From: Chuck Lever <chuck.lever@oracle.com>
To: anna.schumaker@netapp.com
Cc: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: [PATCH v5 04/30] xprtrdma: Replace rpcrdma_receive_wq with a per-xprt workqueue
Date: Wed, 19 Dec 2018 10:58:29 -0500 [thread overview]
Message-ID: <20181219155829.11602.21903.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20181219155152.11602.18605.stgit@manet.1015granger.net>
To address a connection-close ordering problem, we need the ability
to drain the RPC completions running on rpcrdma_receive_wq for just
one transport. Give each transport its own RPC completion workqueue,
and drain that workqueue when disconnecting the transport.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
net/sunrpc/xprtrdma/rpc_rdma.c | 2 +
net/sunrpc/xprtrdma/transport.c | 17 +++-------
net/sunrpc/xprtrdma/verbs.c | 67 +++++++++++++++++++++------------------
net/sunrpc/xprtrdma/xprt_rdma.h | 6 +--
4 files changed, 44 insertions(+), 48 deletions(-)
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index dc23977..5738c9f 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1356,7 +1356,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
clear_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags);
trace_xprtrdma_reply(rqst->rq_task, rep, req, credits);
- queue_work(rpcrdma_receive_wq, &rep->rr_work);
+ queue_work(buf->rb_completion_wq, &rep->rr_work);
return;
out_badversion:
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index ae2a838..91c476a 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -444,10 +444,14 @@
struct rpcrdma_ep *ep = &r_xprt->rx_ep;
struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+ might_sleep();
+
dprintk("RPC: %s: closing xprt %p\n", __func__, xprt);
+ /* Prevent marshaling and sending of new requests */
+ xprt_clear_connected(xprt);
+
if (test_and_clear_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags)) {
- xprt_clear_connected(xprt);
rpcrdma_ia_remove(ia);
return;
}
@@ -858,8 +862,6 @@ void xprt_rdma_cleanup(void)
dprintk("RPC: %s: xprt_unregister returned %i\n",
__func__, rc);
- rpcrdma_destroy_wq();
-
rc = xprt_unregister_transport(&xprt_rdma_bc);
if (rc)
dprintk("RPC: %s: xprt_unregister(bc) returned %i\n",
@@ -870,20 +872,13 @@ int xprt_rdma_init(void)
{
int rc;
- rc = rpcrdma_alloc_wq();
- if (rc)
- return rc;
-
rc = xprt_register_transport(&xprt_rdma);
- if (rc) {
- rpcrdma_destroy_wq();
+ if (rc)
return rc;
- }
rc = xprt_register_transport(&xprt_rdma_bc);
if (rc) {
xprt_unregister_transport(&xprt_rdma);
- rpcrdma_destroy_wq();
return rc;
}
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index e4461e7..cff3a5d 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -80,33 +80,23 @@
static void rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb);
static void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp);
-struct workqueue_struct *rpcrdma_receive_wq __read_mostly;
-
-int
-rpcrdma_alloc_wq(void)
+/* Wait for outstanding transport work to finish.
+ */
+static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt)
{
- struct workqueue_struct *recv_wq;
-
- recv_wq = alloc_workqueue("xprtrdma_receive",
- WQ_MEM_RECLAIM | WQ_HIGHPRI,
- 0);
- if (!recv_wq)
- return -ENOMEM;
-
- rpcrdma_receive_wq = recv_wq;
- return 0;
-}
+ struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+ struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-void
-rpcrdma_destroy_wq(void)
-{
- struct workqueue_struct *wq;
+ /* Flush Receives, then wait for deferred Reply work
+ * to complete.
+ */
+ ib_drain_qp(ia->ri_id->qp);
+ drain_workqueue(buf->rb_completion_wq);
- if (rpcrdma_receive_wq) {
- wq = rpcrdma_receive_wq;
- rpcrdma_receive_wq = NULL;
- destroy_workqueue(wq);
- }
+ /* Deferred Reply processing might have scheduled
+ * local invalidations.
+ */
+ ib_drain_sq(ia->ri_id->qp);
}
/**
@@ -483,7 +473,7 @@
* connection is already gone.
*/
if (ia->ri_id->qp) {
- ib_drain_qp(ia->ri_id->qp);
+ rpcrdma_xprt_drain(r_xprt);
rdma_destroy_qp(ia->ri_id);
ia->ri_id->qp = NULL;
}
@@ -825,8 +815,10 @@
return rc;
}
-/*
- * rpcrdma_ep_disconnect
+/**
+ * rpcrdma_ep_disconnect - Disconnect underlying transport
+ * @ep: endpoint to disconnect
+ * @ia: associated interface adapter
*
* This is separate from destroy to facilitate the ability
* to reconnect without recreating the endpoint.
@@ -837,19 +829,20 @@
void
rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
{
+ struct rpcrdma_xprt *r_xprt = container_of(ep, struct rpcrdma_xprt,
+ rx_ep);
int rc;
+ /* returns without wait if ID is not connected */
rc = rdma_disconnect(ia->ri_id);
if (!rc)
- /* returns without wait if not connected */
wait_event_interruptible(ep->rep_connect_wait,
ep->rep_connected != 1);
else
ep->rep_connected = rc;
- trace_xprtrdma_disconnect(container_of(ep, struct rpcrdma_xprt,
- rx_ep), rc);
+ trace_xprtrdma_disconnect(r_xprt, rc);
- ib_drain_qp(ia->ri_id->qp);
+ rpcrdma_xprt_drain(r_xprt);
}
/* Fixed-size circular FIFO queue. This implementation is wait-free and
@@ -1183,6 +1176,13 @@ struct rpcrdma_req *
if (rc)
goto out;
+ buf->rb_completion_wq = alloc_workqueue("rpcrdma-%s",
+ WQ_MEM_RECLAIM | WQ_HIGHPRI,
+ 0,
+ r_xprt->rx_xprt.address_strings[RPC_DISPLAY_ADDR]);
+ if (!buf->rb_completion_wq)
+ goto out;
+
return 0;
out:
rpcrdma_buffer_destroy(buf);
@@ -1241,6 +1241,11 @@ struct rpcrdma_req *
{
cancel_delayed_work_sync(&buf->rb_refresh_worker);
+ if (buf->rb_completion_wq) {
+ destroy_workqueue(buf->rb_completion_wq);
+ buf->rb_completion_wq = NULL;
+ }
+
rpcrdma_sendctxs_destroy(buf);
while (!list_empty(&buf->rb_recv_bufs)) {
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 788124c..3f198cd 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -412,6 +412,7 @@ struct rpcrdma_buffer {
u32 rb_bc_max_requests;
+ struct workqueue_struct *rb_completion_wq;
struct delayed_work rb_refresh_worker;
};
#define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia)
@@ -547,8 +548,6 @@ struct rpcrdma_xprt {
bool frwr_is_supported(struct rpcrdma_ia *);
bool fmr_is_supported(struct rpcrdma_ia *);
-extern struct workqueue_struct *rpcrdma_receive_wq;
-
/*
* Endpoint calls - xprtrdma/verbs.c
*/
@@ -603,9 +602,6 @@ struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(size_t, enum dma_data_direction,
return __rpcrdma_dma_map_regbuf(ia, rb);
}
-int rpcrdma_alloc_wq(void);
-void rpcrdma_destroy_wq(void);
-
/*
* Wrappers for chunk registration, shared by read/write chunk code.
*/
next prev parent reply other threads:[~2018-12-19 15:58 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-19 15:58 [PATCH v5 00/30] NFS/RDMA client for next (4.21) Chuck Lever
2018-12-19 15:58 ` [PATCH v5 01/30] xprtrdma: Yet another double DMA-unmap Chuck Lever
2018-12-19 15:58 ` [PATCH v5 02/30] xprtrdma: Ensure MRs are DMA-unmapped when posting LOCAL_INV fails Chuck Lever
2018-12-19 15:58 ` [PATCH v5 03/30] xprtrdma: Refactor Receive accounting Chuck Lever
2018-12-19 15:58 ` Chuck Lever [this message]
2018-12-19 15:58 ` [PATCH v5 05/30] xprtrdma: No qp_event disconnect Chuck Lever
2018-12-19 15:58 ` [PATCH v5 06/30] xprtrdma: Don't wake pending tasks until disconnect is done Chuck Lever
2018-12-19 15:58 ` [PATCH v5 07/30] xprtrdma: Fix ri_max_segs and the result of ro_maxpages Chuck Lever
2018-12-19 15:58 ` [PATCH v5 08/30] xprtrdma: Reduce max_frwr_depth Chuck Lever
2018-12-19 15:58 ` [PATCH v5 09/30] xprtrdma: Remove support for FMR memory registration Chuck Lever
2018-12-19 15:59 ` [PATCH v5 10/30] xprtrdma: Remove rpcrdma_memreg_ops Chuck Lever
2018-12-19 15:59 ` [PATCH v5 11/30] xprtrdma: Plant XID in on-the-wire RDMA offset (FRWR) Chuck Lever
2018-12-19 15:59 ` [PATCH v5 12/30] NFS: Make "port=" mount option optional for RDMA mounts Chuck Lever
2018-12-19 15:59 ` [PATCH v5 13/30] xprtrdma: Recognize XDRBUF_SPARSE_PAGES Chuck Lever
2018-12-19 15:59 ` [PATCH v5 14/30] xprtrdma: Remove request_module from backchannel Chuck Lever
2018-12-19 15:59 ` [PATCH v5 15/30] xprtrdma: Expose transport header errors Chuck Lever
2018-12-19 15:59 ` [PATCH v5 16/30] xprtrdma: Simplify locking that protects the rl_allreqs list Chuck Lever
2018-12-19 15:59 ` [PATCH v5 17/30] xprtrdma: Cull dprintk() call sites Chuck Lever
2018-12-19 15:59 ` [PATCH v5 18/30] xprtrdma: Remove unused fields from rpcrdma_ia Chuck Lever
2018-12-19 15:59 ` [PATCH v5 19/30] xprtrdma: Clean up of xprtrdma chunk trace points Chuck Lever
2018-12-19 15:59 ` [PATCH v5 20/30] xprtrdma: Relocate the xprtrdma_mr_map " Chuck Lever
2018-12-19 16:00 ` [PATCH v5 21/30] xprtrdma: Add trace points for calls to transport switch methods Chuck Lever
2018-12-19 16:00 ` [PATCH v5 22/30] xprtrdma: Trace mapping, alloc, and dereg failures Chuck Lever
2018-12-19 16:00 ` [PATCH v5 23/30] NFS: Fix NFSv4 symbolic trace point output Chuck Lever
2018-12-19 16:00 ` [PATCH v5 24/30] SUNRPC: Simplify defining common RPC trace events Chuck Lever
2018-12-19 16:00 ` [PATCH v5 25/30] SUNRPC: Fix some kernel doc complaints Chuck Lever
2018-12-19 16:00 ` [PATCH v5 26/30] xprtrdma: Update comments in frwr_op_send Chuck Lever
2018-12-19 16:00 ` [PATCH v5 27/30] xprtrdma: Replace outdated comment for rpcrdma_ep_post Chuck Lever
2018-12-19 16:00 ` [PATCH v5 28/30] xprtrdma: Add documenting comment for rpcrdma_buffer_destroy Chuck Lever
2018-12-19 16:00 ` [PATCH v5 29/30] xprtrdma: Clarify comments in rpcrdma_ia_remove Chuck Lever
2018-12-19 16:00 ` [PATCH v5 30/30] xprtrdma: Don't leak freed MRs Chuck Lever
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181219155829.11602.21903.stgit@manet.1015granger.net \
--to=chuck.lever@oracle.com \
--cc=anna.schumaker@netapp.com \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).