (IB/mlx5: Fix cleanup order on unload) added to for-rc and
            commit b5ca15ad7e61 (IB/mlx5: Add proper representors support)
            add as part of the devel cycle both needed to modify the
            init/de-init functions used by mlx5.  To support the new
            representors, the new functions added by the cleanup patch
            needed to be made non-static, and the init/de-init list
            added by the representors patch needed to be modified to
            match the init/de-init list changes made by the cleanup
            patch.
    Updates:
            drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function
            prototypes added by representors patch to reflect new function
            names as changed by cleanup patch
            drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init
            stage list to match new order from cleanup patch
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-23 11:31:58 -04:00
Parav Pandit
98f1f4e0ed IB/core: Refer to RoCE port property instead of GID table property
ib_query_gid() in commit [1] refers to RoCE GID table capability of
the HCA using rdma_cap_roce_gid_table().
ib_core maintains the GID table cache regardless of the HCA provider
drivers capability to maintain RoCE GID table.
Therefore, whether to return a GID table entry from the software cache or
from HCA should be done based on whether the port is RoCE or not.

[1] commit 03db3a2d81e6 ("IB/core: Add RoCE GID table management")

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-22 12:42:49 -06:00
Leon Romanovsky
03286030ac RDMA/restrack: Remove ambiguity in resource track clean logic
The restrack clean routine had simple, but powerful WARN_ON check
to see if all resources are cleared prior to releasing device.

The WARN_ON check performed very well, but lack of information
which device caused to resource leak, the object type and origin
made debug to be fun and challenging at the same time.

The fact that all dumps were the same because restrack_clean() is
called in dealloc() didn't help either.

So let's fix spelling error and convert WARN_ON to be more debug
friendly. The dmesg cut below gives example of how the output
will look output for the case fixed in patch [1]

[  438.421372] restrack: ------------[ cut here ]------------
[  438.423448] restrack: BUG: RESTRACK detected leak of resources on mlx5_2
[  438.425600] restrack: Kernel PD object allocated by mlx5_ib is not freed
[  438.427753] restrack: Kernel CQ object allocated by mlx5_ib is not freed
[  438.429660] restrack: ------------[ cut here ]------------

[1] https://patchwork.kernel.org/patch/10298695/

Cc: Michal Kalderon <Michal.Kalderon@cavium.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-22 12:42:48 -06:00
Yixian Liu
e95955773d RDMA/hns: Fix cq record doorbell enable in kernel
Upon detecting both kernel and user space support record doorbell,
the kernel needs to enable this capability in hardware by db_en,
and it should take place before cq context configuration in
hns_roce_cq_alloc. Currently, db_en is configured after cq alloc
and db_map_user has similar problem.

Reported-by: Xiping Zhang <zhangxiping3@huawei.com>
Fixes: 9b44703d0a21 ("RDMA/hns: Support cq record doorbell for the user space")
Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-22 12:42:48 -06:00
Jason Gunthorpe
761fc376c9 RDMA/cxgb3: Use structs to describe the uABI instead of opencoding
Open coding a loose value is not acceptable for describing the uABI in
RDMA. Provide the missing struct.

Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-22 12:42:48 -06:00
Kalderon, Michal
caf61b1b8b RDMA/qedr: Fix QP state initialization race
Once the FW is transitioned to error, FLUSH cqes can be received.
We want the driver to be aware of the fact that QP is already in error.

Without this fix, a user may see false error messages in the dmesg log,
mentioning that a FLUSH cqe was received while QP is not in error state.

Fixes: cecbcddf ("qedr: Add support for QP verbs")
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-21 14:38:41 -06:00
Kalderon, Michal
b15606f47b RDMA/qedr: Fix rc initialization on CNQ allocation failure
Return code wasn't set properly when CNQ allocation failed.
This only affect error message logging, currently user will
receive an error message that says the qedr driver load failed
with rc '0', instead of ENOMEM

Fixes: ec72fce4 ("qedr: Add support for RoCE HW init")
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-21 14:38:41 -06:00
Kalderon, Michal
c3594f2230 RDMA/qedr: fix QP's ack timeout configuration
QPs that were configured with ack timeout value lower than 1
msec will not implement re-transmission timeout.
This means that if a packet / ACK were dropped, the QP
will not retransmit this packet.

This can lead to an application hang.

Fixes: cecbcddf6 ("qedr: Add support for QP verbs")
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-21 14:38:41 -06:00
Chien Tin Tung
5f3e3b85cc RDMA/ucma: Correct option size check using optlen
The option size check is using optval instead of optlen
causing the set option call to fail. Use the correct
field, optlen, for size check.

Fixes: 6a21dfc0d0db ("RDMA/ucma: Limit possible option size")
Signed-off-by: Chien Tin Tung <chien.tin.tung@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-21 14:22:22 -06:00
Leon Romanovsky
103140eccb RDMA/restrack: Move restrack_clean to be symmetrical to restrack_init
The fact that resource tracking commit 02d8883f520e ("RDMA/restrack: Add
general infrastructure to track RDMA resources") was added immediately
after commit 16c1975f1032 ("IB/mlx5: Create profile infrastructure to add
and remove stages") caused us to miss the fact that PD and CQ are created
after ib_register_device, but released after ib_unregister_device() and
not before as it is expected from normal flow.

Fix introduced in commit 42cea83f9524 ("IB/mlx5: Fix cleanup order on
unload") revealed this fact, so this patch is needed to avoid from
restrack warnings

It fixes resource tracking warnings during shutdown.

[   43.473906] CPU: 5 PID: 3016 Comm: modprobe Not tainted 4.16.0-rc5-for-linust-perf-2018-03-19_07-01-58-14 
[   43.473907] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu2 04/01/2014
[   43.473919] RIP: 0010:rdma_restrack_clean+0x25/0x30 [ib_core]
[   43.473921] RSP: 0018:ffffc9000267be48 EFLAGS: 00010282
[   43.473924] RAX: 0000000000000000 RBX: ffff88033c690070 RCX: 0000000180080006
[   43.473925] RDX: ffff88035ce922e0 RSI: ffffea000cf1a200 RDI: ffff88033c6907c8
[   43.473926] RBP: ffff88033c690070 R08: ffff88033c689000 R09: 0000000180080006
[   43.473927] R10: 000000003c68a001 R11: ffff88033c689000 R12: ffff88033c690000
[   43.473929] R13: ffff88033c69005c R14: 0000000000000000 R15: 0000000000000000
[   43.473932] FS:  00007f5928359740(0000) GS:ffff88036c540000(0000) knlGS:0000000000000000
[   43.473933] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   43.473935] CR2: 00007ffffc760cc8 CR3: 000000035620c000 CR4: 00000000000006e0
[   43.473940] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   43.473941] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   43.473942] Call Trace:
[   43.473969]  ib_unregister_device+0xf5/0x190 [ib_core]
[   43.474000]  __mlx5_ib_remove+0x2e/0x40 [mlx5_ib]
[   43.474098]  mlx5_remove_device+0xf5/0x120 [mlx5_core]
[   43.474132]  mlx5_unregister_interface+0x37/0x90 [mlx5_core]
[   43.474142]  mlx5_ib_cleanup+0xc/0x16a [mlx5_ib]
[   43.474152]  SyS_delete_module+0x159/0x260
[   43.474159]  do_syscall_64+0x61/0x110
[   43.474165]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[   43.474168] RIP: 0033:0x7f59278466b7
[   43.474170] RSP: 002b:00007ffffc763e38 EFLAGS: 00000202 ORIG_RAX: 00000000000000b0
[   43.474172] RAX: ffffffffffffffda RBX: 000000000130d590 RCX: 00007f59278466b7
[   43.474173] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 000000000130d5f8
[   43.474175] RBP: 0000000000000000 R08: 00007f5927b0b060 R09: 00007f59278b6a40
[   43.474176] R10: 00007ffffc763bc0 R11: 0000000000000202 R12: 0000000000000000
[   43.474177] R13: 0000000000000001 R14: 000000000130d5f8 R15: 0000000000000000
[   43.474179] Code: 84 00 00 00 00 00 0f 1f 44 00 00 48 83 c7 28 31 c0
eb 0c 48 83 c0 08 48 3d 00 08 00 00 74 0f 48 8d 14 07 48 8b 12 48 85 d2
74 e8 <0f> 0b c3 f3 c3 66 0f 1f 44 00 00 0f 1f 44 00 00 53 48 8b 47 28
[   43.474221] ---[ end trace e89771e2250ffc23 ]---

Fixes: 42cea83f9524 ("IB/mlx5: Fix cleanup order on unload")
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-21 14:22:22 -06:00
Mark Bloch
32927e281c IB/mlx5: Don't clean uninitialized UMR resources
In case we failed to create UMR resources, mark them as invalid so we
won't try to destroy them on the unwind path.

Add the relevant checks to destroy_umrc_res(), this is done for the
unlikely event ib_register_device() or create_umr_res() err out and we
try to destroy invalid objects.

Fixes: 42cea83f9524 ("IB/mlx5: Fix cleanup order on unload")
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-21 14:22:22 -06:00
Sinan Kaya
97d82a48d7 IB/mlx4: Eliminate duplicate barriers on weakly-ordered archs
Code includes wmb() followed by writel(). writel() already has a barrier on
some architectures like arm64.

This ends up CPU observing two barriers back to back before executing the
register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-21 13:51:41 -06:00
Linus Torvalds
303851e14a Fourth pull request for 4.16-rc
- Many bug fixes related to syzkaller from Leon Romanovsky.
   These are still for the mlx driver and ucma interface.
 - Fix a situation with port reuse for iWarp, discovered during scale-up
   testing
 - Bug fixes for the profile and restrack patches accepted during this merge
   window
 - Compile warning cleanups from Arnd, this is apparently the last warning
   to make 32 bit builds quite.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQIcBAABCgAGBQJasZXlAAoJEDht9xV+IJsaOv8QAJ7FwiS/DVadNBD9/Gjksb/V
 co41g9eK4s0qEKXJgMLjSr/aaK7gCG2waeXRSSJm52e1ERyiyceRaoLWqhJ98ZOt
 xs/rAj4aBKmRgQ5j082O3YYVaAHETTIcPYVjlULDNhkqH1xhtm7LmKxTHPxGxLdU
 IMKZeQStY46or3fuOyDmHQ7RbxRbl+7LhL1LEE9+dd7u6fSipgGWv6i3Wrqex/AV
 XC1C1Pabq7Qo+d516mNX2JSjo9jT4kuamLprxQtUJxMeU5UJ+7IlZlTOGgU0q2Zv
 x8W7744zVvifUc1gs3AFRvwhDkTrwnkhFullCyVN86r1jrduG1kxX+N0ksCY79yB
 h9A5r+qV63XPelDJAFQIllkLPh8p3raCfvfQZAMkVqh2Lqn2s1tlukN/6NLAaguW
 YAwbRk0Q1XgXRj4mGW+3vEH7UGMgaIqF2JlnU25hOuoyVSUkgvy88NG9aVx//a5h
 KCdRa/iqTDJthKfnCAu+yYa4k5AKeRkdNKB0GebiPrrdpgJHMBKuPCjLrd4NP9QG
 As1gi9N3gtNoZL7QEyYBL8NIXNpiiY4YANFf7otoZwvFBSzILKWJI74WOg8HWGJT
 jKDQk6WQfYS3Xe3WVy0WOXhsdvYyiCXdag63ErUlzAMffhpp1GZoBEEk+4z+lYL8
 W69w1xQcntpG9N+EBqBT
 =Gal+
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma fixes from Jason Gunthorpe:
 "Not much exciting here, almost entirely syzkaller fixes.

  This is going to be on ongoing theme for some time, I think. Both
  Google and Mellanox are now running syzkaller on different parts of
  the user API.

  Summary:

   - Many bug fixes related to syzkaller from Leon Romanovsky. These are
     still for the mlx driver and ucma interface.

   - Fix a situation with port reuse for iWarp, discovered during
     scale-up testing

   - Bug fixes for the profile and restrack patches accepted during this
     merge window

   - Compile warning cleanups from Arnd, this is apparently the last
     warning to make 32 bit builds quiet"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/ucma: Ensure that CM_ID exists prior to access it
  RDMA/verbs: Remove restrack entry from XRCD structure
  RDMA/ucma: Fix use-after-free access in ucma_close
  RDMA/ucma: Check AF family prior resolving address
  infiniband: bnxt_re: use BIT_ULL() for 64-bit bit masks
  infiniband: qplib_fp: fix pointer cast
  IB/mlx5: Fix cleanup order on unload
  RDMA/ucma: Don't allow join attempts for unsupported AF family
  RDMA/ucma: Fix access to non-initialized CM_ID object
  RDMA/core: Do not use invalid destination in determining port reuse
  RDMA/mlx5: Fix crash while accessing garbage pointer and freed memory
  IB/mlx5: Fix integer overflows in mlx5_ib_create_srq
  IB/mlx5: Fix out-of-bounds read in create_raw_packet_qp_rq
2018-03-20 17:39:07 -07:00
Leon Romanovsky
e8980d67d6 RDMA/ucma: Ensure that CM_ID exists prior to access it
Prior to access UCMA commands, the context should be initialized
and connected to CM_ID with ucma_create_id(). In case user skips
this step, he can provide non-valid ctx without CM_ID and cause
to multiple NULL dereferences.

Also there are situations where the create_id can be raced with
other user access, ensure that the context is only shared to
other threads once it is fully initialized to avoid the races.

[  109.088108] BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
[  109.090315] IP: ucma_connect+0x138/0x1d0
[  109.092595] PGD 80000001dc02d067 P4D 80000001dc02d067 PUD 1da9ef067 PMD 0
[  109.095384] Oops: 0000 [] SMP KASAN PTI
[  109.097834] CPU: 0 PID: 663 Comm: uclose Tainted: G    B 4.16.0-rc1-00062-g2975d5de6428 
[  109.100816] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-project.org 04/01/2014
[  109.105943] RIP: 0010:ucma_connect+0x138/0x1d0
[  109.108850] RSP: 0018:ffff8801c8567a80 EFLAGS: 00010246
[  109.111484] RAX: 0000000000000000 RBX: 1ffff100390acf50 RCX: ffffffff9d7812e2
[  109.114496] RDX: 1ffffffff3f507a5 RSI: 0000000000000297 RDI: 0000000000000297
[  109.117490] RBP: ffff8801daa15600 R08: 0000000000000000 R09: ffffed00390aceeb
[  109.120429] R10: 0000000000000001 R11: ffffed00390aceea R12: 0000000000000000
[  109.123318] R13: 0000000000000120 R14: ffff8801de6459c0 R15: 0000000000000118
[  109.126221] FS:  00007fabb68d6700(0000) GS:ffff8801e5c00000(0000) knlGS:0000000000000000
[  109.129468] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  109.132523] CR2: 0000000000000020 CR3: 00000001d45d8003 CR4: 00000000003606b0
[  109.135573] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  109.138716] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  109.142057] Call Trace:
[  109.144160]  ? ucma_listen+0x110/0x110
[  109.146386]  ? wake_up_q+0x59/0x90
[  109.148853]  ? futex_wake+0x10b/0x2a0
[  109.151297]  ? save_stack+0x89/0xb0
[  109.153489]  ? _copy_from_user+0x5e/0x90
[  109.155500]  ucma_write+0x174/0x1f0
[  109.157933]  ? ucma_resolve_route+0xf0/0xf0
[  109.160389]  ? __mod_node_page_state+0x1d/0x80
[  109.162706]  __vfs_write+0xc4/0x350
[  109.164911]  ? kernel_read+0xa0/0xa0
[  109.167121]  ? path_openat+0x1b10/0x1b10
[  109.169355]  ? fsnotify+0x899/0x8f0
[  109.171567]  ? fsnotify_unmount_inodes+0x170/0x170
[  109.174145]  ? __fget+0xa8/0xf0
[  109.177110]  vfs_write+0xf7/0x280
[  109.179532]  SyS_write+0xa1/0x120
[  109.181885]  ? SyS_read+0x120/0x120
[  109.184482]  ? compat_start_thread+0x60/0x60
[  109.187124]  ? SyS_read+0x120/0x120
[  109.189548]  do_syscall_64+0xeb/0x250
[  109.192178]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[  109.194725] RIP: 0033:0x7fabb61ebe99
[  109.197040] RSP: 002b:00007fabb68d5e98 EFLAGS: 00000202 ORIG_RAX: 0000000000000001
[  109.200294] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fabb61ebe99
[  109.203399] RDX: 0000000000000120 RSI: 00000000200001c0 RDI: 0000000000000004
[  109.206548] RBP: 00007fabb68d5ec0 R08: 0000000000000000 R09: 0000000000000000
[  109.209902] R10: 0000000000000000 R11: 0000000000000202 R12: 00007fabb68d5fc0
[  109.213327] R13: 0000000000000000 R14: 00007fff40ab2430 R15: 00007fabb68d69c0
[  109.216613] Code: 88 44 24 2c 0f b6 84 24 6e 01 00 00 88 44 24 2d 0f
b6 84 24 69 01 00 00 88 44 24 2e 8b 44 24 60 89 44 24 30 e8 da f6 06 ff
31 c0 <66> 41 83 7c 24 20 1b 75 04 8b 44 24 64 48 8d 74 24 20 4c 89 e7
[  109.223602] RIP: ucma_connect+0x138/0x1d0 RSP: ffff8801c8567a80
[  109.226256] CR2: 0000000000000020

Fixes: 75216638572f ("RDMA/cma: Export rdma cm interface to userspace")
Reported-by: <syzbot+36712f50b0552615bf59@syzkaller.appspotmail.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-20 11:07:21 -06:00
Matan Barak
185899ee8d IB/uverbs: Enable ioctl() uAPI by default for new verbs
Enable the ioctl() uAPI for IB by default if the standard write()
uAPI (INFINIBAND_USER_ACCESS) is enabled. Verbs that are
also available under the old write() uAPI are put inside a new
INFINIBAND_EXP_LEGACY_VERBS_NEW_UAPI Kconfig.

Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-19 14:45:17 -06:00
Matan Barak
41b2a71fc8 IB/uverbs: Move ioctl path of create_cq and destroy_cq to a new file
Currently, all objects are declared in uverbs_std_types. This could lead
to a huge file once we implement all objects, methods and handlers.
Moving each object to its own file to keep the files smaller and more
readable. uverbs_std_types.c will only contain the parsing tree
definition and objects without any methods.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-19 14:45:17 -06:00