Age | Commit message (Collapse) | Author | Files | Lines |
|
Compilation of mlx5 driver without CONFIG_INFINIBAND_USER_ACCESS generates
the following error.
on x86_64:
ld: drivers/infiniband/hw/mlx5/main.o: in function `mlx5_ib_handler_MLX5_IB_METHOD_VAR_OBJ_ALLOC':
main.c:(.text+0x186d): undefined reference to `ib_uverbs_get_ucontext_file'
ld: drivers/infiniband/hw/mlx5/main.o:(.rodata+0x2480): undefined reference to `uverbs_idr_class'
ld: drivers/infiniband/hw/mlx5/main.o:(.rodata+0x24d8): undefined reference to `uverbs_destroy_def_handler'
This is happening because some parts of the UAPI description are not
static. This is a hold over from earlier code that relied on struct
pointers to refer to object types, now object types are referenced by
number. Remove the unused globals and add statics to the remaining UAPI
description elements.
Remove the redundent #ifdefs around mlx5_ib_*defs and obsolete
mlx5_ib_get_devx_tree().
The compiler now trims alot more unused code, including the above
problematic definitions when !CONFIG_INFINIBAND_USER_ACCESS.
Fixes: 7be76bef320b ("IB/mlx5: Introduce VAR object and its alloc/destroy methods")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Below commit missed the AF_IB and loopback code flow in
rdma_resolve_addr(). This leads to an unbalanced cm_id refcount in
cma_work_handler() which puts the refcount which was not incremented prior
to queuing the work.
A call trace is observed with such code flow:
BUG: unable to handle kernel NULL pointer dereference at (null)
[<ffffffff96b67e16>] __mutex_lock_slowpath+0x166/0x1d0
[<ffffffff96b6715f>] mutex_lock+0x1f/0x2f
[<ffffffffc0beabb5>] cma_work_handler+0x25/0xa0
[<ffffffff964b9ebf>] process_one_work+0x17f/0x440
[<ffffffff964baf56>] worker_thread+0x126/0x3c0
Hence, hold the cm_id reference when scheduling the resolve work item.
Fixes: 722c7b2bfead ("RDMA/{cma, core}: Avoid callback on rdma_addr_cancel()")
Link: https://lore.kernel.org/r/20200126142652.104803-2-leon@kernel.org
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Except for the last entry, the ending iova alignment sets the maximum
possible page size as the low bits of the iova must be zero when starting
the next chunk.
Fixes: 4a35339958f1 ("RDMA/umem: Add API to find best driver supported page size in an MR")
Link: https://lore.kernel.org/r/20200128135612.174820-1-leon@kernel.org
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Tested-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
All accesses now use the new IBA acessor scheme, so delete the structs
entirely and generate the structures from the schema file.
Link: https://lore.kernel.org/r/20200116170037.30109-8-jgg@ziepe.ca
Tested-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Use a Coccinelle spatch to replace CM structure members used as
structures, arrays, or pointers with IBA_GET/SET versions. Applied with
$ spatch --sp-file edits.sp --in-place drivers/infiniband/core/cm.c
The spatch file was generated using the template pattern:
@@
expression src;
expression len;
{struct} *msg;
@@
- memcpy(msg->{old_name}, src, len)
+ IBA_SET_MEM({new_name}, msg, src, len)
@@
{struct} *msg;
identifier x;
@@
- msg->{old_name}.x
+ IBA_GET_MEM_PTR({new_name}, msg)->x
@@
{struct} *msg;
@@
- &msg->{old_name}
+ IBA_GET_MEM_PTR({new_name}, msg)
For GIDs:
@@
{struct} *msg;
@@
- msg->{old_name}
+ *IBA_GET_MEM_PTR({new_name}, msg)
For non-GIDs:
@@
{struct} *msg;
@@
- msg->{old_name}
+ IBA_GET_MEM_PTR({new_name}, msg)
Iterated for every remaining IBA_CHECK_OFF()/IBA_CHECK_GET()
pairing. Touched up with clang-format after.
Link: https://lore.kernel.org/r/20200116170037.30109-7-jgg@ziepe.ca
Tested-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Use a Coccinelle spatch script to replace use of simple CM structure
members with IBA_GET/SET versions. Applied with
$ spatch --sp-file edits.sp --in-place drivers/infiniband/core/cm.c
The spatch file was generated using the template pattern:
@@
expression val;
{struct} *msg;
@@
- msg->{old_name} = val
+ IBA_SET({new_name}, msg, be{bits}_to_cpu(val))
@@
{struct} *msg;
@@
- msg->{old_name}
+ cpu_to_be{bits}(IBA_GET({new_name}, msg))
Iterated for every IBA_CHECK_OFF that isn't a CM_FIELD_MLOC.
And the below iterated over all byte sizes to remove doubled byte swaps:
@@
expression val;
@@
-be{bits}_to_cpu(cpu_to_be{bits}(val))
+val
(and __be_to_cpu and ntoh varients)
Touched up with clang-format after.
Link: https://lore.kernel.org/r/20200116170037.30109-6-jgg@ziepe.ca
Tested-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Use a Coccinelle spatch script to replace CM helper functions that
return/accept BE values with IBA_GET/SET versions. Applied with
$ spatch --sp-file edits.sp --in-place drivers/infiniband/core/cm.c
The spatch file was generated using the template pattern:
@@
expression val;
{struct} *msg;
@@
- {old_setter}(msg, val)
+ IBA_SET({new_name}, msg, be{bits}_to_cpu(val))
@@
{struct} *msg;
@@
- {old_getter}(msg)
+ cpu_to_be{bits}(IBA_GET({new_name}, msg))
Iterated for every IBA_CHECK_GET_BE()/IBA_CHECK_SET_BE() pairing.
And the below iterated over all byte sizes to remove doubled byte swaps:
@@
expression val;
@@
-be{bits}_to_cpu(cpu_to_be{bits}(val))
+val
(and __be_to_cpu and ntoh varients)
Touched up with clang-format after.
Link: https://lore.kernel.org/r/20200116170037.30109-5-jgg@ziepe.ca
Tested-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Use a Coccinelle spatch to replace CM helper functions with IBA_GET/SET
versions. Applied with
$ spatch --sp-file edits.sp --in-place drivers/infiniband/core/cm.c
The spatch file was generated using the template pattern:
@@
expression val;
{struct} *msg;
@@
- {old_setter}
+ IBA_SET({new_name}, msg, val)
@@
{struct} *msg;
@@
- {old_getter}
+ IBA_GET({new_name}, msg)
Iterated for every IBA_CHECK_GET()/IBA_CHECK_GET() pairing. Touched up
with clang-format after.
Link: https://lore.kernel.org/r/20200116170037.30109-4-jgg@ziepe.ca
Tested-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
There is no separation between RDMA-CM wire format as it is declared in
IBTA and kernel logic which implements needed support. Such situation
causes to many mistakes in conversion between big-endian (wire format)
and CPU format used by kernel. It also mixes RDMA core code with
combination of uXX and beXX variables.
The idea that all accesses to IBA definitions will go through special
GET/SET macros to ensure that no conversion mistakes are made. The
shifting and masking required to read the value is automatically deduced
using the field offset description from the tables in the IBA
specification.
This starts with the CM MADs described in IBTA release 1.3 volume 1.
To confirm that the new macros behave the same as the old accessors a
self-test is included in this patch.
Each macro replacing a straightforward struct field compile-time tests
that the new field has the same offsetof() and width as the old field.
For the fields with accessor functions a runtime test, the 'all ones'
value is placed in a dummy message and read back in several ways to
confirm that both approaches give identical results.
Later patches in this series delete the self test.
This creates a tested table of new field name, old field name(s) and some
meta information like BE coding for the functions which will be used in
the next patches.
Link: https://lore.kernel.org/r/20200116170037.30109-3-jgg@ziepe.ca
Link: https://lore.kernel.org/r/20191212093830.316934-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Tested-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Access the two fields through wrappers, like all other fields, to make it
clearer what is happening.
Link: https://lore.kernel.org/r/20200116170037.30109-2-jgg@ziepe.ca
Tested-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
The set of entry->driver_removed is missing locking, protect it with
xa_lock() which is held by the only reader.
Otherwise readers may continue to see driver_removed = false after
rdma_user_mmap_entry_remove() returns and may continue to try and
establish new mmaps.
Fixes: 3411f9f01b76 ("RDMA/core: Create mmap database and cookie helper functions")
Link: https://lore.kernel.org/r/20200115202041.GA17199@ziepe.ca
Reviewed-by: Gal Pressman <galpress@amazon.com>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
From https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma
Leon Romanovsky says:
====================
Use ODP MRs for kernel ULPs
The following series extends MR creation routines to allow creation of
user MRs through kernel ULPs as a proxy. The immediate use case is to
allow RDS to work over FS-DAX, which requires ODP (on-demand-paging)
MRs to be created and such MRs were not possible to create prior this
series.
The first part of this patchset extends RDMA to have special verb
ib_reg_user_mr(). The common use case that uses this function is a
userspace application that allocates memory for HCA access but the
responsibility to register the memory at the HCA is on an kernel ULP.
This ULP acts as an agent for the userspace application.
The second part provides advise MR functionality for ULPs. This is
integral part of ODP flows and used to trigger pagefaults in advance
to prepare memory before running working set.
The third part is actual user of those in-kernel APIs.
====================
* tag 'rds-odp-for-5.5':
net/rds: Use prefetch for On-Demand-Paging MR
net/rds: Handle ODP mr registration/unregistration
net/rds: Detect need of On-Demand-Paging memory registration
RDMA/mlx5: Fix handling of IOVA != user_va in ODP paths
IB/mlx5: Mask out unsupported ODP capabilities for kernel QPs
RDMA/mlx5: Don't fake udata for kernel path
IB/mlx5: Add ODP WQE handlers for kernel QPs
IB/core: Add interface to advise_mr for kernel users
IB/core: Introduce ib_reg_user_mr
IB: Allow calls to ib_umem_get from kernel ULPs
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Add the core support field to METHOD_GET_CONTEXT, this field should
represent capabilities that are not device-specific.
Return support for optional access flags for memory regions. User-space
will use this capability to mask the optional access flags for
unsupporting kernels.
Link: https://lore.kernel.org/r/1578506740-22188-10-git-send-email-yishaih@mellanox.com
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Allow future extensions of the get context command through the uverbs
ioctl kabi.
Unlike the uverbs version this does not return an async_fd as well, that
has to be done with another command.
Link: https://lore.kernel.org/r/1578506740-22188-5-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This lock only serializes ucontext creation. Instead of checking the
ucontext_lock during destruction hold the existing hw_destroy_rwsem during
creation, which is the standard pattern for object creation.
The simplification of locking is needed for the next patch.
Link: https://lore.kernel.org/r/1578506740-22188-4-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Allow the async FD to be allocated separately from the context.
This is necessary to introduce the ioctl to create a context, as an ioctl
should only ever create a single uobject at a time.
If multiple async FDs are created then the first one is used to deliver
affiliated events from any ib_uevent_object, with all subsequent ones will
receive only unaffiliated events.
Link: https://lore.kernel.org/r/1578506740-22188-3-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Allow ULPs to call advise_mr, so they can control ODP regions
in the same way as user space applications.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
Add ib_reg_user_mr() for kernel ULPs to register user MRs.
The common use case that uses this function is a userspace application
that allocates memory for HCA access but the responsibility to register
the memory at the HCA is on an kernel ULP. This ULP that acts as an agent
for the userspace application.
This function is intended to be used without a user context so vendor
drivers need to be aware of calling reg_user_mr() device operation with
udata equal to NULL.
Among all drivers, i40iw is the only driver which relies on presence
of udata, so check udata existence for that driver.
Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
So far the assumption was that ib_umem_get() and ib_umem_odp_get()
are called from flows that start in UVERBS and therefore has a user
context. This assumption restricts flows that are initiated by ULPs
and need the service that ib_umem_get() provides.
This patch changes ib_umem_get() and ib_umem_odp_get() to get IB device
directly by relying on the fact that both UVERBS and ULPs sets that
field correctly.
Reviewed-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
The writer for async_file holds the ucontext_lock, while the readers are
left unlocked. Most readers rely on an implicit locking, either by having
a uobject (which cannot be created before a context) or by holding the
ib_ufile kref.
However ib_uverbs_free_hw_resources() has no implicit lock and has a
possible race. Make this all clear and sane by using READ_ONCE
consistently.
Link: https://lore.kernel.org/r/1578504126-9400-15-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This makes async events aligned with completion events as both are full
uobjects of FD type and use the same uobject lifecycle.
A bunch of duplicate code is consolidated and the general flow between the
two FDs is now very similar.
Link: https://lore.kernel.org/r/1578504126-9400-14-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Now that all callers provide a non-NULL attrs the ufile is redundant.
Adjust things so that the context handling is done inside alloc_uobj,
and the ib_uverbs_get_ucontext_file() is avoided if we already have the
context.
Link: https://lore.kernel.org/r/1578504126-9400-13-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This function works on an ib_uverbs_async_file. Accept that as a parameter
instead of the struct ib_uverbs_file.
Consoldiate all the callers working from an ib_uevent_object to a single
function and locate the async_file directly from the struct ib_uobject
instead of using context_ptr.
Link: https://lore.kernel.org/r/1578504126-9400-11-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This is a struct ib_uwq_object pointer, instead of using container_of()
all over the place just store it with its actual type.
Link: https://lore.kernel.org/r/1578504126-9400-10-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This is a struct ib_usrq_object pointer, instead of using container_of()
all over the place just store it with its actual type.
Link: https://lore.kernel.org/r/1578504126-9400-9-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This is a struct ib_uqp_object pointer, instead of using container_of()
all over the place just store it with its actual type.
Link: https://lore.kernel.org/r/1578504126-9400-8-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This is a struct ib_ucq_object pointer, instead of using container_of()
all over the place just store it with its actual type.
Link: https://lore.kernel.org/r/1578504126-9400-7-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Any uobject that sends events into the async_event_file should be using
ib_uevent_object so it can use the standard uevent based helper
functions. CQ pushes events into both the async_event and the comp_channel
in an open coded way. Move the async events related stuff to
ib_uevent_object.
Link: https://lore.kernel.org/r/1578504126-9400-6-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This is a left over from an earlier version that creates a lot of
complexity for error unwind, particularly for FD uobjects.
The only reason this was done is so that anon_inode_get_file() could be
called with the final fops and a fully setup uobject. Both need to be
setup since unwinding anon_inode_get_file() via fput will call the
driver's release().
Now that the driver does not provide release, we no longer need to worry
about this complicated sequence, simply create the struct file at the
start and allow the core code's release function to deal with the abort
case.
This allows all the confusing error paths around commit to be removed.
Link: https://lore.kernel.org/r/1578504126-9400-5-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
FD uobjects have a weird split between the struct file and uobject
world. Simplify this to make them pure uobjects and use a generic release
method for all struct file operations.
This fixes the control flow so that mlx5_cmd_cleanup_async_ctx() is always
called before erasing the linked list contents to make the concurrancy
simpler to understand.
For this to work the uobject destruction must fence anything that it is
cleaning up - the design must not rely on struct file lifetime.
Only deliver_event() relies on the struct file to when adding new events
to the queue, add a is_destroyed check under lock to block it.
Link: https://lore.kernel.org/r/1578504126-9400-3-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
dispatch_event_fd() runs from a notifier with minimal locking, and relies
on RCU and a file refcount to keep the uobject and eventfd alive.
As the next patch wants to remove the file_operations release function
from the drivers, re-organize things so that the devx_event_notifier()
path uses the existing RCU to manage the lifetime of the uobject and
eventfd.
Move the refcount puts to a call_rcu so that the objects are guaranteed to
exist and remove the indirect file refcount.
Link: https://lore.kernel.org/r/1578504126-9400-2-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
After device disassociation the uapi_objects are destroyed and freed,
however it is still possible that core code can be holding a kref on the
uobject. When it finally goes to uverbs_uobject_free() via the kref_put()
it can trigger a use-after-free on the uapi_object.
Since needs_kfree_rcu is a micro optimization that only benefits file
uobjects, just get rid of it. There is no harm in using kfree_rcu even if
it isn't required, and the number of involved objects is small.
Link: https://lore.kernel.org/r/20200113143306.GA28717@ziepe.ca
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Since we can return device->ops.query_port directly, so no need to keep
those lines.
Link: https://lore.kernel.org/r/20200109134043.15568-1-guoqing.jiang@cloud.ionos.com
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This should not be using ib_dev to test for disassociation, during
disassociation is_closed is set under lock and the waitq is triggered.
Instead check is_closed and be sure to re-obtain the lock to test the
value after the wait_event returns.
Fixes: 036b10635739 ("IB/uverbs: Enable device removal when there are active user space applications")
Link: https://lore.kernel.org/r/1578504126-9400-12-git-send-email-yishaih@mellanox.com
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
HPAGE_SHIFT is only defined on architectures that support hugepages:
drivers/infiniband/core/umem_odp.c: In function 'ib_umem_odp_get':
drivers/infiniband/core/umem_odp.c:245:26: error: 'HPAGE_SHIFT' undeclared (first use in this function); did you mean 'PAGE_SHIFT'?
Enclose this in an #ifdef.
Fixes: 9ff1b6466a29 ("IB/core: Fix ODP with IB_ACCESS_HUGETLB handling")
Link: https://lore.kernel.org/r/20200109084740.2872079-1-arnd@arndb.de
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
This lock is used to protect the qp->open_list linked list. As a side
effect it seems to also globally serialize the qp event_handler, but it
isn't clear if that is a deliberate design.
Link: https://lore.kernel.org/r/20191212113024.336702-5-leon@kernel.org
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Given that ib_cache structure has only single member now, merge the cache
lock directly in the ib_device.
Link: https://lore.kernel.org/r/20191212113024.336702-4-leon@kernel.org
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Currently when the low level driver notifies Pkey, GID, and port change
events they are notified to the registered handlers in the order they are
registered.
IB core and other ULPs such as IPoIB are interested in GID, LID, Pkey
change events.
Since all GID queries done by ULPs are serviced by IB core, and the IB
core deferes cache updates to a work queue, it is possible for other
clients to see stale cache data when they handle their own events.
For example, the below call tree shows how ipoib will call
rdma_query_gid() concurrently with the update to the cache sitting in the
WQ.
mlx5_ib_handle_event()
ib_dispatch_event()
ib_cache_event()
queue_work() -> slow cache update
[..]
ipoib_event()
queue_work()
[..]
work handler
ipoib_ib_dev_flush_light()
__ipoib_ib_dev_flush()
ipoib_dev_addr_changed_valid()
rdma_query_gid() <- Returns old GID, cache not updated.
Move all the event dispatch to a work queue so that the cache update is
always done before any clients are notified.
Fixes: f35faa4ba956 ("IB/core: Simplify ib_query_gid to always refer to cache")
Link: https://lore.kernel.org/r/20191212113024.336702-3-leon@kernel.org
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Track the lifetime of ib_mr objects. Here's sample output from a test run
with NFS/RDMA:
<...>-361 [009] 79238.772782: mr_alloc: pd.id=3 mr.id=11 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.772812: mr_alloc: pd.id=3 mr.id=12 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.772839: mr_alloc: pd.id=3 mr.id=13 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.772866: mr_alloc: pd.id=3 mr.id=14 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.772893: mr_alloc: pd.id=3 mr.id=15 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.772921: mr_alloc: pd.id=3 mr.id=16 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.772947: mr_alloc: pd.id=3 mr.id=17 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.772974: mr_alloc: pd.id=3 mr.id=18 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.773001: mr_alloc: pd.id=3 mr.id=19 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.773028: mr_alloc: pd.id=3 mr.id=20 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79238.773055: mr_alloc: pd.id=3 mr.id=21 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.270942: mr_alloc: pd.id=3 mr.id=22 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.270975: mr_alloc: pd.id=3 mr.id=23 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271007: mr_alloc: pd.id=3 mr.id=24 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271036: mr_alloc: pd.id=3 mr.id=25 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271067: mr_alloc: pd.id=3 mr.id=26 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271095: mr_alloc: pd.id=3 mr.id=27 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271121: mr_alloc: pd.id=3 mr.id=28 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271153: mr_alloc: pd.id=3 mr.id=29 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271181: mr_alloc: pd.id=3 mr.id=30 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271208: mr_alloc: pd.id=3 mr.id=31 type=MEM_REG max_num_sg=30 rc=0
<...>-361 [009] 79240.271236: mr_alloc: pd.id=3 mr.id=32 type=MEM_REG max_num_sg=30 rc=0
<...>-4351 [001] 79242.299400: mr_dereg: mr.id=32
<...>-4351 [001] 79242.299467: mr_dereg: mr.id=31
<...>-4351 [001] 79242.299554: mr_dereg: mr.id=30
<...>-4351 [001] 79242.299615: mr_dereg: mr.id=29
<...>-4351 [001] 79242.299684: mr_dereg: mr.id=28
<...>-4351 [001] 79242.299748: mr_dereg: mr.id=27
<...>-4351 [001] 79242.299812: mr_dereg: mr.id=26
<...>-4351 [001] 79242.299874: mr_dereg: mr.id=25
<...>-4351 [001] 79242.299944: mr_dereg: mr.id=24
<...>-4351 [001] 79242.300009: mr_dereg: mr.id=23
<...>-4351 [001] 79242.300190: mr_dereg: mr.id=22
<...>-4351 [001] 79242.300263: mr_dereg: mr.id=21
<...>-4351 [001] 79242.300326: mr_dereg: mr.id=20
<...>-4351 [001] 79242.300388: mr_dereg: mr.id=19
<...>-4351 [001] 79242.300450: mr_dereg: mr.id=18
<...>-4351 [001] 79242.300516: mr_dereg: mr.id=17
<...>-4351 [001] 79242.300629: mr_dereg: mr.id=16
<...>-4351 [001] 79242.300718: mr_dereg: mr.id=15
<...>-4351 [001] 79242.300784: mr_dereg: mr.id=14
<...>-4351 [001] 79242.300879: mr_dereg: mr.id=13
<...>-4351 [001] 79242.300945: mr_dereg: mr.id=12
<...>-4351 [001] 79242.301012: mr_dereg: mr.id=11
Some features of the output:
- The lifetime and owner PD of each MR is clearly visible.
- The type of MR is captured, as is the SGE array size.
- Failing MR allocation can be recorded.
Link: https://lore.kernel.org/r/20191218201820.30584.34636.stgit@manet.1015granger.net
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Sample trace events:
kworker/u29:0-300 [007] 120.042217: cq_alloc: cq.id=4 nr_cqe=161 comp_vector=2 poll_ctx=WORKQUEUE
<idle>-0 [002] 120.056292: cq_schedule: cq.id=4
kworker/2:1H-482 [002] 120.056402: cq_process: cq.id=4 wake-up took 109 [us] from interrupt
kworker/2:1H-482 [002] 120.056407: cq_poll: cq.id=4 requested 16, returned 1
<idle>-0 [002] 120.067503: cq_schedule: cq.id=4
kworker/2:1H-482 [002] 120.067537: cq_process: cq.id=4 wake-up took 34 [us] from interrupt
kworker/2:1H-482 [002] 120.067541: cq_poll: cq.id=4 requested 16, returned 1
<idle>-0 [002] 120.067657: cq_schedule: cq.id=4
kworker/2:1H-482 [002] 120.067672: cq_process: cq.id=4 wake-up took 15 [us] from interrupt
kworker/2:1H-482 [002] 120.067674: cq_poll: cq.id=4 requested 16, returned 1
...
systemd-1 [002] 122.392653: cq_schedule: cq.id=4
kworker/2:1H-482 [002] 122.392688: cq_process: cq.id=4 wake-up took 35 [us] from interrupt
kworker/2:1H-482 [002] 122.392693: cq_poll: cq.id=4 requested 16, returned 16
kworker/2:1H-482 [002] 122.392836: cq_poll: cq.id=4 requested 16, returned 16
kworker/2:1H-482 [002] 122.392970: cq_poll: cq.id=4 requested 16, returned 16
kworker/2:1H-482 [002] 122.393083: cq_poll: cq.id=4 requested 16, returned 16
kworker/2:1H-482 [002] 122.393195: cq_poll: cq.id=4 requested 16, returned 3
Several features to note in this output:
- The WCE count and context type are reported at allocation time
- The CPU and kworker for each CQ is evident
- The CQ's restracker ID is tagged on each trace event
- CQ poll scheduling latency is measured
- Details about how often single completions occur versus multiple
completions are evident
- The cost of the ULP's completion handler is recorded
Link: https://lore.kernel.org/r/20191218201815.30584.3481.stgit@manet.1015granger.net
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Record state transitions as each connection is established. The IP address
of both peers and the Type of Service is reported. These trace points are
not in performance hot paths.
Also, record each cm_event_handler call to ULPs. This eliminates the need
for each ULP to add its own similar trace point in its CM event handler
function.
These new trace points appear in a new trace subsystem called "rdma_cma".
Sample events:
<...>-220 [004] 121.430733: cm_id_create: cm.id=0
<...>-472 [003] 121.430991: cm_event_handler: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 ADDR_RESOLVED (0/0)
<...>-472 [003] 121.430995: cm_event_done: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 result=0
<...>-472 [003] 121.431172: cm_event_handler: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 ROUTE_RESOLVED (2/0)
<...>-472 [003] 121.431174: cm_event_done: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 result=0
<...>-220 [004] 121.433480: cm_qp_create: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 pd.id=2 qp_type=RC send_wr=4091 recv_wr=256 qp_num=521 rc=0
<...>-220 [004] 121.433577: cm_send_req: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 qp_num=521
kworker/1:2-973 [001] 121.436190: cm_send_mra: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0
kworker/1:2-973 [001] 121.436340: cm_send_rtu: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0
kworker/1:2-973 [001] 121.436359: cm_event_handler: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 ESTABLISHED (9/0)
kworker/1:2-973 [001] 121.436365: cm_event_done: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 result=0
<...>-1975 [005] 123.161954: cm_disconnect: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0
<...>-1975 [005] 123.161974: cm_sent_dreq: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0
<...>-220 [004] 123.162102: cm_disconnect: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0
kworker/0:1-13 [000] 123.162391: cm_event_handler: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 DISCONNECTED (10/0)
kworker/0:1-13 [000] 123.162393: cm_event_done: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 result=0
<...>-220 [004] 123.164456: cm_qp_destroy: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0 qp_num=521
<...>-220 [004] 123.165290: cm_id_destroy: cm.id=0 src=192.168.2.51:35090 dst=192.168.2.55:20049 tos=0
Some features to note:
- restracker ID of the rdma_cm_id is tagged on each trace event
- The source and destination IP addresses and TOS are reported
- CM event upcalls are shown with decoded event and status
- CM state transitions are reported
- rdma_cm_id lifetime events are captured
- The latency of ULP CM event handlers is reported
- Lifetime events of associated QPs are reported
- Device removal and insertion is reported
This patch is based on previous work by:
Saeed Mahameed <saeedm@mellanox.com>
Mukesh Kacker <mukesh.kacker@oracle.com>
Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com>
Aron Silverton <aron.silverton@oracle.com>
Avinash Repaka <avinash.repaka@oracle.com>
Somasundaram Krishnasamy <somasundaram.krishnasamy@oracle.com>
Link: https://lore.kernel.org/r/20191218201810.30584.3052.stgit@manet.1015granger.net
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Clean the code by deleting ARP functions, which are not called anyway.
Link: https://lore.kernel.org/r/20191212093830.316934-46-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Clean the code by deleting LAP functions, which are not called anyway.
Link: https://lore.kernel.org/r/20191212093830.316934-43-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
As VMAs for a given range might not be available as part of the
registration phase in ODP.
ib_init_umem_odp() considered the expected page shift value that was
previously set and initializes its internals accordingly.
If memory isn't backed by physical contiguous pages aligned to a hugepage
boundary an error will be set as part of the page fault flow and come back
to the user as some failed RDMA operation.
Fixes: 0008b84ea9af ("IB/umem: Add support to huge ODP")
Link: https://lore.kernel.org/r/20191222124649.52300-4-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
The nr_pages argument of get_user_pages_remote() should always be in terms
of the system page size, not the MR page size. Use PAGE_SIZE instead of
umem_odp->page_shift.
Fixes: 403cd12e2cf7 ("IB/umem: Add contiguous ODP support")
Link: https://lore.kernel.org/r/20191222124649.52300-3-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
The RCU mechanism is optimized for read-mostly scenarios and therefore
more suitable to protect the cm_id_private to decrease "cm.lock"
congestion.
This patch replaces the existing spinlock locking mechanism and kfree with
RCU mechanism in places where spinlock(cm.lock) protected xa_load
returning the cm_id_priv
In addition, delete the cm_get_id() function as there is no longer a
distinction if the caller already holds the cm_lock.
Remove an open coded version of cm_get_id().
Link: https://lore.kernel.org/r/20191219134750.413429-1-leon@kernel.org
Signed-off-by: Danit Goldberg <danitg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
In rdma_nl_rcv_skb(), the local variable err is assigned the return value
of the supplied callback function, which could be one of
ib_nl_handle_resolve_resp(), ib_nl_handle_set_timeout(), or
ib_nl_handle_ip_res_resp(). These three functions all return skb->len on
success.
rdma_nl_rcv_skb() is merely a copy of netlink_rcv_skb(). The callback
functions used by the latter have the convention: "Returns 0 on success or
a negative error code".
In particular, the statement (equal for both functions):
if (nlh->nlmsg_flags & NLM_F_ACK || err)
implies that rdma_nl_rcv_skb() always will ack a message, independent of
the NLM_F_ACK being set in nlmsg_flags or not.
The fix could be to change the above statement, but it is better to keep
the two *_rcv_skb() functions equal in this respect and instead change the
three callback functions in the rdma subsystem to the correct convention.
Fixes: 2ca546b92a02 ("IB/sa: Route SA pathrecord query through netlink")
Fixes: ae43f8286730 ("IB/core: Add IP to GID netlink offload")
Link: https://lore.kernel.org/r/20191216120436.3204814-1-haakon.bugge@oracle.com
Suggested-by: Mark Haywood <mark.haywood@oracle.com>
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Tested-by: Mark Haywood <mark.haywood@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
|
Introduce rdma_user_mmap_entry_insert_range() API to be used once the
required key for the given entry should be in a given range.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20191212100237.330654-2-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>
|
|
Some QPs (e.g. XRC QP) are not tracked in kernel, in this case they have
an invalid res and should not be bound to any dynamically-allocated
counter in auto mode.
This fixes below call trace:
BUG: kernel NULL pointer dereference, address: 0000000000000390
PGD 80000001a7233067 P4D 80000001a7233067 PUD 1a7215067 PMD 0
Oops: 0000 [#1] SMP PTI
CPU: 2 PID: 24822 Comm: ibv_xsrq_pingpo Not tainted 5.4.0-rc5+ #21
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014
RIP: 0010:rdma_counter_bind_qp_auto+0x142/0x270 [ib_core]
Code: e1 48 85 c0 48 89 c2 0f 84 bc 00 00 00 49 8b 06 48 39 42 48 75 d6 40 3a aa 90 00 00 00 75 cd 49 8b 86 00 01 00 00 48 8b 4a 28 <8b> 80 90 03 00 00 39 81 90 03 00 00 75 b4 85 c0 74 b0 48 8b 04 24
RSP: 0018:ffffc900003f39c0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000
RDX: ffff88820020ec00 RSI: 0000000000000004 RDI: ffffffffffffffc0
RBP: 0000000000000001 R08: ffff888224149ff0 R09: ffffc900003f3968
R10: ffffffffffffffff R11: ffff8882249c5848 R12: ffffffffffffffff
R13: ffff88821d5aca50 R14: ffff8881f7690800 R15: ffff8881ff890000
FS: 00007fe53a3e1740(0000) GS:ffff888237b00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000390 CR3: 00000001a7292006 CR4: 00000000003606a0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
_ib_modify_qp+0x3a4/0x3f0 [ib_core]
? lookup_get_idr_uobject.part.8+0x23/0x40 [ib_uverbs]
modify_qp+0x322/0x3e0 [ib_uverbs]
ib_uverbs_modify_qp+0x43/0x70 [ib_uverbs]
ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xb1/0xf0 [ib_uverbs]
ib_uverbs_run_method+0x6be/0x760 [ib_uverbs]
? uverbs_disassociate_api+0xd0/0xd0 [ib_uverbs]
ib_uverbs_cmd_verbs+0x18d/0x3a0 [ib_uverbs]
? get_acl+0x1a/0x120
? __alloc_pages_nodemask+0x15d/0x2c0
ib_uverbs_ioctl+0xa7/0x110 [ib_uverbs]
do_vfs_ioctl+0xa5/0x610
ksys_ioctl+0x60/0x90
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x48/0x110
entry_SYSCALL_64_after_hwframe+0x44/0xa9
Fixes: 99fa331dc862 ("RDMA/counter: Add "auto" configuration mode support")
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Ido Kalir <idok@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Link: https://lore.kernel.org/r/20191212091214.315005-2-leon@kernel.org
Signed-off-by: Doug Ledford <dledford@redhat.com>
|
|
The driver forgets to call unregister_pernet_subsys() in the error path
of cma_init().
Add the missed call to fix it.
Fixes: 4be74b42a6d0 ("IB/cma: Separate port allocation to network namespaces")
Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Link: https://lore.kernel.org/r/20191206012426.12744-1-hslester96@gmail.com
Signed-off-by: Doug Ledford <dledford@redhat.com>
|