Current code uses many different types when dealing with a port of a RDMA
device: u8, unsigned int and u32. Switch to u32 to clean up the logic.
This allows us to make (at least) the core view consistent and use the
same type. Unfortunately not all places can be converted. Many uverbs
functions expect port to be u8 so keep those places in order not to break
UAPIs. HW/Spec defined values must also not be changed.
With the switch to u32 we now can support devices with more than 255
ports. U32_MAX is reserved to make control logic a bit easier to deal
with. As a device with U32_MAX ports probably isn't going to happen any
time soon this seems like a non issue.
When a device with more than 255 ports is created uverbs will report the
RDMA device as having 255 ports as this is the max currently supported.
The verbs interface is not changed yet because the IBTA spec limits the
port size in too many places to be u8 and all applications that relies in
verbs won't be able to cope with this change. At this stage, we are
extending the interfaces that are using vendor channel solely
Once the limitation is lifted mlx5 in switchdev mode will be able to have
thousands of SFs created by the device. As the only instance of an RDMA
device that reports more than 255 ports will be a representor device and
it exposes itself as a RAW Ethernet only device CM/MAD/IPoIB and other
ULPs aren't effected by this change and their sysfs/interfaces that are
exposes to userspace can remain unchanged.
While here cleanup some alignment issues and remove unneeded sanity
checks (mainly in rdmavt),
Link: https://lore.kernel.org/r/20210301070420.439400-1-leon@kernel.org
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Pull rdma fixes from Jason Gunthorpe:
"Not much going on, just some small bug fixes:
- Typo causing a regression in mlx5 devx
- Regression in the recent hns rework causing the HW to get out of
sync
- Long-standing cxgb4 adaptor crash when destroying cm ids"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
RDMA/cxgb4: Fix adapter LE hash errors while destroying ipv6 listening server
RDMA/hns: Fix bug during CMDQ initialization
RDMA/mlx5: Fix typo in destroy_mkey inbox
There is no need to create the ODP EQ if the user doesn't use ODP MRs.
Hence, create it only when the first ODP MR is created. This EQ will be
destroyed only when the device is unloaded.
This will decrease the number of EQs created per device. for example: If
we creates 1K devices (SF/VF/etc'), than we will decrease the num of EQs
by 1K.
Link: https://lore.kernel.org/r/20210314125418.179716-1-leon@kernel.org
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Now that each representor stores a pointer to the managing E-Switch
use that information when creating the send-to-vport rules.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Now that a pointer to the managing E-Switch is stored in the representor
use it.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Acked-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
The umem DMA list calculation was locked at 4k pages due to confusion
around how this API works and is used when larger pages are present.
The conclusion is:
- umem's cannot extend past what is mapped into the process, so creating
a lage page size and referring to a sub-range is not allowed
- umem's must always have a page offset of zero, except for sub PAGE_SIZE
umems
- The feature of umem_offset to create multiple objects inside a umem
is buggy and isn't used anyplace. Thus we can assume all users of the
current API have umem_offset == 0 as well
Provide a new page size calculator that limits the DMA list to the VA
range and enforces umem_offset == 0.
Allow user space to specify the page sizes which it can accept, this
bitmap must be derived from the intended use of the umem, based on
per-usage HW limitations.
Link: https://lore.kernel.org/r/20210304130501.1102577-4-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Change uverbs_get_const/uverbs_get_const_default to work properly with
both signed/unsigned parameters.
Current APIs mix s64 and u64 which leads to incorrect check when u64
value was supplied and its upper bit was set. In that case
uverbs_get_const() / uverbs_get_const_default() lower bound check may
fail unexpectedly, target is unsigned (lower bound is 0) but value
became negative as of the s64 usage.
Split to have two different APIs, no change to callers as the required
API will be called internally according to the target type.
Link: https://lore.kernel.org/r/20210304130501.1102577-3-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
mlx5_is_roce_enabled returns the devlink RoCE init value, therefore it
should be used only when driver is loaded. Instead we just need to read
the roce_en field.
In addition, rename mlx5_is_roce_enabled to mlx5_is_roce_init_enabled.
Fixes: 7a58779edd ("IB/mlx5: Improve query port for representor port")
Link: https://lore.kernel.org/r/20210304124517.1100608-2-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Now that this is only used in a few places in mr.c give it a sensible
name. It has nothing to do with the cache and can be invoked on any
MR. DMA is stopped and the user cannot touch the MR any further once it
completes.
Link: https://lore.kernel.org/r/20210304120745.1090751-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Now that the SRCU stuff has been removed the entire MR destroy logic can
be made a lot simpler. Currently there are many different ways to destroy a
MR and it makes it really hard to do this task correctly. Route all
destruction through mlx5_ib_dereg_mr() and make it work for all
situations.
Since it turns out all the different MR types do basically the same thing
this removes a lot of knowledge of MR internals from ODP and leaves ODP
just exporting an operation to clean up children.
This fixes a few weird corner cases bugs and firmly uses the correct
ordering of the MR destruction:
- Stop parallel access to the mkey via the ODP xarray
- Stop DMA
- Release the umem
- Clean up ODP children
- Free/Recycle the MR
Link: https://lore.kernel.org/r/20210304120745.1090751-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The struct mlx5_ib_mr can be used for three different things, but only one
at a time:
- In the user MR cache
- As a kernel MR
- As a user MR
Overlay the three things into a single union with the following rules:
- If the mr is found on the cache_ent->head list then it is a cache MR
and umem == NULL. The entire union is zero after the MR is removed from
the cache.
- If umem != NULL or type == IB_MR_TYPE_USER then it is a user MR.
- If umem == NULL then it is a kernel MR
This reduces the size of struct mlx5_ib_mr to 552 bytes from 702.
The only place the three flows overlap in the code is during dereg, so add
a few extra checks along there.
Link: https://lore.kernel.org/r/20210304120745.1090751-3-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
All of the ODP code assumes when it calls mlx5_mr_cache_alloc() the ODP
related fields are zero'd. This is true if the MR was just allocated, but
if the MR is recycled through the cache then the values are never zero'd.
This causes a bug in the odp_stats, they don't reset when the MR is
reallocated, also is_odp_implicit is never 0'd.
So we can use memset on a block of the mlx5_ib_mr reorganize the structure
to put all the data that can be zero'd by the cache at the end.
It is organized as an anonymous struct because the next patch will make
this a union.
Delete the unused smr_info. Don't set the kernel only desc_size on the
user path. No longer any need to zero mr->parent before freeing it, the
memset() will get it now.
Fixes: a3de94e3d6 ("IB/mlx5: Introduce ODP diagnostic counters")
Link: https://lore.kernel.org/r/20210304120745.1090751-2-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
1. Don't set the ts_format bit to default when it reserved - device is
running in the old mode (free running).
2. XRC doesn't have a CQ therefore the ts format in the QP
context should be default / free running.
3. Set ts_format to WQ.
Fixes: 2fe8d4b878 ("RDMA/mlx5: Fail QP creation if the device can not support the CQE TS")
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
The W=1 allmodconfig build produces the following warning:
drivers/infiniband/hw/mlx5/odp.c:1086: warning: wrong kernel-doc identifier on line:
* Parse a series of data segments for page fault handling.
Fix it by changing /** to be /* as it is written in kernel-doc
documentation.
Fixes: 5e769e444d ("RDMA/hw/mlx5/odp: Fix formatting and add missing descriptions in 'pagefault_data_segments()'")
Link: https://lore.kernel.org/r/20210302074214.1054299-2-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Linux 5.11
Merged to resolve conflicts with RDMA rc commits
- drivers/infiniband/sw/rxe/rxe_net.c
The final logic is to call rxe_get_dev_from_net() again with the master
netdev if the packet was rx'd on a vlan. To keep the elimination of the
local variables requires a trivial edit to the code in -rc
Link: https://lore.kernel.org/r/20210210131542.215ea67c@canb.auug.org.au
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Leon Romanovsky says:
====================
Add an extra timestamp format for mlx5_ib device.
====================
Based on the mlx5-next branch at
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
due to dependencies.
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
* branch 'mlx5_timestamp':
RDMA/mlx5: Fail QP creation if the device can not support the CQE TS
net/mlx5: Add new timestamp mode bits
In ConnectX6Dx device, HW can work in real time timestamp mode according
to the device capabilities per RQ/SQ/QP.
When the flag IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION is set, the user
expect to get TS on the CQEs in free running format, so we need to fail
the QP creation if the current mode of the device doesn't support it.
Link: https://lore.kernel.org/r/20210209131107.698833-3-leon@kernel.org
Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The traditional DevX CQ creation flow goes through mlx5_core_create_cq()
which checks that the given EQN corresponds to an existing EQ and attaches
a devx handler to the EQN for the CQ.
In some cases the EQ will not be a kernel EQ, but will be controlled by
modify CQ, don't block creating these just because the EQN can't be found
in the kernel.
Link: https://lore.kernel.org/r/20210211085549.1277674-1-leon@kernel.org
Signed-off-by: Tal Gilboa <talgi@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Cleanup the synchronize_srcu() from the ODP flow as it was found to be a
very heavy time consumer as part of dereg_mr.
For example de-registration of 10000 ODP MRs each with size of 2M hugepage
took 19.6 sec comparing de-registration of same number of non ODP MRs that
took 172 ms.
The new locking scheme uses the wait_event() mechanism which follows the
use count of the MR instead of using synchronize_srcu().
By that change, the time required for the above test took 95 ms which is
even better than the non ODP flow.
Once fully dropped the srcu usage, had to come with a lock to protect the
XA access.
As part of using the above mechanism we could also clean the
num_deferred_work stuff and follow the use count instead.
Link: https://lore.kernel.org/r/20210202071309.2057998-1-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Instead of open coding the loop for port iteration, use rdma_for_each_port
macro provided by core.
To use such macro, early initialization of phys_port_cnt is needed.
Hence, initialize such constant early enough in the init stage.
Whichever functions are called with port using rdma_for_each_port(),
convert their port type from u8 to unsigned int to match the core API.
Link: https://lore.kernel.org/r/20210203130133.4057329-6-leon@kernel.org
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Currently mlx5 driver caches port GID table length for 2 ports. It is
also cached by IB core as port immutable data.
When mlx5 representor ports are present, which are usually more than 2,
invalid access to port_caps array can happen while validating the GID
table length which is only for 2 ports.
To avoid this, take help of the IB cores port immutable data by exposing
an API to read the port immutable fields.
Remove mlx5 driver's internal cache, thereby reduce code and data.
Link: https://lore.kernel.org/r/20210203130133.4057329-5-leon@kernel.org
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Improve query port functionality for representor port as below.
1. RoCE Qkey violation counters are not applicable for representor port.
2. Avoid setting gid_tbl_len twice for representor port.
3. Avoid setting ip_gids and IB_PORT_CM_SUP property for representor port
as GID table is empty and CM support is not present in representor
mode.
Link: https://lore.kernel.org/r/20210203130133.4057329-4-leon@kernel.org
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Pkey table length for all the ports of the device is the same. Currently
get_ports_cap() reads and stores it for each port by querying the device
which reads more than just pkey table length.
For representor device ports which can be in range of hundreds, it queries
is for each such port and end up returning same value for all the ports.
When in representor mode, modify QP accesses pkey port caps for a port
index that can be outside of the port_caps table.
Hence, simplify the logic to query the max pkey table length only once
during device initialization sequence.
Link: https://lore.kernel.org/r/20210203130133.4057329-3-leon@kernel.org
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The cited commit disallowed creating any QP which isn't raw ethernet, reg
umr or the special UD qp for testing WC, this proved too strict.
While modify can't be done (no GIDS/GID table for example) just creating a
QP is okay.
This patch partially reverts the bellow mentioned commit and places the
restriction at the modify QP stage and not at the creation. DEVX commands
should be used to manipulate such QPs.
Fixes: 42caf9cb59 ("RDMA/mlx5: Allow only raw Ethernet QPs when RoCE isn't enabled")
Link: https://lore.kernel.org/r/20210125120709.836718-1-leon@kernel.org
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Fixes the following W=1 kernel build warning(s):
drivers/infiniband/hw/mlx5/odp.c:1062: warning: Function parameter or member 'dev' not described in 'pagefault_data_segments'
drivers/infiniband/hw/mlx5/odp.c:1062: warning: Function parameter or member 'pfault' not described in 'pagefault_data_segments'
drivers/infiniband/hw/mlx5/odp.c:1062: warning: Function parameter or member 'wqe' not described in 'pagefault_data_segments'
drivers/infiniband/hw/mlx5/odp.c:1062: warning: Function parameter or member 'wqe_end' not described in 'pagefault_data_segments'
drivers/infiniband/hw/mlx5/odp.c:1062: warning: Function parameter or member 'bytes_mapped' not described in 'pagefault_data_segments'
drivers/infiniband/hw/mlx5/odp.c:1062: warning: Function parameter or member 'total_wqe_bytes' not described in 'pagefault_data_segments'
drivers/infiniband/hw/mlx5/odp.c:1062: warning: Function parameter or member 'receive_queue' not described in 'pagefault_data_segments'
Link: https://lore.kernel.org/r/20210121094519.2044049-2-lee.jones@linaro.org
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: linux-rdma@vger.kernel.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This reverts commit fbdd0049d9.
Due to commit in fixes tag, netdevice events were received only in one net
namespace of mlx5_core_dev. Due to this when netdevice events arrive in
net namespace other than net namespace of mlx5_core_dev, they are missed.
This results in empty GID table due to RDMA device being detached from its
net device.
Hence, revert back to receive netdevice events in all net namespaces to
restore back RDMA functionality in non init_net net namespace. The
deadlock will have to be addressed in another patch.
Fixes: fbdd0049d9 ("RDMA/mlx5: Fix devlink deadlock on net namespace deletion")
Link: https://lore.kernel.org/r/20210117092633.10690-1-leon@kernel.org
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Pull rdma updates from Jason Gunthorpe:
"A smaller set of patches, nothing stands out as being particularly
major this cycle. The biggest item would be the new HIP09 HW support
from HNS, otherwise it was pretty quiet for new work here:
- Driver bug fixes and updates: bnxt_re, cxgb4, rxe, hns, i40iw,
cxgb4, mlx4 and mlx5
- Bug fixes and polishing for the new rts ULP
- Cleanup of uverbs checking for allowed driver operations
- Use sysfs_emit all over the place
- Lots of bug fixes and clarity improvements for hns
- hip09 support for hns
- NDR and 50/100Gb signaling rates
- Remove dma_virt_ops and go back to using the IB DMA wrappers
- mlx5 optimizations for contiguous DMA regions"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (147 commits)
RDMA/cma: Don't overwrite sgid_attr after device is released
RDMA/mlx5: Fix MR cache memory leak
RDMA/rxe: Use acquire/release for memory ordering
RDMA/hns: Simplify AEQE process for different types of queue
RDMA/hns: Fix inaccurate prints
RDMA/hns: Fix incorrect symbol types
RDMA/hns: Clear redundant variable initialization
RDMA/hns: Fix coding style issues
RDMA/hns: Remove unnecessary access right set during INIT2INIT
RDMA/hns: WARN_ON if get a reserved sl from users
RDMA/hns: Avoid filling sl in high 3 bits of vlan_id
RDMA/hns: Do shift on traffic class when using RoCEv2
RDMA/hns: Normalization the judgment of some features
RDMA/hns: Limit the length of data copied between kernel and userspace
RDMA/mlx4: Remove bogus dev_base_lock usage
RDMA/uverbs: Fix incorrect variable type
RDMA/core: Do not indicate device ready when device enablement fails
RDMA/core: Clean up cq pool mechanism
RDMA/core: Update kernel documentation for ib_create_named_qp()
MAINTAINERS: SOFT-ROCE: Change Zhu Yanjun's email address
...
If the MR cache entry invalidation failed, then we detach this entry from
the cache, therefore we must to free the memory as well.
Allcation backtrace for the leaker:
[<00000000d8e423b0>] alloc_cache_mr+0x23/0xc0 [mlx5_ib]
[<000000001f21304c>] create_cache_mr+0x3f/0xf0 [mlx5_ib]
[<000000009d6b45dc>] mlx5_ib_alloc_implicit_mr+0x41/0×210 [mlx5_ib]
[<00000000879d0d68>] mlx5_ib_reg_user_mr+0x9e/0×6e0 [mlx5_ib]
[<00000000be74bf89>] create_qp+0x2fc/0xf00 [ib_uverbs]
[<000000001a532d22>] ib_uverbs_handler_UVERBS_METHOD_COUNTERS_READ+0x1d9/0×230 [ib_uverbs]
[<0000000070f46001>] rdma_alloc_commit_uobject+0xb5/0×120 [ib_uverbs]
[<000000006d8a0b38>] uverbs_alloc+0x2b/0xf0 [ib_uverbs]
[<00000000075217c9>] ksysioctl+0x234/0×7d0
[<00000000eb5c120b>] __x64_sys_ioctl+0x16/0×20
[<00000000db135b48>] do_syscall_64+0x59/0×2e0
Fixes: 1769c4c575 ("RDMA/mlx5: Always remove MRs from the cache before destroying them")
Link: https://lore.kernel.org/r/20201213132940.345554-2-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Currently, DM MR registration flow doesn't set the mlx5_ib_dev pointer and
can cause a NULL pointer dereference if userspace dumps the MR via rdma
tool.
Assign the IB device together with the other fields and remove the
redundant reference of mlx5_ib_dev from mlx5_ib_mr.
Cc: stable@vger.kernel.org
Fixes: 6c29f57ea4 ("IB/mlx5: Device memory mr registration support")
Link: https://lore.kernel.org/r/20201203190807.127189-1-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This is all a giant train wreck of error handling, in many cases the MR is
left in some corrupted state where continuing on is going to lead to
chaos, or various unwinds/order is missed.
rereg had three possible completely different actions, depending on flags
and various details about the MR. Split the three actions into three
functions, and call the right action from the start.
For each action carefully design the error handling to fit the action:
- UMR access/PD update is a simple UMR, if it fails the MR isn't changed,
so do nothing
- PAS update over UMR is multiple UMR operations. To keep everything sane
revoke access to the MKey while it is being changed and restore it once
the MR is correct.
- Recreating the mkey should completely build a parallel MR with a fully
loaded PAS then swap and destroy the old one. If it fails the original
should be left untouched. This is handled in the core code. Directly
call the normal MR creation functions, possibly re-using the existing
umem.
Add support for working with ODP MRs. The READ/WRITE access flags can be
changed by UMR and we can trivially convert to/from ODP MRs using the
logic to build a completely new MR.
This new logic also fixes various problems with MRs continuing to work
while their PAS lists are no longer valid, eg during a page size change.
Link: https://lore.kernel.org/r/20201130075839.278575-6-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
mlx5 has an ugly flow where it tries to allocate a new MR and replace the
existing MR in the same memory during rereg. This is very complicated and
buggy. Instead of trying to replace in-place inside the driver, provide
support from uverbs to change the entire HW object assigned to a handle
during rereg_mr.
Since destroying a MR is allowed to fail (ie if a MW is pointing at it)
and can't be detected in advance, the algorithm creates a completely new
uobject to hold the new MR and swaps the IDR entries of the two objects.
The old MR in the temporary IDR entry is destroyed, and if it fails
rereg_mr succeeds and destruction is deferred to FD release. This
complexity is why this cannot live in a driver safely.
Link: https://lore.kernel.org/r/20201130075839.278575-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
