On RoCE systems, a CM REQ contains a Primary Hop Limit > 1 and Primary
Subnet Local is zero.

In cm_req_handler(), the cm_process_routed_req() function is called. Since
the Primary Subnet Local value is zero in the request, and since this is
RoCE (Primary Local LID is permissive), the following statement will be
executed:

      IBA_SET(CM_REQ_PRIMARY_SL, req_msg, wc->sl);

This corrupts SL in req_msg if it was different from zero. In other words,
a request to setup a connection using an SL != zero, will not be honored,
and a connection using SL zero will be created instead.

Fixed by not calling cm_process_routed_req() on RoCE systems, the
cm_process_route_req() is only for IB anyhow.

Fixes: 3971c9f6 ("IB/cm: Add interim support for routed paths")
Link: https://lore.kernel.org/r/1616420132-31005-1-git-send-email-haakon.bugge@oracle.comSigned-off-by: NHåkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

The function isn't implemented - delete the declaration.

Fixes: a9d2e9ae ("RDMA/siw,rxe: Make emulated devices virtual in the device tree")
Link: https://lore.kernel.org/r/20210331102043.691950-1-kamalheib1@gmail.comSigned-off-by: NKamal Heib <kamalheib1@gmail.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

spinlock can be initialized automatically with DEFINE_SPINLOCK() rather
than explicitly calling spin_lock_init().

Link: https://lore.kernel.org/r/20210331020105.4858-1-tangyizhou@huawei.comReported-by: NHulk Robot <hulkci@huawei.com>
Signed-off-by: NTang Yizhou <tangyizhou@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

struct iscsi_iser_task has been declared at 201st line. Remove the
duplicate.

Link: https://lore.kernel.org/r/20210326113347.903976-1-wanjiabing@vivo.comSigned-off-by: NWan Jiabing <wanjiabing@vivo.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

s/caculating/calculating

Link: https://lore.kernel.org/r/20210330122912.19989-1-gongruiqi1@huawei.comReported-by: NHulk Robot <hulkci@huawei.com>
Signed-off-by: NRuiqi Gong <gongruiqi1@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

In the original rxe implementation it was intended to use a common object
to represent MRs and MWs but they are different enough to separate these
into two objects.

This allows replacing the mem name with mr for MRs which is more
consistent with the style for the other objects and less likely to be
confusing. This is a long patch that mostly changes mem to mr where it
makes sense and adds a new rxe_mw struct.

Link: https://lore.kernel.org/r/20210325212425.2792-1-rpearson@hpe.comSigned-off-by: NBob Pearson <rpearson@hpe.com>
Acked-by: NZhu Yanjun <zyjzyj2000@gmail.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

The strlcpy function doesn't limit the source length, use the preferred
strscpy function instead.

Link: https://lore.kernel.org/r/20210329120131.18793-1-galpress@amazon.comReviewed-by: NFiras JahJah <firasj@amazon.com>
Reviewed-by: NYossi Leybovich <sleybo@amazon.com>
Signed-off-by: NGal Pressman <galpress@amazon.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

The device is got by isert_device_get() with refcount is 1, and is
assigned to isert_conn by
  isert_conn->device = device.

When isert_create_qp() failed, device will be freed with
isert_device_put().

Later, the device is used in isert_free_login_buf(isert_conn) by the
isert_conn->device->ib_device statement.

Free the device in the correct order.

Fixes: ae9ea9ed ("iser-target: Split some logic in isert_connect_request to routines")
Link: https://lore.kernel.org/r/20210322161325.7491-1-lyl2019@mail.ustc.edu.cnSigned-off-by: NLv Yunlong <lyl2019@mail.ustc.edu.cn>
Acked-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NLeon Romanovsky <leonro@nvidia.com>
Reviewed-by: NMax Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

s/struture/structure/

And add the missing colon for kdoc

Link: https://lore.kernel.org/r/20210322062923.3306167-1-unixbhaskar@gmail.comSigned-off-by: NBhaskar Chowdhury <unixbhaskar@gmail.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Correct the following spelling errors:
1. shold -> should
2. uncontext -> ucontext

Link: https://lore.kernel.org/r/1616147749-49106-1-git-send-email-liweihang@huawei.comSigned-off-by: NYangyang Li <liyangyang20@huawei.com>
Signed-off-by: NWeihang Li <liweihang@huawei.com>
Reviewed-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Currently, ODP caps are set during the init stage of mlx5_ib_dev,
regardless of whether the device profile supports ODP or not.  There is no
point in setting ODP caps if the device profile doesn't support
ODP. Hence, move setting the ODP caps to the odp_init stage.

Link: https://lore.kernel.org/r/20210318135259.681264-1-leon@kernel.orgReviewed-by: NMaor Gottlieb <maorg@nvidia.com>
Signed-off-by: NShay Drory <shayd@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Initial drop action support missed that drop action can be added to egress
flow tables as well. Add the missing support.

This requires making sure that dest_type isn't set to PORT which in turn
exposes a possibility of passing dst while indicating number of dsts as
zero. Explicitly check for number of dsts and pass the appropriate
pointer.

Fixes: f29de9ee ("RDMA/mlx5: Add support for drop action in DV steering")
Link: https://lore.kernel.org/r/20210318135123.680759-1-leon@kernel.orgReviewed-by: NMark Bloch <markb@nvidia.com>
Signed-off-by: NMaor Gottlieb <maorg@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Success is returned in the following flows:
 * New mode is the same as the current one.
 * Switched to new mode and there are no bound counters yet.

Link: https://lore.kernel.org/r/20210318110502.673676-1-leon@kernel.orgSigned-off-by: NPatrisious Haddad <phaddad@nvidia.com>
Reviewed-by: NMark Zhang <markzhang@nvidia.com>
Reviewed-by: NMaor Gottlieb <maorg@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

When the L2 driver detects a device crash or device undergone reset, it
invokes a stop callback to recover from error.

The current RoCE driver doesn't recover the device. So move the device to
error state and dispatch fatal events to all qps Release the MSIx vectors
to avoid a crash when L2 driver disables the MSIx.  Also, check for the
device state to avoid posting further commands to the HW.

Link: https://lore.kernel.org/r/1615968942-30970-1-git-send-email-selvin.xavier@broadcom.comSigned-off-by: NNaresh Kumar PBS <nareshkumar.pbs@broadcom.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Current code uses many different types when dealing with a port of a RDMA
device: u8, unsigned int and u32. Switch to u32 to clean up the logic.

This allows us to make (at least) the core view consistent and use the
same type. Unfortunately not all places can be converted. Many uverbs
functions expect port to be u8 so keep those places in order not to break
UAPIs.  HW/Spec defined values must also not be changed.

With the switch to u32 we now can support devices with more than 255
ports. U32_MAX is reserved to make control logic a bit easier to deal
with. As a device with U32_MAX ports probably isn't going to happen any
time soon this seems like a non issue.

When a device with more than 255 ports is created uverbs will report the
RDMA device as having 255 ports as this is the max currently supported.

The verbs interface is not changed yet because the IBTA spec limits the
port size in too many places to be u8 and all applications that relies in
verbs won't be able to cope with this change. At this stage, we are
extending the interfaces that are using vendor channel solely

Once the limitation is lifted mlx5 in switchdev mode will be able to have
thousands of SFs created by the device. As the only instance of an RDMA
device that reports more than 255 ports will be a representor device and
it exposes itself as a RAW Ethernet only device CM/MAD/IPoIB and other
ULPs aren't effected by this change and their sysfs/interfaces that are
exposes to userspace can remain unchanged.

While here cleanup some alignment issues and remove unneeded sanity
checks (mainly in rdmavt),

Link: https://lore.kernel.org/r/20210301070420.439400-1-leon@kernel.orgSigned-off-by: NMark Bloch <mbloch@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Implement the ops named get_dev_fw_str to support ib_get_device_fw_str().

Link: https://lore.kernel.org/r/1615882161-53827-1-git-send-email-liweihang@huawei.comSigned-off-by: NLang Cheng <chenglang@huawei.com>
Signed-off-by: NWeihang Li <liweihang@huawei.com>
Reviewed-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

There is no need to create the ODP EQ if the user doesn't use ODP MRs.
Hence, create it only when the first ODP MR is created. This EQ will be
destroyed only when the device is unloaded.
This will decrease the number of EQs created per device. for example: If
we creates 1K devices (SF/VF/etc'), than we will decrease the num of EQs
by 1K.

Link: https://lore.kernel.org/r/20210314125418.179716-1-leon@kernel.orgSigned-off-by: NShay Drory <shayd@nvidia.com>
Reviewed-by: NMaor Gottlieb <maorg@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

It's incorrect to cast the type of pointer to xrcdn from (u32 *) to
(unsigned long *), then pass it into hns_roce_bitmap_alloc(), this will
lead to a memory corruption.

Fixes: 32548870 ("RDMA/hns: Add support for XRC on HIP09")
Link: https://lore.kernel.org/r/1616381069-51759-1-git-send-email-liweihang@huawei.comReported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NWeihang Li <liweihang@huawei.com>
Reviewed-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Commit ee1c60b1 ("IB/SA: Modify SA to implicitly cache Class Port
info") removed the class_port_info_context struct usage, remove a couple
of leftovers.

Link: https://lore.kernel.org/r/20210314143427.76101-1-galpress@amazon.comSigned-off-by: NGal Pressman <galpress@amazon.com>
Reviewed-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Perform mass deletion of static inline functions that are not used.

Link: https://lore.kernel.org/r/20210314133908.291945-3-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

This patch fixes bunch of kernel-doc compilation warnings like below:

 drivers/infiniband/hw/i40iw/i40iw_cm.c:4372: warning: expecting prototype for i40iw_ifdown_notify(). Prototype was for i40iw_if_notify() instead

Link: https://lore.kernel.org/r/20210314133908.291945-2-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Fix the following smatch error:

drivers/infiniband/hw/mlx5/mr.c:1950 mlx5_ib_dereg_mr() error: uninitialized symbol 'rc'.

Fixes: e6fb246c ("RDMA/mlx5: Consolidate MR destruction to mlx5_ib_dereg_mr()")
Link: https://lore.kernel.org/r/20210314082250.10143-1-leon@kernel.orgReported-by: Nkernel test robot <lkp@intel.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

The umem DMA list calculation was locked at 4k pages due to confusion
around how this API works and is used when larger pages are present.

The conclusion is:

 - umem's cannot extend past what is mapped into the process, so creating
   a lage page size and referring to a sub-range is not allowed

 - umem's must always have a page offset of zero, except for sub PAGE_SIZE
   umems

 - The feature of umem_offset to create multiple objects inside a umem
   is buggy and isn't used anyplace. Thus we can assume all users of the
   current API have umem_offset == 0 as well

Provide a new page size calculator that limits the DMA list to the VA
range and enforces umem_offset == 0.

Allow user space to specify the page sizes which it can accept, this
bitmap must be derived from the intended use of the umem, based on
per-usage HW limitations.

Link: https://lore.kernel.org/r/20210304130501.1102577-4-leon@kernel.orgSigned-off-by: NYishai Hadas <yishaih@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Change uverbs_get_const/uverbs_get_const_default to work properly with
both signed/unsigned parameters.

Current APIs mix s64 and u64 which leads to incorrect check when u64
value was supplied and its upper bit was set. In that case
uverbs_get_const() / uverbs_get_const_default() lower bound check may
fail unexpectedly, target is unsigned (lower bound is 0) but value
became negative as of the s64 usage.

Split to have two different APIs, no change to callers as the required
API will be called internally according to the target type.

Link: https://lore.kernel.org/r/20210304130501.1102577-3-leon@kernel.orgSigned-off-by: NYishai Hadas <yishaih@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

The WARN_ON() issued as part of ib_umem_find_best_pgsz() blocked cases
when only page sizes larger than PAGE_SIZE were set, drop it to enable
those cases.

In addition, there is no need to have a specific check for zero
pgsz_bitmap, the function will do its job and return 0 at the end if
nothing match will be found.

Link: https://lore.kernel.org/r/20210304130501.1102577-2-leon@kernel.orgSigned-off-by: NYishai Hadas <yishaih@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Correct the map between mlx5 rates and corresponding ib rates, as they
don't always have a fixed offset between them.

Fixes: e126ba97 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Link: https://lore.kernel.org/r/20210304124517.1100608-4-leon@kernel.orgSigned-off-by: NMark Zhang <markzhang@nvidia.com>
Reviewed-by: NMaor Gottlieb <maorg@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

mlx5_is_roce_enabled returns the devlink RoCE init value, therefore it
should be used only when driver is loaded. Instead we just need to read
the roce_en field.

In addition, rename mlx5_is_roce_enabled to mlx5_is_roce_init_enabled.

Fixes: 7a58779e ("IB/mlx5: Improve query port for representor port")
Link: https://lore.kernel.org/r/20210304124517.1100608-2-leon@kernel.orgSigned-off-by: NMaor Gottlieb <maorg@nvidia.com>
Signed-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Now that this is only used in a few places in mr.c give it a sensible
name. It has nothing to do with the cache and can be invoked on any
MR. DMA is stopped and the user cannot touch the MR any further once it
completes.

Link: https://lore.kernel.org/r/20210304120745.1090751-5-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Now that the SRCU stuff has been removed the entire MR destroy logic can
be made a lot simpler. Currently there are many different ways to destroy a
MR and it makes it really hard to do this task correctly. Route all
destruction through mlx5_ib_dereg_mr() and make it work for all
situations.

Since it turns out all the different MR types do basically the same thing
this removes a lot of knowledge of MR internals from ODP and leaves ODP
just exporting an operation to clean up children.

This fixes a few weird corner cases bugs and firmly uses the correct
ordering of the MR destruction:
 - Stop parallel access to the mkey via the ODP xarray
 - Stop DMA
 - Release the umem
 - Clean up ODP children
 - Free/Recycle the MR

Link: https://lore.kernel.org/r/20210304120745.1090751-4-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

The struct mlx5_ib_mr can be used for three different things, but only one
at a time:

 - In the user MR cache
 - As a kernel MR
 - As a user MR

Overlay the three things into a single union with the following rules:

 - If the mr is found on the cache_ent->head list then it is a cache MR
   and umem == NULL. The entire union is zero after the MR is removed from
   the cache.

 - If umem != NULL or type == IB_MR_TYPE_USER then it is a user MR.

 - If umem == NULL then it is a kernel MR

This reduces the size of struct mlx5_ib_mr to 552 bytes from 702.

The only place the three flows overlap in the code is during dereg, so add
a few extra checks along there.

Link: https://lore.kernel.org/r/20210304120745.1090751-3-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

All of the ODP code assumes when it calls mlx5_mr_cache_alloc() the ODP
related fields are zero'd. This is true if the MR was just allocated, but
if the MR is recycled through the cache then the values are never zero'd.

This causes a bug in the odp_stats, they don't reset when the MR is
reallocated, also is_odp_implicit is never 0'd.

So we can use memset on a block of the mlx5_ib_mr reorganize the structure
to put all the data that can be zero'd by the cache at the end.

It is organized as an anonymous struct because the next patch will make
this a union.

Delete the unused smr_info. Don't set the kernel only desc_size on the
user path. No longer any need to zero mr->parent before freeing it, the
memset() will get it now.

Fixes: a3de94e3 ("IB/mlx5: Introduce ODP diagnostic counters")
Link: https://lore.kernel.org/r/20210304120745.1090751-2-leon@kernel.orgSigned-off-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

The HIP09 supports XRC transport service, it greatly saves the number of
QPs required to connect all processes in a large cluster.

Link: https://lore.kernel.org/r/1614826558-35423-1-git-send-email-liweihang@huawei.comSigned-off-by: NWenpeng Liang <liangwenpeng@huawei.com>
Signed-off-by: NWeihang Li <liweihang@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

It's easier to understand a string instead of enum.

Link: https://lore.kernel.org/r/20210222141551.54345-2-jinpu.wang@cloud.ionos.comSigned-off-by: NJack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Have the driver use shared CQs which provids a ~10%-20% improvement during
test.

Instead of opening a CQ for each QP per connection, a CQ for each QP will
be provided by the RDMA core driver that will be shared between the QPs on
that core reducing interrupt overhead.

Link: https://lore.kernel.org/r/20210222141551.54345-1-jinpu.wang@cloud.ionos.comSigned-off-by: NJack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: NLeon Romanovsky <leonro@nvidia.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

The request_ncomp_notif device operation and function are unused, remove
them.

Link: https://lore.kernel.org/r/20210311150921.23726-1-galpress@amazon.comSigned-off-by: NGal Pressman <galpress@amazon.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

Binding IPv6 address/port to AF_INET6 domain only is provided via
rdma_set_afonly(), but was not signalled to the provider.  Applications
like NFS/RDMA bind the same port to both IPv4 and IPv6 addresses
simultaneously and thus rely on it working correctly.

Link: https://lore.kernel.org/r/20210219143441.1068-1-bmt@zurich.ibm.comTested-by: NChuck Lever <chuck.lever@oracle.com>
Tested-by: NBenjamin Coddington <bcodding@redhat.com>
Signed-off-by: NBernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

HIP09 uses new address space to map SQ doorbell registers, the doorbell of
each QP is isolated based on the size of 64KB, which can improve the
performance in concurrency scenarios.

Link: https://lore.kernel.org/r/1614082833-23130-1-git-send-email-liweihang@huawei.comSigned-off-by: NLang Cheng <chenglang@huawei.com>
Signed-off-by: NWeihang Li <liweihang@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

In rxe_comp.c in rxe_completer() the function free_pkt() did not clear skb
which triggered a warning at 'done:' and could possibly at 'exit:'. The
WARN_ONCE() calls are not actually needed.  The call to free_pkt() is
moved to the end to clearly show that all skbs are freed.

Fixes: 899aba89 ("RDMA/rxe: Fix FIXME in rxe_udp_encap_recv()")
Link: https://lore.kernel.org/r/20210304192048.2958-1-rpearson@hpe.comSigned-off-by: NBob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

rxe_rcv_mcast_pkt() dropped a reference to ib_device when no error
occurred causing an underflow on the reference counter.  This code is
cleaned up to be clearer and easier to read.

Fixes: 899aba89 ("RDMA/rxe: Fix FIXME in rxe_udp_encap_recv()")
Link: https://lore.kernel.org/r/20210304192048.2958-1-rpearson@hpe.comSigned-off-by: NBob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>

When the noted patch below extending the reference taken by
rxe_get_dev_from_net() in rxe_udp_encap_recv() until each skb is freed it
was not matched by a reference in the loopback path resulting in
underflows.

Fixes: 899aba89 ("RDMA/rxe: Fix FIXME in rxe_udp_encap_recv()")
Link: https://lore.kernel.org/r/20210304192048.2958-1-rpearson@hpe.comSigned-off-by: NBob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>