xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

xprtrdma: Remove logic that constructs RDMA_MSGP type calls

Browse Source 
RDMA_MSGP type calls insert a zero pad in the middle of the RPC
message to align the RPC request's data payload to the server's
alignment preferences. A server can then "page flip" the payload
into place to avoid a data copy in certain circumstances. However:

1. The client has to have a priori knowledge of the server's
   preferred alignment

2. Requests eligible for RDMA_MSGP are requests that are small
   enough to have been sent inline, and convey a data payload
   at the _end_ of the RPC message

Today 1. is done with a sysctl, and is a global setting that is
copied during mount. Linux does not support CCP to query the
server's preferences (RFC 5666, Section 6).

A small-ish NFSv3 WRITE might use RDMA_MSGP, but no NFSv4
compound fits bullet 2.

Thus the Linux client currently leaves RDMA_MSGP disabled. The
Linux server handles RDMA_MSGP, but does not use any special
page flipping, so it confers no benefit.

Clean up the marshaling code by removing the logic that constructs
RDMA_MSGP type calls. This also reduces the maximum send iovec size
from four to just two elements.

/proc/sys/sunrpc/rdma_inline_write_padding is a kernel API, and
thus is left in place.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Devesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
This commit is contained in:
Chuck Lever
2015-08-03 13:03:39 -04:00
committed by Anna Schumaker
parent d1ed857e57
commit b3221d6a53
3 changed files with 50 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
net/sunrpc/xprtrdma/verbs.c
View File

@@ -605,6 +605,12 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
struct ib_cq_init_attr cq_attr = {};
int rc, err;
if (devattr->max_sge < RPCRDMA_MAX_IOVS) {
dprintk("RPC: %s: insufficient sge's available\n",
__func__);
return -ENOMEM;
}
/* check provider's send/recv wr limits */
if (cdata->max_requests > devattr->max_qp_wr)
cdata->max_requests = devattr->max_qp_wr;
@@ -617,23 +623,13 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
if (rc)
return rc;
ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
ep->rep_attr.cap.max_send_sge = (cdata->padding ? 4 : 2);
ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_IOVS;
ep->rep_attr.cap.max_recv_sge = 1;
ep->rep_attr.cap.max_inline_data = 0;
ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
ep->rep_attr.qp_type = IB_QPT_RC;
ep->rep_attr.port_num = ~0;
if (cdata->padding) {
ep->rep_padbuf = rpcrdma_alloc_regbuf(ia, cdata->padding,
GFP_KERNEL);
if (IS_ERR(ep->rep_padbuf)) {
rc = PTR_ERR(ep->rep_padbuf);
goto out0;
}
} else
ep->rep_padbuf = NULL;
dprintk("RPC: %s: requested max: dtos: send %d recv %d; "
"iovs: send %d recv %d\n",
__func__,
@@ -716,8 +712,6 @@ out2:
dprintk("RPC: %s: ib_destroy_cq returned %i\n",
__func__, err);
out1:
rpcrdma_free_regbuf(ia, ep->rep_padbuf);
out0:
if (ia->ri_dma_mr)
ib_dereg_mr(ia->ri_dma_mr);
return rc;
@@ -746,8 +740,6 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
ia->ri_id->qp = NULL;
}
rpcrdma_free_regbuf(ia, ep->rep_padbuf);
rpcrdma_clean_cq(ep->rep_attr.recv_cq);
rc = ib_destroy_cq(ep->rep_attr.recv_cq);
if (rc)
@@ -1279,9 +1271,11 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
struct rpcrdma_ep *ep,
struct rpcrdma_req *req)
{
struct ib_device *device = ia->ri_device;
struct ib_send_wr send_wr, *send_wr_fail;
struct rpcrdma_rep *rep = req->rl_reply;
int rc;
struct ib_sge *iov = req->rl_send_iov;
int i, rc;
if (rep) {
rc = rpcrdma_ep_post_recv(ia, ep, rep);
@@ -1292,22 +1286,15 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
send_wr.next = NULL;
send_wr.wr_id = RPCRDMA_IGNORE_COMPLETION;
send_wr.sg_list = req->rl_send_iov;
send_wr.sg_list = iov;
send_wr.num_sge = req->rl_niovs;
send_wr.opcode = IB_WR_SEND;
if (send_wr.num_sge == 4) /* no need to sync any pad (constant) */
ib_dma_sync_single_for_device(ia->ri_device,
req->rl_send_iov[3].addr,
req->rl_send_iov[3].length,
DMA_TO_DEVICE);
ib_dma_sync_single_for_device(ia->ri_device,
req->rl_send_iov[1].addr,
req->rl_send_iov[1].length,
DMA_TO_DEVICE);
ib_dma_sync_single_for_device(ia->ri_device,
req->rl_send_iov[0].addr,
req->rl_send_iov[0].length,
DMA_TO_DEVICE);
for (i = 0; i < send_wr.num_sge; i++)
ib_dma_sync_single_for_device(device, iov[i].addr,
iov[i].length, DMA_TO_DEVICE);
dprintk("RPC: %s: posting %d s/g entries\n",
__func__, send_wr.num_sge);
if (DECR_CQCOUNT(ep) > 0)
send_wr.send_flags = 0;