aboutsummaryrefslogtreecommitdiff
path: root/scripts/gdb/linux/tasks.py
diff options
context:
space:
mode:
authorChuck Lever <[email protected]>2021-02-09 10:48:57 -0500
committerChuck Lever <[email protected]>2021-02-15 10:45:00 -0500
commit0ac24c320c4d89a9de6ec802591398b8675c7b3c (patch)
tree028e11f7256f1d549a261cd7292ed2126225021a /scripts/gdb/linux/tasks.py
parentbd5ae9288d6451bd346a1b4a59d4fe7e62ba29b7 (diff)
svcrdma: Hold private mutex while invoking rdma_accept()
RDMA core mutex locking was restructured by commit d114c6feedfe ("RDMA/cma: Add missing locking to rdma_accept()") [Aug 2020]. When lock debugging is enabled, the RPC/RDMA server trips over the new lockdep assertion in rdma_accept() because it doesn't call rdma_accept() from its CM event handler. As a temporary fix, have svc_rdma_accept() take the handler_mutex explicitly. In the meantime, let's consider how to restructure the RPC/RDMA transport to invoke rdma_accept() from the proper context. Calls to svc_rdma_accept() are serialized with calls to svc_rdma_free() by the generic RPC server layer. Suggested-by: Jason Gunthorpe <[email protected]> Link: https://lore.kernel.org/linux-rdma/[email protected]/ Fixes: d114c6feedfe ("RDMA/cma: Add missing locking to rdma_accept()") Signed-off-by: Chuck Lever <[email protected]>
Diffstat (limited to 'scripts/gdb/linux/tasks.py')
0 files changed, 0 insertions, 0 deletions