Skip to content

L
linux
Switch branch/tag
  1. 13 Aug, 2018 4 commits
    • Jason Gunthorpe's avatar
      IB/uverbs: Remove struct uverbs_root_spec and all supporting code · 51d0a2b4
      Jason Gunthorpe authored 
      Everything now uses the uverbs_uapi data structure.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      51d0a2b4
    • Jason Gunthorpe's avatar
      IB/uverbs: Use uverbs_api to unmarshal ioctl commands · 3a863577
      Jason Gunthorpe authored 
      Convert the ioctl method syscall path to use the uverbs_api data
structures. The new uapi structure includes all the same information, just
in a different and more optimal way.

 - Use attr_bkey instead of 2 level radix trees for everything related to
   attributes. This includes the attribute storage, presence, and
   detection of missing mandatory attributes.
 - Avoid iterating over all attribute storage at finish, instead use
   find_first_bit with the attr_bkey to locate only those attrs that need
   cleanup.
 - Organize things to always run, and always rely on, cleanup. This
   avoids a bunch of tricky error unwind cases.
 - Locate the method using the radix tree, and locate the attributes
   using a very efficient incremental radix tree lookup
 - Use the precomputed destroy_bkey to handle uobject destruction
 - Use the precomputed allocation sizes and precomputed 'need_stack'
   to avoid maths in the fast path. This is optimal if userspace
   does not pass (many) unsupported attributes.

Overall this results in much better codegen for the attribute accessors,
everything is now stored in bitmaps or linear arrays indexed by attr_bkey.
The compiler can compute attr_bkey values at compile time for all method
attributes, meaning things like uverbs_attr_is_valid() now compile into
single instruction bit tests.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      3a863577
    • Jason Gunthorpe's avatar
      IB/uverbs: Use uverbs_alloc for allocations · b61815e2
      Jason Gunthorpe authored 
      Several handlers need temporary allocations for the life of the method,
switch them to use the uverbs_alloc allocator.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
Reviewed-by: default avatarLeon Romanovsky <leonro@mellanox.com>
      b61815e2
    • Jason Gunthorpe's avatar
      IB/uverbs: Add a simple allocator to uverbs_attr_bundle · 461bb2ee
      Jason Gunthorpe authored 
      This is similar in spirit to devm, it keeps track of any allocations
linked to this method call and ensures they are all freed when the method
exits. Further, if there is space in the internal/onstack buffer then the
allocator will hand out that memory and avoid an expensive call to
kalloc/kfree in the syscall path.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
Reviewed-by: default avatarLeon Romanovsky <leonro@mellanox.com>
      461bb2ee
  3. 10 Aug, 2018 5 commits
    • Jason Gunthorpe's avatar
      IB/uverbs: Remove the ib_uverbs_attr pointer from each attr · 6a1f444f
      Jason Gunthorpe authored 
      Memory in the bundle is valuable, do not waste it holding an 8 byte
pointer for the rare case of writing to a PTR_OUT. We can compute the
pointer by storing a small 1 byte array offset and the base address of the
uattr memory in the bundle private memory.

This also means we can access the kernel's copy of the ib_uverbs_attr, so
drop the copy of flags as well.

Since the uattr base should be private bundle information this also
de-inlines the already too big uverbs_copy_to inline and moves
create_udata into uverbs_ioctl.c so they can see the private struct
definition.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
Reviewed-by: default avatarLeon Romanovsky <leonro@mellanox.com>
      6a1f444f
    • Jason Gunthorpe's avatar
      IB/uverbs: Provide implementation private memory for the uverbs_attr_bundle · 4b3dd2bb
      Jason Gunthorpe authored 
      This already existed as the anonymous 'ctx' structure, but this was not
really a useful form. Hoist this struct into bundle_priv and rework the
internal things to use it instead.

Move a bunch of the processing internal state into the priv and reduce the
excessive use of function arguments.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
Reviewed-by: default avatarLeon Romanovsky <leonro@mellanox.com>
      4b3dd2bb
    • Jason Gunthorpe's avatar
      IB/uverbs: Use uverbs_api to manage the object type inside the uobject · 6b0d08f4
      Jason Gunthorpe authored 
      Currently the struct uverbs_obj_type stored in the ib_uobject is part of
the .rodata segment of the module that defines the object. This is a
problem if drivers define new uapi objects as we will be left with a
dangling pointer after device disassociation.

Switch the uverbs_obj_type for struct uverbs_api_object, which is
allocated memory that is part of the uverbs_api and is guaranteed to
always exist. Further this moves the 'type_class' into this memory which
means access to the IDR/FD function pointers is also guaranteed. Drivers
cannot define new types.

This makes it safe to continue to use all uobjects, including driver
defined ones, after disassociation.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      6b0d08f4
    • Jason Gunthorpe's avatar
      IB/uverbs: Build the specs into a radix tree at runtime · 9ed3e5f4
      Jason Gunthorpe authored 
      This radix tree datastructure is intended to replace the 'hash' structure
used today for parsing ioctl methods during system calls. This first
commit introduces the structure and builds it from the existing .rodata
descriptions.

The so-called hash arrangement is actually a 5 level open coded radix tree.
This new version uses a 3 level radix tree built using the radix tree
library.

Overall this is much less code and much easier to build as the radix tree
API allows for dynamic modification during the building. There is a small
memory penalty to pay for this, but since the radix tree is allocated on
a per device basis, a few kb of RAM seems immaterial considering the
gained simplicity.

The radix tree is similar to the existing tree, but also has a 'attr_bkey'
concept, which is a small value'd index for each method attribute. This is
used to simplify and improve performance of everything in the next
patches.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
Reviewed-by: default avatarLeon Romanovsky <leonro@mellanox.com>
Reviewed-by: default avatarMichael J. Ruhl <michael.j.ruhl@intel.com>
      9ed3e5f4
    • Jason Gunthorpe's avatar
      IB/uverbs: Have the core code create the uverbs_root_spec · 7d96c9b1
      Jason Gunthorpe authored 
      There is no reason for drivers to do this, the core code should take of
everything. The drivers will provide their information from rodata to
describe their modifications to the core's base uapi specification.

The core uses this to build up the runtime uapi for each device.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
Reviewed-by: default avatarMichael J. Ruhl <michael.j.ruhl@intel.com>
Reviewed-by: default avatarLeon Romanovsky <leonro@mellanox.com>
      7d96c9b1
  5. 09 Aug, 2018 1 commit
  7. 08 Aug, 2018 5 commits
  9. 07 Aug, 2018 1 commit
  11. 03 Aug, 2018 13 commits
  13. 01 Aug, 2018 11 commits
    • Denis Drozdov's avatar
      IB/IPoIB: Set ah valid flag in multicast send flow · 75da9606
      Denis Drozdov authored 
      The change of ipoib_ah data structure with adding "valid" flag and
checks of ah->valid in ipoib_start_xmit affected multicast packet flow.

Since the multicast flow doesn't invoke path_rec_start, "ah->valid" flag
remains unset, so that ipoib_start_xmit end up with neigh_refresh_path
instead of sending the packet using neigh.

"ah->valid" has to be set in multicast send flow. As a result IPoIB
starts sending packets via neigh immediately and eliminates 60sec delay
of neigh keep alive interval.

The typical example of this issue are two sequential arpings:

arping 11.134.208.9 -> got response (mcast_send)
arping 11.134.208.9 -> no response  (ah->valid = 0)

Fixes: fa9391db ("RDMA/ipoib: Update paths on CLIENT_REREG/SM_CHANGE events")
Signed-off-by: default avatarDenis Drozdov <denisd@mellanox.com>
Reviewed-by: default avatarErez Shitrit <erezsh@mellanox.com>
Reviewed-by: default avatarFeras Daoud <ferasda@mellanox.com>
Signed-off-by: default avatarLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      75da9606
    • Jason Gunthorpe's avatar
      IB/uverbs: Allow all DESTROY commands to succeed after disassociate · 0f50d88a
      Jason Gunthorpe authored 
      The disassociate function was broken by design because it failed all
commands. This prevents userspace from calling destroy on a uobject after
it has detected a device fatal error and thus reclaiming the resources in
userspace is prevented.

This fix is now straightforward, when anything destroys a uobject that is
not the user the object remains on the IDR with a NULL context and object
pointer. All lookup locking modes other than DESTROY will fail. When the
user ultimately calls the destroy function it is simply dropped from the
IDR while any related information is returned.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      0f50d88a
    • Jason Gunthorpe's avatar
      IB/uverbs: Do not block disassociate during write() · a9b66d64
      Jason Gunthorpe authored 
      Now that all the callbacks are safe to run concurrently with
disassociation this test can be eliminated. The ufile core infrastructure
becomes entirely self contained and is not sensitive to disassociation.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      a9b66d64
    • Jason Gunthorpe's avatar
      IB/uverbs: Do not pass struct ib_device to the ioctl methods · e83f0ecd
      Jason Gunthorpe authored 
      This does the same as the patch before, except for ioctl. The rules are
the same, but for the ioctl methods the core code handles setting up the
uobject.

- Retrieve the ib_dev from the uobject->context->device. This is
  safe under ioctl as the core has already done rdma_alloc_begin_uobject
  and so CREATE calls are entirely protected by the rwsem.
- Retrieve the ib_dev from uobject->object
- Call ib_uverbs_get_ucontext()
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      e83f0ecd
    • Jason Gunthorpe's avatar
      IB/uverbs: Do not pass struct ib_device to the write based methods · bbd51e88
      Jason Gunthorpe authored 
      This is a step to get rid of the global check for disassociation. In this
model, the ib_dev is not proven to be valid by the core code and cannot be
provided to the method. Instead, every method decides if it is able to
run after disassociation and obtains the ib_dev using one of three
different approaches:

- Call srcu_dereference on the udevice's ib_dev. As before, this means
  the method cannot be called after disassociation begins.
  (eg alloc ucontext)
- Retrieve the ib_dev from the ucontext, via ib_uverbs_get_ucontext()
- Retrieve the ib_dev from the uobject->object after checking
  under SRCU if disassociation has started (eg uobj_get)

Largely, the code is all ready for this, the main work is to provide a
ib_dev after calling uobj_alloc(). The few other places simply use
ib_uverbs_get_ucontext() to get the ib_dev.

This flexibility will let the next patches allow destroy to operate
after disassociation.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      bbd51e88
    • Jason Gunthorpe's avatar
      IB/uverbs: Lower the test for ongoing disassociation · cc2e14e6
      Jason Gunthorpe authored 
      Commands that are reading/writing to objects can test for an ongoing
disassociation during their initial call to rdma_lookup_get_uobject.  This
directly prevents all of these commands from conflicting with an ongoing
disassociation.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      cc2e14e6
    • Jason Gunthorpe's avatar
      IB/uverbs: Allow uobject allocation to work concurrently with disassociate · 1e857e65
      Jason Gunthorpe authored 
      After all the recent structural changes this is now straightforward, hold
the hw_destroy_rwsem across the entire uobject creation. We already take
this semaphore on the success path, so holding it a bit longer is not
going to change the performance.

After this change none of the create callbacks require the
disassociate_srcu lock to be correct.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      1e857e65
    • Jason Gunthorpe's avatar
      IB/uverbs: Allow RDMA_REMOVE_DESTROY to work concurrently with disassociate · 7452a3c7
      Jason Gunthorpe authored 
      After all the recent structural changes this is now straightfoward, hoist
the hw_destroy_rwsem up out of rdma_destroy_explicit and wrap it around
the uobject write lock as well as the destroy.

This is necessary as obtaining a write lock concurrently with
uverbs_destroy_ufile_hw() will cause malfunction.

After this change none of the destroy callbacks require the
disassociate_srcu lock to be correct.

This requires introducing a new lookup mode, UVERBS_LOOKUP_DESTROY as the
IOCTL interface needs to hold an unlocked kref until all command
verification is completed.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      7452a3c7
    • Jason Gunthorpe's avatar
      IB/uverbs: Convert 'bool exclusive' into an enum · 9867f5c6
      Jason Gunthorpe authored 
      This is more readable, and future patches will need a 3rd lookup type.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      9867f5c6
    • Jason Gunthorpe's avatar
      IB/uverbs: Consolidate uobject destruction · 87ad80ab
      Jason Gunthorpe authored 
      There are several flows that can destroy a uobject and each one is
minimized and sprinkled throughout the code base, making it difficult to
understand and very hard to modify the destroy path.

Consolidate all of these into uverbs_destroy_uobject() and call it in all
cases where a uobject has to be destroyed.

This makes one change to the lifecycle, during any abort (eg when
alloc_commit is not called) we always call out to alloc_abort, even if
remove_commit needs to be called to delete a HW object.

This also renames RDMA_REMOVE_DURING_CLEANUP to RDMA_REMOVE_ABORT to
clarify its actual usage and revises some of the comments to reflect what
the life cycle is for the type implementation.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      87ad80ab
    • Jason Gunthorpe's avatar
      IB/uverbs: Make the write path destroy methods use the same flow as ioctl · 32ed5c00
      Jason Gunthorpe authored 
      The ridiculous dance with uobj_remove_commit() is not needed, the write
path can follow the same flow as ioctl - lock and destroy the HW object
then use the data left over in the uobject to form the response to
userspace.

Two helpers are introduced to make this flow straightforward for the
caller.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
      32ed5c00
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7