Chuck Lever 07e10308ee xprtrdma: Prevent leak of rpcrdma_rep objects ... If a reply has been processed but the RPC is later retransmitted anyway, the req->rl_reply field still contains the only pointer to the old rpcrdma rep. When the next reply comes in, the reply handler will stomp on the rl_reply field, leaking the old rep. A trace event is added to capture such leaks. This problem seems to be worsened by the restructuring of the RPC Call path in v4.20. Fully addressing this issue will require at least a re-architecture of the disconnect logic, which is not appropriate during -rc. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>		2019-01-02 12:05:19 -05:00
..
backchannel.c	xprtrdma: Cull dprintk() call sites	2019-01-02 12:05:18 -05:00
frwr_ops.c	xprtrdma: Don't leak freed MRs	2019-01-02 12:05:18 -05:00
Makefile	xprtrdma: Remove support for FMR memory registration	2019-01-02 12:05:17 -05:00
module.c	NFS client updates for Linux 4.18	2018-06-12 10:09:03 -07:00
rpc_rdma.c	xprtrdma: Prevent leak of rpcrdma_rep objects	2019-01-02 12:05:19 -05:00
svc_rdma.c	sunrpc: remove redundant variables 'checksumlen','blocksize' and 'data'	2018-08-09 16:11:21 -04:00
svc_rdma_backchannel.c	xprtrdma: Don't wake pending tasks until disconnect is done	2019-01-02 12:05:16 -05:00
svc_rdma_recvfrom.c	A mistake on my part caused me to tag my branch 6 commits too early,	2018-08-23 16:00:10 -07:00
svc_rdma_rw.c	A mistake on my part caused me to tag my branch 6 commits too early,	2018-08-23 16:00:10 -07:00
svc_rdma_sendto.c	A mistake on my part caused me to tag my branch 6 commits too early,	2018-08-23 16:00:10 -07:00
svc_rdma_transport.c	svcrdma: Reduce max_send_sges	2018-10-29 16:58:04 -04:00
transport.c	xprtrdma: Add trace points for calls to transport switch methods	2019-01-02 12:05:18 -05:00
verbs.c	xprtrdma: Add documenting comment for rpcrdma_buffer_destroy	2019-01-02 12:05:18 -05:00
xprt_rdma.h	xprtrdma: Remove unused fields from rpcrdma_ia	2019-01-02 12:05:18 -05:00