Replace the internal interval tree based mmu notifier with the new common
mmu_interval_notifier_insert() API. This removes a lot of code and fixes a
deadlock that can be triggered in ODP:
zap_page_range()
mmu_notifier_invalidate_range_start()
[..]
ib_umem_notifier_invalidate_range_start()
down_read(&per_mm->umem_rwsem)
unmap_single_vma()
[..]
__split_huge_page_pmd()
mmu_notifier_invalidate_range_start()
[..]
ib_umem_notifier_invalidate_range_start()
down_read(&per_mm->umem_rwsem) // DEADLOCK
mmu_notifier_invalidate_range_end()
up_read(&per_mm->umem_rwsem)
mmu_notifier_invalidate_range_end()
up_read(&per_mm->umem_rwsem)
The umem_rwsem is held across the range_start/end as the ODP algorithm for
invalidate_range_end cannot tolerate changes to the interval
tree. However, due to the nested invalidation regions the second
down_read() can deadlock if there are competing writers. The new core code
provides an alternative scheme to solve this problem.
Fixes: ca748c39ea ("RDMA/umem: Get rid of per_mm->notifier_count")
Link: https://lore.kernel.org/r/20191112202231.3856-6-jgg@ziepe.ca
Tested-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Provide ability to get node and port GUIDs of VFs to be symmetrical
to already existing set option.
Signed-off-by: Danit Goldberg <danitg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
The argument is always ignored, so remove it.
Link: https://lore.kernel.org/r/20191113073214.9514-3-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
All users of process_mad() converts input pointers from ib_mad_hdr to be
ib_mad, update the function declaration to use ib_mad directly.
Also remove not used input MAD size parameter.
Link: https://lore.kernel.org/r/20191029062745.7932-17-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Tested-By: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The rdma_user_mmap_io interface created a common interface for drivers to
correctly map hw resources and zap them once the ucontext is destroyed
enabling the drivers to safely free the hw resources.
However, this meant the drivers need to delay freeing the resource to the
ucontext destroy phase to ensure they were no longer mapped. The new
mechanism for a common way of handling user/driver address mapping enabled
notifying the driver if all umap_priv mappings were removed, and enabled
freeing the hw resources when they are done with and not delay it until
ucontext destroy.
Since not all drivers use the mechanism, NULL can be sent to the
rdma_user_mmap_io interface to continue working as before. Drivers that
use the mmap_xa interface can pass the entry being mapped to the
rdma_user_mmap_io function to be linked together.
Link: https://lore.kernel.org/r/20191030094417.16866-4-michal.kalderon@marvell.com
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Create some common API's for adding entries to a xa_mmap. Searching for
an entry and freeing one.
The general approach is copied from the EFA driver and improved to be more
general and do more to help the drivers. Integration with the core allows
a reference counted scheme with a free function so that the driver can
know when its mmaps are all gone.
This significant new functionality will be helpful for drivers to have the
correct lifetime model for mmap objects.
Link: https://lore.kernel.org/r/20191030094417.16866-3-michal.kalderon@marvell.com
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe says:
====================
In order to hoist the interval tree code out of the drivers and into the
mmu_notifiers it is necessary for the drivers to not use the interval tree
for other things.
This series replaces the interval tree with an xarray and along the way
re-aligns all the locking to use a sensible SRCU model where the 'update'
step is done by modifying an xarray.
The result is overall much simpler and with less locking in the critical
path. Many functions were reworked for clarity and small details like
using 'imr' to refer to the implicit MR make the entire code flow here
more readable.
This also squashes at least two race bugs on its own, and quite possibily
more that haven't been identified.
====================
Merge conflicts with the odp statistics patch resolved.
* branch 'odp_rework':
RDMA/odp: Remove broken debugging call to invalidate_range
RDMA/mlx5: Do not race with mlx5_ib_invalidate_range during create and destroy
RDMA/mlx5: Do not store implicit children in the odp_mkeys xarray
RDMA/mlx5: Rework implicit ODP destroy
RDMA/mlx5: Avoid double lookups on the pagefault path
RDMA/mlx5: Reduce locking in implicit_mr_get_data()
RDMA/mlx5: Use an xarray for the children of an implicit ODP
RDMA/mlx5: Split implicit handling from pagefault_mr
RDMA/mlx5: Set the HW IOVA of the child MRs to their place in the tree
RDMA/mlx5: Lift implicit_mr_alloc() into the two routines that call it
RDMA/mlx5: Rework implicit_mr_get_data
RDMA/mlx5: Delete struct mlx5_priv->mkey_table
RDMA/mlx5: Use a dedicated mkey xarray for ODP
RDMA/mlx5: Split sig_err MR data into its own xarray
RDMA/mlx5: Use SRCU properly in ODP prefetch
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use SRCU in a sensible way by removing all MRs in the implicit tree from
the two xarrays (the update operation), then a synchronize, followed by a
normal single threaded teardown.
This is only a little unusual from the normal pattern as there can still
be some work pending in the unbound wq that may also require a workqueue
flush. This is tracked with a single atomic, consolidating the redundant
existing atomics and wait queue.
For understand-ability the entire ODP implicit create/destroy flow now
largely exists in a single pair of functions within odp.c, with a few
support functions for tearing down an unused child.
Link: https://lore.kernel.org/r/20191009160934.3143-13-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently the child leaves are stored in the shared interval tree and
every lookup for a child must be done under the interval tree rwsem.
This is further complicated by dropping the rwsem during iteration (ie the
odp_lookup(), odp_next() pattern), which requires a very tricky an
difficult to understand locking scheme with SRCU.
Instead reserve the interval tree for the exclusive use of the mmu
notifier related code in umem_odp.c and give each implicit MR a xarray
containing all the child MRs.
Since the size of each child is 1GB of VA, a 1 level xarray will index 64G
of VA, and a 2 level will index 2TB, making xarray a much better
data structure choice than an interval tree.
The locking properties of xarray will be used in the next patches to
rework the implicit ODP locking scheme into something simpler.
At this point, the xarray is locked by the implicit MR's umem_mutex, and
read can also be locked by the odp_srcu.
Link: https://lore.kernel.org/r/20191009160934.3143-10-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add Mellanox to lust of copyright holders and replace copyright
boilerplate with relevant SPDX tag.
Link: https://lore.kernel.org/r/20191020071559.9743-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There is a specific define keyword to check if define exists or not,
let's use it instead of open-coded variant.
Link: https://lore.kernel.org/r/20191020071559.9743-3-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Provide an ODP explicit/implicit type as part of 'rdma -dd resource show
mr' dump.
For example:
$ rdma -dd resource show mr
dev mlx5_0 mrn 1 rkey 0xa99a lkey 0xa99a mrlen 50000000
pdn 9 pid 7372 comm ibv_rc_pingpong drv_odp explicit
For non-ODP MRs, we won't print "drv_odp ..." at all.
Link: https://lore.kernel.org/r/20191016062308.11886-4-leon@kernel.org
Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Introduce ODP diagnostic counters and count the following
per MR within IB/mlx5 driver:
1) Page faults:
Total number of faulted pages.
2) Page invalidations:
Total number of pages invalidated by the OS during all
invalidation events. The translations can be no longer
valid due to either non-present pages or mapping changes.
Link: https://lore.kernel.org/r/20191016062308.11886-2-leon@kernel.org
Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The issue is in drivers/infiniband/core/uverbs_std_types_cq.c in the
UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE) function. We check that:
if (attr.comp_vector >= attrs->ufile->device->num_comp_vectors) {
But we don't check if "attr.comp_vector" is negative. It could
potentially lead to an array underflow. My concern would be where
cq->vector is used in the create_cq() function from the cxgb4 driver.
And really "attr.comp_vector" is appears as a u32 to user space so that's
the right type to use.
Fixes: 9ee79fce36 ("IB/core: Add completion queue (cq) object actions")
Link: https://lore.kernel.org/r/20191011133419.GA22905@mwanda
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
If there are more scatter entries than the recommended limit provided by
the ib device, UMR registration is used. This will provide optimal
performance when performing large RDMA READs over devices that advertise
the threshold capability.
With ConnectX-5 running NVMeoF RDMA with FIO single QP 128KB writes:
Without use of cap: 70Gb/sec
With use of cap: 84Gb/sec
Link: https://lore.kernel.org/r/20191007135933.12483-3-leon@kernel.org
Signed-off-by: Yamin Friedman <yaminf@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This cycle mainly saw lots of bug fixes and clean up code across the core
code and several drivers, few new functional changes were made.
- Many cleanup and bug fixes for hns
- Various small bug fixes and cleanups in hfi1, mlx5, usnic, qed,
bnxt_re, efa
- Share the query_port code between all the iWarp drivers
- General rework and cleanup of the ODP MR umem code to fit better with
the mmu notifier get/put scheme
- Support rdma netlink in non init_net name spaces
- mlx5 support for XRC devx and DC ODP
-----BEGIN PGP SIGNATURE-----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=zHXW
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull RDMA subsystem updates from Jason Gunthorpe:
"This cycle mainly saw lots of bug fixes and clean up code across the
core code and several drivers, few new functional changes were made.
- Many cleanup and bug fixes for hns
- Various small bug fixes and cleanups in hfi1, mlx5, usnic, qed,
bnxt_re, efa
- Share the query_port code between all the iWarp drivers
- General rework and cleanup of the ODP MR umem code to fit better
with the mmu notifier get/put scheme
- Support rdma netlink in non init_net name spaces
- mlx5 support for XRC devx and DC ODP"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (99 commits)
RDMA: Fix double-free in srq creation error flow
RDMA/efa: Fix incorrect error print
IB/mlx5: Free mpi in mp_slave mode
IB/mlx5: Use the original address for the page during free_pages
RDMA/bnxt_re: Fix spelling mistake "missin_resp" -> "missing_resp"
RDMA/hns: Package operations of rq inline buffer into separate functions
RDMA/hns: Optimize cmd init and mode selection for hip08
IB/hfi1: Define variables as unsigned long to fix KASAN warning
IB/{rdmavt, hfi1, qib}: Add a counter for credit waits
IB/hfi1: Add traces for TID RDMA READ
RDMA/siw: Relax from kmap_atomic() use in TX path
IB/iser: Support up to 16MB data transfer in a single command
RDMA/siw: Fix page address mapping in TX path
RDMA: Fix goto target to release the allocated memory
RDMA/usnic: Avoid overly large buffers on stack
RDMA/odp: Add missing cast for 32 bit
RDMA/hns: Use devm_platform_ioremap_resource() to simplify code
Documentation/infiniband: update name of some functions
RDMA/cma: Fix false error message
RDMA/hns: Fix wrong assignment of qp_access_flags
...
This is more cleanup and consolidation of the hmm APIs and the very
strongly related mmu_notifier interfaces. Many places across the tree
using these interfaces are touched in the process. Beyond that a cleanup
to the page walker API and a few memremap related changes round out the
series:
- General improvement of hmm_range_fault() and related APIs, more
documentation, bug fixes from testing, API simplification &
consolidation, and unused API removal
- Simplify the hmm related kconfigs to HMM_MIRROR and DEVICE_PRIVATE, and
make them internal kconfig selects
- Hoist a lot of code related to mmu notifier attachment out of drivers by
using a refcount get/put attachment idiom and remove the convoluted
mmu_notifier_unregister_no_release() and related APIs.
- General API improvement for the migrate_vma API and revision of its only
user in nouveau
- Annotate mmu_notifiers with lockdep and sleeping region debugging
Two series unrelated to HMM or mmu_notifiers came along due to
dependencies:
- Allow pagemap's memremap_pages family of APIs to work without providing
a struct device
- Make walk_page_range() and related use a constant structure for function
pointers
-----BEGIN PGP SIGNATURE-----
iQIzBAABCgAdFiEEfB7FMLh+8QxL+6i3OG33FX4gmxoFAl1/nnkACgkQOG33FX4g
mxqaRg//c6FqowV1pQlLutvAOAgMdpzfZ9eaaDKngy9RVQxz+k/MmJrdRH/p/mMA
Pq93A1XfwtraGKErHegFXGEDk4XhOustVAVFwvjyXO41dTUdoFVUkti6ftbrl/rS
6CT+X90jlvrwdRY7QBeuo7lxx7z8Qkqbk1O1kc1IOracjKfNJS+y6LTamy6weM3g
tIMHI65PkxpRzN36DV9uCN5dMwFzJ73DWHp1b0acnDIigkl6u5zp6orAJVWRjyQX
nmEd3/IOvdxaubAoAvboNS5CyVb4yS9xshWWMbH6AulKJv3Glca1Aa7QuSpBoN8v
wy4c9+umzqRgzgUJUe1xwN9P49oBNhJpgBSu8MUlgBA4IOc3rDl/Tw0b5KCFVfkH
yHkp8n6MP8VsRrzXTC6Kx0vdjIkAO8SUeylVJczAcVSyHIo6/JUJCVDeFLSTVymh
EGWJ7zX2iRhUbssJ6/izQTTQyCH3YIyZ5QtqByWuX2U7ZrfkqS3/EnBW1Q+j+gPF
Z2yW8iT6k0iENw6s8psE9czexuywa/Lttz94IyNlOQ8rJTiQqB9wLaAvg9hvUk7a
kuspL+JGIZkrL3ouCeO/VA6xnaP+Q7nR8geWBRb8zKGHmtWrb5Gwmt6t+vTnCC2l
olIDebrnnxwfBQhEJ5219W+M1pBpjiTpqK/UdBd92A4+sOOhOD0=
=FRGg
-----END PGP SIGNATURE-----
Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull hmm updates from Jason Gunthorpe:
"This is more cleanup and consolidation of the hmm APIs and the very
strongly related mmu_notifier interfaces. Many places across the tree
using these interfaces are touched in the process. Beyond that a
cleanup to the page walker API and a few memremap related changes
round out the series:
- General improvement of hmm_range_fault() and related APIs, more
documentation, bug fixes from testing, API simplification &
consolidation, and unused API removal
- Simplify the hmm related kconfigs to HMM_MIRROR and DEVICE_PRIVATE,
and make them internal kconfig selects
- Hoist a lot of code related to mmu notifier attachment out of
drivers by using a refcount get/put attachment idiom and remove the
convoluted mmu_notifier_unregister_no_release() and related APIs.
- General API improvement for the migrate_vma API and revision of its
only user in nouveau
- Annotate mmu_notifiers with lockdep and sleeping region debugging
Two series unrelated to HMM or mmu_notifiers came along due to
dependencies:
- Allow pagemap's memremap_pages family of APIs to work without
providing a struct device
- Make walk_page_range() and related use a constant structure for
function pointers"
* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (75 commits)
libnvdimm: Enable unit test infrastructure compile checks
mm, notifier: Catch sleeping/blocking for !blockable
kernel.h: Add non_block_start/end()
drm/radeon: guard against calling an unpaired radeon_mn_unregister()
csky: add missing brackets in a macro for tlb.h
pagewalk: use lockdep_assert_held for locking validation
pagewalk: separate function pointers from iterator data
mm: split out a new pagewalk.h header from mm.h
mm/mmu_notifiers: annotate with might_sleep()
mm/mmu_notifiers: prime lockdep
mm/mmu_notifiers: add a lockdep map for invalidate_range_start/end
mm/mmu_notifiers: remove the __mmu_notifier_invalidate_range_start/end exports
mm/hmm: hmm_range_fault() infinite loop
mm/hmm: hmm_range_fault() NULL pointer bug
mm/hmm: fix hmm_range_fault()'s handling of swapped out pages
mm/mmu_notifiers: remove unregister_no_release
RDMA/odp: remove ib_ucontext from ib_umem
RDMA/odp: use mmu_notifier_get/put for 'struct ib_ucontext_per_mm'
RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
RDMA/mlx5: Use ib_umem_start instead of umem.address
...
This patch adds a counter for credit waits to assist field debugging.
Link: https://lore.kernel.org/r/20190911113047.126040.10857.stgit@awfm-01.aw.intel.com
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
To resolve dependencies in following patches
mlx5_ib.h conflict resolved by keeing both hunks
Linux 5.3-rc8
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
At this point the ucontext is only being stored to access the ib_device,
so just store the ib_device directly instead. This is more natural and
logical as the umem has nothing to do with the ucontext.
Link: https://lore.kernel.org/r/20190806231548.25242-8-jgg@ziepe.ca
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This is a significant simplification, no extra list is kept per FD, and
the interval tree is now shared between all the ucontexts, reducing
overhead if there are multiple ucontexts active.
Link: https://lore.kernel.org/r/20190806231548.25242-7-jgg@ziepe.ca
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe says:
====================
This is a collection of general cleanups for ODP to clarify some of the
flows around umem creation and use of the interval tree.
====================
The branch is based on v5.3-rc5 due to dependencies
* odp_fixes:
RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
RDMA/mlx5: Use ib_umem_start instead of umem.address
RDMA/core: Make invalidate_range a device operation
RDMA/odp: Use kvcalloc for the dma_list and page_list
RDMA/odp: Check for overflow when computing the umem_odp end
RDMA/odp: Provide ib_umem_odp_release() to undo the allocs
RDMA/odp: Split creating a umem_odp from ib_umem_get
RDMA/odp: Make the three ways to create a umem_odp clear
RMDA/odp: Consolidate umem_odp initialization
RDMA/odp: Make it clearer when a umem is an implicit ODP umem
RDMA/odp: Iterate over the whole rbtree directly
RDMA/odp: Use the common interval tree library instead of generic
RDMA/mlx5: Fix MR npages calculation for IB_ACCESS_HUGETLB
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The callback function 'invalidate_range' is implemented in a driver so the
place for it is in the ib_device_ops structure and not in ib_ucontext.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Guy Levi <guyle@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Link: https://lore.kernel.org/r/20190819111710.18440-11-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Since the page size can be extended in the ODP case by IB_ACCESS_HUGETLB
the existing overflow checks done by ib_umem_get() are not
sufficient. Check for overflow again.
Further, remove the unchecked math from the inlines and just use the
precomputed value stored in the interval_tree_node.
Link: https://lore.kernel.org/r/20190819111710.18440-9-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This is the last creation API that is overloaded for both, there is very
little code sharing and a driver has to be specifically ready for a
umem_odp to be created to use the odp version.
Link: https://lore.kernel.org/r/20190819111710.18440-7-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The three paths to build the umem_odps are kind of muddled, they are:
- As a normal ib_mr umem
- As a child in an implicit ODP umem tree
- As the root of an implicit ODP umem tree
Only the first two are actually umem's, the last is an abuse.
The implicit case can only be triggered by explicit driver request, it
should never be co-mingled with the normal case. While we are here, make
sensible function names and add some comments to make this clearer.
Link: https://lore.kernel.org/r/20190819111710.18440-6-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Implicit ODP umems are special, they don't have any page lists, they don't
exist in the interval tree and they are never DMA mapped.
Instead of trying to guess this based on a zero length use an explicit
flag.
Further, do not allow non-implicit umems to be 0 size.
Link: https://lore.kernel.org/r/20190819111710.18440-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
ODP is working with userspace VA's in the interval tree which always fit
into an unsigned long, so we can use the common code.
This comes at a cost of a 16 byte increase in ib_umem_odp struct size due
to storing the interval tree start/last in addition to the umem
addr/length. However these values were computed and are performance
critical for the interval lookup, so this seems like a worthwhile trade
off.
Removes 2k of .text from the kernel.
Link: https://lore.kernel.org/r/20190819111710.18440-2-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
task_active_pid_ns() is wrong API to check PID namespace because it
posses some restrictions and return PID namespace where the process
was allocated. It created mismatches with current namespace, which
can be different.
Rewrite whole rdma_is_visible_in_pid_ns() logic to provide reliable
results without any relation to allocated PID namespace.
Fixes: 8be565e65f ("RDMA/nldev: Factor out the PID namespace check")
Fixes: 6a6c306a09 ("RDMA/restrack: Make is_visible_in_pid_ns() as an API")
Reviewed-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20190815083834.9245-4-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>
In order to improve readability, add ib_port_phys_state enum to replace
the use of magic numbers.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Andrew Boyer <aboyer@tobark.org>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Acked-by: Bernard Metzler <bmt@zurich.ibm.com>
Link: https://lore.kernel.org/r/20190807103138.17219-2-kamalheib1@gmail.com
Signed-off-by: Doug Ledford <dledford@redhat.com>
Send and Receive completion is handled on a single CPU selected at
the time each Completion Queue is allocated. Typically this is when
an initiator instantiates an RDMA transport, or when a target
accepts an RDMA connection.
Some ULPs cannot open a connection per CPU to spread completion
workload across available CPUs and MSI vectors. For such ULPs,
provide an API that allows the RDMA core to select a completion
vector based on the device's complement of available comp_vecs.
ULPs that invoke ib_alloc_cq() with only comp_vector 0 are converted
to use the new API so that their completion workloads interfere less
with each other.
Suggested-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Cc: <linux-cifs@vger.kernel.org>
Cc: <v9fs-developer@lists.sourceforge.net>
Link: https://lore.kernel.org/r/20190729171923.13428.52555.stgit@manet.1015granger.net
Signed-off-by: Doug Ledford <dledford@redhat.com>
Due to the complexity of client->remove() callbacks it is desirable to not
hold any locks while calling them. Remove the last one by tracking only
the highest client ID and running backwards from there over the xarray.
Since the only purpose of that lock was to protect the linked list, we can
drop the lock.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20190731081841.32345-3-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>
lockdep reports:
WARNING: possible circular locking dependency detected
modprobe/302 is trying to acquire lock:
0000000007c8919c ((wq_completion)ib_cm){+.+.}, at: flush_workqueue+0xdf/0x990
but task is already holding lock:
000000002d3d2ca9 (&device->client_data_rwsem){++++}, at: remove_client_context+0x79/0xd0 [ib_core]
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (&device->client_data_rwsem){++++}:
down_read+0x3f/0x160
ib_get_net_dev_by_params+0xd5/0x200 [ib_core]
cma_ib_req_handler+0x5f6/0x2090 [rdma_cm]
cm_process_work+0x29/0x110 [ib_cm]
cm_req_handler+0x10f5/0x1c00 [ib_cm]
cm_work_handler+0x54c/0x311d [ib_cm]
process_one_work+0x4aa/0xa30
worker_thread+0x62/0x5b0
kthread+0x1ca/0x1f0
ret_from_fork+0x24/0x30
-> #1 ((work_completion)(&(&work->work)->work)){+.+.}:
process_one_work+0x45f/0xa30
worker_thread+0x62/0x5b0
kthread+0x1ca/0x1f0
ret_from_fork+0x24/0x30
-> #0 ((wq_completion)ib_cm){+.+.}:
lock_acquire+0xc8/0x1d0
flush_workqueue+0x102/0x990
cm_remove_one+0x30e/0x3c0 [ib_cm]
remove_client_context+0x94/0xd0 [ib_core]
disable_device+0x10a/0x1f0 [ib_core]
__ib_unregister_device+0x5a/0xe0 [ib_core]
ib_unregister_device+0x21/0x30 [ib_core]
mlx5_ib_stage_ib_reg_cleanup+0x9/0x10 [mlx5_ib]
__mlx5_ib_remove+0x3d/0x70 [mlx5_ib]
mlx5_ib_remove+0x12e/0x140 [mlx5_ib]
mlx5_remove_device+0x144/0x150 [mlx5_core]
mlx5_unregister_interface+0x3f/0xf0 [mlx5_core]
mlx5_ib_cleanup+0x10/0x3a [mlx5_ib]
__x64_sys_delete_module+0x227/0x350
do_syscall_64+0xc3/0x6a4
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Which is due to the read side of the client_data_rwsem being obtained
recursively through a work queue flush during cm client removal.
The lock is being held across the remove in remove_client_context() so
that the function is a fence, once it returns the client is removed. This
is required so that the two callers do not proceed with destruction until
the client completes removal.
Instead of using client_data_rwsem use the existing device unregistration
refcount and add a similar client unregistration (client->uses) refcount.
This will fence the two unregistration paths without holding any locks.
Cc: <stable@vger.kernel.org>
Fixes: 921eab1143 ("RDMA/devices: Re-organize device.c locking")
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20190731081841.32345-2-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>
The fix for IB port statistics initialization ("IB/core: Fix querying
total rdma stats") is needed before we take a follow-on patch to
for-next.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Now that IB core supports RDMA device binding with specific net namespace,
enable IB core to accept netlink commands in non init_net namespaces.
This is done by having per net namespace netlink socket.
At present only netlink device handling client RDMA_NL_NLDEV supports
device handling in multiple net namespaces. Hence do not accept netlink
messages for other clients in non init_net net namespaces.
Link: https://lore.kernel.org/r/20190723070205.6247-1-leon@kernel.org
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When an OPFN request is flushed, the request is completed without
unreserving itself from the send queue. Subsequently, when a new
request is post sent, the following warning will be triggered:
WARNING: CPU: 4 PID: 8130 at rdmavt/qp.c:1761 rvt_post_send+0x72a/0x880 [rdmavt]
Call Trace:
[<ffffffffbbb61e41>] dump_stack+0x19/0x1b
[<ffffffffbb497688>] __warn+0xd8/0x100
[<ffffffffbb4977cd>] warn_slowpath_null+0x1d/0x20
[<ffffffffc01c941a>] rvt_post_send+0x72a/0x880 [rdmavt]
[<ffffffffbb4dcabe>] ? account_entity_dequeue+0xae/0xd0
[<ffffffffbb61d645>] ? __kmalloc+0x55/0x230
[<ffffffffc04e1a4c>] ib_uverbs_post_send+0x37c/0x5d0 [ib_uverbs]
[<ffffffffc04e5e36>] ? rdma_lookup_put_uobject+0x26/0x60 [ib_uverbs]
[<ffffffffc04dbce6>] ib_uverbs_write+0x286/0x460 [ib_uverbs]
[<ffffffffbb6f9457>] ? security_file_permission+0x27/0xa0
[<ffffffffbb641650>] vfs_write+0xc0/0x1f0
[<ffffffffbb64246f>] SyS_write+0x7f/0xf0
[<ffffffffbbb74ddb>] system_call_fastpath+0x22/0x27
This patch fixes the problem by moving rvt_qp_wqe_unreserve() into
rvt_qp_complete_swqe() to simplify the code and make it less
error-prone.
Fixes: ca95f802ef ("IB/hfi1: Unreserve a reserved request when it is completed")
Link: https://lore.kernel.org/r/20190715164528.74174.31364.stgit@awfm-01.aw.intel.com
Cc: <stable@vger.kernel.org>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
5.4-rc1 will have new compile time debugging to test that headers can be
compiled stand alone. Many rdma headers are already broken and excluded
from the mechanism, however to avoid compile failures during the merge
window fix enough so that the newly added header compiles clean.
Fixes: 413d334750 ("RDMA/counter: Add set/clear per-port auto mode support")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Mark Zhang <markz@mellanox.com>
Userspace expects the IB_TM_CAP_RC bit to indicate that the device
supports RC transport tag matching with rendezvous offload. However the
firmware splits this into two capabilities for eager and rendezvous tag
matching.
Only if the FW supports both modes should userspace be told the tag
matching capability is available.
Cc: <stable@vger.kernel.org> # 4.13
Fixes: eb76189435 ("IB/mlx5: Fill XRQ capabilities")
Signed-off-by: Danit Goldberg <danitg@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch adds the ability to return the hwstats of per-port default
counters (which can also be queried through sysfs nodes).
Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Provide an option to allow users to manually bind a qp with a counter
through RDMA netlink. Limit it to users with ADMIN capability only.
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
In manual mode a QP is bound to a counter manually. If counter is not
specified then a new one will be allocated.
Manual mode is enabled when user binds a QP, and disabled when the last
manually bound QP is unbound.
When auto-mode is turned off and there are counters left, manual mode is
enabled so that the user is able to access these counters.
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Since a QP can only be bound to one counter, then if it is bound to a
separate counter, for backward compatibility purpose, the statistic value
must be:
* stat of default counter
+ stat of all running allocated counters
+ stat of all deallocated counters (history stats)
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch adds the ability to return all available counters together with
their properties and hwstats.
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
In auto mode all QPs belong to one category are bind automatically to a
single counter set. Currently only "qp type" is supported.
In this mode the qp counter is set in RST2INIT modification, and when a qp
is destroyed the counter is unbound.
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add an API to support set/clear per-port auto mode.
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Introduce statistic counter as a new resource. It allows a user to monitor
specific objects (e.g., QPs) by binding to a counter.
In some cases a user counter resource is created with task other then
"current", because its creation is done as part of rdmatool call.
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add some helper functions to hide struct rvt_swqe details.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Historically rdmavt destroy_ah() has returned an -EBUSY when the AH has a
non-zero reference count. IBTA 11.2.2 notes no such return value or error
case:
Output Modifiers:
- Verb results:
- Operation completed successfully.
- Invalid HCA handle.
- Invalid address handle.
ULPs never test for this error and this will leak memory.
The reference count exists to allow for driver independent progress
mechanisms to process UD SWQEs in parallel with post sends. The SWQE will
hold a reference count until the UD SWQE completes and then drops the
reference.
Fix by removing need to reference count the AH. Add a UD specific
allocation to each SWQE entry to cache the necessary information for
independent progress. Copy the information during the post send
processing.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When a completion queue is full, the associated queue pairs are not put
into the error state. According to the IBTA specification, this is a
violation.
Quote from IBTA spec:
C9-218: A Requester Class F error occurs when the CQ is inaccessible or
full and an attempt is made to complete a WQE. The Affected QP shall be
moved to the error state and affiliated asynchronous errors generated as
described in 11.6.3.1 Affiliated Asynchronous Events on page 678. The
current WQE and any subsequent WQEs are left in an unknown state.
C11-37: The CI shall generate a CQ Error when a CQ overrun is
detected. This condition will result in an Affiliated Asynchronous Error
for any associated Work Queues when they attempt to use that
CQ. Completions can no longer be added to the CQ. It is not guaranteed
that completions present in the CQ at the time the error occurred can be
retrieved. Possible causes include a CQ overrun or a CQ protection error.
Put the qp in error state when cq is full. Implement a state called full
to continue to put other associated QPs in error state.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Kamenee Arumugam <kamenee.arumugam@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Usage of single lock prevents fetching posted and processing receive work
queue entries from progressing simultaneously and impacts overall
performance.
Fracture the single lock used for posting and processing Receive Work
Queue Entries (RWQEs) to allow the circular buffer to be filled and
emptied at the same time. Two new spinlocks - one for the producers and
one for the consumers used for posting and processing RWQEs simultaneously
and the two indices are define on two different cache lines. The threshold
count is used to avoid reading other index in different cache line every
time.
Signed-off-by: Harish Chegondi <harish.chegondi@intel.com>
Signed-off-by: Kamenee Arumugam <kamenee.arumugam@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The rvt_rwqe and rvt_rwq struct elements are shared between rdmavt and the
providers but are not in uapi directory. As per the comment in
https://marc.info/?l=linux-rdma&m=152296522708522&w=2, The hfi1 driver and
the rdma core driver are not using shared structures in the uapi
directory.
Move rvt_rwqe and rvt_rwq struct into rvt-abi.h header in uapi directory.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Kamenee Arumugam <kamenee.arumugam@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The rvt_cq_wc struct elements are shared between rdmavt and the providers
but not in uapi directory. As per the comment in
https://marc.info/?l=linux-rdma&m=152296522708522&w=2 The hfi1 driver and
the rdma core driver are not using shared structures in the uapi
directory.
In that case, move rvt_cq_wc struct into the rvt-abi.h header file and
create a rvt_k_cq_w for the kernel completion queue.
Signed-off-by: Kamenee Arumugam <kamenee.arumugam@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAl0Os1seHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGtx4H/j6i482XzcGFKTBm
A7mBoQpy+kLtoUov4EtBAR62OuwI8rsahW9di37QKndPoQrczWaKBmr3De6LCdPe
v3pl3O6wBbvH5ru+qBPFX9PdNbDvimEChh7LHxmMxNQq3M+AjZAZVJyfpoiFnx35
Fbge+LZaH/k8HMwZmkMr5t9Mpkip715qKg2o9Bua6dkH0AqlcpLlC8d9a+HIVw/z
aAsyGSU8jRwhoAOJsE9bJf0acQ/pZSqmFp0rDKqeFTSDMsbDRKLGq/dgv4nW0RiW
s7xqsjb/rdcvirRj3rv9+lcTVkOtEqwk0PVdL9WOf7g4iYrb3SOIZh8ZyViaDSeH
VTS5zps=
=huBY
-----END PGP SIGNATURE-----
Merge tag 'v5.2-rc6' into rdma.git for-next
For dependencies in next patches.
Resolve conflicts:
- Use uverbs_get_cleared_udata() with new cq allocation flow
- Continue to delete nes despite SPDX conflict
- Resolve list appends in mlx5_command_str()
- Use u16 for vport_rule stuff
- Resolve list appends in struct ib_client
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
For all string attributes for which we don't currently accept the element
as input, we only use it as output, set the string length to
RDMA_NLDEV_ATTR_EMPTY_STRING which is defined as 1. That way we will only
accept a null string for that element. This will prevent someone from
writing a new input routine that uses the element without also updating
the policy to have a valid value.
Also while there, make sure the existing entries that are valid have the
correct policy, if not, correct the policy. Remove unnecessary checks
for nla_strlcpy() overflow once the policy has been set correctly.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
IB_WR_REG_SIG_MR is not needed after IB_WR_REG_MR_INTEGRITY
was used.
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Replace the old signature handover API with the new one. The new API
simplifes PI handover code complexity for ULPs and improve performance.
For RW API it will reduce the maximum number of work requests per task
and the need of dealing with multiple MRs (and their registrations and
invalidations) per task. All the mappings and registration of the data
and the protection buffers is done by the LLD using a single WR and a
special MR type (IB_MR_TYPE_INTEGRITY) for the PI handover operation.
The setup of the tested benchmark (using iSER ULP):
- 2 servers with 24 cores (1 initiator and 1 target)
- ConnectX-4/ConnectX-5 adapters
- 24 target sessions with 1 LUN each
- ramdisk backstore
- PI active
Performance results running fio (24 jobs, 128 iodepth) using
write_generate=1 and read_verify=1 (w/w.o patch):
bs IOPS(read) IOPS(write)
---- ---------- ----------
512 1243.3K/1182.3K 1725.1K/1680.2K
4k 571233/528835 743293/748259
32k 72388/71086 71789/93573
Using write_generate=0 and read_verify=0 (w/w.o patch):
bs IOPS(read) IOPS(write)
---- ---------- ----------
512 1572.1K/1427.2K 1823.5K/1724.3K
4k 921992/916194 753772/768267
32k 75052/73960 73180/95484
There is a performance degradation when writing big block sizes.
Degradation is caused by the complexity of combining multiple
indirections and perform RDMA READ operation from it. This will be
fixed in the following patches by reducing the indirections if
possible.
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Protect the case that a ULP tries to allocate a QP with signature
enabled flag while the LLD doesn't support this feature.
While we're here, also move integrity_en attribute from mlx5_qp to
ib_qp as a preparation for adding new integrity API to the rw-API
(that is part of ib_core module).
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Rename IB_QP_CREATE_SIGNATURE_EN to IB_QP_CREATE_INTEGRITY_EN
and IB_DEVICE_SIGNATURE_HANDOVER to IB_DEVICE_INTEGRITY_HANDOVER.
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This is a preparation for adding new signature API to the rw-API.
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This new WR will be used to perform PI (protection information) handover
using the new API. Using the new API, the user will post a single WR that
will internally perform all the needed actions to complete PI operation.
This new WR will use a memory region that was allocated as
IB_MR_TYPE_INTEGRITY and was mapped using ib_map_mr_sg_pi to perform the
registration. In the old API, in order to perform a signature handover
operation, each ULP should perform the following:
1. Map and register the data buffers.
2. Map and register the protection buffers.
3. Post a special reg WR to configure the signature handover operation
layout.
4. Invalidate the signature memory key.
5. Invalidate protection buffers memory key.
6. Invalidate data buffers memory key.
In the new API, the mapping of both data and protection buffers is
performed using a single call to ib_map_mr_sg_pi function. Also the
registration of the buffers and the configuration of the signature
operation layout is done by a single new work request called
IB_WR_REG_MR_INTEGRITY.
This patch implements this operation for mlx5 devices that are capable to
offload data integrity generation/validation while performing the actual
buffer transfer.
This patch will not remove the old signature API that is used by the iSER
initiator and target drivers. This will be done in the future.
In the internal implementation, for each IB_WR_REG_MR_INTEGRITY work
request, we are using a single UMR operation to register both data and
protection buffers using KLM's.
Afterwards, another UMR operation will describe the strided block format.
These will be followed by 2 SET_PSV operations to set the memory/wire
domains initial signature parameters passed by the user.
In the end of the whole transaction, only the signature memory key
(the one that exposed for the RDMA operation) will be invalidated.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
PI offload (protection information) is a feature that each RDMA provider
can implement differently. Thus, introduce new device attribute to define
the maximal length of the page list for PI fast registration operation. For
example, mlx5 driver uses a single internal MR to map both data and
protection SGL's, so it's equal to max_fast_reg_page_list_len / 2.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This element will describe the needed characteristics for the signature
operation per signature enabled memory region (type IB_MR_TYPE_INTEGRITY).
Also add meta_length attribute to ib_sig_attrs structure for saving the
mapped metadata length (needed for the new API implementation).
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This function will map the previously dma mapped SG lists for PI
(protection information) and data to an appropriate memory region for
future registration.
The given MR must be allocated as IB_MR_TYPE_INTEGRITY.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This is a preparation for signature verbs API re-design. In the new
design a single MR with IB_MR_TYPE_INTEGRITY type will be used to perform
the needed mapping for data integrity operations.
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This is a preparation for the signature verbs API change. This change is
needed since the MR type will define, in the upcoming patches, the need
for allocating internal resources in LLD for signature handover related
operations. It will also help to make sure that signature related
functions are called with an appropriate MR type and fail otherwise.
Also introduce new mr types IB_MR_TYPE_USER, IB_MR_TYPE_DMA and
IB_MR_TYPE_DM for correctness.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Ease the exhausted ib_verbs.h file and make the code more readable.
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Convert all completions to use the new completion routine that
fixes a race between post send and completion where fields from
a SWQE can be read after SWQE has been freed.
This patch also addresses issues reported in
https://marc.info/?l=linux-kernel&m=155656897409107&w=2.
The reserved operation path has no need for any barrier.
The barrier for the other path is addressed by the
smp_load_acquire() barrier.
Cc: Andrea Parri <andrea.parri@amarulasolutions.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
There is opencoded send completion logic all over all
the drivers.
We need to convert to this routine to enforce ordering
issues for completions. This routine fixes an ordering
issue where the read of the SWQE fields necessary for creating
the completion can race with a post send if the post send catches
a send queue at the edge of being full. Is is possible in that situation
to read SWQE fields that are being written.
This new routine insures that SWQE fields are read prior to advancing
the index that post send uses to determine queue fullness.
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
All callers of destroy WQ are always success and there is no need
to check their return value, so convert destroy_wq to be void.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Update the struct ib_client for all modules exporting cdevs related to the
ibdevice to also implement RDMA_NLDEV_CMD_GET_CHARDEV. All cdevs are now
autoloadable and discoverable by userspace over netlink instead of relying
on sysfs.
uverbs also exposes the DRIVER_ID for drivers that are able to support
driver id binding in rdma-core.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Allow userspace to issue a netlink query against the ib_device for
something like "uverbs" and get back the char dev name, inode major/minor,
and interface ABI information for "uverbs0".
Since we are now in netlink this can also trigger a module autoload to
make the uverbs device come into existence.
Largely this will let us replace searching and reading inside sysfs to
setup devices, and provides an alternative (using driver_id) to device
name based provider binding for things like rxe.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This enum is exposed over the sysfs file 'node_type' and over netlink via
RDMA_NLDEV_ATTR_DEV_NODE_TYPE, so declare it in the uapi headers.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Ensure that CQ is allocated and freed by IB/core and not by drivers.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Tested-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Like all other destroy commands, .destroy_cq() call is not supposed
to fail. In all flows, the attempt to return earlier caused to memory
leaks.
This patch converts .destroy_cq() to do not return any errors.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: Gal Pressman <galpress@amazon.com>
Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This more closely follows how other subsytems work, with owner being a
member of the structure containing the function pointers.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
No reason for every driver to emit code to set this, just make it part of
the driver's existing static const ops structure.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
No reason for every driver to emit code to set this, just make it part of
the driver's existing static const ops structure.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Another round of SPDX header file fixes for 5.2-rc4
These are all more "GPL-2.0-or-later" or "GPL-2.0-only" tags being
added, based on the text in the files. We are slowly chipping away at
the 700+ different ways people tried to write the license text. All of
these were reviewed on the spdx mailing list by a number of different
people.
We now have over 60% of the kernel files covered with SPDX tags:
$ ./scripts/spdxcheck.py -v 2>&1 | grep Files
Files checked: 64533
Files with SPDX: 40392
Files with errors: 0
I think the majority of the "easy" fixups are now done, it's now the
start of the longer-tail of crazy variants to wade through.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
iG0EABECAC0WIQT0tgzFv3jCIUoxPcsxR9QN2y37KQUCXPuGTg8cZ3JlZ0Brcm9h
aC5jb20ACgkQMUfUDdst+ykBvQCg2SG+HmDH+tlwKLT/q7jZcLMPQigAoMpt9Uuy
sxVEiFZo8ZU9v1IoRb1I
=qU++
-----END PGP SIGNATURE-----
Merge tag 'spdx-5.2-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull yet more SPDX updates from Greg KH:
"Another round of SPDX header file fixes for 5.2-rc4
These are all more "GPL-2.0-or-later" or "GPL-2.0-only" tags being
added, based on the text in the files. We are slowly chipping away at
the 700+ different ways people tried to write the license text. All of
these were reviewed on the spdx mailing list by a number of different
people.
We now have over 60% of the kernel files covered with SPDX tags:
$ ./scripts/spdxcheck.py -v 2>&1 | grep Files
Files checked: 64533
Files with SPDX: 40392
Files with errors: 0
I think the majority of the "easy" fixups are now done, it's now the
start of the longer-tail of crazy variants to wade through"
* tag 'spdx-5.2-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (159 commits)
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 450
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 449
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 448
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 446
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 445
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 444
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 443
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 442
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 441
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 440
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 438
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 437
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 436
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 435
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 434
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 433
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 432
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 431
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 430
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 429
...
Based on 1 normalized pattern(s):
this program is free software you can redistribute it and or modify
it under the terms and conditions of the gnu general public license
version 2 as published by the free software foundation this program
is distributed in the hope it will be useful but without any
warranty without even the implied warranty of merchantability or
fitness for a particular purpose see the gnu general public license
for more details
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-only
has been chosen to replace the boilerplate/reference in 263 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Allison Randal <allison@lohutok.net>
Reviewed-by: Alexios Zavras <alexios.zavras@intel.com>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190529141901.208660670@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Kernel destroy CQ flows can't fail and the returned value of
ib_destroy_cq() is not interested in those flows.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This value has always been set to PAGE_SHIFT in the core code, the only
thing that does differently was the ODP path. Move the value into the ODP
struct and still use it for ODP, but change all the non-ODP things to just
use PAGE_SHIFT/PAGE_SIZE/PAGE_MASK directly.
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
SRP logic used device name and port index as symlink to relevant
kobject. If the IB device is renamed then the prior name will be re-used
by the next device plugged in and sysfs will panic as SRP will try to
re-use the same name.
mlx5_ib: Mellanox Connect-IB Infiniband driver v5.0-0
sysfs: cannot create duplicate filename '/class/infiniband_srp/srp-mlx5_0-1'
CPU: 3 PID: 1107 Comm: modprobe Not tainted 5.1.0-for-upstream-perf-2019-05-12_15-09-52-87 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Call Trace:
dump_stack+0x5a/0x73
sysfs_warn_dup+0x58/0x70
sysfs_do_create_link_sd.isra.2+0xa3/0xb0
device_add+0x33f/0x660
srp_add_one+0x301/0x4f0 [ib_srp]
add_client_context+0x99/0xe0 [ib_core]
enable_device_and_get+0xd1/0x1b0 [ib_core]
ib_register_device+0x533/0x710 [ib_core]
? mutex_lock+0xe/0x30
__mlx5_ib_add+0x23/0x70 [mlx5_ib]
mlx5_add_device+0x4e/0xd0 [mlx5_core]
mlx5_register_interface+0x85/0xc0 [mlx5_core]
? 0xffffffffa0791000
do_one_initcall+0x4b/0x1cb
? kmem_cache_alloc_trace+0xc6/0x1d0
? do_init_module+0x22/0x21f
do_init_module+0x5a/0x21f
load_module+0x17f2/0x1ca0
? m_show+0x1c0/0x1c0
__do_sys_finit_module+0x94/0xe0
do_syscall_64+0x48/0x120
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7f157cce10d9
The module load/unload sequence was used to trigger such kernel panic:
sudo modprobe ib_srp
sudo modprobe -r mlx5_ib
sudo modprobe -r mlx5_core
sudo modprobe mlx5_core
Have SRP track the name of the core device so that it can't have a name
collision.
Fixes: d21943dd19 ("RDMA/core: Implement IB device rename function")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add EFA driver ID to the IOCTL interface uapi. This patch also adds
unspecified node/transport type that will be used by EFA (usnic is left
unchanged as it's already part of our ABI).
Signed-off-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The drivers i40iw and bnxt_re no longer dependent on the hugetlb flag. So
remove this flag from ib_umem structure.
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This helper iterates over a DMA-mapped SGL and returns contiguous memory
blocks aligned to a HW supported page size.
Suggested-by: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This helper iterates through the SG list to find the best page size to use
from a bitmap of HW supported page sizes. Drivers that support multiple
page sizes, but not mixed sizes in an MR can use this API.
Suggested-by: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When there is active traffic through a GID, a QP/AH holds reference to
this GID entry. RoCE GID entry holds reference to its attached
netdevice. Due to this when netdevice is deleted by admin user, its
refcount is not dropped.
Therefore, while deleting RoCE GID, wait for all GID attribute's netdev
users to finish accessing netdev in rcu context. Once all users done
accessing it, release the netdev refcount.
Signed-off-by: Huy Nguyen <huyn@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>
To access the netdevice of the GID attribute, use an existing API
rdma_read_gid_attr_ndev_rcu().
This further reduces dependency on open access to netdevice of GID
attribute.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Instead of RoCE drivers figuring out vlan, smac fields while working on
QP/AH, provide a helper routine to read the L2 fields such as vlan_id and
source mac address.
This moves logic from mlx5 driver to core for wider usage for RoCE ports.
This is a preparation patch to allow detaching netdev in subsequent patch.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Integrate iw_cm_verbs data members into ib_device_ops and ib_device
structs, this is done to achieve the following:
1) Avoid memory related bugs durring error unwind
2) Make the code more cleaner
3) Reduce code duplication
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Jason Gunthorpe says:
====================
Upon review it turns out there are some long standing problems in BAR
mapping area:
* BAR pages intended for read-only can be switched to writable via mprotect.
* Missing use of rdma_user_mmap_io for the mlx5 clock BAR page.
* Disassociate causes SIGBUS when touching the pages.
* CPU pages are being mapped through to the process via remap_pfn_range
instead of the more appropriate vm_insert_page, causing weird behaviors
during disassociation.
This series adds the missing VM_* flag manipulation, adds faulting a zero
page for disassociation and revises the CPU page mappings to use
vm_insert_page.
====================
For dependencies this branch is based on for-rc from
git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git
* branch 'rdma_mmap':
RDMA: Remove rdma_user_mmap_page
RDMA/mlx5: Use get_zeroed_page() for clock_info
RDMA/ucontext: Fix regression with disassociate
RDMA/mlx5: Use rdma_user_map_io for mapping BAR pages
RDMA/mlx5: Do not allow the user to write to the clock page
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Upon further research drivers that want this should simply call the core
function vm_insert_page(). The VMA holds a reference on the page and it
will be automatically freed when the last reference drops. No need for
disassociate to sequence the cleanup.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The reference count adjustments on reference count completion
are open coded throughout.
Add a routine to do all reference count adjustments and use.
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The currently include file ordering for rdmavt headers has an
ab/ba include issue the precludes using inlines from rdma_vt.h
in rdmavt_qp.h.
At the heart of the issue is that rdma_vt.h includes rdmavt_qp.h.
Fix the ordering issue by adjusting rdma_vt.h to not require rdmavt_qp.h
and move qp related inlines to rdmavt_qp.h.
Additionally, promote rvt_mmap_info to rdma_vt.h since it is shared
by rdmavt_cq.h and rdmavt_qp.h.
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch fixes miscellaneous comment errors.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Convert SRQ allocation from drivers to be in the IB/core
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Simplify drivers by ensuring lifetime of ib_ah object. The changes
in .create_ah() go hand in hand with relevant update in .destroy_ah().
We will use this opportunity and convert .destroy_ah() to don't fail, as
it was suggested a long time ago, because there is nothing to do in case
of failure during destroy.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
AH objects are allocated in atomic context and those allocations should
be done with GFP_ATOMIC.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The ucontext and ufile should not be accessed via the uobject, all these
cases have an attrs so use that instead.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Combine contiguous regions of PAGE_SIZE pages into single scatter list
entry while building the scatter table for a umem. This minimizes the
number of the entries in the scatter list and reduces the DMA mapping
overhead, particularly with the IOMMU.
Set default max_seg_size in core for IB devices to 2G and do not combine
if we exceed this limit.
Also, purge npages in struct ib_umem as we now DMA map the umem SGL with
sg_nents and npage computation is not needed. Drivers should now be using
ib_umem_num_pages(), so fix the last stragglers.
Move npages tracking to ib_umem_odp as ODP drivers still need it.
Suggested-by: Jason Gunthorpe <jgg@ziepe.ca>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Acked-by: Adit Ranadive <aditr@vmware.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Tested-by: Gal Pressman <galpress@amazon.com>
Tested-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now when ib_udata is passed to all the driver's object create/destroy APIs
the ib_udata will carry the ib_ucontext for every user command. There is
no need to also pass the ib_ucontext via the functions prototypes.
Make ib_udata the only argument psssed.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The uverbs_attr_bundle with the ucontext is sent down to the drivers ib_x
destroy path as ib_udata. The next patch will use the ib_udata to free the
drivers destroy path from the dependency in 'uobject->context' as we
already did for the create path.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Pass uverbs_attr_bundle down the uobject destroy path. The next patch will
use this to eliminate the dependecy of the drivers in ib_x->uobject
pointers.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
the Attempt to use the below commit to initialize the ucontext for the
uobject destroy path has shown that the below commit is incomplete.
Parts were reverted and the ucontext set up in the uverbs_attr_bundle was
moved to rdma_lookup_get_uobject which is called from the uobj_get_XXX
macros and rdma_alloc_begin_uobject which is called when uobject is
created.
Fixes: 3d9dfd0603 ("IB/uverbs: Add ib_ucontext to uverbs_attr_bundle sent from ioctl and cmd flows")
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There is no need to perform extra comparison after boolean AND.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Introduce an API rdma_dev_access_netns() to check whether a rdma device
can be accessed from the specified net namespace or not.
Use rdma_dev_access_netns() while opening character uverbs, umad network
device and also check while rdma cm_id binds to rdma device.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Implement compatibility layer sysfs entries of ib_core so that non
init_net net namespaces can also discover rdma devices.
Each non init_net net namespace has ib_core_device created in it.
Such ib_core_device sysfs tree resembles rdma devices found in
init_net namespace.
This allows discovering rdma devices in multiple non init_net net
namespaces via sysfs entries and helpful to rdma-core userspace.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
In order to support sysfs entries in multiple net namespaces for a rdma
device, introduce a ib_core_device whose scope is limited to hold core
device and per port sysfs related entries.
This is preparation patch so that multiple ib_core_devices in each net
namespace can be created in subsequent patch who all can share ib_device.
(a) Move sysfs specific fields to ib_core_device.
(b) Make sysfs and device life cycle related routines to work on
ib_core_device.
(c) Introduce and use rdma_init_coredev() helper to initialize
coredev fields.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
"__attribute__" set of macros has been standardized, have became more
potentially portable and consistent code back in v2.6.21 by commit
82ddcb040 ("[PATCH] extend the set of "__attribute__" shortcut macros").
Moreover, nowadays checkpatch.pl warns about using __attribute__((packed))
instead of __packed.
This patch converts all the "__attribute__ ((packed))" annotations to
"__packed" within the RDMA subsystem.
Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Following the PD conversion patch, do the same for ucontext allocations.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add support for new LINK messages to allow adding and deleting rdma
interfaces. This will be used initially for soft rdma drivers which
instantiate device instances dynamically by the admin specifying a netdev
device to use. The rdma_rxe module will be the first user of these
messages.
The design is modeled after RTNL_NEWLINK/DELLINK: rdma drivers register
with the rdma core if they provide link add/delete functions. Each driver
registers with a unique "type" string, that is used to dispatch messages
coming from user space. A new RDMA_NLDEV_ATTR is defined for the "type"
string. User mode will pass 3 attributes in a NEWLINK message:
RDMA_NLDEV_ATTR_DEV_NAME for the desired rdma device name to be created,
RDMA_NLDEV_ATTR_LINK_TYPE for the "type" of link being added, and
RDMA_NLDEV_ATTR_NDEV_NAME for the net_device interface to use for this
link. The DELLINK message will contain the RDMA_NLDEV_ATTR_DEV_INDEX of
the device to delete.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Since rxe allows unregistration from other threads the rxe pointer can
become invalid any moment after ib_register_driver returns. This could
cause a user triggered use after free.
Add another driver callback to be called right after the device becomes
registered to complete any device setup required post-registration. This
callback has enough core locking to prevent the device from becoming
unregistered.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
These APIs are intended to support drivers that exist outside the usual
driver core probe()/remove() callbacks. Normally the driver core will
prevent remove() from running concurrently with probe(), once this safety
is lost drivers need more support to get the locking and lifetimes right.
ib_unregister_driver() is intended to be used during module_exit of a
driver using these APIs. It unregisters all the associated ib_devices.
ib_unregister_device_and_put() is to be used by a driver-specific removal
function (ie removal by name, removal from a netdev notifier, removal from
netlink)
ib_unregister_queued() is to be used from netdev notifier chains where
RTNL is held.
The locking is tricky here since once things become async it is possible
to race unregister with registration. This is largely solved by relying on
the registration refcount, unregistration will only ever work on something
that has a positive registration refcount - and then an unregistration
mutex serializes all competing unregistrations of the same device.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Several drivers need to find the ib_device from a given netdev. rxe needs
this at speed in an unsleepable context, so choose to implement the
translation using a RCU safe hash table.
The hash table can have a many to one mapping. This is intended to support
some future case where multiple IB drivers (ie iWarp and RoCE) connect to
the same netdevs. driver_ids will need to be different to support this.
In the process this makes the struct ib_device and ib_port_data RCU safe
by deferring their kfrees.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The associated netdev should not actually be very dynamic, so for most
drivers there is no reason for a callback like this. Provide an API to
inform the core code about the net dev affiliation and use a core
maintained data structure instead.
This allows the core code to be more aware of the ndev relationship which
will allow some new APIs based around this.
This also uses locking that makes some kind of sense, many drivers had a
confusing RCU lock, or missing locking which isn't right.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Like the other cases there no real reason to have another array just for
the cache. This larger conversion gets its own patch.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There is no reason to have three allocations of per-port data. Combine
them together and make the lifetime for all the per-port data match the
struct ib_device.
Following patches will require more port-specific data, now there is a
good place to put it.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
We have many loops iterating over all of the end port numbers on a struct
ib_device, simplify them with a for_each helper.
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There is no need to expose internals of restrack DB to IB/core.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
XArray uses internal lock for updates to XArray. This means that our
external RW lock is needed to ensure that entry is not deleted while we
are performing iteration over list.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add new general helper to get restrack entry given by ID and their
respective type.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The additions of .doit callbacks posses new access pattern to the resource
entries by some user visible index. Back then, the legacy DB was
implemented as hash because per-index access wasn't needed and XArray
wasn't accepted yet.
Acceptance of XArray together with per-index access requires the refresh
of DB implementation.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now when we have the udata passed to all the ib_xxx object creation APIs
and the additional macro 'rdma_udata_to_drv_context' to get the
ib_ucontext from ib_udata stored in uverbs_attr_bundle, we can finally
start to remove the dependency of the drivers in the
ib_xxx->uobject->context.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Helper function to get driver's context out of ib_udata wrapped in
uverbs_attr_bundle for user objects or NULL for kernel objects.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add ib_ucontext to the uverbs_attr_bundle sent down the iocl and cmd flows
as soon as the flow has ib_uobject.
In addition, remove rdma_get_ucontext helper function that is only used by
ib_umem_get.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
I had merged the hfi1-tid code into my local copy of for-next, but was
waiting on 0day testing before pushing it (I pushed it to my wip
branch). Having waited several days for 0day testing to show up, I'm
finally just going to push it out. In the meantime, though, Jason
pushed other stuff to for-next, so I needed to merge up the branches
before pushing.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Due to concurrent work by myself and Jason, a normal fast forward merge
was not possible. This brings in a number of hfi1 changes, mainly the
hfi1 TID RDMA support (roughly 10,000 LOC change), which was reviewed
and integrated over a period of days.
Signed-off-by: Doug Ledford <dledford@redhat.com>
The locking here started out with a single lock that covered everything
and then has lately veered into crazy town.
The fundamental problem is that several places need to iterate over a
linked list, but also need to drop their locks to avoid deadlock during
client callbacks.
xarray's restartable iteration offers a simple solution to the
problem. Once all the lists are xarrays we can drop locks in the places
that need that and rely on xarray to provide consistency and locking for
the data structure.
The resulting simplification is that each of the three lists has a
dedicated rwsem that must be held when working with the list it
covers. One data structure is no longer covered by multiple locks.
The sleeping semaphore is selected because the read side generally needs
to be held over something sleeping, and using RCU reader locking in those
cases is overkill.
In the process this simplifies the entire registration/unregistration flow
to be the expected list of setups and the reversed list of matching
teardowns, and the registration lock 'refcount' can now be revised to be
released after the ULPs are removed, providing a very sane semantic for
this feature.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now that we have a small ID for each client we can use xarray instead of
linearly searching linked lists for client data. This will give much
faster and scalable client data lookup, and will lets us revise the
locking scheme.
Since xarray can store 'going_down' using a mark just entirely eliminate
the struct ib_client_data and directly store the client_data value in the
xarray. However this does require a special iterator as we must still
iterate over any NULL client_data values.
Also eliminate the client_data_lock in favour of internal xarray locking.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This gives each client a unique ID and will let us move client_data to use
xarray, and revise the locking scheme.
clients have to be add/removed in strict FIFO/LIFO order as they
interdepend. To support this the client_ids are assigned to increase in
FIFO order. The existing linked list is kept to support reverse iteration
until xarray can get a reverse iteration API.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
This really has no purpose anymore, refcount can be used to tell if the
device is still registered. Keeping it around just invites mis-use.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
The PD allocations in IB/core allows us to simplify drivers and their
error flows in their .alloc_pd() paths. The changes in .alloc_pd() go hand
in had with relevant update in .dealloc_pd().
We will use this opportunity and convert .dealloc_pd() to don't fail, as
it was suggested a long time ago, failures are not happening as we have
never seen a WARN_ON print.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add new macros to be used in drivers while registering ops structure and
IB/core while calling allocation routines, so drivers won't need to
perform kzalloc/kfree in their paths.
The change in allocation stage allows us to initialize common fields prior
to calling to drivers (e.g. restrack).
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When creating many MAD agents in a short period of time, receive packet
processing can be delayed long enough to cause timeouts while new agents
are being added to the atomic notifier chain with IRQs disabled. Notifier
chain registration and unregstration is an O(n) operation. With large
numbers of MAD agents being created and destroyed simultaneously the CPUs
spend too much time with interrupts disabled.
Instead of each MAD agent registering for it's own LSM notification,
maintain a list of agents internally and register once, this registration
already existed for handling the PKeys. This list is write mostly, so a
normal spin lock is used vs a read/write lock. All MAD agents must be
checked, so a single list is used instead of breaking them down per
device.
Notifier calls are done under rcu_read_lock, so there isn't a risk of
similar packet timeouts while checking the MAD agents security settings
when notified.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This allows drivers to know the tos was actively set by the application.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Define new option in 'rdma_set_option' to override calculated QP timeout
when requested to provide QP attributes to modify a QP.
At the same time, pack tos_set to be bitfield.
Signed-off-by: Danit Goldberg <danitg@mellanox.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch integrates TID RDMA WRITE protocol into normal RDMA verbs
framework. The TID RDMA WRITE protocol is an end-to-end protocol
between the hfi1 drivers on two OPA nodes that converts a qualified
RDMA WRITE request into a TID RDMA WRITE request to avoid data copying
on the responder side.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The s_ack_queue is managed by two pointers into the ring:
r_head_ack_queue and s_tail_ack_queue. r_head_ack_queue is the index of
where the next received request is going to be placed and s_tail_ack_queue
is the entry of the request currently being processed. This works
perfectly fine for normal Verbs as the requests are processed one at a
time and the s_tail_ack_queue is not moved until the request that it
points to is fully completed.
In this fashion, s_tail_ack_queue constantly chases r_head_ack_queue and
the two pointers can easily be used to determine "queue full" and "queue
empty" conditions.
The detection of these two conditions are imported in determining when an
old entry can safely be overwritten with a new received request and the
resources associated with the old request be safely released.
When pipelined TID RDMA WRITE is introduced into this mix, things look
very different. r_head_ack_queue is still the point at which a newly
received request will be inserted, s_tail_ack_queue is still the
currently processed request. However, with pipelined TID RDMA WRITE
requests, s_tail_ack_queue moves to the next request once all TID RDMA
WRITE responses for that request have been sent. The rest of the protocol
for a particular request is managed by other pointers specific to TID RDMA
- r_tid_tail and r_tid_ack - which point to the entries for which the next
TID RDMA DATA packets are going to arrive and the request for which
the next TID RDMA ACK packets are to be generated, respectively.
What this means is that entries in the ring, which are "behind"
s_tail_ack_queue (entries which s_tail_ack_queue has gone past) are no
longer considered complete. This is where the problem is - a newly
received request could potentially overwrite a still active TID RDMA WRITE
request.
The reason why the TID RDMA pointers trail s_tail_ack_queue is that the
normal Verbs send engine uses s_tail_ack_queue as the pointer for the next
response. Since TID RDMA WRITE responses are processed by the normal Verbs
send engine, s_tail_ack_queue had to be moved to the next entry once all
TID RDMA WRITE response packets were sent to get the desired pipelining
between requests. Doing otherwise would mean that the normal Verbs send
engine would not be able to send the TID RDMA WRITE responses for the next
TID RDMA request until the current one is fully completed.
This patch introduces the s_acked_ack_queue index to point to the next
request to complete on the responder side. For requests other than TID
RDMA WRITE, s_acked_ack_queue should always be kept in sync with
s_tail_ack_queue. For TID RDMA WRITE request, it may fall behind
s_tail_ack_queue.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This patch adds the functions to build TID RDMA WRITE request.
The work request opcode, packet opcode, and packet formats for TID
RDMA WRITE protocol are also defined in this patch.
Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The RC retry timeout value is based on the estimated time for the
response packet to come back. However, for TID RDMA READ request, due
to the use of header suppression, the driver is normally not notified
for each incoming response packet until the last TID RDMA READ response
packet. Consequently, the retry timeout value should be extended to
cover the transaction time for the entire length of a segment (default
256K) instead of that for a single packet. This patch addresses the
issue by introducing new retry timer functions to account for multiple
packets and wrapper functions for backward compatibility.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This patch adds the helper functions to build the TID RDMA READ request
on the requester side. The key is to allocate TID resources (TID flow
and TID entries) and send the resource information to the responder side
along with the read request. Since the TID resources are limited, each
TID RDMA READ request has to be split into segments with a default
segment size of 256K. A software flow is allocated to track the data
transaction for each segment. The work request opcode, packet opcode, and
packet formats for TID RDMA READ protocol are also defined in this patch.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
TID entries are used by hfi1 hardware to receive data payload from
incoming packets directly into a user buffer and thus avoid data copying
by software. This patch implements the functions for TID allocation,
freeing, and programming TID RcvArray entries in hardware for kernel
clients. TID entries are managed via lists of TID groups similar to PSM.
Furthermore, to track TID resource allocation for each request, software
flows are also allocated and freed as needed. Since software flows
consume large amount of memory for tracking TID allocation and freeing,
it is generally desirable to allocate them dynamically in the send queue
and only for TID RDMA requests, but pre-allocate them for receive queue
because the send queue could have thousands of entries while the receive
queue has only a limited number of entries.
Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This patch moves some RC helper functions into a header file so that
they can be called from both RC and TID RDMA functions. In addition,
a common function for rewinding a request is created in rdmavt so that
it can be shared between qib and hfi1 driver.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Move the iwpm kdoc comments from the prototype declarations to above
the function bodies. There are no functional changes in this patch.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
A soft iwarp driver that uses the host TCP stack via a kernel mode socket
does not need port mapping. In fact, if the port map daemon, iwpmd, is
running, then iwpmd must not try and create/bind a socket to the actual
port for a soft iwarp connection, since the driver already has that socket
bound.
Yet if the soft iwarp driver wants to interoperate with hard iwarp devices
that -are- using port mapping, then the soft iwarp driver's mappings still
need to be maintained and advertised by the iwpm protocol.
This patch enhances the rdma driver<->iwcm interface to allow an iwarp
driver to specify that it does not want port mapping. The iwpm
kernel<->iwpmd interface is also enhanced to pass up this information on
map requests.
Care is taken to interoperate with the current iwpmd version (ABI version
3) and only use the new NL attributes if iwpmd supports ABI version 4.
The ABI version define has also been created in rdma_netlink.h so both
kernel and user code can share it. The iwcm and iwpmd negotiate the ABI
version to use with a new HELLO netlink message.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Tatyana Nikolova <Tatyana.E.Nikolova@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAlxXYaEeHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGkSQH/2yrfnviNPFYpZOR
QQdc71Bfhkd8m85SmWIsSebkxmi3hKFVj15sGbWXd6+0/VxjEEGvQCZpvVwJceke
LwDxtkKGg/74wAqJvlSAWxFNZ+Had4jDeoSoeQChddsBVXBBCxQx2v6ECg3o2x7W
k8Z8t4+3RijDf8fYXY9ETyO2zW8R/wgT+dnl+DPgUH7u4dxh7FzAUfc4bgZIDg+i
FzBQfbTJuz4BU7uRZ9IJiwhWKv0Iyi2DR3BY8Z1pqEpRaUMJMrCs2WGytHbTgt9e
0EtO1airbVneU4eumU/ZaF9cyEbah9HousEPnP7J09WG4s/Odxc4zE+uK1QqS2im
5Xv88is=
=dVd1
-----END PGP SIGNATURE-----
Merge tag 'v5.0-rc5' into rdma.git for-next
Linux 5.0-rc5
Needed to merge the include/uapi changes so we have an up to date
single-tree for these files. Patches already posted are also expected to
need this for dependencies.
Keeping single line wrapper functions is not useful. Hence remove the
ib_sg_dma_address() and ib_sg_dma_len() functions. This patch does not
change any functionality.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Expose XRC ODP capabilities as part of the extended device capabilities.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The ODP support matrix is per operation and per transport. The support for
each transport (RC, UD, etc.) is described with a bit field.
ODP for SRQ WQEs is considered a different kind of support from ODP for RQ
WQs and therefore needs a different capability bit.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The OPFN protocol uses the COMPARE_SWAP request to exchange data
between the requester and the responder and therefore needs to
be stored in the QP's s_ack_queue when the request is received
on the responder side. However, because the user does not know
anything about the OPFN protocol, this extra entry in the
queue cannot be advertised to the user. This patch adds an extra
entry in a QP's s_ack_queue.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
As preparation to hide rdma_restrack_root, refactor the code to use the
ops structure instead of a special callback which is hidden in
rdma_restrack_root.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
In the current implementation, we have one restrack root per-device and
all users are simply providing it directly. Let's simplify the interface
and have callers provide the ib_device and internally access the
restrack_root.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Drivers that do not provide kernel verbs support should not be used by ib
kernel clients at all.
In case a device does not implement all mandatory verbs for kverbs usage
mark it as a non kverbs provider and prevent its usage for all clients
except for uverbs.
The device is marked as a non kverbs provider using the 'kverbs_provider'
flag which should only be set by the core code. The clients can choose
whether kverbs are requested for its usage using the 'no_kverbs_req' flag
which is currently set for uverbs only.
This patch allows drivers to remove mandatory verbs stubs and simply set
the callbacks to NULL. The IB device will be registered as a non-kverbs
provider. Note that verbs that are required for the device registration
process must be implemented.
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
All callers to ib_alloc_device() provide a larger size than struct
ib_device and rely on the fact that struct ib_device is embedded in their
driver specific structure as the first member.
Provide a safer variant of ib_alloc_device() that checks and enforces this
approach to make sure the drivers are using it right.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The default behavior of the SCSI core is to set the block layer request
queue parameter max_segment_size to 64 KB. That means that elements of
scatterlists are limited to 64 KB. Since RDMA adapters support larger
sizes, increase max_segment_size for the SRP initiator.
Notes:
- The SCSI max_segment_size parameter was introduced in kernel v5.0. See
also commit 50c2e9107f ("scsi: introduce a max_segment_size
host_template parameters").
- Some other block drivers already set max_segment_size to UINT_MAX,
e.g. nbd and rbd.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Yishai Hadas says:
Enable DEVX asynchronous query commands
This series enables querying a DEVX object in an asynchronous mode.
The userspace application won't block when calling the firmware and it will be
able to get the response back once that it will be ready.
To enable the above functionality:
- DEVX asynchronous command completion FD object was introduced.
- The applicable file operations were implemented to enable using it by
the user application.
- Query asynchronous method was added to the DEVX object, it will call the
firmware asynchronously and manages the response on the given input FD.
- Hot unplug support was added for the FD to work properly upon
unbind/disassociate.
- mlx5 core fence for asynchronous commands was implemented and used to
prevent racing upon unbind/disassociate.
This branch is based on mlx5-next & v5.0-rc2 due to dependencies, from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
* branch 'devx-async':
IB/mlx5: Implement DEVX hot unplug for async command FD
IB/mlx5: Implement the file ops of DEVX async command FD
IB/mlx5: Introduce async DEVX obj query API
IB/mlx5: Introduce MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Introduce MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD and its initial implementation.
This object is from type class FD and will be used to read DEVX async
commands completion.
The core layer should allow the driver to set object from type FD in a
safe mode, this option was added with a matching comment in place.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When CONFIG_INFINIBAND_ON_DEMAND_PAGING is not set there is no caller to
ib_alloc_odp_umem() so let's remove it.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
A sub-range in ODP implicit MR should take its write permission from the
MR and not be set always to allow.
Fixes: d07d1d70ce ("IB/umem: Update on demand page (ODP) support")
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
It turns out future patches need this capability quite widely now, not
just for netlink, so provide two global functions to manage the
registration lock refcount.
This also moves the point the lock becomes 1 to within
ib_register_device() so that the semantics of the public API are very sane
and clear. Calling ib_device_try_get() will fail on devices that are only
allocated but not yet registered.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Introduce and use rdma_device_to_ibdev() API for those drivers which are
registering one sysfs group and also use in ib_core.
In subsequent patch, device->provider_ibdev one-to-one mapping is no
longer holds true during accessing sysfs entries.
Therefore, introduce an API rdma_device_to_ibdev() that provides such
information.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Most provider routines are callback routines which ib core invokes.
_callback suffix doesn't convey information about when such callback is
invoked. Therefore, rename port_callback to init_port.
Additionally, store the init_port function pointer in ib_device_ops, so
that it can be accessed in subsequent patches when binding rdma device to
net namespace.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
ib_umem_get() can only be called in a method callback, which always has a
udata parameter. This allows ib_umem_get() to derive the ucontext pointer
directly from the udata without requiring the drivers to find it in some
way or another.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Convert various places to more readable code, which embeds
CONFIG_INFINIBAND_ON_DEMAND_PAGING into the code flow.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
CONFIG_INFINIBAND_ON_DEMAND_PAGING is used in general structures to
micro-optimize the memory footprint. Remove it, so it will allow us to
simplify various ODP device flows.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add a helper to zero fill fields before copying data to
UVERBS_ATTR_STRUCT.
As UVERBS_ATTR_STRUCT can be used as an extensible struct, we want to make
sure that if the user supplies us with a struct that has new fields that
we are not aware of, we return them zeroed to the user.
This helper should be used when using UVERBS_ATTR_STRUCT for an extendable
data structure and there is a need to make sure that extended members of
the struct, that the kernel doesn't handle, are returned zeroed to the
user. This is needed due to the fact that UVERBS_ATTR_STRUCT allows
non-zero values for members after 'last' member.
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Introduce a 'flags' field to destroy address handle callback and add a
flag that marks whether the callback is executed in an atomic context or
not.
This will allow drivers to wait for completion instead of polling for it
when it is allowed.
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Introduce a 'flags' field to create address handle callback and add a flag
that marks whether the callback is executed in an atomic context or not.
This will allow drivers to wait for completion instead of polling for it
when it is allowed.
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Having uobject pointer embedded in ib core objects is not aligned with a
future shared ib_x model. The resource tracker only does this to keep
track of user/kernel objects - track this directly instead.
Signed-off-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add new ioctl method for the MR object - ADVISE_MR.
This command can be used by users to give an advice or directions to the
kernel about an address range that belongs to memory regions.
A new ib_device callback, advise_mr(), is introduced here to suupport the
new command. This command takes the following arguments:
- pd: The protection domain to which all memory regions belong
- advice: The type of the advice
* IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH - Pre-fetch a range of
an on-demand paging MR
* IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE - Pre-fetch a range
of an on-demand paging MR with write intention
- flags: The properties of the advice
* IB_UVERBS_ADVISE_MR_FLAG_FLUSH - Operation must end before
return to the caller
- sg_list: The list of memory ranges
- num_sge: The number of memory ranges in the list
- attrs: More attributes to be parsed by the provider
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When the parser of an ioctl command has the knowledge that a ptr attribute
in a bundle represents an array of structures, it is useful for it to know
the number of elements in the array. This is done by dividing the
attribute length with the element size.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Make all the required change to start use the ib_device_ops structure.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This change introduces the ib_device_ops structure that defines all the
InfiniBand device operations in one place, so the code will be more
readable and clean, unlike today when the ops are mixed with ib_device
data members.
The providers will need to define the supported operations and assign them
using ib_set_device_ops(), that will also make the providers code more
readable and clean.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
IB representors don't support creation of RAW ethernet QP flows. Disable
them by reusing existing RDMA/core support macros. We do it for both
creation and matcher because latter is not usable if no flow creation is
available.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add the new rates that were added to Infiniband spec as part of HDR and 2x
support.
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add the new 2X port width that is part of IB spec 1.3
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
CapabilityMask2 was added in IB Spec 1.3 under PortInfo attribute. The
new Capapbility mask is needed in order to expose the new 2X width and HDR
speed.
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Reviewed-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch adds an interface to allow the driver to initialize the QP priv
struct when the QP is created and after the qpn has been assigned. A
field is added to the QP priv struct to reference the rcd and two new
files are added to contain the function to initialize the rcd field so
that more TID RDMA related code can be added here later.
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Enable getting an object type from a given uobject, the type is saved
upon tree merging and is returned as part of some helper function.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Introduce the UVERBS_IDR_ANY_OBJECT type to match any IDR object.
Once used, the infrastructure skips checking for the IDR type, it
becomes the driver handler responsibility.
This enables drivers to get in a given method an object from various of
types.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Add ability to track allocated ib_ucontext, which are limited
resource and worth to be visible by users.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
All of the old arguments can be derived from the uverbs_attr_bundle
structure, so get rid of the redundant arguments. Most of the prior work
has been removing users of the arguments to allow this to be a simple
patch.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This creates a consistent way to access the two core buffers across write
and write_ex handlers.
Remove the open coded ucore conversion in the write/ex compatibility
handlers.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Have the core code initialize the driver_udata if the method has a udata
description. This is done using the same create_udata the handler was
supposed to call.
This makes ioctl consistent with the write and write_ex paths.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
The core code needs to compute the udata so we may as well pass it in the
uverbs_attr_bundle instead of on the stack. This converts the simple case
of write_ex() which already has a core calculation.
Also change the write() path to use the attrs for ib_uverbs_init_udata()
instead of on the stack. This lets the write to write_ex compatibility
path continue to follow the lead of the _ex path.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
We need the structure sizes to compute the location of the udata in the
core code. Annotate the sizes into the new macro language.
This is generated largely by script and checked by comparing against the
similar list in rdma-core.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
The uverbs_attr_bundle already contains this pointer, and most methods
don't actually need it. Get rid of the redundant function argument.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Currently they return the command length, while all other handlers return
0. This makes the write path closer to the write_ex and ioctl path.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Now that we can add meta-data to the description of write() methods we
need to pass the uverbs_attr_bundle into all write based handlers so
future patches can use it as a container for any new data transferred out
of the core.
This is the first step to bringing the write() and ioctl() methods to a
common interface signature.
This is a simple search/replace, and we push the attr down into the uobj
and other APIs to keep changes minimal.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
When the rdma device is getting removed, get resource info can race with
device removal, as below:
CPU-0 CPU-1
-------- --------
rdma_nl_rcv_msg()
nldev_res_get_cq_dumpit()
mutex_lock(device_lock);
get device reference
mutex_unlock(device_lock); [..]
ib_unregister_device()
/* Valid reference to
* device->dev exists.
*/
ib_dealloc_device()
[..]
provider->fill_res_entry();
Even though device object is not freed, fill_res_entry() can get called on
device which doesn't have a driver anymore. Kernel core device reference
count is not sufficient, as this only keeps the structure valid, and
doesn't guarantee the driver is still loaded.
Similar race can occur with device renaming and device removal, where
device_rename() tries to rename a unregistered device. While this is fine
for devices of a class which are not net namespace aware, but it is
incorrect for net namespace aware class coming in subsequent series. If a
class is net namespace aware, then the below [1] call trace is observed in
above situation.
Therefore, to avoid the race, keep a reference count and let device
unregistration wait until all netlink users drop the reference.
[1] Call trace:
kernfs: ns required in 'infiniband' for 'mlx5_0'
WARNING: CPU: 18 PID: 44270 at fs/kernfs/dir.c:842 kernfs_find_ns+0x104/0x120
libahci i2c_core mlxfw libata dca [last unloaded: devlink]
RIP: 0010:kernfs_find_ns+0x104/0x120
Call Trace:
kernfs_find_and_get_ns+0x2e/0x50
sysfs_rename_link_ns+0x40/0xb0
device_rename+0xb2/0xf0
ib_device_rename+0xb3/0x100 [ib_core]
nldev_set_doit+0x165/0x190 [ib_core]
rdma_nl_rcv_msg+0x249/0x250 [ib_core]
? netlink_deliver_tap+0x8f/0x3e0
rdma_nl_rcv+0xd6/0x120 [ib_core]
netlink_unicast+0x17c/0x230
netlink_sendmsg+0x2f0/0x3e0
sock_sendmsg+0x30/0x40
__sys_sendto+0xdc/0x160
Fixes: da5c850782 ("RDMA/nldev: add driver-specific resource tracking")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>