IB/mlx4: Report TSO capabilities

Report to the user area the TSO device capabilities, it includes the
max_tso size and the QP types that support it.

The TSO is applicable only when when of the ports is ETH and the device
supports it.

uresp logic around rss_caps is updated to fix a till-now harmless bug
computing the length of the structure to copy. The code did not handle the
implicit padding before rss_caps correctly. This is necessay to copy
tss_caps successfully.

Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

i40iw: Tear-down connection after CQP Modify QP failure

There is no explicit tear-down sequence initiated on
connections if the Control QP OP, Modify QP to close,
fails. Fix this by triggering a driver generated
Asynchronous Event (AE) on Modify QP failures and
tear-down the connection on receipt of the AE.

This fix can be generalized to other Modify QP failures
(i.e. RTS->TERM, IDLE->RTS, etc) as any modify failure
will require a connection tear-down.

Fixes: d37498417947 ("i40iw: add files for iwarp interface")
Signed-off-by: Henry Orosco <henry.orosco@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

i40iw: Refactor of driver generated AEs

The flush CQP OP can be used to optionally generate
Asynchronous Events (AEs) in addition to QP flush.
Consolidate all HW AE generation code under a new
function i40iw_gen_ae which use the flush CQP OP
to only generate AEs.

Signed-off-by: Henry Orosco <henry.orosco@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/cxgb4: 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.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/hns: 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.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/i40iw: Move uapi header to include/uapi

All of these defines are part of the uABI for the driver, this
header duplicates providers/i40iw/i40iw-abi.h in rdma-core.

Acked-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/mlx4: Move flag constants to uapi header

MLX4_USER_DEV_CAP_LARGE_CQE (via mlx4_ib_alloc_ucontext_resp.dev_caps)
and MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET (via
mlx4_uverbs_ex_query_device_resp.comp_mask) are copied directly to
userspace and form part of the uAPI.

Move them to the uapi header where they belong.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/rxe: Use structs to describe the uABI instead of opencoding

Open coding pointer math is not acceptable for describing the uABI in
RDMA. Provide structs for all the cases.

The udata is casted to the struct as close to the verbs entry point
as possible for maximum clarity. Function signatures and so forth
are revised to allow for this.

Tested-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/rxe: Get rid of confusing udata parameter to rxe_cq_chk_attr

It isn't used and it couldn't possibly ever be used correctly.

Tested-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMAVT: Fix synchronization around percpu_ref

rvt_mregion uses percpu_ref for reference counting and RCU to protect
accesses from lkey_table.  When a rvt_mregion needs to be freed, it
first gets unregistered from lkey_table and then rvt_check_refs() is
called to wait for in-flight usages before the rvt_mregion is freed.

rvt_check_refs() seems to have a couple issues.

* It has a fast exit path which tests percpu_ref_is_zero().  However,
  a percpu_ref reading zero doesn't mean that the object can be
  released.  In fact, the ->release() callback might not even have
  started executing yet.  Proceeding with freeing can lead to
  use-after-free.

* lkey_table is RCU protected but there is no RCU grace period in the
  free path.  percpu_ref uses RCU internally but it's sched-RCU whose
  grace periods are different from regular RCU.  Also, it generally
  isn't a good idea to depend on internal behaviors like this.

To address the above issues, this patch removes the fast exit and adds
an explicit synchronize_rcu().

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: linux-rdma@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/qedr: eliminate duplicate barriers on weakly-ordered archs

Code includes wmb() followed by writel() in multiple places. 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>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

RDMA/hns: Fix cqn type and init resp

This patch changes the type of cqn from u32 to u64 to keep
userspace and kernel consistent, initializes resp both for
cq and qp to zeros, and also changes the condition judgment
of outlen considering future caps extension.

Suggested-by: Jason Gunthorpe <jgg@mellanox.com>
Fixes: e088a685eae9 (hns: Support rq record doorbell for the user space)
Fixes: 9b44703d0a21 (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: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Shaobo Xu <xushaobo2@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Move rdma_addr_find_l2_eth_by_grh to core_priv.h

Before commit [1], rdma_addr_find_l2_eth_by_grh() was an exported function
and therefore declaration in include/rdma/ib_addr.h was fine.

But now that its scope is limited to ib_core module, its better to have it
in core_priv.h.

[1] commit 1060f8653414 ("IB/{core/cm}: Fix generating a return AH for
RoCEE")

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/cm: Introduce and use helper function to get cm_port from path

Introduce and use helper function get_cm_port_from_path() to get
cm_port based on the the path record entry.

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Refactor ib_init_ah_attr_from_path() for RoCE

Resolving route for RoCE for a path record is needed only for the
received CM requests.
Therefore,
(a) ib_init_ah_attr_from_path() is refactored first to isolate the
code of resolving route.
(b) Setting dlid, path bits is not needed for RoCE.

Additionally ah attribute initialization is done from the path record
entry, so it is better to refer to path record entry type for
different link layer instead of ah attribute type while initializing
ah attribute itself.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/cm: Add and use a helper function to add cm_id's to the port list

Add and use helper function add_cm_id_to_port_list() to attach
cm_id to port list.

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/ocrdma: Removed GID add/del null routines

add_gid() and del_gid() are optional callback routines.
ib_core ignores invoking them while updating GID table entries if
they are not implemented by provider drivers. Therefore remove them.

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Remove rdma_resolve_ip_route() as exported symbol

rdma_resolve_ip_route() is used only by ib_core module. Therefore it is
removed as an exported symbol.

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/cma: Use rdma_protocol_roce() and remove cma_protocol_roce_dev_port()

rdma_protocol_roce() API from the ib_core already provides a way to
detect whether a given device+port is RoCE or not.
Therefore, make use of it and avoid implementing it again in rdmacm
module.

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Honor port_num while resolving GID for IB link layer

ah_attr contains the port number to which cm_id is bound. However, while
searching for GID table for matching GID entry, the port number is
ignored.

This could cause the wrong GID to be used when the ah_attr is converted to
an AH.

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Honor return status of ib_init_ah_from_mcmember()

The return status of ib_init_ah_from_mcmember() is ignored by
cma_ib_mc_handler().  Honor it and return error event if ah attribute
initialization failed.

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/{core, ipoib}: Simplify ib_find_gid() for unused ndev

ib_find_gid() is only used by IPoIB driver. For IB link layer, GID table
entries are not based on netdevice. Netdevice parameter is unused here.
Therefore, it is removed.

Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

IB/core: Fix comments of GID query functions

Exported symbol's comments should be with function definition and not in
the header file. Therefore comments of ib_find_cached_gid() and
ib_find_cached_gid_by_port() functions are moved closer to their
definitions.

The function name in then comment is different than the actual function
name, fix it to be same as ib_cache_gid_find_by_filter().

Also current comment section of ib_find_cached_gid_by_port() contains the
desciption of ib_find_cached_gid(), fix that as well.

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>

RDMA/mlx5: Simplify clean and destroy MR calls

The failure to destroy the MRs is printed on mlx5_core layer
as error and it makes warning prints useless.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/mlx5: Guard ODP specific assignments with specific CONFIG

"live" is needed for ODP only and is better to be guarded
by appropriate CONFIG.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/mlx5: Unify error flows in rereg MR failure paths

According to the IBTA spec 1.3, the driver failure in
MR reregister shall release old and new MRs.

 C11-20: If the CI returns any other error, the CI shall
 invalidate both "old" and "new" registrations, and release
 any associated resources.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/mlx5: Return proper value for not-supported command

Return -EOPNOTSUPP value to the user for unsupported reg_user_mr.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/mlx5: Protect from NULL pointer derefence

The mlx5_ib_alloc_implicit_mr() can fail to acquire pages
and the returned mr pointer won't be valid. Ensure that it
is not error prior to access.

Cc: <stable@vger.kernel.org> # 4.10
Fixes: 81713d3788d2 ("IB/mlx5: Add implicit MR support")
Reported-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

Merge branch 'k.o/wip/dl-for-rc' into k.o/wip/dl-for-next

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: Doug Ledford <dledford@redhat.com>

infiniband: bnxt_re: use BIT_ULL() for 64-bit bit masks

On 32-bit targets, we otherwise get a warning about an impossible constant
integer expression:

In file included from include/linux/kernel.h:11,
                 from include/linux/interrupt.h:6,
                 from drivers/infiniband/hw/bnxt_re/ib_verbs.c:39:
drivers/infiniband/hw/bnxt_re/ib_verbs.c: In function 'bnxt_re_query_device':
include/linux/bitops.h:7:24: error: left shift count >= width of type [-Werror=shift-count-overflow]
 #define BIT(nr)   (1UL << (nr))
                        ^~
drivers/infiniband/hw/bnxt_re/bnxt_re.h:61:34: note: in expansion of macro 'BIT'
 #define BNXT_RE_MAX_MR_SIZE_HIGH BIT(39)
                                  ^~~
drivers/infiniband/hw/bnxt_re/bnxt_re.h:62:30: note: in expansion of macro 'BNXT_RE_MAX_MR_SIZE_HIGH'
 #define BNXT_RE_MAX_MR_SIZE  BNXT_RE_MAX_MR_SIZE_HIGH
                              ^~~~~~~~~~~~~~~~~~~~~~~~
drivers/infiniband/hw/bnxt_re/ib_verbs.c:149:25: note: in expansion of macro 'BNXT_RE_MAX_MR_SIZE'
  ib_attr->max_mr_size = BNXT_RE_MAX_MR_SIZE;
                         ^~~~~~~~~~~~~~~~~~~

Fixes: 872f3578241d ("RDMA/bnxt_re: Add support for MRs with Huge pages")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

infiniband: qplib_fp: fix pointer cast

Building for a 32-bit target results in a couple of warnings from casting
between a 32-bit pointer and a 64-bit integer:

drivers/infiniband/hw/bnxt_re/qplib_fp.c: In function 'bnxt_qplib_service_nq':
drivers/infiniband/hw/bnxt_re/qplib_fp.c:333:23: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
    bnxt_qplib_arm_srq((struct bnxt_qplib_srq *)q_handle,
                       ^
drivers/infiniband/hw/bnxt_re/qplib_fp.c:336:12: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
            (struct bnxt_qplib_srq *)q_handle,
            ^
In file included from include/linux/byteorder/little_endian.h:5,
                 from arch/arm/include/uapi/asm/byteorder.h:22,
                 from include/asm-generic/bitops/le.h:6,
                 from arch/arm/include/asm/bitops.h:342,
                 from include/linux/bitops.h:38,
                 from include/linux/kernel.h:11,
                 from include/linux/interrupt.h:6,
                 from drivers/infiniband/hw/bnxt_re/qplib_fp.c:39:
drivers/infiniband/hw/bnxt_re/qplib_fp.c: In function 'bnxt_qplib_create_srq':
include/uapi/linux/byteorder/little_endian.h:31:43: error: cast from pointer to integer of different size [-Werror=pointer-to-int-cast]
 #define __cpu_to_le64(x) ((__force __le64)(__u64)(x))
                                           ^
include/linux/byteorder/generic.h:86:21: note: in expansion of macro '__cpu_to_le64'
 #define cpu_to_le64 __cpu_to_le64
                     ^~~~~~~~~~~~~
drivers/infiniband/hw/bnxt_re/qplib_fp.c:569:19: note: in expansion of macro 'cpu_to_le64'
  req.srq_handle = cpu_to_le64(srq);

Using a uintptr_t as an intermediate works on all architectures.

Fixes: 37cb11acf1f7 ("RDMA/bnxt_re: Add SRQ support for Broadcom adapters")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/ulp/srpt/ib_srpt.c: fix build with gcc-4.4.4

gcc-4.4.4 has issues with initialization of anonymous unions:

drivers/infiniband/ulp/srpt/ib_srpt.c: In function 'srpt_zerolength_write':
drivers/infiniband/ulp/srpt/ib_srpt.c:854: error: unknown field 'wr_cqe' specified in initializer
drivers/infiniband/ulp/srpt/ib_srpt.c:854: warning: initialization makes integer from pointer without a cast

Work aound this.

Fixes: 2a78cb4db487 ("IB/srpt: Fix an out-of-bounds stack access in srpt_zerolength_write()")
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/core/verbs.c: fix build with gcc-4.4.4

gcc-4.4.4 has issues with initialization of anonymous unions.

drivers/infiniband/core/verbs.c: In function '__ib_drain_sq':
drivers/infiniband/core/verbs.c:2204: error: unknown field 'wr_cqe' specified in initializer
drivers/infiniband/core/verbs.c:2204: warning: initialization makes integer from pointer without a cast

Work around this.

Fixes: a1ae7d0345edd5 ("RDMA/core: Avoid that ib_drain_qp() triggers an out-of-bounds stack access")
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/mlx5: Fix cleanup order on unload

On load we create private CQ/QP/PD in order to be used by UMR, we create
those resources after we register ourself as an IB device, and we destroy
them after we unregister as an IB device. This was changed by commit
16c1975f1032 ("IB/mlx5: Create profile infrastructure to add and remove
stages") which moved the destruction before we unregistration. This
allowed to trigger an invalid memory access when unloading mlx5_ib while
there are open resources:

BUG: unable to handle kernel paging request at 00000001002c012c
...
Call Trace:
 mlx5_ib_post_send_wait+0x75/0x110 [mlx5_ib]
 __slab_free+0x9a/0x2d0
 delay_time_func+0x10/0x10 [mlx5_ib]
 unreg_umr.isra.15+0x4b/0x50 [mlx5_ib]
 mlx5_mr_cache_free+0x46/0x150 [mlx5_ib]
 clean_mr+0xc9/0x190 [mlx5_ib]
 dereg_mr+0xba/0xf0 [mlx5_ib]
 ib_dereg_mr+0x13/0x20 [ib_core]
 remove_commit_idr_uobject+0x16/0x70 [ib_uverbs]
 uverbs_cleanup_ucontext+0xe8/0x1a0 [ib_uverbs]
 ib_uverbs_cleanup_ucontext.isra.9+0x19/0x40 [ib_uverbs]
 ib_uverbs_remove_one+0x162/0x2e0 [ib_uverbs]
 ib_unregister_device+0xd4/0x190 [ib_core]
 __mlx5_ib_remove+0x2e/0x40 [mlx5_ib]
 mlx5_remove_device+0xf5/0x120 [mlx5_core]
 mlx5_unregister_interface+0x37/0x90 [mlx5_core]
 mlx5_ib_cleanup+0xc/0x225 [mlx5_ib]
 SyS_delete_module+0x153/0x230
 do_syscall_64+0x62/0x110
 entry_SYSCALL_64_after_hwframe+0x21/0x86
...

We restore the original behavior by breaking the UMR stage into two parts,
pre and post IB registration stages, this way we can restore the original
functionality and maintain clean separation of logic between stages.

Fixes: 16c1975f1032 ("IB/mlx5: Create profile infrastructure to add and remove stages")
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

rdma_rxe: make rxe work over 802.1q VLAN devices

This patch fixes RDMA/rxe over 802.1q VLAN devices.

Without it, I observed the following behavior:

a) adding a VLAN device to RXE via rxe_net_add() creates a non-functional
   RDMA device. This is caused by the logic in enum_all_gids_of_dev_cb() /
   is_eth_port_of_netdev(), which only considers networks connected to
   "upper devices" of the configured network device, resulting in an empty
   set of gids for a VLAN interface that is an "upper device" itself.
   Later attempts to connect via this rdma device fail in cma_acuire_dev()
   because no gids can be resolved.

b) adding the master device of the VLAN device instead seems to work
   initially, target addresses via VLAN devices are resolved successfully.
   But the connection times out because no 802.1q VLAN headers are
   inserted in the ethernet packets, which are therefore never received.
   This happens because the RXE layer sends the packets via the master
   device rather than the VLAN device.

The problem could be solved by changing either a) or b). My thinking was
that the logic in a) was created deliberately, thus I decided to work on
b). It turns out that the information about the VLAN interface for the gid
at hand is available in the AV information. My patch converts the RXE code
to use this netdev instead of rxe->ndev. With this change, RXE over vlan
works on my test system.

Signed-off-by: Martin Wilck <mwilck@suse.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/ucma: Don't allow join attempts for unsupported AF family

Users can provide garbage while calling to ucma_join_ip_multicast(),
it will indirectly cause to rdma_addr_size() return 0, making the
call to ucma_process_join(), which had the right checks, but it is
better to check the input as early as possible.

The following crash from syzkaller revealed it.

kernel BUG at lib/string.c:1052!
invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 4113 Comm: syz-executor0 Not tainted 4.16.0-rc5+ #261
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:fortify_panic+0x13/0x20 lib/string.c:1051
RSP: 0018:ffff8801ca81f8f0 EFLAGS: 00010286
RAX: 0000000000000022 RBX: 1ffff10039503f23 RCX: 0000000000000000
RDX: 0000000000000022 RSI: 1ffff10039503ed3 RDI: ffffed0039503f12
RBP: ffff8801ca81f8f0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000006 R11: 0000000000000000 R12: ffff8801ca81f998
R13: ffff8801ca81f938 R14: ffff8801ca81fa58 R15: 000000000000fa00
FS:  0000000000000000(0000) GS:ffff8801db200000(0063) knlGS:000000000a12a900
CS:  0010 DS: 002b ES: 002b CR0: 0000000080050033
CR2: 0000000008138024 CR3: 00000001cbb58004 CR4: 00000000001606f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 memcpy include/linux/string.h:344 [inline]
 ucma_join_ip_multicast+0x36b/0x3b0 drivers/infiniband/core/ucma.c:1421
 ucma_write+0x2d6/0x3d0 drivers/infiniband/core/ucma.c:1633
 __vfs_write+0xef/0x970 fs/read_write.c:480
 vfs_write+0x189/0x510 fs/read_write.c:544
 SYSC_write fs/read_write.c:589 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:581
 do_syscall_32_irqs_on arch/x86/entry/common.c:330 [inline]
 do_fast_syscall_32+0x3ec/0xf9f arch/x86/entry/common.c:392
 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f9ec99
RSP: 002b:00000000ff8172cc EFLAGS: 00000282 ORIG_RAX: 0000000000000004
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000020000100
RDX: 0000000000000063 RSI: 0000000000000000 RDI: 0000000000000000
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
Code: 08 5b 41 5c 41 5d 41 5e 41 5f 5d c3 0f 0b 48 89 df e8 42 2c e3 fb eb de
55 48 89 fe 48 c7 c7 80 75 98 86 48 89 e5 e8 85 95 94 fb <0f> 0b 90 90 90 90
90 90 90 90 90 90 90 55 48 89 e5 41 57 41 56
RIP: fortify_panic+0x13/0x20 lib/string.c:1051 RSP: ffff8801ca81f8f0

Fixes: 5bc2b7b397b0 ("RDMA/ucma: Allow user space to specify AF_IB when joining multicast")
Reported-by: <syzbot+2287ac532caa81900a4e@syzkaller.appspotmail.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/ucma: Fix access to non-initialized CM_ID object

The attempt to join multicast group without ensuring that CMA device
exists will lead to the following crash reported by syzkaller.

[   64.076794] BUG: KASAN: null-ptr-deref in rdma_join_multicast+0x26e/0x12c0
[   64.076797] Read of size 8 at addr 00000000000000b0 by task join/691
[   64.076797]
[   64.076800] CPU: 1 PID: 691 Comm: join Not tainted 4.16.0-rc1-00219-gb97853b65b93 #23
[   64.076802] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-proj4
[   64.076803] Call Trace:
[   64.076809]  dump_stack+0x5c/0x77
[   64.076817]  kasan_report+0x163/0x380
[   64.085859]  ? rdma_join_multicast+0x26e/0x12c0
[   64.086634]  rdma_join_multicast+0x26e/0x12c0
[   64.087370]  ? rdma_disconnect+0xf0/0xf0
[   64.088579]  ? __radix_tree_replace+0xc3/0x110
[   64.089132]  ? node_tag_clear+0x81/0xb0
[   64.089606]  ? idr_alloc_u32+0x12e/0x1a0
[   64.090517]  ? __fprop_inc_percpu_max+0x150/0x150
[   64.091768]  ? tracing_record_taskinfo+0x10/0xc0
[   64.092340]  ? idr_alloc+0x76/0xc0
[   64.092951]  ? idr_alloc_u32+0x1a0/0x1a0
[   64.093632]  ? ucma_process_join+0x23d/0x460
[   64.094510]  ucma_process_join+0x23d/0x460
[   64.095199]  ? ucma_migrate_id+0x440/0x440
[   64.095696]  ? futex_wake+0x10b/0x2a0
[   64.096159]  ucma_join_multicast+0x88/0xe0
[   64.096660]  ? ucma_process_join+0x460/0x460
[   64.097540]  ? _copy_from_user+0x5e/0x90
[   64.098017]  ucma_write+0x174/0x1f0
[   64.098640]  ? ucma_resolve_route+0xf0/0xf0
[   64.099343]  ? rb_erase_cached+0x6c7/0x7f0
[   64.099839]  __vfs_write+0xc4/0x350
[   64.100622]  ? perf_syscall_enter+0xe4/0x5f0
[   64.101335]  ? kernel_read+0xa0/0xa0
[   64.103525]  ? perf_sched_cb_inc+0xc0/0xc0
[   64.105510]  ? syscall_exit_register+0x2a0/0x2a0
[   64.107359]  ? __switch_to+0x351/0x640
[   64.109285]  ? fsnotify+0x899/0x8f0
[   64.111610]  ? fsnotify_unmount_inodes+0x170/0x170
[   64.113876]  ? __fsnotify_update_child_dentry_flags+0x30/0x30
[   64.115813]  ? ring_buffer_record_is_on+0xd/0x20
[   64.117824]  ? __fget+0xa8/0xf0
[   64.119869]  vfs_write+0xf7/0x280
[   64.122001]  SyS_write+0xa1/0x120
[   64.124213]  ? SyS_read+0x120/0x120
[   64.126644]  ? SyS_read+0x120/0x120
[   64.128563]  do_syscall_64+0xeb/0x250
[   64.130732]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[   64.132984] RIP: 0033:0x7f5c994ade99
[   64.135699] RSP: 002b:00007f5c99b97d98 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[   64.138740] RAX: ffffffffffffffda RBX: 00000000200001e4 RCX: 00007f5c994ade99
[   64.141056] RDX: 00000000000000a0 RSI: 00000000200001c0 RDI: 0000000000000015
[   64.143536] RBP: 00007f5c99b97ec0 R08: 0000000000000000 R09: 0000000000000000
[   64.146017] R10: 0000000000000000 R11: 0000000000000246 R12: 00007f5c99b97fc0
[   64.148608] R13: 0000000000000000 R14: 00007fff660e1c40 R15: 00007f5c99b989c0
[   64.151060]
[   64.153703] Disabling lock debugging due to kernel taint
[   64.156032] BUG: unable to handle kernel NULL pointer dereference at 00000000000000b0
[   64.159066] IP: rdma_join_multicast+0x26e/0x12c0
[   64.161451] PGD 80000001d0298067 P4D 80000001d0298067 PUD 1dea39067 PMD 0
[   64.164442] Oops: 0000 [#1] SMP KASAN PTI
[   64.166817] CPU: 1 PID: 691 Comm: join Tainted: G    B 4.16.0-rc1-00219-gb97853b65b93 #23
[   64.170004] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-proj4
[   64.174985] RIP: 0010:rdma_join_multicast+0x26e/0x12c0
[   64.177246] RSP: 0018:ffff8801c8207860 EFLAGS: 00010282
[   64.179901] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff94789522
[   64.183344] RDX: 1ffffffff2d50fa5 RSI: 0000000000000297 RDI: 0000000000000297
[   64.186237] RBP: ffff8801c8207a50 R08: 0000000000000000 R09: ffffed0039040ea7
[   64.189328] R10: 0000000000000001 R11: ffffed0039040ea6 R12: 0000000000000000
[   64.192634] R13: 0000000000000000 R14: ffff8801e2022800 R15: ffff8801d4ac2400
[   64.196105] FS:  00007f5c99b98700(0000) GS:ffff8801e5d00000(0000) knlGS:0000000000000000
[   64.199211] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   64.202046] CR2: 00000000000000b0 CR3: 00000001d1c48004 CR4: 00000000003606a0
[   64.205032] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   64.208221] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   64.211554] Call Trace:
[   64.213464]  ? rdma_disconnect+0xf0/0xf0
[   64.216124]  ? __radix_tree_replace+0xc3/0x110
[   64.219337]  ? node_tag_clear+0x81/0xb0
[   64.222140]  ? idr_alloc_u32+0x12e/0x1a0
[   64.224422]  ? __fprop_inc_percpu_max+0x150/0x150
[   64.226588]  ? tracing_record_taskinfo+0x10/0xc0
[   64.229763]  ? idr_alloc+0x76/0xc0
[   64.232186]  ? idr_alloc_u32+0x1a0/0x1a0
[   64.234505]  ? ucma_process_join+0x23d/0x460
[   64.237024]  ucma_process_join+0x23d/0x460
[   64.240076]  ? ucma_migrate_id+0x440/0x440
[   64.243284]  ? futex_wake+0x10b/0x2a0
[   64.245302]  ucma_join_multicast+0x88/0xe0
[   64.247783]  ? ucma_process_join+0x460/0x460
[   64.250841]  ? _copy_from_user+0x5e/0x90
[   64.253878]  ucma_write+0x174/0x1f0
[   64.257008]  ? ucma_resolve_route+0xf0/0xf0
[   64.259877]  ? rb_erase_cached+0x6c7/0x7f0
[   64.262746]  __vfs_write+0xc4/0x350
[   64.265537]  ? perf_syscall_enter+0xe4/0x5f0
[   64.267792]  ? kernel_read+0xa0/0xa0
[   64.270358]  ? perf_sched_cb_inc+0xc0/0xc0
[   64.272575]  ? syscall_exit_register+0x2a0/0x2a0
[   64.275367]  ? __switch_to+0x351/0x640
[   64.277700]  ? fsnotify+0x899/0x8f0
[   64.280530]  ? fsnotify_unmount_inodes+0x170/0x170
[   64.283156]  ? __fsnotify_update_child_dentry_flags+0x30/0x30
[   64.286182]  ? ring_buffer_record_is_on+0xd/0x20
[   64.288749]  ? __fget+0xa8/0xf0
[   64.291136]  vfs_write+0xf7/0x280
[   64.292972]  SyS_write+0xa1/0x120
[   64.294965]  ? SyS_read+0x120/0x120
[   64.297474]  ? SyS_read+0x120/0x120
[   64.299751]  do_syscall_64+0xeb/0x250
[   64.301826]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[   64.304352] RIP: 0033:0x7f5c994ade99
[   64.306711] RSP: 002b:00007f5c99b97d98 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[   64.309577] RAX: ffffffffffffffda RBX: 00000000200001e4 RCX: 00007f5c994ade99
[   64.312334] RDX: 00000000000000a0 RSI: 00000000200001c0 RDI: 0000000000000015
[   64.315783] RBP: 00007f5c99b97ec0 R08: 0000000000000000 R09: 0000000000000000
[   64.318365] R10: 0000000000000000 R11: 0000000000000246 R12: 00007f5c99b97fc0
[   64.320980] R13: 0000000000000000 R14: 00007fff660e1c40 R15: 00007f5c99b989c0
[   64.323515] Code: e8 e8 79 08 ff 4c 89 ff 45 0f b6 a7 b8 01 00 00 e8 68 7c 08 ff 49 8b 1f 4d 89 e5 49 c1 e4 04 48 8
[   64.330753] RIP: rdma_join_multicast+0x26e/0x12c0 RSP: ffff8801c8207860
[   64.332979] CR2: 00000000000000b0
[   64.335550] ---[ end trace 0c00c17a408849c1 ]---

Reported-by: <syzbot+e6aba77967bd72cbc9d6@syzkaller.appspotmail.com>
Fixes: c8f6a362bf3e ("RDMA/cma: Add multicast communication support")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/i40iw: include linux/irq.h

We get a build failure on ARM unless the header is included explicitly:

drivers/infiniband/hw/i40iw/i40iw_verbs.c: In function 'i40iw_get_vector_affinity':
drivers/infiniband/hw/i40iw/i40iw_verbs.c:2747:9: error: implicit declaration of function 'irq_get_affinity_mask'; did you mean 'irq_create_affinity_masks'? [-Werror=implicit-function-declaration]
  return irq_get_affinity_mask(msix_vec->irq);
         ^~~~~~~~~~~~~~~~~~~~~
         irq_create_affinity_masks
drivers/infiniband/hw/i40iw/i40iw_verbs.c:2747:9: error: returning 'int' from a function with return type 'const struct cpumask *' makes pointer from integer without a cast [-Werror=int-conversion]
  return irq_get_affinity_mask(msix_vec->irq);

Fixes: 7e952b19eb63 ("i40iw: Implement get_vector_affinity API")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/mlx5: Maintain a single emergency page

The mlx5 driver needs to be able to issue invalidation to ODP MRs
even if it cannot allocate memory. To this end it preallocates
emergency pages to use when the situation arises.

This flow should be extremely rare enough, that we don't need
to worry about contention and therefore a single emergency page
is good enough.

Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/mlx5: Only synchronize RCU once when removing mkeys

Instead synchronizing RCU in a loop when removing mkeys in a batch do it
once at the end before freeing them. The result is only waiting for one
RCU grace period instead of many serially.

Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/mlx5: Expose more priorities for bypass namespace

BYPASS namespace is used by the RDMA side to insert flow rules into
the vport RX flow tables. Currently only 8 priorities are exposed,
increase this to 16 to allow more flexibility. This change will also
cause the BYPASS namespace to use 32 levels (as apposed to 16 today) of
flow tables, 16 levels for regular rules and 16 for don't trap rules.

Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/core: Do not use invalid destination in determining port reuse

cma_port_is_unique() allows local port reuse if the quad (source
address and port, destination address and port) for this connection
is unique. However, if the destination info is zero or unspecified, it
can't make a correct decision but still allows port reuse. For example,
sometimes rdma_bind_addr() is called with unspecified destination and
reusing the port can lead to creating a connection with a duplicate quad,
after the destination is resolved. The issue manifests when MPI scale-up
tests hang after the duplicate quad is used.

Set the destination address family and add checks for zero destination
address and port to prevent source port reuse based on invalid destination.

Fixes: 19b752a19dce ("IB/cma: Allow port reuse for rdma_id")
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srp: Fix IPv6 address parsing

Split IPv6 addresses at the colon that separates the IPv6 address
and the port number instead of at a colon in the middle of the IPv6
address. Check whether the IPv6 address is surrounded with square
brackets.

Fixes: 19f313438c77 ("IB/srp: Add RDMA/CM support")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/mlx5: Fix crash while accessing garbage pointer and freed memory

The failure in rereg_mr flow caused to set garbage value (error value)
into mr->umem pointer. This pointer is accessed at the release stage
and it causes to the following crash.

There is not enough to simply change umem to point to NULL, because the
MR struct is needed to be accessed during MR deregistration phase, so
delay kfree too.

[    6.237617] BUG: unable to handle kernel NULL pointer dereference a 0000000000000228
[    6.238756] IP: ib_dereg_mr+0xd/0x30
[    6.239264] PGD 80000000167eb067 P4D 80000000167eb067 PUD 167f9067 PMD 0
[    6.240320] Oops: 0000 [#1] SMP PTI
[    6.240782] CPU: 0 PID: 367 Comm: dereg Not tainted 4.16.0-rc1-00029-gc198fafe0453 #183
[    6.242120] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[    6.244504] RIP: 0010:ib_dereg_mr+0xd/0x30
[    6.245253] RSP: 0018:ffffaf5d001d7d68 EFLAGS: 00010246
[    6.246100] RAX: 0000000000000000 RBX: ffff95d4172daf00 RCX: 0000000000000000
[    6.247414] RDX: 00000000ffffffff RSI: 0000000000000001 RDI: ffff95d41a317600
[    6.248591] RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000
[    6.249810] R10: ffff95d417033c10 R11: 0000000000000000 R12: ffff95d4172c3a80
[    6.251121] R13: ffff95d4172c3720 R14: ffff95d4172c3a98 R15: 00000000ffffffff
[    6.252437] FS:  0000000000000000(0000) GS:ffff95d41fc00000(0000) knlGS:0000000000000000
[    6.253887] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    6.254814] CR2: 0000000000000228 CR3: 00000000172b4000 CR4: 00000000000006b0
[    6.255943] Call Trace:
[    6.256368]  remove_commit_idr_uobject+0x1b/0x80
[    6.257118]  uverbs_cleanup_ucontext+0xe4/0x190
[    6.257855]  ib_uverbs_cleanup_ucontext.constprop.14+0x19/0x40
[    6.258857]  ib_uverbs_close+0x2a/0x100
[    6.259494]  __fput+0xca/0x1c0
[    6.259938]  task_work_run+0x84/0xa0
[    6.260519]  do_exit+0x312/0xb40
[    6.261023]  ? __do_page_fault+0x24d/0x490
[    6.261707]  do_group_exit+0x3a/0xa0
[    6.262267]  SyS_exit_group+0x10/0x10
[    6.262802]  do_syscall_64+0x75/0x180
[    6.263391]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[    6.264253] RIP: 0033:0x7f1b39c49488
[    6.264827] RSP: 002b:00007ffe2de05b68 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
[    6.266049] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1b39c49488
[    6.267187] RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000
[    6.268377] RBP: 00007f1b39f258e0 R08: 00000000000000e7 R09: ffffffffffffff98
[    6.269640] R10: 00007f1b3a147260 R11: 0000000000000246 R12: 00007f1b39f258e0
[    6.270783] R13: 00007f1b39f2ac20 R14: 0000000000000000 R15: 0000000000000000
[    6.271943] Code: 74 07 31 d2 e9 25 d8 6c 00 b8 da ff ff ff c3 0f 1f
44 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8b 07 53 48 8b
5f 08 <48> 8b 80 28 02 00 00 e8 f7 d7 6c 00 85 c0 75 04 3e ff 4b 18 5b
[    6.274927] RIP: ib_dereg_mr+0xd/0x30 RSP: ffffaf5d001d7d68
[    6.275760] CR2: 0000000000000228
[    6.276200] ---[ end trace a35641f1c474bd20 ]---

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Cc: syzkaller <syzkaller@googlegroups.com>
Cc: <stable@vger.kernel.org>
Reported-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/verbs: Simplify modify QP check

All callers to ib_modify_qp_is_ok() provides enum ib_qp_state
makes the checks of out-of-scope redundant. Let's remove them
together with updating function signature to return boolean result.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/pvrdma: Properly annotate QP states

QP states provided by core layer are converted to enum ib_qp_state
and better to use internal variable in that type instead of int.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/uverbs: Ensure validity of current QP state value

The QP state is internal enum which is checked at the driver
level by calling to ib_modify_qp_is_ok(). Move this check closer
to user and leave kernel users to be checked by compiler.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/mlx5: Fix NULL dereference while accessing XRC_TGT QPs

mlx5 modify_qp() relies on FW that the error will be thrown if wrong
state is supplied. The missing check in FW causes the following crash
while using XRC_TGT QPs.

[   14.769632] BUG: unable to handle kernel NULL pointer dereference at (null)
[   14.771085] IP: mlx5_ib_modify_qp+0xf60/0x13f0
[   14.771894] PGD 800000001472e067 P4D 800000001472e067 PUD 14529067 PMD 0
[   14.773126] Oops: 0002 [#1] SMP PTI
[   14.773763] CPU: 0 PID: 365 Comm: ubsan Not tainted 4.16.0-rc1-00038-g8151138c0793 #119
[   14.775192] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[   14.777522] RIP: 0010:mlx5_ib_modify_qp+0xf60/0x13f0
[   14.778417] RSP: 0018:ffffbf48001c7bd8 EFLAGS: 00010246
[   14.779346] RAX: 0000000000000000 RBX: ffff9a8f9447d400 RCX: 0000000000000000
[   14.780643] RDX: 0000000000000000 RSI: 000000000000000a RDI: 0000000000000000
[   14.781930] RBP: 0000000000000000 R08: 00000000000217b0 R09: ffffffffbc9c1504
[   14.783214] R10: fffff4a180519480 R11: ffff9a8f94523600 R12: ffff9a8f9493e240
[   14.784507] R13: ffff9a8f9447d738 R14: 000000000000050a R15: 0000000000000000
[   14.785800] FS:  00007f545b466700(0000) GS:ffff9a8f9fc00000(0000) knlGS:0000000000000000
[   14.787073] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   14.787792] CR2: 0000000000000000 CR3: 00000000144be000 CR4: 00000000000006b0
[   14.788689] Call Trace:
[   14.789007]  _ib_modify_qp+0x71/0x120
[   14.789475]  modify_qp.isra.20+0x207/0x2f0
[   14.790010]  ib_uverbs_modify_qp+0x90/0xe0
[   14.790532]  ib_uverbs_write+0x1d2/0x3c0
[   14.791049]  ? __handle_mm_fault+0x93c/0xe40
[   14.791644]  __vfs_write+0x36/0x180
[   14.792096]  ? handle_mm_fault+0xc1/0x210
[   14.792601]  vfs_write+0xad/0x1e0
[   14.793018]  SyS_write+0x52/0xc0
[   14.793422]  do_syscall_64+0x75/0x180
[   14.793888]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[   14.794527] RIP: 0033:0x7f545ad76099
[   14.794975] RSP: 002b:00007ffd78787468 EFLAGS: 00000287 ORIG_RAX: 0000000000000001
[   14.795958] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f545ad76099
[   14.797075] RDX: 0000000000000078 RSI: 0000000020009000 RDI: 0000000000000003
[   14.798140] RBP: 00007ffd78787470 R08: 00007ffd78787480 R09: 00007ffd78787480
[   14.799207] R10: 00007ffd78787480 R11: 0000000000000287 R12: 00005599ada98760
[   14.800277] R13: 00007ffd78787560 R14: 0000000000000000 R15: 0000000000000000
[   14.801341] Code: 4c 8b 1c 24 48 8b 83 70 02 00 00 48 c7 83 cc 02 00
00 00 00 00 00 48 c7 83 24 03 00 00 00 00 00 00 c7 83 2c 03 00 00 00 00
00 00 <c7> 00 00 00 00 00 48 8b 83 70 02 00 00 c7 40 04 00 00 00 00 4c
[   14.804012] RIP: mlx5_ib_modify_qp+0xf60/0x13f0 RSP: ffffbf48001c7bd8
[   14.804838] CR2: 0000000000000000
[   14.805288] ---[ end trace 3f1da0df5c8b7c37 ]---

Cc: syzkaller <syzkaller@googlegroups.com>
Reported-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB: remove duplicate header files

In hfi.h, the header file opa_addr.h is included twice.
In vt.h, the header file mmap.h is included twice.

Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/hns: Support cq record doorbell for kernel space

This patch updates to support cq record doorbell for
the kernel space.

Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Shaobo Xu <xushaobo2@huawei.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/hns: Support rq record doorbell for kernel space

This patch updates to support rq record doorbell for
the kernel space.

Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Shaobo Xu <xushaobo2@huawei.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/hns: Support cq record doorbell for the user space

This patch updates to 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: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Shaobo Xu <xushaobo2@huawei.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/hns: Support rq record doorbell for the user space

This patch adds interfaces and definitions to support the rq 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: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Shaobo Xu <xushaobo2@huawei.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/mlx5: Fix integer overflows in mlx5_ib_create_srq

This patch validates user provided input to prevent integer overflow due
to integer manipulation in the mlx5_ib_create_srq function.

Cc: syzkaller <syzkaller@googlegroups.com>
Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/mlx5: Fix out-of-bounds read in create_raw_packet_qp_rq

Add a check for the length of the qpin structure to prevent out-of-bounds reads

BUG: KASAN: slab-out-of-bounds in create_raw_packet_qp+0x114c/0x15e2
Read of size 8192 at addr ffff880066b99290 by task syz-executor3/549

CPU: 3 PID: 549 Comm: syz-executor3 Not tainted 4.15.0-rc2+ #27 Hardware
name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
Call Trace:
 dump_stack+0x8d/0xd4
 print_address_description+0x73/0x290
 kasan_report+0x25c/0x370
 ? create_raw_packet_qp+0x114c/0x15e2
 memcpy+0x1f/0x50
 create_raw_packet_qp+0x114c/0x15e2
 ? create_raw_packet_qp_tis.isra.28+0x13d/0x13d
 ? lock_acquire+0x370/0x370
 create_qp_common+0x2245/0x3b50
 ? destroy_qp_user.isra.47+0x100/0x100
 ? kasan_kmalloc+0x13d/0x170
 ? sched_clock_cpu+0x18/0x180
 ? fs_reclaim_acquire.part.15+0x5/0x30
 ? __lock_acquire+0xa11/0x1da0
 ? sched_clock_cpu+0x18/0x180
 ? kmem_cache_alloc_trace+0x17e/0x310
 ? mlx5_ib_create_qp+0x30e/0x17b0
 mlx5_ib_create_qp+0x33d/0x17b0
 ? sched_clock_cpu+0x18/0x180
 ? create_qp_common+0x3b50/0x3b50
 ? lock_acquire+0x370/0x370
 ? __radix_tree_lookup+0x180/0x220
 ? uverbs_try_lock_object+0x68/0xc0
 ? rdma_lookup_get_uobject+0x114/0x240
 create_qp.isra.5+0xce4/0x1e20
 ? ib_uverbs_ex_create_cq_cb+0xa0/0xa0
 ? copy_ah_attr_from_uverbs.isra.2+0xa00/0xa00
 ? ib_uverbs_cq_event_handler+0x160/0x160
 ? __might_fault+0x17c/0x1c0
 ib_uverbs_create_qp+0x21b/0x2a0
 ? ib_uverbs_destroy_cq+0x2e0/0x2e0
 ib_uverbs_write+0x55a/0xad0
 ? ib_uverbs_destroy_cq+0x2e0/0x2e0
 ? ib_uverbs_destroy_cq+0x2e0/0x2e0
 ? ib_uverbs_open+0x760/0x760
 ? futex_wake+0x147/0x410
 ? check_prev_add+0x1680/0x1680
 ? do_futex+0x3d3/0xa60
 ? sched_clock_cpu+0x18/0x180
 __vfs_write+0xf7/0x5c0
 ? ib_uverbs_open+0x760/0x760
 ? kernel_read+0x110/0x110
 ? lock_acquire+0x370/0x370
 ? __fget+0x264/0x3b0
 vfs_write+0x18a/0x460
 SyS_write+0xc7/0x1a0
 ? SyS_read+0x1a0/0x1a0
 ? trace_hardirqs_on_thunk+0x1a/0x1c
 entry_SYSCALL_64_fastpath+0x18/0x85
RIP: 0033:0x4477b9
RSP: 002b:00007f1822cadc18 EFLAGS: 00000292 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 00000000004477b9
RDX: 0000000000000070 RSI: 000000002000a000 RDI: 0000000000000005
RBP: 0000000000708000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000292 R12: 00000000ffffffff
R13: 0000000000005d70 R14: 00000000006e6e30 R15: 0000000020010ff0

Allocated by task 549:
 __kmalloc+0x15e/0x340
 kvmalloc_node+0xa1/0xd0
 create_user_qp.isra.46+0xd42/0x1610
 create_qp_common+0x2e63/0x3b50
 mlx5_ib_create_qp+0x33d/0x17b0
 create_qp.isra.5+0xce4/0x1e20
 ib_uverbs_create_qp+0x21b/0x2a0
 ib_uverbs_write+0x55a/0xad0
 __vfs_write+0xf7/0x5c0
 vfs_write+0x18a/0x460
 SyS_write+0xc7/0x1a0
 entry_SYSCALL_64_fastpath+0x18/0x85

Freed by task 368:
 kfree+0xeb/0x2f0
 kernfs_fop_release+0x140/0x180
 __fput+0x266/0x700
 task_work_run+0x104/0x180
 exit_to_usermode_loop+0xf7/0x110
 syscall_return_slowpath+0x298/0x370
 entry_SYSCALL_64_fastpath+0x83/0x85

The buggy address belongs to the object at ffff880066b99180  which
belongs to the cache kmalloc-512 of size 512 The buggy address is
located 272 bytes inside of  512-byte region [ffff880066b99180,
ffff880066b99380) The buggy address belongs to the page:
page:000000006040eedd count:1 mapcount:0 mapping:          (null)
index:0x0 compound_mapcount: 0
flags: 0x4000000000008100(slab|head)
raw: 4000000000008100 0000000000000000 0000000000000000 0000000180190019
raw: ffffea00019a7500 0000000b0000000b ffff88006c403080 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff880066b99180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff880066b99200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>ffff880066b99280: 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc
                         ^
 ffff880066b99300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff880066b99380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

Cc: syzkaller <syzkaller@googlegroups.com>
Fixes: 0fb2ed66a14c ("IB/mlx5: Add create and destroy functionality for Raw Packet QP")
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/bnxt_re: Remove an unused variable

This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Selvin Xavier <selvin.xavier@broadcom.com>
Cc: Devesh Sharma <devesh.sharma@broadcom.com>
Cc: Somnath Kotur <somnath.kotur@broadcom.com>
Cc: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/hfi1: Fix a kernel-doc warning

Avoid that building with W=1 causes the following warning to appear:

drivers/infiniband/hw/hfi1/qp.c:484: warning: Cannot understand * on line 484 - I thought it was a doc line

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

Merge tag 'mlx5-updates-2018-02-28-2' of git://git./linux/kernel/git/mellanox/linux into k.o/wip/dl-for-next

mlx5-updates-2018-02-28-2 (IPSec-2)

This series follows our previous one to lay out the foundations for IPSec
in user-space and extend current kernel netdev IPSec support. As noted in
our previous pull request cover letter "mlx5-updates-2018-02-28-1 (IPSec-1)",
the IPSec mechanism will be supported through our flow steering mechanism.
Therefore, we need to change the initialization order. Furthermore, IPsec
is also supported in both egress and ingress. Since our current flow
steering is egress only, we add an empty (only implemented through FPGA
steering ops) egress namespace to handle that case. We also implement
the required flow steering callbacks and logic in our FPGA driver.

We extend the FPGA support for ESN and modifying a xfrm too. Therefore, we
add support for some new FPGA command interface that supports them. The
other required bits are added too. The new features and requirements are
advertised via cap bits.

Last but not least, we revise our driver's accel_esp API. This API will be
shared between our netdev and IB driver, so we need to have all the required
functionality from both worlds.

Regards,
Aviad and Matan

Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/mlx5: Fix integer overflow while resizing CQ

The user can provide very large cqe_size which will cause to integer
overflow as it can be seen in the following UBSAN warning:

=======================================================================
UBSAN: Undefined behaviour in drivers/infiniband/hw/mlx5/cq.c:1192:53
signed integer overflow:
64870 * 65536 cannot be represented in type 'int'
CPU: 0 PID: 267 Comm: syzkaller605279 Not tainted 4.15.0+ #90 Hardware
name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
Call Trace:
 dump_stack+0xde/0x164
 ? dma_virt_map_sg+0x22c/0x22c
 ubsan_epilogue+0xe/0x81
 handle_overflow+0x1f3/0x251
 ? __ubsan_handle_negate_overflow+0x19b/0x19b
 ? lock_acquire+0x440/0x440
 mlx5_ib_resize_cq+0x17e7/0x1e40
 ? cyc2ns_read_end+0x10/0x10
 ? native_read_msr_safe+0x6c/0x9b
 ? cyc2ns_read_end+0x10/0x10
 ? mlx5_ib_modify_cq+0x220/0x220
 ? sched_clock_cpu+0x18/0x200
 ? lookup_get_idr_uobject+0x200/0x200
 ? rdma_lookup_get_uobject+0x145/0x2f0
 ib_uverbs_resize_cq+0x207/0x3e0
 ? ib_uverbs_ex_create_cq+0x250/0x250
 ib_uverbs_write+0x7f9/0xef0
 ? cyc2ns_read_end+0x10/0x10
 ? print_irqtrace_events+0x280/0x280
 ? ib_uverbs_ex_create_cq+0x250/0x250
 ? uverbs_devnode+0x110/0x110
 ? sched_clock_cpu+0x18/0x200
 ? do_raw_spin_trylock+0x100/0x100
 ? __lru_cache_add+0x16e/0x290
 __vfs_write+0x10d/0x700
 ? uverbs_devnode+0x110/0x110
 ? kernel_read+0x170/0x170
 ? sched_clock_cpu+0x18/0x200
 ? security_file_permission+0x93/0x260
 vfs_write+0x1b0/0x550
 SyS_write+0xc7/0x1a0
 ? SyS_read+0x1a0/0x1a0
 ? trace_hardirqs_on_thunk+0x1a/0x1c
 entry_SYSCALL_64_fastpath+0x1e/0x8b
RIP: 0033:0x433549
RSP: 002b:00007ffe63bd1ea8 EFLAGS: 00000217
=======================================================================

Cc: syzkaller <syzkaller@googlegroups.com>
Cc: <stable@vger.kernel.org> # 3.13
Fixes: bde51583f49b ("IB/mlx5: Add support for resize CQ")
Reported-by: Noa Osherovich <noaos@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

Revert "RDMA/mlx5: Fix integer overflow while resizing CQ"

The original commit of this patch has a munged log message that is
missing several of the tags the original author intended to be on the
patch.  This was due to patchworks misinterpreting a cut-n-paste
separator line as an end of message line and munging the mbox that was
used to import the patch:

https://patchwork.kernel.org/patch/10264089/

The original patch will be reapplied with a fixed commit message so the
proper tags are applied.

This reverts commit aa0de36a40f446f5a21a7c1e677b98206e242edb.

Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: provide detailed PD information

Implement the RDMA nldev netlink interface for dumping detailed PD
information.

Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

mlx4_ib: zero out struct ib_pd when allocating

Zero out the fields of the struct ib_pd for user mode pds so that
users querying pds via nldev will not get garbage.  For simplicity,
use kzalloc() to allocate the mlx4_ib_pd struct.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: provide detailed MR information

Implement the RDMA nldev netlink interface for dumping detailed
MR information.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

mlx4_ib: set user mr attributes in struct ib_mr

Setting iova, length, and page_size allows this information to be
seen via NLDEV netlink queries, which can aid in user rdma debugging.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

iw_cxgb4: initialize ib_mr fields for user mrs

Some of the struct ib_mr fields weren't getting initialized.  This was
benign, but will cause problems when dumping the mr resource via
nldev/restrack.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: provide detailed CQ information

Implement the RDMA nldev netlink interface for dumping detailed
CQ information.

Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: provide detailed CM_ID information

Implement RDMA nldev netlink interface to get detailed CM_ID information.

Because cm_id's are attached to rdma devices in various work queue
contexts, the pid and task information at restrak_add() time is sometimes
not useful.  For example, an nvme/f host connection cm_id ends up being
bound to a device in a work queue context and the resulting pid at attach
time no longer exists after connection setup.  So instead we mark all
cm_id's created via the rdma_ucm as "user", and all others as "kernel".
This required tweaking the restrack code a little.  It also required
wrapping some rdma_cm functions to allow passing the module name string.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/CM: move rdma_id_private to cma_priv.h

Move struct rdma_id_private to a new header cma_priv.h so the resource
tracking services in core/nldev.c can read useful information about cm_ids.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/nldev: common resource dumpit function

Create a common dumpit function that can be used by all common resource
types.  This reduces code replication and simplifies the code as we add
more resource types.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/restrack: clean up res_to_dev()

Simplify res_to_dev() to make it easier to read/maintain.

Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

net/mlx5: Fix wrongly assigned CQ reference counter

The kernel compiled with CONFIG_REFCOUNT_FULL produces the following
error. The reason to it that initial value of refcount_t is supposed
to be more than 0, change it.

[    3.106634] ------------[ cut here ]------------
[    3.107756] refcount_t: increment on 0; use-after-free.
[    3.109130] WARNING: CPU: 0 PID: 1 at lib/refcount.c:153 refcount_inc+0x27/0x30
[    3.110085] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.16.0-rc1-00028-gf683e04bdccc #137
[    3.110085] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[    3.110085] RIP: 0010:refcount_inc+0x27/0x30
[    3.110085] RSP: 0000:ffffaa620000fba0 EFLAGS: 00010286
[    3.110085] RAX: 0000000000000000 RBX: ffff9a6d1a1821c8 RCX: ffffffff98a50f48
[    3.110085] RDX: 0000000000000001 RSI: 0000000000000086 RDI: 0000000000000246
[    3.110085] RBP: ffff9a6d1ac800a0 R08: 0000000000000289 R09: 000000000000000a
[    3.110085] R10: fffff03bc0682840 R11: ffffffff9949856d R12: ffff9a6d1b4a4000
[    3.110085] R13: 0000000000000000 R14: ffff9a6d1a0a6c00 R15: ffffaa620000fc5c
[    3.110085] FS:  0000000000000000(0000) GS:ffff9a6d1fc00000(0000) knlGS:0000000000000000
[    3.110085] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    3.110085] CR2: 0000000000000000 CR3: 000000000ba0a000 CR4: 00000000000006b0
[    3.110085] Call Trace:
[    3.110085]  mlx5_core_create_cq+0xde/0x250
[    3.110085]  ? __kmalloc+0x1ce/0x1e0
[    3.110085]  mlx5e_create_cq+0x15c/0x1e0
[    3.110085]  mlx5e_open_drop_rq+0xea/0x190
[    3.110085]  mlx5e_attach_netdev+0x53/0x140
[    3.110085]  mlx5e_attach+0x3d/0x60
[    3.110085]  mlx5e_add+0x11d/0x2f0
[    3.110085]  mlx5_add_device+0x77/0x170
[    3.110085]  mlx5_register_interface+0x74/0xc0
[    3.110085]  ? set_debug_rodata+0x11/0x11
[    3.110085]  init+0x67/0x72
[    3.110085]  ? mlx4_en_init_ptys2ethtool_map+0x346/0x346
[    3.110085]  do_one_initcall+0x98/0x147
[    3.110085]  ? set_debug_rodata+0x11/0x11
[    3.110085]  kernel_init_freeable+0x164/0x1e0
[    3.110085]  ? rest_init+0xb0/0xb0
[    3.110085]  kernel_init+0xa/0x100
[    3.110085]  ret_from_fork+0x35/0x40
[    3.110085] Code: 00 00 00 00 e8 ab ff ff ff 84 c0 74 02 f3 c3 80 3d 3b c3 64 01 00 75 f5 48 c7 c7 68 0b 81 98 c6 05 2b c3 64 01 01 e8 79 d7 a3 ff <0f> ff c3 66 0f 1f 44 00 00 8b 06 83 f8 ff 74 39 31 c9 39 f8 89
[    3.110085] ---[ end trace a0068e1c68438a74 ]---

Fixes: f105b45bf77c ("net/mlx5: CQ hold/put API")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: IPSec, Add support for ESN

Currently ESN is not supported with IPSec device offload.

This patch adds ESN support to IPsec device offload.
Implementing new xfrm device operation to synchronize offloading device
ESN with xfrm received SN. New QP command to update SA state at the
following:

           ESN 1                    ESN 2                  ESN 3
|-----------*-----------|-----------*-----------|-----------*
^           ^           ^           ^           ^           ^

^ - marks where QP command invoked to update the SA ESN state
    machine.
| - marks the start of the ESN scope (0-2^32-1). At this point move SA
    ESN overlap bit to zero and increment ESN.
* - marks the middle of the ESN scope (2^31). At this point move SA
    ESN overlap bit to one.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Yossef Efraim <yossefe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5e: Added common function for to_ipsec_sa_entry

New function for getting driver internal sa entry from xfrm state.
All checks are done in one function.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Add flow-steering commands for FPGA IPSec implementation

In order to add a context to the FPGA, we need to get both the software
transform context (which includes the keys, etc) and the
source/destination IPs (which are included in the steering
rule). Therefore, we register new set of firmware like commands for
the FPGA. Each time a rule is added, the steering core infrastructure
calls the FPGA command layer. If the rule is intended for the FPGA,
it combines the IPs information with the software transformation
context and creates the respective hardware transform.
Afterwards, it calls the standard steering command layer.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Refactor accel IPSec code

The current code has one layer that executed FPGA commands and
the Ethernet part directly used this code. Since downstream patches
introduces support for IPSec in mlx5_ib, we need to provide some
abstractions. This patch refactors the accel code into one layer
that creates a software IPSec transformation and another one which
creates the actual hardware context.
The internal command implementation is now hidden in the FPGA
core layer. The code also adds the ability to share FPGA hardware
contexts. If two contexts are the same, only a reference count
is taken.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Added required metadata capability for ipsec

Currently our device requires additional metadata in packet
to perform ipsec crypto offload.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Export ipsec capabilities

We will need that for ipsec verbs.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: IPSec, Add command V2 support

This patch adds V2 command support.
New fpga devices support extended features (udp encap, esn etc...), this
features require new hardware sadb format therefore we have a new version
of commands to manipulate it.

Signed-off-by: Yossef Efraim <yossefe@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5e: IPSec, Add support for ESP trailer removal by hardware

Current hardware decrypts and authenticates incoming ESP packets.
Subsequently, the software extracts the nexthdr field, truncates the
trailer and adjusts csum accordingly.

With this patch and a capable device, the trailer is being removed
by the hardware and the nexthdr field is conveyed via PET. This way
we avoid both the need to access the trailer (cache miss) and to
compute its relative checksum, which significantly improve
the performance.

Experiment shows that trailer removal improves the performance by
2Gbps, (netperf). Both forwarding and host-to-host configurations.

Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: IPSec, Generalize sandbox QP commands

The current code assume only SA QP commands.
Refactor in order to pave the way for new QP commands:
1. Generic cmd response format.
2. SA cmd checks are in dedicated functions.
3. Aligned debug prints.

Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Use MLX5_IPSEC_DEV macro for ipsec caps

Fix build break of mlx5_accel_ipsec_device_caps is not defined when
MLX5_ACCEL is not selected, use MLX5_IPSEC_DEV instead which handles
such case.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reported-by: Doug Ledford <dledford@redhat.com>

IB/mlx4: Move mlx4_uverbs_ex_query_device_resp to include/uapi/

This struct is involved in the user API for mlx4 and should not be hidden
inside a driver header file.

Fixes: 09d208b258a2 ("IB/mlx4: Add report for RSS capabilities by vendor channel")
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Merge tag 'mlx5-updates-2018-02-28-1' of git://git./linux/kernel/git/mellanox/linux into k.o/wip/dl-for-next

mlx5-updates-2018-02-28-1 (IPSec-1)

This series consists of some fixes and refactors for the mlx5 drivers,
especially around the FPGA and flow steering. Most of them are trivial
fixes and are the foundation of allowing IPSec acceleration from user-space.

We use flow steering abstraction in order to accelerate IPSec packets.
When a user creates a steering rule, [s]he states that we'll carry an
encrypt/decrypt flow action (using a specific configuration) for every
packet which conforms to a certain match. Since currently offloading these
packets is done via FPGA, we'll add another set of flow steering ops.
These ops will execute the required FPGA commands and then call the
standard steering ops.

In order to achieve this, we need that the commands will get all the
required information. Therefore, we pass the fte object and embed the
flow_action struct inside the fte. In addition, we add the shim layer
that will later be used for alternating between the standard and the
FPGA steering commands.

Some fixes, like " net/mlx5e: Wait for FPGA command responses with a timeout"
are very relevant for user-space applications, as these applications could
be killed, but we still want to wait for the FPGA and update the kernel's
database.

Regards,
Aviad and Matan

Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/rxe: change the function rxe_init_device_param type

The function rxe_init_device_param always return 0. So the function
type is changed to void.

CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/rxe: remove unnecessary rxe in rxe_send

In the function rxe_send, the variable rxe is not used in it.
So it should be removed.

CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/rxe: remove unnecessary skb_clone

In send_atomic_ack function, it is not necessary to make a
skb_clone. To gain better performance (high throughput and
low latency), this skb_clone is removed.

The following tests are made.

 server                       client
---------                    ---------
|1.1.1.1|<----rxe-channel--->|1.1.1.2|
---------                    ---------

On server: rping -s -a 1.1.1.1 -v -C 1000 -S 512
On client: rping -c -a 1.1.1.1 -v -C 1000 -S 512

The kernel config CONFIG_DEBUG_KMEMLEAK is enabled on both server
and client.

This test runs for several hours. There is no memory leak and the whole
system can work well.

Based on the above network, the following tests are made.

Server: ibv_rc_pingpong -d rxe0 -g 1
Client: ibv_rc_pingpong -d rxe0 -g 1 1.1.1.1

The test results on Server(10 tests are made).
Before:
Throughput is 137.07 Mbit/sec
Latency is 517.76 usec/iter

After:
Throughput is 148.85 Mbit/sec
Latency is 476.64 usec/iter

The throughput is enhanced and the latency is reduced.

CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/srpt: Add RDMA/CM support

Add a parameter for configuring the port on which the ib_srpt driver
listens for incoming RDMA/CM connections, namely
/sys/kernel/config/target/srpt/discovery_auth/rdma_cm_port. The default
value for this parameter is 0 which means "do not listen for incoming
RDMA/CM connections". Add RDMA/CM support to all code that handles
connection state changes. Modify srpt_init_nodeacl() such that ACLs can
be configured for IPv4 and IPv6 addresses.

Note: incoming connection requests are only accepted for ports that
have been enabled. See also the "if (!sport->enabled)" code in the
connection request handler. See also the following configfs attribute:
/sys/kernel/config/target/srpt/$port/$port/enable.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/ucma: Check that user doesn't overflow QP state

The QP state is limited and declared in enum ib_qp_state,
but ucma user was able to supply any possible (u32) value.

Reported-by: syzbot+0df1ab766f8924b1edba@syzkaller.appspotmail.com
Fixes: 75216638572f ("RDMA/cma: Export rdma cm interface to userspace")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/mlx5: Fix integer overflow while resizing CQ

The user can provide very large cqe_size which will cause to integer
overflow as it can be seen in the following UBSAN warning:

Signed-off-by: Doug Ledford <dledford@redhat.com>

RDMA/ucma: Limit possible option size

Users of ucma are supposed to provide size of option level,
in most paths it is supposed to be equal to u8 or u16, but
it is not the case for the IB path record, where it can be
multiple of struct ib_path_rec_data.

This patch takes simplest possible approach and prevents providing
values more than possible to allocate.

Reported-by: syzbot+a38b0e9f694c379ca7ce@syzkaller.appspotmail.com
Fixes: 7ce86409adcd ("RDMA/ucma: Allow user space to set service type")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

IB/core: Fix possible crash to access NULL netdev

resolved_dev returned might be NULL as ifindex is transient number.
Ignoring NULL check of resolved_dev might crash the kernel.
Therefore perform NULL check before accessing resolved_dev.

Additionally rdma_resolve_ip_route() invokes addr_resolve() which
performs check and address translation for loopback ifindex.
Therefore, checking it again in rdma_resolve_ip_route() is not helpful.
Therefore, the code is simplified to avoid IFF_LOOPBACK check.

Fixes: 200298326b27 ("IB/core: Validate route when we init ah")
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

net/mlx5: Flow steering cmd interface should get the fte when deleting

Previously, deleting a flow steering entry only got the index.
Since the FPGA implementation of FTE's deletion might need to dig
inside the FTE itself, we would like to get the FTE's context.
Changing the interface to pass the FTE context.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

{net,IB}/mlx5: Add flow steering helpers

Add helper functions that check if a protocol is
part of a flow steering match criteria.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Embed mlx5_flow_act into fs_fte

fte objects contain the match value and action. Currently, extending
the actions require in adding them both to the API and fs_fte.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Add empty egress namespace to flow steering core

Currently, we don't support egress flow steering namespace in mlx5
flow steering core implementation. However, when we want to encrypt
a packet, we model it as a flow steering rule in the egress path.
To overcome this, we add an empty egress namespace to flow steering.
This namespace is initialized only when ipsec support exists.
In the future, this will grow to a full blown full steering
implementation, resembling the ingress path.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5: Add shim layer between fs and cmd

The shim layer allows each namespace to define possibly different
functionality for add/delete/update commands. The shim layer
introduced here, will be used to support flow steering with the FPGA.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

{net,IB}/mlx5: Add has_tag to mlx5_flow_act

The has_tag member will indicate whether a tag action was specified
in flow specification.

A flow tag 0 = MLX5_FS_DEFAULT_FLOW_TAG is assumed a valid flow tag
that is currently used by mlx5 RDMA driver, whereas in HW flow_tag = 0
means that the user doesn't care about flow_tag.  HW always provide
a flow_tag = 0 if all flow tags requested on a specific flow are 0.

So we need a way (in the driver) to differentiate between a user really
requesting flow_tag = 0 and a user who does not care, in order to be
able to report conflicting flow tags on a specific flow.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

IB/mlx5: Pass mlx5_flow_act struct instead of multiple arguments

Group and pass all function arguments of parse_flow_attr call in one
common struct mlx5_flow_act.

This patch passes all the action arguments of parse_flow_attr in one common
struct mlx5_flow_act. It allows us to scale the number of actions without adding
new arguments to the function.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Jason Gunthorpe <jgg@mellanox.com>

net/mlx5: FPGA and IPSec initialization to be before flow steering

Some flow steering namespace initialization (i.e. egress namespace)
might depend on FPGA capabilities. Changing the initialization order
such that the FPGA will be initialized before flow steering.

Flow steering fs cmds initialization might depend on
IPSec capabilities. Changing the initialization order such
that the IPSec will be initialized before flow steering as well.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

net/mlx5e: Removed not need synchronize_rcu

This is already done by xfrm layer between state_dev_del callback
to state_dev_free callback.

Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>