netdev has several interfaces that expect to call alloc_netdev_mqs from
the core code, with the driver only providing the arguments. This is
incompatible with the rdma_netdev interface that returns the netdev
directly.
Thus re-organize the API used by ipoib so that the verbs core code calls
alloc_netdev_mqs for the driver. This is done by allowing the drivers to
provide the allocation parameters via a 'get_params' callback and then
initializing an allocated netdev as a second step.
Fixes: cd565b4b51 ("IB/IPoIB: Support acceleration options callbacks")
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Denis Drozdov <denisd@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Tracking CM_ID resource is performed in two stages: creation of cm_id
and connecting it to the cma_dev. It is needed because rdma-cm protocol
exports two separate user-visible calls rdma_create_id and rdma_accept.
At the time of CM_ID creation, the real owner of that object is unknown
yet and we need to grab task_struct. This task_struct is released or
reassigned in attach phase later on. but call to rdma_destroy_id left
this task_struct unreleased.
Such separation is unique to CM_ID and other restrack objects initialize
in one shot. It means that it is safe to use "res->valid" check to catch
unfinished CM_ID flow and release task_struct for that object.
Fixes: 00313983cd ("RDMA/nldev: provide detailed CM_ID information")
Reported-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Yossi Itigin <yosefe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Unify task update and kernel name set in one place.
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Yossi Itigin <yosefe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Prepare rdma_restrack_set_task() call to accommodate more
code by moving its implementation from *.h to *.c.
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Yossi Itigin <yosefe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
rdma_find_ndev_for_src_ip_rcu() returns either valid netdev pointer or
ERR_PTR(). Instead of checking for NULL, check for error.
Fixes: caf1e3ae9f ("RDMA/core Introduce and use rdma_find_ndev_for_src_ip_rcu")
Reported-by: syzbot+20c32fa6ff84a2d28c36@syzkaller.appspotmail.com
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
All users of rdma_nl_chk_listeners() are interested to get boolean answer
if netlink socket has listeners, so update all places to boolean function.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The ll parameter is not used in ib_modify_qp_is_ok(), so remove it.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The uapi radix tree is a write-once data structure protected by kref.
Once we get to the ioctl() fop it is not possible for anything else
to be writing to it, so the access should use rcu_dereference_protected.
Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When RDMA CM connect request arrives for IB transport, it already contains
device, port, netdevice (optional).
Instead of traversing all the cma devices, use the cma device already
found by the cma_find_listener() for which a listener id is provided.
iWarp devices doesn't need to derive RoCE GIDs, therefore drop RoCE
specific checks from cma_acquire_dev() and rename it to
cma_iw_acquire_dev().
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Light weight version of cma_acquire_dev() just for binding with rdma
device based on source IP(v4/v6) address.
This simplifies cma_acquire_dev() to avoid listen_id specific checks and
also for subsequent simplification for IB vs iWarp.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When IP failover is used between multiple ports of a given rdma device,
allow accepting CM requests from either of the ports. This is applicable
for IPv4 and IPv6 non link local addressing scheme.
IPv6 link local addresses are bound. IP failover requests for listen
cm_ids bound to specific netdev interfaces cannot be supported.
(Similar to traditional sockets).
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently mmap_sem is read locked while pinning the memory. In a
multi-threaded application of a process, holding mmap_sem lock creates
contention with other threads who might be either registering memory,
creating QPs or simply doing mmap() as such operations also require to
hold the mmap_sem write lock.
All such operation cannot make forward progress until one memory pin
operation is completed. It becomes more worse if the memory is unpinned
and/or memory registration is large (in GB range).
Therefore, instead of holding mmap_sem for too long (for whole region
pinning), acquire and release the lock for every few pages. For example
on x86 with 4K page size, acquire and release mmap_sem for every 2Mbytes
memory chunk.
This allows other competing threads to make progress who might wish to
hold mmap_sem for shorter duration.
When memory registration latency is measured using [1] for memory sizes
ranging from 4K to 48GB, <= 1% or 0.5% degradation is noticed. In many
runs no difference is seen other than run-to-run variance.
In other targeted tests of users with large memory, desired improvements
are seen due to reduced contention of mmap_sem.
[1] https://github.com/paravmellanox/rtool
$ rdma_resource_lat -c 1 -s 48G -a -u L -i 500 -A
It registers pinned memory from 4K to 48GB size with 500 iterations for
each memory size.
$ rdma_resource_lat -c 1 -s 12G -a -u L -i 500 -t 4
4 competing threads pin memory, each of 12GB size with 500 iterations.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
rdma_nl_multicast() returns either negative error code
or zero if succeeded. Remove unnecessary ret code checks
and reassignments.
Reviewed-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Alex Estrin <alex.estrin@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
These return the same thing but dev_name is a more conventional use of the
kernel API.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Any messages related to a device should be printed with the dev_*
formatters. This provides greater consistency for the user.
The core does not set pr_fmt so this has no significant change.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
The current code has two copies of the device name, ibdev->dev and
dev_name(&ibdev->dev), and they are setup at different times, which is
very confusing.
Set them both up at the same time and make dev_name() the lead name, which
is the proper use of the driver core APIs. To make it very clear that the
name is not valid until registration pass it in to the
ib_register_device() call rather than messing with ibdev->name directly.
Also the reorganization now checks that dev_name is unique even if it does
not contain a %.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Acked-by: Adit Ranadive <aditr@vmware.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Acked-by: Devesh Sharma <devesh.sharma@broadcom.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Given a large enough memory allocation, it is possible to wrap the
pinned_vm counter. Check for addition overflow to prevent such
eventualities.
Fixes: 40ddacf2dd ("RDMA/umem: Don't hold mmap_sem for too long")
Reported-by: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Noticed while reviewing commit d4b4dd1b97 ("RDMA/umem: Do not use
current->tgid to track the mm_struct") patch. Why would we take a lock,
adjust a protected variable, drop the lock, and *then* check the input
into our protected variable adjustment? Then we have to take the lock
again on our error unwind. Let's just check the input early and skip
taking the locks needlessly if the input isn't valid.
It was also noticed that we set mm = current->mm, we then never modify
mm, but we still go back and reference current->mm a number of times
needlessly. Be consistent in using the stored reference in mm.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently add_modify_gid() for IB link layer has followong issue
in cache update path.
When GID update event occurs, core releases reference to the GID
table without updating its state and/or entry pointer.
CPU-0 CPU-1
------ -----
ib_cache_update() IPoIB ULP
add_modify_gid() [..]
put_gid_entry()
refcnt = 0, but
state = valid,
entry is valid.
(work item is not yet executed).
ipoib_create_ah()
rdma_create_ah()
rdma_get_gid_attr() <--
Tries to acquire gid_attr
which has refcnt = 0.
This is incorrect.
GID entry state and entry pointer is provides the accurate GID enty
state. Such fields must be updated with rwlock to protect against
readers and, such fields must be in sane state before refcount can drop
to zero. Otherwise above race condition can happen leading to
use-after-free situation.
Following backtrace has been observed when cache update for an IB port
is triggered while IPoIB ULP is creating an AH.
Therefore, when updating GID entry, first mark a valid entry as invalid
through state and set the barrier so that no callers can acquired
the GID entry, followed by release reference to it.
refcount_t: increment on 0; use-after-free.
WARNING: CPU: 4 PID: 29106 at lib/refcount.c:153 refcount_inc_checked+0x30/0x50
Workqueue: ib-comp-unb-wq ib_cq_poll_work [ib_core]
RIP: 0010:refcount_inc_checked+0x30/0x50
RSP: 0018:ffff8802ad36f600 EFLAGS: 00010082
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000002 RSI: 0000000000000008 RDI: ffffffff86710100
RBP: ffff8802d6e60a30 R08: ffffed005d67bf8b R09: ffffed005d67bf8b
R10: 0000000000000001 R11: ffffed005d67bf8a R12: ffff88027620cee8
R13: ffff8802d6e60988 R14: ffff8802d6e60a78 R15: 0000000000000202
FS: 0000000000000000(0000) GS:ffff8802eb200000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f3ab35e5c88 CR3: 00000002ce84a000 CR4: 00000000000006e0
IPv6: ADDRCONF(NETDEV_CHANGE): ib1: link becomes ready
Call Trace:
rdma_get_gid_attr+0x220/0x310 [ib_core]
? lock_acquire+0x145/0x3a0
rdma_fill_sgid_attr+0x32c/0x470 [ib_core]
rdma_create_ah+0x89/0x160 [ib_core]
? rdma_fill_sgid_attr+0x470/0x470 [ib_core]
? ipoib_create_ah+0x52/0x260 [ib_ipoib]
ipoib_create_ah+0xf5/0x260 [ib_ipoib]
ipoib_mcast_join_complete+0xbbe/0x2540 [ib_ipoib]
Fixes: b150c3862d ("IB/core: Introduce GID entry reference counts")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Make sure we free struct uverbs_api once we clean the radix tree. It was
allocated by uverbs_alloc_api().
Fixes: 9ed3e5f447 ("IB/uverbs: Build the specs into a radix tree at runtime")
Reported-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Nothing uses this now, just delete it.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
synchronize_rcu is slow enough that it should be avoided on the syscall
path when user space is destroying MRs. After all the rework we can now
trivially do this by having call_srcu kfree the per_mm.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
mmu_notifier_unregister() can race between a invalidate_start/end and
cause the invalidate_end to be skipped. This causes an imbalance in the
locking, which lockdep complains about.
This is not actually a bug, as we immediately kfree the memory holding the
lock, but it simple enough to fix.
Mark when the notifier is being destroyed and abort the start callback.
This can be done under the lock we already obtained, and can re-purpose
the invalidate_range test we already have.
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 is intrinsically racy and the scheme is simply unnecessary. New MR
registration can wait for any on going invalidation to fully complete.
CPU0 CPU1
if (atomic_read())
if (atomic_dec_and_test() &&
!list_empty())
{ /* not taken */ }
list_add()
Putting the new UMEM into some kind of purgatory until another invalidate
rolls through..
Instead hold the read side of the umem_rwsem across the pair'd start/end
and get rid of the racy 'deferred add' approach.
Since all umem's in the rbt are always ready to go, also get rid of the
mn_counters_active stuff.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Since ODP had a single struct mmu_notifier located in the ucontext it
could only handle a single MM at a time, and this prevented it from using
the new owning_mm system.
With the prior rework it is now simple to let ODP track multiple MMs per
ucontext, finish the job so that the per_mm is allocated on a mm by mm
basis, and freed when the last umem is dropped from the ucontext.
As a side effect the new saner locking removes the lockdep splat about
nesting the umem_rwsem between mmu_notifier_unregister and
ib_umem_odp_release.
It also makes ODP work with multiple processes, across, fork, etc.
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 is the first step to make ODP use the owning_mm that is now part of
struct ib_umem.
Each ODP umem is linked to a single per_mm structure, which in turn, is
linked to a single mm, via the embedded mmu_notifier. This first patch
introduces the structure and reworks eveything to use it.
This also needs to introduce tgid into the ib_ucontext_per_mm, as
get_user_pages_remote() requires the originating task for statistics
tracking.
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 no longer has any use, we can use container_of to get to the
umem_odp, and a simple flag to indicate if this is an odp MR. Remove the
few remaining references to it.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
These two structures are linked together, use the container_of pattern
instead of a double allocation to make the code simpler and easier to
follow.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
All of these functions already require the ODP version of the umem struct,
make this very clear by having the signature require it. This paves the
way to using the container_of() pattern to link umem_odp and umem
together.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Uverbs shouldn't enforce QP state in the command unless the user set the QP
state bit in the attribute mask.
In addition, only copy qp attr fields which have the corresponding bit set
in the attribute mask over to the internal attr structure.
Fixes: 88de869bbe ("RDMA/uverbs: Ensure validity of current QP state value")
Fixes: bc38a6abdd ("[PATCH] IB uverbs: core implementation")
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This is just wrong, the process that calls into the reg_mr is the process
associated with the umem, and that does not have to be the same process
that created the context.
When this code was first written mmgrab() didn't exist, however these days
we can just directly hold the mm_struct pointer in the umem and have no
ambiguity when it comes to releasing the umem as to which mm it was
associated with.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The disassociate_ucontext function in every driver is now empty, so we
don't need this ugly and wrong code that was messing with tgids.
rdma_user_mmap_io does this same work in a better way.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
To support disassociation and PCI hot unplug, we have to track all the
VMAs that refer to the device IO memory. When disassociation occurs the
VMAs have to be revised to point to the zero page, not the IO memory, to
allow the physical HW to be unplugged.
The three drivers supporting this implemented three different versions
of this algorithm, all leaving something to be desired. This new common
implementation has a few differences from the driver versions:
- Track all VMAs, including splitting/truncating/etc. Tie the lifetime of
the private data allocation to the lifetime of the vma. This avoids any
tricks with setting vm_ops which Linus didn't like. (see link)
- Support multiple mms, and support properly tracking mmaps triggered by
processes other than the one first opening the uverbs fd. This makes
fork behavior of disassociation enabled drivers the same as fork support
in normal drivers.
- Don't use crazy get_task stuff.
- Simplify the approach for to racing between vm_ops close and
disassociation, fixing the related bugs most of the driver
implementations had. Since we are in core code the tracking list can be
placed in struct ib_uverbs_ufile, which has a lifetime strictly longer
than any VMAs created by mmap on the uverbs FD.
Link: https://www.spinics.net/lists/stable/msg248747.html
Link: https://lkml.kernel.org/r/CA+55aFxJTV_g46AQPoPXen-UPiqR1HGMZictt7VpC-SMFbm3Cw@mail.gmail.com
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
The error path has several mistakes
- cdev_del should not be called if cdev_device_add fails
- We must call put_device on all the goto exit paths as that is what frees
the uapi, SRCU and the struct itself.
While we are here consolidate all the uvdev_dev init that cannot fail at
the top.
Fixes: c5c4d92e70 ("RDMA/uverbs: Use cdev_device_add() instead of cdev_add()")
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
rdma_set_src_addr_rcu should check copy_src_l2_addr fails, rather than
always return 0. Also copy_src_l2_addr should return 'ret' as its return
value when rdma_translate_ip fails.
Fixes: c31d4b2ddf ("RDMA/core: Protect against changing dst->dev during destination resolve")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This does nothing but indicate if the uverbs_file is in the device's list,
use list_del_init instead.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
There is a race condition between ucma_close() and ucma_resolve_ip():
CPU0 CPU1
ucma_resolve_ip(): ucma_close():
ctx = ucma_get_ctx(file, cmd.id);
list_for_each_entry_safe(ctx, tmp, &file->ctx_list, list) {
mutex_lock(&mut);
idr_remove(&ctx_idr, ctx->id);
mutex_unlock(&mut);
...
mutex_lock(&mut);
if (!ctx->closing) {
mutex_unlock(&mut);
rdma_destroy_id(ctx->cm_id);
...
ucma_free_ctx(ctx);
ret = rdma_resolve_addr();
ucma_put_ctx(ctx);
Before idr_remove(), ucma_get_ctx() could still find the ctx
and after rdma_destroy_id(), rdma_resolve_addr() may still
access id_priv pointer. Also, ucma_put_ctx() may use ctx after
ucma_free_ctx() too.
ucma_close() should call ucma_put_ctx() too which tests the
refcnt and waits for the last one releasing it. The similar
pattern is already used by ucma_destroy_id().
Reported-and-tested-by: syzbot+da2591e115d57a9cbb8b@syzkaller.appspotmail.com
Reported-by: syzbot+cfe3c1e8ef634ba8964b@syzkaller.appspotmail.com
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
When resolving destination address or route, when net namespace is
unavailable, refer to the net namespace of the netdevice of the SGID
attribute. This is typically the case for requests arriving from the
network for RoCE ports.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Introduce an API rdma_read_gid_attr_ndev_rcu() to return GID attribute
netdevice which is in UP state for accessing netdevice's fields such as
net namespace and ifindex.
This is useful for users who intent to access netdevice fields under rcu
lock.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently RoCE route resolve functionality is split between two
functions. (a) roce_resolve_route_from_path() and its helper function
rdma_resolve_ip_route().
Due to this multiple sockaddr src structures are created in both functions
with rdma_dev_addr is an interface between the two for checks.
Since there is only one user of rdma_resolve_ip_route() as RoCE, combine
the functionality of both functions to roce_resolve_route_from_path() and
further reduce the scope of rdma_dev_addr to core/addr.c
This also allow to extend addr_resolve() in subsequent patch to consider
netdev properties of GID in safer way under rcu lock.
Additionally src and dst addresses were always provided, so skip the src
addr NULL pointer check as they are present on the stack now.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
During resolving address process, during route lookup and while performing
src address translation in case of loopback mode, hold the rcu lock so
that if netdevice is moving to different net namespace, or being
unregistered, it can be synchronized with net/core/dev.c, ie
change_net_namespace()
->dev_close_many()
->rt6_uncached_list_flush_dev() who would change dst->dev
to loopback device of the given net namespace.
Therefore, hold the rcu lock and sync with synchronize_net() of
change_net_namespace() to ensure that netdevice cannot get freed while
dst->dev is being used.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Set and refer to rdma_dev_addr network type instead of dst->ndev to reduce
dependency on accessing dst netdevice.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use common code flow for resolving neighbour and for finding source
addresses.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now that rdma_copy_addr() only copies the source addresses and all callers
are interested in copying only source addresses, simplify it to drop the
destination address argument.
Given that it only copies source layer2 addresses, rename it to
rdma_copy_src_l2_addr for better code readability.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
rdma_translate_ip() is done while resolving address for the loopback
addresses. The current flow is convoluted with resolve neighbor being
optional.
This patch simplifies the code in following ways.
(a) Use common code between IPv4 and IPv6 for address translation,
loopback checks and acquiring netdevice.
(b) During neigh resolve in addr_resolve_neigh(), only copy destination
address.
(c) Always resolve the source address before the destination address,
because it doesn't depend on resolving neigh being requested or not.
This helps to reduce 3 calls of rdma_copy_addr and rdma_translate_ip to
one and makes it easier to follow the code flow.
Now that ib_nl_fetch_ha() doesn't depend on dst, drop dst argument from
ib_nl_fetch_ha().
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Current code typecasts destination address using extra variable but uses
source address as is.
Even though the compiler optimizes such code well, just let each protocol
specific function typecast for src and dest both and have symmetric code.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
addr4_resolve() and addr6_resolve() are called by checking the value of
sa_family.
Both above functions overwrite the value after typecasting, this is not
necessary.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This fixes two issues:
1. When address family is other than IPv4 or v6, rdma_translate_ip()
returns success which is incorrect.
2. When address familty is AF_INET6, and if the source address is not
found, it returns success, which is also incorrect.
Therefore, introduce and use rdma_find_ndev_for_src_ip_rcu() helper
function which returns correct success or error status and is also useful
for future code refactor in addr_resolve().
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently a uverbs completion event queue is flushed of events in
ib_uverbs_comp_event_close() with the queue spinlock held and then
released. Yet setting ev_queue->is_closed is not set until later in
uverbs_hot_unplug_completion_event_file().
In between the time ib_uverbs_comp_event_close() releases the lock and
uverbs_hot_unplug_completion_event_file() acquires the lock, a completion
event can arrive and be inserted into the event queue by
ib_uverbs_comp_handler().
This can cause a "double add" list_add warning or crash depending on the
kernel configuration, or a memory leak because the event is never dequeued
since the queue is already closed down.
So add setting ev_queue->is_closed = 1 to ib_uverbs_comp_event_close().
Cc: stable@vger.kernel.org
Fixes: 1e7710f3f6 ("IB/core: Change completion channel to use the reworked objects schema")
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Support attaching flow actions to a flow rule via raw create flow.
For now only NIC RX path is supported. This change requires to export
flow resources management functions so we can maintain proper bookkeeping
of flow actions.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Use ib_set_flow() when initializing flow related resources.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Methods sometimes need to get a flexible set of IDRs and not a strict set
as can be achieved today by the conventional IDR attribute. Add a new
IDRS_ARRAY attribute to the generic uverbs ioctl layer.
IDRS_ARRAY points to array of idrs of the same object type and same access
rights, only write and read are supported.
Signed-off-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>``
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Even though device->ifindex is assigned before adding the device in the
list which is read by netlink flow, it is better to assign rdma device
index before publishing the device in the system to users and clients.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
During register_device() init sequence is,
(a) register with rdma cgroup followed by
(b) register with sysfs
Therefore, unregister_device() sequence should follow the reverse order.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Lockdep engine handles correctly downgrade of locks and it simply
incorrect to disable lockdep checks prior to calling mmu_notifier.
Remove lockdep_off and ensure locks correctness.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Even though device registration/unregistration and client
registration/unregistration is not a performance path, define the
client_data_lock as rwlock for code clarity.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
add_client_context(), ib_unregister_device() and ib_unregister_client()
are designed to call from blocking context. There is no need to save and
restore last interrupt state when called from such blocking context. Even
though this is not a performance path, using the right spin lock API is
desired for code clarity.
To avoid checkpatch warning while removing flags, sizeof() is used.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
While unregistering a device, remove the context elements from the list to
not have any stale entries. With that any errors/bugs can be checked when
device is freed.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
While traversing client_data_list in following conditions, linked list is
only read, no elements of the list are removed. Therefore, use
list_for_each_entry(), instead of list_for_each_safe().
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
While unregistering a client, only context removal should be protected
with lock. There is no need to protect a freeing of such context which is
already removed from the list.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently rdma_addr_cancel() is an async operation, which notifies that
cancel is done by executing the callback function given during
rdma_resolve_ip(). If resolve_ip request is already completed than
callback is not executed.
Instead, now rdma_resolve_addr() and rdma_addr_cancel() simplified in
following ways.
1. rdma_addr_cancel() now a synchronous method. If request was
pending, after it is cancelled, no callback is notified.
2. rdma_resolve_addr() and respective addr_handler() callback doesn't
need to hold reference to cm_id.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
While registering a mad agent, a user space can trigger various errors
and flood the logs.
Therefore, decrease verbosity and rate limit such error messages.
While we are at it, use __func__ to print function name.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When requested QP type is not supported for a {device, port}, return the
error right away before validating all parameters during mad agent
registration time.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When AF_IB addresses are used during rdma_resolve_addr() a lock is not
held. A cma device can get removed while list traversal is in progress
which may lead to crash. ie
CPU0 CPU1
==== ====
rdma_resolve_addr()
cma_resolve_ib_dev()
list_for_each() cma_remove_one()
cur_dev->device mutex_lock(&lock)
list_del();
mutex_unlock(&lock);
cma_process_remove();
Therefore, hold a lock while traversing the list which avoids such
situation.
Cc: <stable@vger.kernel.org> # 3.10
Fixes: f17df3b0de ("RDMA/cma: Add support for AF_IB to rdma_resolve_addr()")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
For dependencies, branch based on rdma.git 'for-rc' of
https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git/
Pull 'uverbs_dev_cleanups' from Leon Romanovsky:
====================
Reuse the char device code interfaces to simplify ib_uverbs_device
creation and destruction. As part of this series, we are sending fix to
cleanup path, which was discovered during internal review,
The fix definitely can go to -rc, but it means that this series will be
dependent on rdma-rc.
====================
* branch 'uverbs_dev_cleanups':
RDMA/uverbs: Use device.groups to initialize device attributes
RDMA/uverbs: Use cdev_device_add() instead of cdev_add()
RDMA/core: Depend on device_add() to add device attributes
RDMA/uverbs: Fix error cleanup path of ib_uverbs_add_one()
Resolved conflict in ib_device_unregister_sysfs()
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Instead of explicitly adding device attribute files and handling such
error conditions, depend on device core layer to create device attributes
files based group pointer NULL terminated array.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Instead of doing two step process to add char device and create underlying
device, use cdev_device_add() which does both.
Currently a kobject per uverbs_device is created to keep reference to its
holding ib_uverbs_device in addition to its underlying device 'dev'.
Instead just use uverbs_device->dev to keep a reference to.
With this change there is single reference tracker for ib_uverbs_device
structure.
This allows for subsequent patch to registers group attribute as well
using single API cdev_device_add().
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Instead of adding/removing device attribute files, depend on device_add()
which considers adding these device files based on NULL terminated
attributes group array.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
If ib_uverbs_create_uapi() fails, dev_num should be freed from the bitmap.
Fixes: 7d96c9b176 ("IB/uverbs: Have the core code create the uverbs_root_spec")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reuse existing get_device() API to do it symmetric to already used
put_device() in commit 924b8900a4 ("RDMA/core: Replace open-coded
variant of put_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>
The "closing" variable is used as boolean and set to "true" in one
place, update the declaration of that variable and their other
assignment to proper type.
Fixes: e951747a08 ("IB/uverbs: Rework the locking for cleaning up the ucontext")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The upstream kernel commit cited below modified the workqueue in the
new CQ API to be bound to a specific CPU (instead of being unbound).
This caused ALL users of the new CQ API to use the same bound WQ.
Specifically, MAD handling was severely delayed when the CPU bound
to the WQ was busy handling (higher priority) interrupts.
This caused a delay in the MAD "heartbeat" response handling,
which resulted in ports being incorrectly classified as "down".
To fix this, add a new "unbound" WQ type to the new CQ API, so that users
have the option to choose either a bound WQ or an unbound WQ.
For MADs, choose the new "unbound" WQ.
Fixes: b7363e67b2 ("IB/device: Convert ib-comp-wq to be CPU-bound")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.m>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Refactor the initialization of a flow action object to a common function.
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This makes it clear and safe to access constants passed in from user
space. We define a consistent ABI of u64 for all constants, and verify
that the data passed in can be represented by the type the user supplies.
The expectation is this will always be used with an enum declaring the
constant values, and the user will use the enum type as input to the
accessor.
To retrieve the attribute value we introduce two helper calls - one
standard which may fail if attribute is not valid and one where caller can
provide a default value which will be used in case the attribute is not
valid (useful when attribute is optional).
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
The object lock was supposed to always be released during destroy, but
when the destruction retry series was integrated with the destroy series
it created a failure path that missed the unlock.
Keep with convention, if destroy fails the caller must undo all locking.
Fixes: 87ad80abc7 ("IB/uverbs: Consolidate uobject destruction")
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The current code grabs the private_data of whatever file descriptor
userspace has supplied and implicitly casts it to a `struct ucma_file *`,
potentially causing a type confusion.
This is probably fine in practice because the pointer is only used for
comparisons, it is never actually dereferenced; and even in the
comparisons, it is unlikely that a file from another filesystem would have
a ->private_data pointer that happens to also be valid in this context.
But ->private_data is not always guaranteed to be a valid pointer to an
object owned by the file's filesystem; for example, some filesystems just
cram numbers in there.
Check the type of the supplied file descriptor to be safe, analogous to how
other places in the kernel do it.
Fixes: 88314e4dda ("RDMA/cma: add support for rdma_migrate_id()")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There are several blockable mmu notifiers which might sleep in
mmu_notifier_invalidate_range_start and that is a problem for the
oom_reaper because it needs to guarantee a forward progress so it cannot
depend on any sleepable locks.
Currently we simply back off and mark an oom victim with blockable mmu
notifiers as done after a short sleep. That can result in selecting a new
oom victim prematurely because the previous one still hasn't torn its
memory down yet.
We can do much better though. Even if mmu notifiers use sleepable locks
there is no reason to automatically assume those locks are held. Moreover
majority of notifiers only care about a portion of the address space and
there is absolutely zero reason to fail when we are unmapping an unrelated
range. Many notifiers do really block and wait for HW which is harder to
handle and we have to bail out though.
This patch handles the low hanging fruit.
__mmu_notifier_invalidate_range_start gets a blockable flag and callbacks
are not allowed to sleep if the flag is set to false. This is achieved by
using trylock instead of the sleepable lock for most callbacks and
continue as long as we do not block down the call chain.
I think we can improve that even further because there is a common pattern
to do a range lookup first and then do something about that. The first
part can be done without a sleeping lock in most cases AFAICS.
The oom_reaper end then simply retries if there is at least one notifier
which couldn't make any progress in !blockable mode. A retry loop is
already implemented to wait for the mmap_sem and this is basically the
same thing.
The simplest way for driver developers to test this code path is to wrap
userspace code which uses these notifiers into a memcg and set the hard
limit to hit the oom. This can be done e.g. after the test faults in all
the mmu notifier managed memory and set the hard limit to something really
small. Then we are looking for a proper process tear down.
[akpm@linux-foundation.org: coding style fixes]
[akpm@linux-foundation.org: minor code simplification]
Link: http://lkml.kernel.org/r/20180716115058.5559-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Christian König <christian.koenig@amd.com> # AMD notifiers
Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx and umem_odp
Reported-by: David Rientjes <rientjes@google.com>
Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: Dennis Dalessandro <dennis.dalessandro@intel.com>
Cc: Sudeep Dutt <sudeep.dutt@intel.com>
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
rdma.git merge resolution for the 4.19 merge window
Conflicts:
drivers/infiniband/core/rdma_core.c
- Use the rdma code and revise with the new spelling for
atomic_fetch_add_unless
drivers/nvme/host/rdma.c
- Replace max_sge with max_send_sge in new blk code
drivers/nvme/target/rdma.c
- Use the blk code and revise to use NULL for ib_post_recv when
appropriate
- Replace max_sge with max_recv_sge in new blk code
net/rds/ib_send.c
- Use the net code and revise to use NULL for ib_post_recv when
appropriate
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAltwm2geHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGITkH/iSzkVhT2OxHoir0
mLVzTi7/Z17L0e/ELl7TvAC0iLFlWZKdlGR0g3b4/QpXLPmNK4HxiDRTQuWn8ke0
qDZyDq89HqLt+mpeFZ43PCd9oqV8CH2xxK3iCWReqv6bNnowGnRpSStlks4rDqWn
zURC/5sUh7TzEG4s997RrrpnyPeQWUlf/Mhtzg2/WvK2btoLWgu5qzjX1uFh3s7u
vaF2NXVJ3X03gPktyxZzwtO1SwLFS1jhwUXWBZ5AnoJ99ywkghQnkqS/2YpekNTm
wFk80/78sU+d91aAqO8kkhHj8VRrd+9SGnZ4mB2aZHwjZjGcics4RRtxukSfOQ+6
L47IdXo=
=sJkt
-----END PGP SIGNATURE-----
Merge tag 'v4.18' into rdma.git for-next
Resolve merge conflicts from the -rc cycle against the rdma.git tree:
Conflicts:
drivers/infiniband/core/uverbs_cmd.c
- New ifs added to ib_uverbs_ex_create_flow in -rc and for-next
- Merge removal of file->ucontext in for-next with new code in -rc
drivers/infiniband/core/uverbs_main.c
- for-next removed code from ib_uverbs_write() that was modified
in for-rc
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Filter functions returns either 0 or 1, therefore better change their
return type from int to bool to reflect the same. Additionally some
filter functions have suffix of _filter some doesn't. Make all filter
function consistent to have __filter suffix to improve code readability.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Update all GID table entries of the netdevice whose MAC address changed.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently following issues exist:
1. Default GIDs of the lower (slave) netdevice if the bond netdevice is
added. Rather default GID should be of bond master netdevice.
2. Due to this, when failover event occurs FAILOVER event handler attempts
to delete the GID of the upper device and tries to add the default GID
of the lower device. This is incorrect behavior.
To have simple and correct code:
(a) Split default GIDs addition out of add_netdev_ips(). This allows
easier removal in future if RoCE default GIDs are removed.
(b) Add default GIDs of the bond master device by using right filter and
callback function.
(c) Remove unused function enum_netdev_default_gids().
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now that we correctly delete the default GIDs of lower devices during
CHANGEUPPER event, add default GIDs of the bonding master 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>
When NETDEV_CHANGEUPPER event occurs, lower device is not yet established
as slave of the master, and when upper device is bond device, default GID
entries not deleted.
Due to this, when bond device is fully configured, default GID entries of
bond device cannot be added as default GID entries are occupied by the
lower netdevice. This is incorrect.
Default GID entries should really be of bond netdevice because in all RoCE
GIDs (default or IP), MAC address of the bond device will be used. It is
confusing to have default GID of netdevice which is not really used for
any purpose.
Therefore, as first step, implement
(a) filter function which filters if a CHANGEUPPER event netdevice and
associated upper device is master device or not.
(b) callback function which deletes the default GIDs of lower (event
netdevice).
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently bond_delete_netdev_default_gids() is called by two callers.
(a) del_netdev_default_ips_join()
(b) del_netdev_default_ips()
Both above functions changes the argument order while calling
bond_delete_netdev_default_gids(). This required silly
del_netdev_default_ips() wrapper.
Additionally, del_netdev_default_ips() deletes default GIDs not IP based
GIDs. del_netdev_default_ips() having _ips suffix is confusing.
Therefore, get rid of confusing del_netdev_default_ips() and simplify
bond_delete_netdev_default_gids() to follow same argument order as its
caller.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add comment for handling CHANGEUPPER netevent handling.
To improve code readability,
(a) move cmd definitions to its respective if-else branches,
(b) avoid single line structure definitions.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Even though this interface is marked CONFIG_BROKEN we still expect it to
compile, at least until we delete it completely.
Also mark INFINIBAND_USER_ACCESS_UCM with COMPILE_TEST so these situations
can be detected.
Fixes: e7ff98aefc ("RDMA/cma: Constify path record, ib_cm_event, listen_id pointers")
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Pull locking/atomics update from Thomas Gleixner:
"The locking, atomics and memory model brains delivered:
- A larger update to the atomics code which reworks the ordering
barriers, consolidates the atomic primitives, provides the new
atomic64_fetch_add_unless() primitive and cleans up the include
hell.
- Simplify cmpxchg() instrumentation and add instrumentation for
xchg() and cmpxchg_double().
- Updates to the memory model and documentation"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
locking/atomics: Rework ordering barriers
locking/atomics: Instrument cmpxchg_double*()
locking/atomics: Instrument xchg()
locking/atomics: Simplify cmpxchg() instrumentation
locking/atomics/x86: Reduce arch_cmpxchg64*() instrumentation
tools/memory-model: Rename litmus tests to comply to norm7
tools/memory-model/Documentation: Fix typo, smb->smp
sched/Documentation: Update wake_up() & co. memory-barrier guarantees
locking/spinlock, sched/core: Clarify requirements for smp_mb__after_spinlock()
sched/core: Use smp_mb() in wake_woken_function()
tools/memory-model: Add informal LKMM documentation to MAINTAINERS
locking/atomics/Documentation: Describe atomic_set() as a write operation
tools/memory-model: Make scripts executable
tools/memory-model: Remove ACCESS_ONCE() from model
tools/memory-model: Remove ACCESS_ONCE() from recipes
locking/memory-barriers.txt/kokr: Update Korean translation to fix broken DMA vs. MMIO ordering example
MAINTAINERS: Add Daniel Lustig as an LKMM reviewer
tools/memory-model: Fix ISA2+pooncelock+pooncelock+pombonce name
tools/memory-model: Add litmus test for full multicopy atomicity
locking/refcount: Always allow checked forms
...
Now that the ioctl path and uobjects are converted to use uverbs_api, it
is now safe to remove the disassociation protection from the common ioctl
code.
This completes the work to make destroy functions continue to work even
after device disassociation.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
Several handlers need temporary allocations for the life of the method,
switch them to use the uverbs_alloc allocator.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
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: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
This is missing a zeroing of the high bits of flags, and is also not
correct for big endian machines. Properly zero extend the 32 bit flags
into the 64 bit stack variable.
Reported-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Fixes: bccd06223f ("IB/uverbs: Add UVERBS_ATTR_FLAGS_IN to the specs language")
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
sgid_attr is uninitialized on the stack, initialize it to NULL.
Fixes: 398391071f ("IB/cm: Replace members of sa_path_rec with 'struct sgid_attr *'")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Yossi Itigin <yosefe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
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: Jason Gunthorpe <jgg@mellanox.com>
The core code will destroy the HW object on behalf of the method, if the
method provides an implementation it must simply copy data from the stub
uobj into the response. Destroy methods cannot touch the HW object.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
In rdma cm module, functions which are common between IB and iWarp
are named with cma_.
iWarp specific functions are prefixed with cma_iw.
IB specific functions are perfixed with cma_ib.
However some functions in request processing path didn't follow
cma_ib notion. Prefix them with _ib for better code clarity.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
cma_add_one() initializes the default GID regardless of device type.
listen_id is bound to a device and an IP address, its GID type is
initialized by cma_acquire_dev().
Therefore a valid default GID type is always available, it is not needed
to check port type during cma_acquire_dev().
Initialize gid type of a cm id when the cm_id is created instead of
doing conditional checks during cma_acquire_dev() and trying to
initialize to 0 during _cma_attach_to_dev().
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
In various functions rdma_cm_event is zero initialized on stack using
memset() while holding lock which is not necessary.
Therefore, don't hold the lock while initializing on stack.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Return bool for following internal and inline functions as their
underlying APIs return bool too.
1. cma_zero_addr()
2. cma_loopback_addr()
3. cma_any_addr()
4. ib_addr_any()
5. ib_addr_loopback()
While we are touching cma_loopback_addr(), remove extra white spaces
in it.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Arrange fields of cma_req_info structure for efficiency on
stack and get rid of one bit boolean field.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Constify several pointers such as path_rec, ib_cm_event and listen_id
pointers in several functions.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Following APIs are not supposed to modify addr or dest_addr contents.
Therefore make those function argument const for better code
readability.
1. rdma_resolve_ip()
2. rdma_addr_size()
3. rdma_resolve_addr()
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently dst address is first set and later on cleared on either of the
3 error conditions are met.
However none of the APIs or checks are supposed to refer to the
destination address of the cm_id.
Therefore, set the destination address after necessary checks pass which
simplifies the error flow.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently rdma_cm_id's resource tracking fields such as owner task and
kern_name and other non resource tracking fields are initialized in
in single function __rdma_create_id().
Therefore, initialize rdma_cm_id's resource type also in same init
function.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Make sure the providers implement the verbs callbacks before calling
them, otherwise return -EOPNOTSUPP.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
{create,destroy}_ah aren't mandatory verbs, because not all providers
are implementing them.
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This clearly indicates that the input is a bitwise combination of values
in an enum, and identifies which enum contains the definition of the bits.
Special accessors are provided that handle the mandatory validation of the
allowed bits and enforce the correct type for bitwise flags.
If we had introduced this at the start then the kabi would have uniformly
used u64 data to pass flags, however today there is a mixture of u64 and
u32 flags. All places are converted to accept both sizes and the accessor
fixes it. This allows all existing flags to grow to u64 in future without
any hassle.
Finally all flags are, by definition, optional. If flags are not passed
the accessor does not fail, but provides a value of zero.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Since neither ib_post_send() nor ib_post_recv() modify the data structure
their second argument points at, declare that argument const. This change
makes it necessary to declare the 'bad_wr' argument const too and also to
modify all ULPs that call ib_post_send(), ib_post_recv() or
ib_post_srq_recv(). This patch does not change any functionality but makes
it possible for the compiler to verify whether the
ib_post_(send|recv|srq_recv) really do not modify the posted work request.
To make this possible, only one cast had to be introduce that casts away
constness, namely in rpcrdma_post_recvs(). The only way I can think of to
avoid that cast is to introduce an additional loop in that function or to
change the data type of bad_wr from struct ib_recv_wr ** into int
(an index that refers to an element in the work request list). However,
both approaches would require even more extensive changes than this
patch.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently if the cm_id is not bound to any netdevice, than for such cm_id,
net namespace is ignored; which is incorrect.
Regardless of cm_id bound to a netdevice or not, net namespace must
match. When a cm_id is bound to a netdevice, in such case net namespace
and netdevice both must match.
Fixes: 4c21b5bcef ("IB/cma: Add net_dev and private data checks to RDMA CM")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When netdevice is not found for a request, and if it for RoCE port,
currently it allows matching the listener as long as port number matches
by ignoring the netdevice.
Now that we always prefer to have netdevice associated with RoCE, when
netdevice is not found, don't consider RoCE ports.
In other words, a NULL netdevice with RoCE is not acceptable. Therefore,
remove this confusing RoCE port ignorance check.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
For RoCE, when CM requests are received for RC and UD connections,
netdevice of the incoming request is unavailable. Because of that CM
requests are always forwarded to init_net namespace.
Now that we have the GID attribute available, introduce SGID attribute in
incoming CM requests and refer to the netdevice of it. This is similar to
existing SGID attribute field in outgoing CM requests for RC and UD
transports.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Remove unnecessary parentheses to fix the clang warning of extraneous
parentheses.
Signed-off-by: Varsha Rao <rvarsha016@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
We have a parallel unlocked reader and writer with ib_uverbs_get_context()
vs everything else, and nothing guarantees this works properly.
Audit and fix all of the places that access ucontext to use one of the
following locking schemes:
- Call ib_uverbs_get_ucontext() under SRCU and check for failure
- Access the ucontext through an struct ib_uobject context member
while holding a READ or WRITE lock on the uobject.
This value cannot be NULL and has no race.
- Hold the ucontext_lock and check for ufile->ucontext !NULL
This also re-implements ib_uverbs_get_ucontext() in a way that is safe
against concurrent ib_uverbs_get_context() and disassociation.
As a side effect, every access to ucontext in the commands is via
ib_uverbs_get_context() with an error check, or via the uobject, so there
is no longer any need for the core code to check ucontext on every command
call. These checks are also removed.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Allocating the struct file during alloc_begin creates this strange
asymmetry with IDR, where the FD has two krefs pointing at it during the
pre-commit phase. In particular this makes the abort process for FD very
strange and confusing.
For instance abort currently calls the type's destroy_object twice, and
the fops release once if abort is done. This is very counter intuitive. No
fops should be called until alloc_commit succeeds, and destroy_object
should only ever be called once.
Moving the struct file allocation to the alloc_commit is now simple, as we
already support failure of rdma_alloc_commit_uobject, with all the
required rollback pieces.
This creates an understandable symmetry with IDR and simplifies/fixes the
abort handling for FD types.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The ioctl framework already does this correctly, but the write path did
not. This is trivially fixed by simply using a standard pattern to return
uobj_alloc_commit() as the last statement in every function.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The locking here has always been a bit crazy and spread out, upon some
careful analysis we can simplify things.
Create a single function uverbs_destroy_ufile_hw() that internally handles
all locking. This pulls together pieces of this process that were
sprinkled all over the places into one place, and covers them with one
lock.
This eliminates several duplicate/confusing locks and makes the control
flow in ib_uverbs_close() and ib_uverbs_free_hw_resources() extremely
simple.
Unfortunately we have to keep an extra mutex, ucontext_lock. This lock is
logically part of the rwsem and provides the 'down write, fail if write
locked, wait if read locked' semantic we require.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Rename 'cleanup_rwsem' to 'hw_destroy_rwsem' which is held across any call
to the type destroy function (aka 'hw' destroy). The main purpose of this
lock is to prevent normal add and destroy from running concurrently with
uverbs_cleanup_ufile()
Since the uobjects list is always manipulated under the 'hw_destroy_rwsem'
we can eliminate the uobjects_lock in the cleanup function. This allows
converting that lock to a very simple spinlock with a narrow critical
section.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The locking requirements here have changed slightly now that we can rely
on the ib_uverbs_file always existing and containing all the necessary
locking infrastructure.
That means we can get rid of the cleanup_mutex usage (this was protecting
the check on !uboj->context).
Otherwise, follow the same pattern that IDR uses for destroy, acquire
exclusive write access, then call destroy and the undo the 'lookup'.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This wasn't wrong, but the placement of two krefs didn't make any
sense. Follow some simple rules.
- A kref is held inside uobjects_list
- A kref is held inside the IDR
- A kref is held inside file->private
- A stack based kref is passed bettwen alloc_begin and
alloc_abort/alloc_commit
Any place we destroy one of the above pointers, we stick a put,
or 'move' the kref into another pointer.
The key functions have sensible semantics:
- alloc_uobj fully initializes the common members in uobj, including
the list
- Get rid of the uverbs_idr_remove_uobj helper since IDR remove
does require put, but it depends on the situation. Later
patches will re-consolidate this differently.
- alloc_abort always consumes the passed kref, done in the type
- alloc_commit always consumes the passed kref, done in the type
- rdma_remove_commit_uobject always pairs with a lookup_get
After it is all done the only control flow change is to:
- move a get from alloc_commit_fd_uobject to rdma_alloc_commit_uobject
- add a put to remove_commit_idr_uobject
- Consistenly use rdma_lookup_put in rdma_remove_commit_uobject at
the right place
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The alloc_commit callback makes the uobj visible to other threads,
and it does so using a 'move' semantic of the uobj kref on the stack
into the public storage (eg the IDR, uobject list and file_private_data)
Once this is done another thread could start up and trigger deletion
of the kref. Fortunately cleanup_rwsem happens to prevent this from
being a bug, but that is a fantastically unclear side effect.
Re-organize things so that alloc_commit is that last thing to touch
the uobj, get rid of the sneaky implicit dependency on cleanup_rwsem,
and add a comment reminding that uobj is no longer kref'd after
alloc_commit.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Our ABI for write() uses a s32 for FDs and a u32 for IDRs, but internally
we ended up implicitly casting these ABI values into an 'int'. For ioctl()
we use a s64 for FDs and a u64 for IDRs, again casting to an int.
The various casts to int are all missing range checks which can cause
userspace values that should be considered invalid to be accepted.
Fix this by making the generic lookup routine accept a s64, which does not
truncate the write API's u32/s32 or the ioctl API's s64. Then push the
detailed range checking down to the actual type implementations to be
shared by both interfaces.
Finally, change the copy of the uobj->id to sign extend into a s64, so eg,
if we ever wish to return a negative value for a FD it is carried
properly.
This ensures that userspace values are never weirdly interpreted due to
the various trunctations and everything that is really out of range gets
an EINVAL.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
If the method fails after calling rdma_explicit_destroy (eg if
copy_to_user faults) then it will trigger a kernel oops:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
PGD 800000000548d067 P4D 800000000548d067 PUD 54a0067 PMD 0
SMP PTI
CPU: 0 PID: 359 Comm: ibv_rc_pingpong Not tainted 4.18.0-rc1+ #28
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
RIP: 0010: (null)
Code: Bad RIP value.
RSP: 0018:ffffc900001a3bf0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff88000603bd00 RCX: 0000000000000003
RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff88000603bd00
RBP: 0000000000000001 R08: ffffc900001a3cf8 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffc900001a3cf0
R13: 0000000000000000 R14: ffffc900001a3cf0 R15: 0000000000000000
FS: 00007fb00dda8700(0000) GS:ffff880007c00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffffffffd6 CR3: 000000000548e004 CR4: 00000000003606b0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
? rdma_lookup_put_uobject+0x22/0x50 [ib_uverbs]
? uverbs_finalize_object+0x3b/0x60 [ib_uverbs]
? uverbs_finalize_attrs+0x128/0x140 [ib_uverbs]
? ib_uverbs_cmd_verbs+0x698/0x7c0 [ib_uverbs]
? find_held_lock+0x2d/0x90
? __might_fault+0x39/0x90
? ib_uverbs_ioctl+0x111/0x1f0 [ib_uverbs]
? do_vfs_ioctl+0xa0/0x6d0
? trace_hardirqs_on_caller+0xed/0x180
? _raw_spin_unlock_irq+0x24/0x40
? syscall_trace_enter+0x138/0x1d0
? ksys_ioctl+0x35/0x60
? __x64_sys_ioctl+0x11/0x20
? do_syscall_64+0x5b/0x1c0
? entry_SYSCALL_64_after_hwframe+0x49/0xbe
This is because the type was replaced with the null_type during explicit
destroy that cannot complete the destruction.
One of the side effects of replacing the type is to make the object
handle totally unreachable - so no other command could attempt to use
it, even though it remains on the uboject list.
We can get the same end result by just fully destroying the object inside
rdma_explicit_destroy and leaving the caller the residual kref for the
uobj with no attached HW object, and no presence in the ubojects list.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Instead of declaring and passing a dummy 'bad_wr' pointer, pass NULL
as third argument to ib_post_(send|recv|srq_recv)().
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The commit cited below checked that the port numbers provided in the
primary and alt AVs are legal.
That is sufficient to prevent a kernel panic. However, it is not
sufficient for correct operation.
In Linux, AVs (both primary and alt) must be completely self-described.
We do not accept an AV from userspace without an embedded port number.
(This has been the case since kernel 3.14 commit dbf727de74
("IB/core: Use GID table in AH creation and dmac resolution")).
For the primary AV, this embedded port number must match the port number
specified with IB_QP_PORT.
We also expect the port number embedded in the alt AV to match the
alt_port_num value passed by the userspace driver in the modify_qp command
base structure.
Add these checks to modify_qp.
Cc: <stable@vger.kernel.org> # 4.16
Fixes: 5d4c05c3ee ("RDMA/uverbs: Sanitize user entered port numbers prior to access it")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This patch considers the case that ib_flow is created by some device
driver with its specific parameters using the KABI infrastructure.
In that case both QP and ib_uflow_resources might not be applicable.
Downstream patches from this series use the above functionality.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Introduce flow steering matcher object and its create and destroy methods.
This matcher object holds some mlx5 specific driver properties that
matches the underlay device specification when an mlx5 flow steering group
is created.
It will be used in downstream patches to be part of mlx5 specific create
flow method.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This variable isn't read and written to with proper locking, so it is
racy. Instead of using an unlocked bool use presence in the mc->list
The caller could race rdma_join_multicast with rdma_leave_multicast which
would leak a mc join and cause a use after free of mc.
Instead, do not add the mc to the list until it has completed
initialization, all mcs on the list require leaving.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Simplify exit paths in ib_umem_get to use the standard goto unwind
pattern.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
DMA mapping is time consuming operation and doesn't need to be performed
with mmap_sem semaphore is held.
The semaphore only needs to be held for accounting and get_user_pages
related activities.
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Enable uverbs_destroy_def_handler to be used by drivers and replace
current code to use it.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Userspace also needs to know if the port requires GRHs to properly form
the AVs it creates.
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Extend the existing grh_required flag to check when AV's are handled that
a GRH is present.
Since we don't want to do query_port during the AV checks for performance
reasons move the flag into the immutable_data.
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
grh_required is intended to be a global setting where all AV's will
require a GRH, not just the sm_lid. Move the special logic to the creation
of the SM AH.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
