aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/ocrdma
diff options
context:
space:
mode:
authorJason Gunthorpe <jgg@mellanox.com>2018-07-10 13:43:06 -0600
committerJason Gunthorpe <jgg@mellanox.com>2018-07-25 14:21:46 -0600
commit22fa27fbc64d01cbbe1e4da751e64cc22d24a6e4 (patch)
tree98ba4f304011ac9a6e05d9bbdd12045b7a6b4598 /drivers/infiniband/hw/ocrdma
parentIB/mlx5: Use the ucontext from the uobj, not the file (diff)
downloadlinux-dev-22fa27fbc64d01cbbe1e4da751e64cc22d24a6e4.tar.xz
linux-dev-22fa27fbc64d01cbbe1e4da751e64cc22d24a6e4.zip
IB/uverbs: Fix locking around struct ib_uverbs_file ucontext
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>
Diffstat (limited to 'drivers/infiniband/hw/ocrdma')
0 files changed, 0 insertions, 0 deletions