kernel_optimize_test/net
Chuck Lever 426b8fb3d6 svcrdma: Hold private mutex while invoking rdma_accept()
[ Upstream commit 0ac24c320c4d89a9de6ec802591398b8675c7b3c ]

RDMA core mutex locking was restructured by commit d114c6feed
("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 <jgg@nvidia.com>
Link: https://lore.kernel.org/linux-rdma/20210209154014.GO4247@nvidia.com/
Fixes: d114c6feed ("RDMA/cma: Add missing locking to rdma_accept()")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-03-04 11:38:08 +01:00
..
6lowpan
9p
802
8021q
appletalk
atm
ax25
batman-adv
bluetooth
bpf
bpfilter
bridge
caif
can
ceph
core
dcb
dccp
decnet
dns_resolver
dsa
ethernet
ethtool
hsr
ieee802154
ife
ipv4
ipv6
iucv
kcm
key
l2tp
l3mdev
lapb
llc
mac80211
mac802154
mpls
mptcp
ncsi
netfilter
netlabel
netlink
netrom
nfc
nsh
openvswitch
packet
phonet
psample
qrtr
rds
rfkill
rose
rxrpc
sched
sctp
smc
strparser
sunrpc svcrdma: Hold private mutex while invoking rdma_accept() 2021-03-04 11:38:08 +01:00
switchdev
tipc
tls
unix
vmw_vsock
wimax
wireless
x25
xdp
xfrm
compat.c
devres.c
Kconfig
Makefile
socket.c
sysctl_net.c