summaryrefslogtreecommitdiff
path: root/net/sunrpc/xprtrdma/frwr_ops.c
diff options
context:
space:
mode:
authorChuck Lever <chuck.lever@oracle.com>2016-06-29 13:53:43 -0400
committerAnna Schumaker <Anna.Schumaker@Netapp.com>2016-07-11 15:50:43 -0400
commit7a89f9c626e337ba6528d8a2829b228c933877fb (patch)
treefb37fd67ab882087a162d6ae0d1966909f7ee4e6 /net/sunrpc/xprtrdma/frwr_ops.c
parent3d4cf35bd4fab56c3aa0ec4323fccb24970aaf79 (diff)
downloadlwn-7a89f9c626e337ba6528d8a2829b228c933877fb.tar.gz
lwn-7a89f9c626e337ba6528d8a2829b228c933877fb.zip
xprtrdma: Honor ->send_request API contract
Commit c93c62231cf5 ("xprtrdma: Disconnect on registration failure") added a disconnect for some RPC marshaling failures. This is needed only in a handful of cases, but it was triggering for simple stuff like temporary resource shortages. Try to straighten this out. Fix up the lower layers so they don't return -ENOMEM or other error codes that the RPC client's FSM doesn't explicitly recognize. Also fix up the places in the send_request path that do want a disconnect. For example, when ib_post_send or ib_post_recv fail, this is a sign that there is a send or receive queue resource miscalculation. That should be rare, and is a sign of a software bug. But xprtrdma can recover: disconnect to reset the transport and start over. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Diffstat (limited to 'net/sunrpc/xprtrdma/frwr_ops.c')
-rw-r--r--net/sunrpc/xprtrdma/frwr_ops.c13
1 files changed, 7 insertions, 6 deletions
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index fc2826b3518c..d7613db9185d 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -382,7 +382,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
rpcrdma_defer_mr_recovery(mw);
mw = rpcrdma_get_mw(r_xprt);
if (!mw)
- return -ENOMEM;
+ return -ENOBUFS;
} while (mw->frmr.fr_state != FRMR_IS_INVALID);
frmr = &mw->frmr;
frmr->fr_state = FRMR_IS_VALID;
@@ -456,18 +456,18 @@ out_dmamap_err:
pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n",
mw->mw_sg, mw->mw_nents);
rpcrdma_defer_mr_recovery(mw);
- return -ENOMEM;
+ return -EIO;
out_mapmr_err:
pr_err("rpcrdma: failed to map mr %p (%u/%u)\n",
frmr->fr_mr, n, mw->mw_nents);
- rc = n < 0 ? n : -EIO;
rpcrdma_defer_mr_recovery(mw);
- return rc;
+ return -EIO;
out_senderr:
+ pr_err("rpcrdma: FRMR registration ib_post_send returned %i\n", rc);
rpcrdma_defer_mr_recovery(mw);
- return rc;
+ return -ENOTCONN;
}
static struct ib_send_wr *
@@ -569,7 +569,8 @@ unmap:
return;
reset_mrs:
- pr_warn("%s: ib_post_send failed %i\n", __func__, rc);
+ pr_err("rpcrdma: FRMR invalidate ib_post_send returned %i\n", rc);
+ rdma_disconnect(ia->ri_id);
/* Find and reset the MRs in the LOCAL_INV WRs that did not
* get posted. This is synchronous, and slow.