From 0e0b854cfb3302b1907e9d3a927469b95710238f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 May 2018 15:35:14 -0400 Subject: xprtrdma: Clean up Receive trace points For clarity, report the posting and completion of Receive CQEs. Also, the wc->byte_len field contains garbage if wc->status is non-zero, and the vendor error field contains garbage if wc->status is zero. For readability, don't save those fields in those cases. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 39 ++++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 19 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 50ed3f8bf534..99c0049e51a5 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -528,24 +528,21 @@ TRACE_EVENT(xprtrdma_post_send, TRACE_EVENT(xprtrdma_post_recv, TP_PROTO( - const struct rpcrdma_rep *rep, - int status + const struct ib_cqe *cqe ), - TP_ARGS(rep, status), + TP_ARGS(cqe), TP_STRUCT__entry( - __field(const void *, rep) - __field(int, status) + __field(const void *, cqe) ), TP_fast_assign( - __entry->rep = rep; - __entry->status = status; + __entry->cqe = cqe; ), - TP_printk("rep=%p status=%d", - __entry->rep, __entry->status + TP_printk("cqe=%p", + __entry->cqe ) ); @@ -584,28 +581,32 @@ TRACE_EVENT(xprtrdma_wc_send, TRACE_EVENT(xprtrdma_wc_receive, TP_PROTO( - const struct rpcrdma_rep *rep, const struct ib_wc *wc ), - TP_ARGS(rep, wc), + TP_ARGS(wc), TP_STRUCT__entry( - __field(const void *, rep) - __field(unsigned int, byte_len) + __field(const void *, cqe) + __field(u32, byte_len) __field(unsigned int, status) - __field(unsigned int, vendor_err) + __field(u32, vendor_err) ), TP_fast_assign( - __entry->rep = rep; - __entry->byte_len = wc->byte_len; + __entry->cqe = wc->wr_cqe; __entry->status = wc->status; - __entry->vendor_err = __entry->status ? wc->vendor_err : 0; + if (wc->status) { + __entry->byte_len = 0; + __entry->vendor_err = wc->vendor_err; + } else { + __entry->byte_len = wc->byte_len; + __entry->vendor_err = 0; + } ), - TP_printk("rep=%p, %u bytes: %s (%u/0x%x)", - __entry->rep, __entry->byte_len, + TP_printk("cqe=%p %u bytes: %s (%u/0x%x)", + __entry->cqe, __entry->byte_len, rdma_show_wc_status(__entry->status), __entry->status, __entry->vendor_err ) -- cgit v1.2.3 From 7c8d9e7c8863905951d4eaa7a8d277150f3a37f7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 May 2018 15:35:20 -0400 Subject: xprtrdma: Move Receive posting to Receive handler Receive completion and Reply handling are done by a BOUND workqueue, meaning they run on only one CPU. Posting receives is currently done in the send_request path, which on large systems is typically done on a different CPU than the one handling Receive completions. This results in movement of Receive-related cachelines between the sending and receiving CPUs. More importantly, it means that currently Receives are posted while the transport's write lock is held, which is unnecessary and costly. Finally, allocation of Receive buffers is performed on-demand in the Receive completion handler. This helps guarantee that they are allocated on the same NUMA node as the CPU that handles Receive completions. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 40 +++++++-- net/sunrpc/xprtrdma/backchannel.c | 32 ++----- net/sunrpc/xprtrdma/rpc_rdma.c | 22 ++--- net/sunrpc/xprtrdma/transport.c | 3 - net/sunrpc/xprtrdma/verbs.c | 176 +++++++++++++++++++++----------------- net/sunrpc/xprtrdma/xprt_rdma.h | 6 +- 6 files changed, 150 insertions(+), 129 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 99c0049e51a5..ad27e192cdf8 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -546,6 +546,39 @@ TRACE_EVENT(xprtrdma_post_recv, ) ); +TRACE_EVENT(xprtrdma_post_recvs, + TP_PROTO( + const struct rpcrdma_xprt *r_xprt, + unsigned int count, + int status + ), + + TP_ARGS(r_xprt, count, status), + + TP_STRUCT__entry( + __field(const void *, r_xprt) + __field(unsigned int, count) + __field(int, status) + __field(int, posted) + __string(addr, rpcrdma_addrstr(r_xprt)) + __string(port, rpcrdma_portstr(r_xprt)) + ), + + TP_fast_assign( + __entry->r_xprt = r_xprt; + __entry->count = count; + __entry->status = status; + __entry->posted = r_xprt->rx_buf.rb_posted_receives; + __assign_str(addr, rpcrdma_addrstr(r_xprt)); + __assign_str(port, rpcrdma_portstr(r_xprt)); + ), + + TP_printk("peer=[%s]:%s r_xprt=%p: %u new recvs, %d active (rc %d)", + __get_str(addr), __get_str(port), __entry->r_xprt, + __entry->count, __entry->posted, __entry->status + ) +); + /** ** Completion events **/ @@ -800,7 +833,6 @@ TRACE_EVENT(xprtrdma_allocate, __field(unsigned int, task_id) __field(unsigned int, client_id) __field(const void *, req) - __field(const void *, rep) __field(size_t, callsize) __field(size_t, rcvsize) ), @@ -809,15 +841,13 @@ TRACE_EVENT(xprtrdma_allocate, __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; __entry->req = req; - __entry->rep = req ? req->rl_reply : NULL; __entry->callsize = task->tk_rqstp->rq_callsize; __entry->rcvsize = task->tk_rqstp->rq_rcvsize; ), - TP_printk("task:%u@%u req=%p rep=%p (%zu, %zu)", + TP_printk("task:%u@%u req=%p (%zu, %zu)", __entry->task_id, __entry->client_id, - __entry->req, __entry->rep, - __entry->callsize, __entry->rcvsize + __entry->req, __entry->callsize, __entry->rcvsize ) ); diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 4034788c9856..c8f1c2b89dad 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -71,23 +71,6 @@ out_fail: return -ENOMEM; } -/* Allocate and add receive buffers to the rpcrdma_buffer's - * existing list of rep's. These are released when the - * transport is destroyed. - */ -static int rpcrdma_bc_setup_reps(struct rpcrdma_xprt *r_xprt, - unsigned int count) -{ - int rc = 0; - - while (count--) { - rc = rpcrdma_create_rep(r_xprt); - if (rc) - break; - } - return rc; -} - /** * xprt_rdma_bc_setup - Pre-allocate resources for handling backchannel requests * @xprt: transport associated with these backchannel resources @@ -116,14 +99,6 @@ int xprt_rdma_bc_setup(struct rpc_xprt *xprt, unsigned int reqs) if (rc) goto out_free; - rc = rpcrdma_bc_setup_reps(r_xprt, reqs); - if (rc) - goto out_free; - - rc = rpcrdma_ep_post_extra_recv(r_xprt, reqs); - if (rc) - goto out_free; - r_xprt->rx_buf.rb_bc_srv_max_requests = reqs; request_module("svcrdma"); trace_xprtrdma_cb_setup(r_xprt, reqs); @@ -228,6 +203,7 @@ int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst) if (rc < 0) goto failed_marshal; + rpcrdma_post_recvs(r_xprt, true); if (rpcrdma_ep_post(&r_xprt->rx_ia, &r_xprt->rx_ep, req)) goto drop_connection; return 0; @@ -268,10 +244,14 @@ void xprt_rdma_bc_destroy(struct rpc_xprt *xprt, unsigned int reqs) */ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst) { + struct rpcrdma_req *req = rpcr_to_rdmar(rqst); struct rpc_xprt *xprt = rqst->rq_xprt; dprintk("RPC: %s: freeing rqst %p (req %p)\n", - __func__, rqst, rpcr_to_rdmar(rqst)); + __func__, rqst, req); + + rpcrdma_recv_buffer_put(req->rl_reply); + req->rl_reply = NULL; spin_lock_bh(&xprt->bc_pa_lock); list_add_tail(&rqst->rq_bc_pa_list, &xprt->bc_pa_list); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 8f89e3faae8e..d676106295ff 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1027,8 +1027,6 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep) out_short: pr_warn("RPC/RDMA short backward direction call\n"); - if (rpcrdma_ep_post_recv(&r_xprt->rx_ia, rep)) - xprt_disconnect_done(&r_xprt->rx_xprt); return true; } #else /* CONFIG_SUNRPC_BACKCHANNEL */ @@ -1334,13 +1332,14 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) u32 credits; __be32 *p; + --buf->rb_posted_receives; + if (rep->rr_hdrbuf.head[0].iov_len == 0) goto out_badstatus; + /* Fixed transport header fields */ xdr_init_decode(&rep->rr_stream, &rep->rr_hdrbuf, rep->rr_hdrbuf.head[0].iov_base); - - /* Fixed transport header fields */ p = xdr_inline_decode(&rep->rr_stream, 4 * sizeof(*p)); if (unlikely(!p)) goto out_shortreply; @@ -1379,17 +1378,10 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) trace_xprtrdma_reply(rqst->rq_task, rep, req, credits); + rpcrdma_post_recvs(r_xprt, false); queue_work(rpcrdma_receive_wq, &rep->rr_work); return; -out_badstatus: - rpcrdma_recv_buffer_put(rep); - if (r_xprt->rx_ep.rep_connected == 1) { - r_xprt->rx_ep.rep_connected = -EIO; - rpcrdma_conn_func(&r_xprt->rx_ep); - } - return; - out_badversion: trace_xprtrdma_reply_vers(rep); goto repost; @@ -1409,7 +1401,7 @@ out_shortreply: * receive buffer before returning. */ repost: - r_xprt->rx_stats.bad_reply_count++; - if (rpcrdma_ep_post_recv(&r_xprt->rx_ia, rep)) - rpcrdma_recv_buffer_put(rep); + rpcrdma_post_recvs(r_xprt, false); +out_badstatus: + rpcrdma_recv_buffer_put(rep); } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 79885aa39c24..0c775f05123c 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -722,9 +722,6 @@ xprt_rdma_send_request(struct rpc_task *task) if (rc < 0) goto failed_marshal; - if (req->rl_reply == NULL) /* e.g. reconnection */ - rpcrdma_recv_buffer_get(req); - /* Must suppress retransmit to maintain credits */ if (rqst->rq_connect_cookie == xprt->connect_cookie) goto drop_connection; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 4b18926de912..2ed2ee4f2c6c 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -74,6 +74,7 @@ */ static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf); +static int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt, bool temp); static void rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb); struct workqueue_struct *rpcrdma_receive_wq __read_mostly; @@ -726,7 +727,6 @@ rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) { struct rpcrdma_xprt *r_xprt = container_of(ia, struct rpcrdma_xprt, rx_ia); - unsigned int extras; int rc; retry: @@ -770,9 +770,8 @@ retry: } dprintk("RPC: %s: connected\n", __func__); - extras = r_xprt->rx_buf.rb_bc_srv_max_requests; - if (extras) - rpcrdma_ep_post_extra_recv(r_xprt, extras); + + rpcrdma_post_recvs(r_xprt, true); out: if (rc) @@ -1082,14 +1081,8 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) return req; } -/** - * rpcrdma_create_rep - Allocate an rpcrdma_rep object - * @r_xprt: controlling transport - * - * Returns 0 on success or a negative errno on failure. - */ -int -rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt) +static int +rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt, bool temp) { struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data; struct rpcrdma_buffer *buf = &r_xprt->rx_buf; @@ -1117,6 +1110,7 @@ rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt) rep->rr_recv_wr.wr_cqe = &rep->rr_cqe; rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov; rep->rr_recv_wr.num_sge = 1; + rep->rr_temp = temp; spin_lock(&buf->rb_lock); list_add(&rep->rr_list, &buf->rb_recv_bufs); @@ -1168,12 +1162,8 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) list_add(&req->rl_list, &buf->rb_send_bufs); } + buf->rb_posted_receives = 0; INIT_LIST_HEAD(&buf->rb_recv_bufs); - for (i = 0; i <= buf->rb_max_requests; i++) { - rc = rpcrdma_create_rep(r_xprt); - if (rc) - goto out; - } rc = rpcrdma_sendctxs_create(r_xprt); if (rc) @@ -1263,7 +1253,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) rep = rpcrdma_buffer_get_rep_locked(buf); rpcrdma_destroy_rep(rep); } - buf->rb_send_count = 0; spin_lock(&buf->rb_reqslock); while (!list_empty(&buf->rb_allreqs)) { @@ -1278,7 +1267,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) spin_lock(&buf->rb_reqslock); } spin_unlock(&buf->rb_reqslock); - buf->rb_recv_count = 0; rpcrdma_mrs_destroy(buf); } @@ -1351,27 +1339,11 @@ rpcrdma_mr_unmap_and_put(struct rpcrdma_mr *mr) __rpcrdma_mr_put(&r_xprt->rx_buf, mr); } -static struct rpcrdma_rep * -rpcrdma_buffer_get_rep(struct rpcrdma_buffer *buffers) -{ - /* If an RPC previously completed without a reply (say, a - * credential problem or a soft timeout occurs) then hold off - * on supplying more Receive buffers until the number of new - * pending RPCs catches up to the number of posted Receives. - */ - if (unlikely(buffers->rb_send_count < buffers->rb_recv_count)) - return NULL; - - if (unlikely(list_empty(&buffers->rb_recv_bufs))) - return NULL; - buffers->rb_recv_count++; - return rpcrdma_buffer_get_rep_locked(buffers); -} - -/* - * Get a set of request/reply buffers. +/** + * rpcrdma_buffer_get - Get a request buffer + * @buffers: Buffer pool from which to obtain a buffer * - * Reply buffer (if available) is attached to send buffer upon return. + * Returns a fresh rpcrdma_req, or NULL if none are available. */ struct rpcrdma_req * rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) @@ -1379,23 +1351,21 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) struct rpcrdma_req *req; spin_lock(&buffers->rb_lock); - if (list_empty(&buffers->rb_send_bufs)) - goto out_reqbuf; - buffers->rb_send_count++; + if (unlikely(list_empty(&buffers->rb_send_bufs))) + goto out_noreqs; req = rpcrdma_buffer_get_req_locked(buffers); - req->rl_reply = rpcrdma_buffer_get_rep(buffers); spin_unlock(&buffers->rb_lock); - return req; -out_reqbuf: +out_noreqs: spin_unlock(&buffers->rb_lock); return NULL; } -/* - * Put request/reply buffers back into pool. - * Pre-decrement counter/array index. +/** + * rpcrdma_buffer_put - Put request/reply buffers back into pool + * @req: object to return + * */ void rpcrdma_buffer_put(struct rpcrdma_req *req) @@ -1406,27 +1376,16 @@ rpcrdma_buffer_put(struct rpcrdma_req *req) req->rl_reply = NULL; spin_lock(&buffers->rb_lock); - buffers->rb_send_count--; - list_add_tail(&req->rl_list, &buffers->rb_send_bufs); + list_add(&req->rl_list, &buffers->rb_send_bufs); if (rep) { - buffers->rb_recv_count--; - list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs); + if (!rep->rr_temp) { + list_add(&rep->rr_list, &buffers->rb_recv_bufs); + rep = NULL; + } } spin_unlock(&buffers->rb_lock); -} - -/* - * Recover reply buffers from pool. - * This happens when recovering from disconnect. - */ -void -rpcrdma_recv_buffer_get(struct rpcrdma_req *req) -{ - struct rpcrdma_buffer *buffers = req->rl_buffer; - - spin_lock(&buffers->rb_lock); - req->rl_reply = rpcrdma_buffer_get_rep(buffers); - spin_unlock(&buffers->rb_lock); + if (rep) + rpcrdma_destroy_rep(rep); } /* @@ -1438,10 +1397,13 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep) { struct rpcrdma_buffer *buffers = &rep->rr_rxprt->rx_buf; - spin_lock(&buffers->rb_lock); - buffers->rb_recv_count--; - list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs); - spin_unlock(&buffers->rb_lock); + if (!rep->rr_temp) { + spin_lock(&buffers->rb_lock); + list_add(&rep->rr_list, &buffers->rb_recv_bufs); + spin_unlock(&buffers->rb_lock); + } else { + rpcrdma_destroy_rep(rep); + } } /** @@ -1537,13 +1499,6 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, struct ib_send_wr *send_wr = &req->rl_sendctx->sc_wr; int rc; - if (req->rl_reply) { - rc = rpcrdma_ep_post_recv(ia, req->rl_reply); - if (rc) - return rc; - req->rl_reply = NULL; - } - if (!ep->rep_send_count || test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) { send_wr->send_flags |= IB_SEND_SIGNALED; @@ -1618,3 +1573,70 @@ out_rc: rpcrdma_recv_buffer_put(rep); return rc; } + +/** + * rpcrdma_post_recvs - Maybe post some Receive buffers + * @r_xprt: controlling transport + * @temp: when true, allocate temp rpcrdma_rep objects + * + */ +void +rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct ib_recv_wr *wr, *bad_wr; + int needed, count, rc; + + needed = buf->rb_credits + (buf->rb_bc_srv_max_requests << 1); + if (buf->rb_posted_receives > needed) + return; + needed -= buf->rb_posted_receives; + + count = 0; + wr = NULL; + while (needed) { + struct rpcrdma_regbuf *rb; + struct rpcrdma_rep *rep; + + spin_lock(&buf->rb_lock); + rep = list_first_entry_or_null(&buf->rb_recv_bufs, + struct rpcrdma_rep, rr_list); + if (likely(rep)) + list_del(&rep->rr_list); + spin_unlock(&buf->rb_lock); + if (!rep) { + if (rpcrdma_create_rep(r_xprt, temp)) + break; + continue; + } + + rb = rep->rr_rdmabuf; + if (!rpcrdma_regbuf_is_mapped(rb)) { + if (!__rpcrdma_dma_map_regbuf(&r_xprt->rx_ia, rb)) { + rpcrdma_recv_buffer_put(rep); + break; + } + } + + trace_xprtrdma_post_recv(rep->rr_recv_wr.wr_cqe); + rep->rr_recv_wr.next = wr; + wr = &rep->rr_recv_wr; + ++count; + --needed; + } + if (!count) + return; + + rc = ib_post_recv(r_xprt->rx_ia.ri_id->qp, wr, &bad_wr); + if (rc) { + for (wr = bad_wr; wr; wr = wr->next) { + struct rpcrdma_rep *rep; + + rep = container_of(wr, struct rpcrdma_rep, rr_recv_wr); + rpcrdma_recv_buffer_put(rep); + --count; + } + } + buf->rb_posted_receives += count; + trace_xprtrdma_post_recvs(r_xprt, count, rc); +} diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 1d7bb6e5db18..4915a6dd58c9 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -197,6 +197,7 @@ struct rpcrdma_rep { __be32 rr_proc; int rr_wc_flags; u32 rr_inv_rkey; + bool rr_temp; struct rpcrdma_regbuf *rr_rdmabuf; struct rpcrdma_xprt *rr_rxprt; struct work_struct rr_work; @@ -397,11 +398,11 @@ struct rpcrdma_buffer { struct rpcrdma_sendctx **rb_sc_ctxs; spinlock_t rb_lock; /* protect buf lists */ - int rb_send_count, rb_recv_count; struct list_head rb_send_bufs; struct list_head rb_recv_bufs; u32 rb_max_requests; u32 rb_credits; /* most recent credit grant */ + int rb_posted_receives; u32 rb_bc_srv_max_requests; spinlock_t rb_reqslock; /* protect rb_allreqs */ @@ -558,13 +559,13 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_req *); int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_rep *); +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* * Buffer calls - xprtrdma/verbs.c */ struct rpcrdma_req *rpcrdma_create_req(struct rpcrdma_xprt *); void rpcrdma_destroy_req(struct rpcrdma_req *); -int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt); int rpcrdma_buffer_create(struct rpcrdma_xprt *); void rpcrdma_buffer_destroy(struct rpcrdma_buffer *); struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf); @@ -577,7 +578,6 @@ void rpcrdma_mr_defer_recovery(struct rpcrdma_mr *mr); struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_req *); -void rpcrdma_recv_buffer_get(struct rpcrdma_req *); void rpcrdma_recv_buffer_put(struct rpcrdma_rep *); struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(size_t, enum dma_data_direction, -- cgit v1.2.3 From a7986f09986ac1befc85bcab30970312c476dbc7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 May 2018 15:35:25 -0400 Subject: xprtrdma: Remove rpcrdma_ep_{post_recv, post_extra_recv} Clean up: These functions are no longer used. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 2 -- net/sunrpc/xprtrdma/verbs.c | 59 ----------------------------------------- net/sunrpc/xprtrdma/xprt_rdma.h | 3 --- 3 files changed, 64 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index ad27e192cdf8..ac82849954e4 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -879,8 +879,6 @@ TRACE_EVENT(xprtrdma_rpc_done, ) ); -DEFINE_RXPRT_EVENT(xprtrdma_noreps); - /** ** Callback events **/ diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 2ed2ee4f2c6c..601b78b64483 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1515,65 +1515,6 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, return 0; } -int -rpcrdma_ep_post_recv(struct rpcrdma_ia *ia, - struct rpcrdma_rep *rep) -{ - struct ib_recv_wr *recv_wr_fail; - int rc; - - if (!rpcrdma_dma_map_regbuf(ia, rep->rr_rdmabuf)) - goto out_map; - rc = ib_post_recv(ia->ri_id->qp, &rep->rr_recv_wr, &recv_wr_fail); - trace_xprtrdma_post_recv(rep->rr_recv_wr.wr_cqe); - if (rc) - return -ENOTCONN; - return 0; - -out_map: - pr_err("rpcrdma: failed to DMA map the Receive buffer\n"); - return -EIO; -} - -/** - * rpcrdma_ep_post_extra_recv - Post buffers for incoming backchannel requests - * @r_xprt: transport associated with these backchannel resources - * @count: minimum number of incoming requests expected - * - * Returns zero if all requested buffers were posted, or a negative errno. - */ -int -rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *r_xprt, unsigned int count) -{ - struct rpcrdma_buffer *buffers = &r_xprt->rx_buf; - struct rpcrdma_ia *ia = &r_xprt->rx_ia; - struct rpcrdma_rep *rep; - int rc; - - while (count--) { - spin_lock(&buffers->rb_lock); - if (list_empty(&buffers->rb_recv_bufs)) - goto out_reqbuf; - rep = rpcrdma_buffer_get_rep_locked(buffers); - spin_unlock(&buffers->rb_lock); - - rc = rpcrdma_ep_post_recv(ia, rep); - if (rc) - goto out_rc; - } - - return 0; - -out_reqbuf: - spin_unlock(&buffers->rb_lock); - trace_xprtrdma_noreps(r_xprt); - return -ENOMEM; - -out_rc: - rpcrdma_recv_buffer_put(rep); - return rc; -} - /** * rpcrdma_post_recvs - Maybe post some Receive buffers * @r_xprt: controlling transport diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 4915a6dd58c9..44a31246b8f7 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -558,7 +558,6 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_req *); -int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_rep *); void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* @@ -599,8 +598,6 @@ rpcrdma_dma_map_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb) return __rpcrdma_dma_map_regbuf(ia, rb); } -int rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *, unsigned int); - int rpcrdma_alloc_wq(void); void rpcrdma_destroy_wq(void); -- cgit v1.2.3 From 98895edbe377e990e61817d00ab029c7b8b99f21 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:11 -0400 Subject: svcrdma: Trace key RPC/RDMA protocol events This includes: * Transport accept and tear-down * Decisions about using Write and Reply chunks * Each RDMA segment that is handled * Whenever an RDMA_ERR is sent As a clean-up, I've standardized the order of the includes, and removed some now redundant dprintk call sites. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/trace/events/rpcrdma.h | 262 ++++++++++++++++++++++++++++++- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 36 ++--- net/sunrpc/xprtrdma/svc_rdma_rw.c | 23 +-- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 19 +-- net/sunrpc/xprtrdma/svc_rdma_transport.c | 19 ++- 5 files changed, 311 insertions(+), 48 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 50ed3f8bf534..633520ac99cd 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright (c) 2017 Oracle. All rights reserved. + * Copyright (c) 2017, 2018 Oracle. All rights reserved. + * + * Trace point definitions for the "rpcrdma" subsystem. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM rpcrdma @@ -885,6 +887,264 @@ TRACE_EVENT(xprtrdma_cb_setup, DEFINE_CB_EVENT(xprtrdma_cb_call); DEFINE_CB_EVENT(xprtrdma_cb_reply); +/** + ** Server-side RPC/RDMA events + **/ + +DECLARE_EVENT_CLASS(svcrdma_xprt_event, + TP_PROTO( + const struct svc_xprt *xprt + ), + + TP_ARGS(xprt), + + TP_STRUCT__entry( + __field(const void *, xprt) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->xprt = xprt; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("xprt=%p addr=%s", + __entry->xprt, __get_str(addr) + ) +); + +#define DEFINE_XPRT_EVENT(name) \ + DEFINE_EVENT(svcrdma_xprt_event, svcrdma_xprt_##name, \ + TP_PROTO( \ + const struct svc_xprt *xprt \ + ), \ + TP_ARGS(xprt)) + +DEFINE_XPRT_EVENT(accept); +DEFINE_XPRT_EVENT(fail); +DEFINE_XPRT_EVENT(free); + +TRACE_DEFINE_ENUM(RDMA_MSG); +TRACE_DEFINE_ENUM(RDMA_NOMSG); +TRACE_DEFINE_ENUM(RDMA_MSGP); +TRACE_DEFINE_ENUM(RDMA_DONE); +TRACE_DEFINE_ENUM(RDMA_ERROR); + +#define show_rpcrdma_proc(x) \ + __print_symbolic(x, \ + { RDMA_MSG, "RDMA_MSG" }, \ + { RDMA_NOMSG, "RDMA_NOMSG" }, \ + { RDMA_MSGP, "RDMA_MSGP" }, \ + { RDMA_DONE, "RDMA_DONE" }, \ + { RDMA_ERROR, "RDMA_ERROR" }) + +TRACE_EVENT(svcrdma_decode_rqst, + TP_PROTO( + __be32 *p, + unsigned int hdrlen + ), + + TP_ARGS(p, hdrlen), + + TP_STRUCT__entry( + __field(u32, xid) + __field(u32, vers) + __field(u32, proc) + __field(u32, credits) + __field(unsigned int, hdrlen) + ), + + TP_fast_assign( + __entry->xid = be32_to_cpup(p++); + __entry->vers = be32_to_cpup(p++); + __entry->credits = be32_to_cpup(p++); + __entry->proc = be32_to_cpup(p); + __entry->hdrlen = hdrlen; + ), + + TP_printk("xid=0x%08x vers=%u credits=%u proc=%s hdrlen=%u", + __entry->xid, __entry->vers, __entry->credits, + show_rpcrdma_proc(__entry->proc), __entry->hdrlen) +); + +TRACE_EVENT(svcrdma_decode_short, + TP_PROTO( + unsigned int hdrlen + ), + + TP_ARGS(hdrlen), + + TP_STRUCT__entry( + __field(unsigned int, hdrlen) + ), + + TP_fast_assign( + __entry->hdrlen = hdrlen; + ), + + TP_printk("hdrlen=%u", __entry->hdrlen) +); + +DECLARE_EVENT_CLASS(svcrdma_badreq_event, + TP_PROTO( + __be32 *p + ), + + TP_ARGS(p), + + TP_STRUCT__entry( + __field(u32, xid) + __field(u32, vers) + __field(u32, proc) + __field(u32, credits) + ), + + TP_fast_assign( + __entry->xid = be32_to_cpup(p++); + __entry->vers = be32_to_cpup(p++); + __entry->credits = be32_to_cpup(p++); + __entry->proc = be32_to_cpup(p); + ), + + TP_printk("xid=0x%08x vers=%u credits=%u proc=%u", + __entry->xid, __entry->vers, __entry->credits, __entry->proc) +); + +#define DEFINE_BADREQ_EVENT(name) \ + DEFINE_EVENT(svcrdma_badreq_event, svcrdma_decode_##name,\ + TP_PROTO( \ + __be32 *p \ + ), \ + TP_ARGS(p)) + +DEFINE_BADREQ_EVENT(badvers); +DEFINE_BADREQ_EVENT(drop); +DEFINE_BADREQ_EVENT(badproc); +DEFINE_BADREQ_EVENT(parse); + +DECLARE_EVENT_CLASS(svcrdma_segment_event, + TP_PROTO( + u32 handle, + u32 length, + u64 offset + ), + + TP_ARGS(handle, length, offset), + + TP_STRUCT__entry( + __field(u32, handle) + __field(u32, length) + __field(u64, offset) + ), + + TP_fast_assign( + __entry->handle = handle; + __entry->length = length; + __entry->offset = offset; + ), + + TP_printk("%u@0x%016llx:0x%08x", + __entry->length, (unsigned long long)__entry->offset, + __entry->handle + ) +); + +#define DEFINE_SEGMENT_EVENT(name) \ + DEFINE_EVENT(svcrdma_segment_event, svcrdma_encode_##name,\ + TP_PROTO( \ + u32 handle, \ + u32 length, \ + u64 offset \ + ), \ + TP_ARGS(handle, length, offset)) + +DEFINE_SEGMENT_EVENT(rseg); +DEFINE_SEGMENT_EVENT(wseg); + +DECLARE_EVENT_CLASS(svcrdma_chunk_event, + TP_PROTO( + u32 length + ), + + TP_ARGS(length), + + TP_STRUCT__entry( + __field(u32, length) + ), + + TP_fast_assign( + __entry->length = length; + ), + + TP_printk("length=%u", + __entry->length + ) +); + +#define DEFINE_CHUNK_EVENT(name) \ + DEFINE_EVENT(svcrdma_chunk_event, svcrdma_encode_##name,\ + TP_PROTO( \ + u32 length \ + ), \ + TP_ARGS(length)) + +DEFINE_CHUNK_EVENT(pzr); +DEFINE_CHUNK_EVENT(write); +DEFINE_CHUNK_EVENT(reply); + +TRACE_EVENT(svcrdma_encode_read, + TP_PROTO( + u32 length, + u32 position + ), + + TP_ARGS(length, position), + + TP_STRUCT__entry( + __field(u32, length) + __field(u32, position) + ), + + TP_fast_assign( + __entry->length = length; + __entry->position = position; + ), + + TP_printk("length=%u position=%u", + __entry->length, __entry->position + ) +); + +DECLARE_EVENT_CLASS(svcrdma_error_event, + TP_PROTO( + __be32 xid + ), + + TP_ARGS(xid), + + TP_STRUCT__entry( + __field(u32, xid) + ), + + TP_fast_assign( + __entry->xid = be32_to_cpu(xid); + ), + + TP_printk("xid=0x%08x", + __entry->xid + ) +); + +#define DEFINE_ERROR_EVENT(name) \ + DEFINE_EVENT(svcrdma_error_event, svcrdma_err_##name, \ + TP_PROTO( \ + __be32 xid \ + ), \ + TP_ARGS(xid)) + +DEFINE_ERROR_EVENT(vers); +DEFINE_ERROR_EVENT(chunk); + #endif /* _TRACE_RPCRDMA_H */ #include diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 9eae95de89a7..78ca5806ff0a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -93,17 +93,19 @@ * (see rdma_read_complete() below). */ +#include #include #include #include -#include - #include #include #include #include +#include "xprt_rdma.h" +#include + #define RPCDBG_FACILITY RPCDBG_SVCXPRT /* @@ -295,7 +297,6 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg) { __be32 *p, *end, *rdma_argp; unsigned int hdr_len; - char *proc; /* Verify that there's enough bytes for header + something */ if (rq_arg->len <= RPCRDMA_HDRLEN_ERR) @@ -307,10 +308,8 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg) switch (*(rdma_argp + 3)) { case rdma_msg: - proc = "RDMA_MSG"; break; case rdma_nomsg: - proc = "RDMA_NOMSG"; break; case rdma_done: @@ -340,30 +339,27 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg) hdr_len = (unsigned long)p - (unsigned long)rdma_argp; rq_arg->head[0].iov_len -= hdr_len; rq_arg->len -= hdr_len; - dprintk("svcrdma: received %s request for XID 0x%08x, hdr_len=%u\n", - proc, be32_to_cpup(rdma_argp), hdr_len); + trace_svcrdma_decode_rqst(rdma_argp, hdr_len); return hdr_len; out_short: - dprintk("svcrdma: header too short = %d\n", rq_arg->len); + trace_svcrdma_decode_short(rq_arg->len); return -EINVAL; out_version: - dprintk("svcrdma: bad xprt version: %u\n", - be32_to_cpup(rdma_argp + 1)); + trace_svcrdma_decode_badvers(rdma_argp); return -EPROTONOSUPPORT; out_drop: - dprintk("svcrdma: dropping RDMA_DONE/ERROR message\n"); + trace_svcrdma_decode_drop(rdma_argp); return 0; out_proc: - dprintk("svcrdma: bad rdma procedure (%u)\n", - be32_to_cpup(rdma_argp + 3)); + trace_svcrdma_decode_badproc(rdma_argp); return -EINVAL; out_inval: - dprintk("svcrdma: failed to parse transport header\n"); + trace_svcrdma_decode_parse(rdma_argp); return -EINVAL; } @@ -412,12 +408,16 @@ static void svc_rdma_send_error(struct svcxprt_rdma *xprt, *p++ = *(rdma_argp + 1); *p++ = xprt->sc_fc_credits; *p++ = rdma_error; - if (status == -EPROTONOSUPPORT) { + switch (status) { + case -EPROTONOSUPPORT: *p++ = err_vers; *p++ = rpcrdma_version; *p++ = rpcrdma_version; - } else { + trace_svcrdma_err_vers(*rdma_argp); + break; + default: *p++ = err_chunk; + trace_svcrdma_err_chunk(*rdma_argp); } length = (unsigned long)p - (unsigned long)err_msgp; @@ -532,8 +532,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) } spin_unlock(&rdma_xprt->sc_rq_dto_lock); - dprintk("svcrdma: recvfrom: ctxt=%p on xprt=%p, rqstp=%p\n", - ctxt, rdma_xprt, rqstp); atomic_inc(&rdma_stat_recv); svc_rdma_build_arg_xdr(rqstp, ctxt); @@ -559,8 +557,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) complete: svc_rdma_put_context(ctxt, 0); - dprintk("svcrdma: recvfrom: xprt=%p, rqstp=%p, rq_arg.len=%u\n", - rdma_xprt, rqstp, rqstp->rq_arg.len); rqstp->rq_prot = IPPROTO_MAX; svc_xprt_copy_addrs(rqstp, xprt); return rqstp->rq_arg.len; diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 12b9a7e0b6d2..4b9cb54cf58b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -5,11 +5,14 @@ * Use the core R/W API to move RPC-over-RDMA Read and Write chunks. */ +#include + #include #include #include -#include +#include "xprt_rdma.h" +#include #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -437,6 +440,7 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, if (ret < 0) goto out_initerr; + trace_svcrdma_encode_wseg(seg_handle, write_len, seg_offset); list_add(&ctxt->rw_list, &cc->cc_rwctxts); cc->cc_sqecount += ret; if (write_len == seg_length - info->wi_seg_off) { @@ -526,6 +530,8 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, ret = svc_rdma_post_chunk_ctxt(&info->wi_cc); if (ret < 0) goto out_err; + + trace_svcrdma_encode_write(xdr->page_len); return xdr->page_len; out_err: @@ -582,6 +588,8 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, __be32 *rp_ch, ret = svc_rdma_post_chunk_ctxt(&info->wi_cc); if (ret < 0) goto out_err; + + trace_svcrdma_encode_reply(consumed); return consumed; out_err: @@ -606,9 +614,6 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, goto out_noctx; ctxt->rw_nents = sge_no; - dprintk("svcrdma: reading segment %u@0x%016llx:0x%08x (%u sges)\n", - len, offset, rkey, sge_no); - sg = ctxt->rw_sg_table.sgl; for (sge_no = 0; sge_no < ctxt->rw_nents; sge_no++) { seg_len = min_t(unsigned int, len, @@ -686,6 +691,7 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, if (ret < 0) break; + trace_svcrdma_encode_rseg(rs_handle, rs_length, rs_offset); info->ri_chunklen += rs_length; } @@ -706,9 +712,6 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head = info->ri_readctxt; int ret; - dprintk("svcrdma: Reading Read chunk at position %u\n", - info->ri_position); - info->ri_pageno = head->hdr_count; info->ri_pageoff = 0; @@ -716,6 +719,8 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp, if (ret < 0) goto out; + trace_svcrdma_encode_read(info->ri_chunklen, info->ri_position); + /* Split the Receive buffer between the head and tail * buffers at Read chunk's position. XDR roundup of the * chunk is not included in either the pagelist or in @@ -764,8 +769,6 @@ static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head = info->ri_readctxt; int ret; - dprintk("svcrdma: Reading Position Zero Read chunk\n"); - info->ri_pageno = head->hdr_count - 1; info->ri_pageoff = offset_in_page(head->byte_len); @@ -773,6 +776,8 @@ static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp, if (ret < 0) goto out; + trace_svcrdma_encode_pzr(info->ri_chunklen); + head->arg.len += info->ri_chunklen; head->arg.buflen += info->ri_chunklen; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 79bd3a394da2..4c580833ec2e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -99,14 +99,19 @@ * where two different Write segments send portions of the same page. */ -#include -#include #include #include + #include #include + +#include +#include #include +#include "xprt_rdma.h" +#include + #define RPCDBG_FACILITY RPCDBG_SVCXPRT static u32 xdr_padsize(u32 len) @@ -524,12 +529,6 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma, u32 inv_rkey; int ret; - dprintk("svcrdma: sending %s reply: head=%zu, pagelen=%u, tail=%zu\n", - (rp_ch ? "RDMA_NOMSG" : "RDMA_MSG"), - rqstp->rq_res.head[0].iov_len, - rqstp->rq_res.page_len, - rqstp->rq_res.tail[0].iov_len); - ctxt = svc_rdma_get_context(rdma); ret = svc_rdma_map_reply_hdr(rdma, ctxt, rdma_resp, @@ -580,6 +579,7 @@ static int svc_rdma_send_error_msg(struct svcxprt_rdma *rdma, /* Replace the original transport header with an * RDMA_ERROR response. XID etc are preserved. */ + trace_svcrdma_err_chunk(*rdma_resp); p = rdma_resp + 3; *p++ = rdma_error; *p = err_chunk; @@ -635,9 +635,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) rdma_argp = page_address(rqstp->rq_pages[0]); svc_rdma_get_write_arrays(rdma_argp, &wr_lst, &rp_ch); - dprintk("svcrdma: preparing response for XID 0x%08x\n", - be32_to_cpup(rdma_argp)); - /* Create the RDMA response header. xprt->xpt_mutex, * acquired in svc_send(), serializes RPC replies. The * code path below that inserts the credit grant value diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 22e2595b1df6..d2cdffa9fccb 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -41,21 +41,25 @@ * Author: Tom Tucker */ -#include -#include -#include -#include #include #include #include #include #include +#include + #include #include #include + +#include +#include +#include +#include #include -#include + #include "xprt_rdma.h" +#include #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -862,10 +866,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) dprintk(" max_requests : %d\n", newxprt->sc_max_requests); dprintk(" ord : %d\n", conn_param.initiator_depth); + trace_svcrdma_xprt_accept(&newxprt->sc_xprt); return &newxprt->sc_xprt; errout: dprintk("svcrdma: failure accepting new connection rc=%d.\n", ret); + trace_svcrdma_xprt_fail(&newxprt->sc_xprt); /* Take a reference in case the DTO handler runs */ svc_xprt_get(&newxprt->sc_xprt); if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp)) @@ -896,7 +902,6 @@ static void svc_rdma_detach(struct svc_xprt *xprt) { struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); - dprintk("svc: svc_rdma_detach(%p)\n", xprt); /* Disconnect and flush posted WQE */ rdma_disconnect(rdma->sc_cm_id); @@ -908,7 +913,7 @@ static void __svc_rdma_free(struct work_struct *work) container_of(work, struct svcxprt_rdma, sc_work); struct svc_xprt *xprt = &rdma->sc_xprt; - dprintk("svcrdma: %s(%p)\n", __func__, rdma); + trace_svcrdma_xprt_free(xprt); if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) ib_drain_qp(rdma->sc_qp); -- cgit v1.2.3 From bd2abef33394dc16d63580c38c01420db991f0f2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 May 2018 15:27:16 -0400 Subject: svcrdma: Trace key RDMA API events This includes: * Posting on the Send and Receive queues * Send, Receive, Read, and Write completion * Connect upcalls * QP errors Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/trace/events/rpcrdma.h | 322 +++++++++++++++++++++++++++++ net/sunrpc/xprtrdma/backchannel.c | 1 + net/sunrpc/xprtrdma/fmr_ops.c | 2 + net/sunrpc/xprtrdma/frwr_ops.c | 1 + net/sunrpc/xprtrdma/rpc_rdma.c | 2 + net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 3 + net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 2 - net/sunrpc/xprtrdma/svc_rdma_rw.c | 14 +- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 6 +- net/sunrpc/xprtrdma/svc_rdma_transport.c | 67 +++--- net/sunrpc/xprtrdma/transport.c | 3 + 11 files changed, 372 insertions(+), 51 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 633520ac99cd..094a676d92a7 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1145,6 +1145,328 @@ DECLARE_EVENT_CLASS(svcrdma_error_event, DEFINE_ERROR_EVENT(vers); DEFINE_ERROR_EVENT(chunk); +/** + ** Server-side RDMA API events + **/ + +TRACE_EVENT(svcrdma_dma_map_page, + TP_PROTO( + const struct svcxprt_rdma *rdma, + const void *page + ), + + TP_ARGS(rdma, page), + + TP_STRUCT__entry( + __field(const void *, page); + __string(device, rdma->sc_cm_id->device->name) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->page = page; + __assign_str(device, rdma->sc_cm_id->device->name); + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s device=%s page=%p", + __get_str(addr), __get_str(device), __entry->page + ) +); + +TRACE_EVENT(svcrdma_dma_map_rwctx, + TP_PROTO( + const struct svcxprt_rdma *rdma, + int status + ), + + TP_ARGS(rdma, status), + + TP_STRUCT__entry( + __field(int, status) + __string(device, rdma->sc_cm_id->device->name) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->status = status; + __assign_str(device, rdma->sc_cm_id->device->name); + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s device=%s status=%d", + __get_str(addr), __get_str(device), __entry->status + ) +); + +TRACE_EVENT(svcrdma_send_failed, + TP_PROTO( + const struct svc_rqst *rqst, + int status + ), + + TP_ARGS(rqst, status), + + TP_STRUCT__entry( + __field(int, status) + __field(u32, xid) + __field(const void *, xprt) + __string(addr, rqst->rq_xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->status = status; + __entry->xid = __be32_to_cpu(rqst->rq_xid); + __entry->xprt = rqst->rq_xprt; + __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); + ), + + TP_printk("xprt=%p addr=%s xid=0x%08x status=%d", + __entry->xprt, __get_str(addr), + __entry->xid, __entry->status + ) +); + +DECLARE_EVENT_CLASS(svcrdma_sendcomp_event, + TP_PROTO( + const struct ib_wc *wc + ), + + TP_ARGS(wc), + + TP_STRUCT__entry( + __field(const void *, cqe) + __field(unsigned int, status) + __field(unsigned int, vendor_err) + ), + + TP_fast_assign( + __entry->cqe = wc->wr_cqe; + __entry->status = wc->status; + if (wc->status) + __entry->vendor_err = wc->vendor_err; + else + __entry->vendor_err = 0; + ), + + TP_printk("cqe=%p status=%s (%u/0x%x)", + __entry->cqe, rdma_show_wc_status(__entry->status), + __entry->status, __entry->vendor_err + ) +); + +#define DEFINE_SENDCOMP_EVENT(name) \ + DEFINE_EVENT(svcrdma_sendcomp_event, svcrdma_wc_##name, \ + TP_PROTO( \ + const struct ib_wc *wc \ + ), \ + TP_ARGS(wc)) + +TRACE_EVENT(svcrdma_post_send, + TP_PROTO( + const struct ib_send_wr *wr, + int status + ), + + TP_ARGS(wr, status), + + TP_STRUCT__entry( + __field(const void *, cqe) + __field(unsigned int, num_sge) + __field(u32, inv_rkey) + __field(int, status) + ), + + TP_fast_assign( + __entry->cqe = wr->wr_cqe; + __entry->num_sge = wr->num_sge; + __entry->inv_rkey = (wr->opcode == IB_WR_SEND_WITH_INV) ? + wr->ex.invalidate_rkey : 0; + __entry->status = status; + ), + + TP_printk("cqe=%p num_sge=%u inv_rkey=0x%08x status=%d", + __entry->cqe, __entry->num_sge, + __entry->inv_rkey, __entry->status + ) +); + +DEFINE_SENDCOMP_EVENT(send); + +TRACE_EVENT(svcrdma_post_recv, + TP_PROTO( + const struct ib_recv_wr *wr, + int status + ), + + TP_ARGS(wr, status), + + TP_STRUCT__entry( + __field(const void *, cqe) + __field(int, status) + ), + + TP_fast_assign( + __entry->cqe = wr->wr_cqe; + __entry->status = status; + ), + + TP_printk("cqe=%p status=%d", + __entry->cqe, __entry->status + ) +); + +TRACE_EVENT(svcrdma_wc_receive, + TP_PROTO( + const struct ib_wc *wc + ), + + TP_ARGS(wc), + + TP_STRUCT__entry( + __field(const void *, cqe) + __field(u32, byte_len) + __field(unsigned int, status) + __field(u32, vendor_err) + ), + + TP_fast_assign( + __entry->cqe = wc->wr_cqe; + __entry->status = wc->status; + if (wc->status) { + __entry->byte_len = 0; + __entry->vendor_err = wc->vendor_err; + } else { + __entry->byte_len = wc->byte_len; + __entry->vendor_err = 0; + } + ), + + TP_printk("cqe=%p byte_len=%u status=%s (%u/0x%x)", + __entry->cqe, __entry->byte_len, + rdma_show_wc_status(__entry->status), + __entry->status, __entry->vendor_err + ) +); + +TRACE_EVENT(svcrdma_post_rw, + TP_PROTO( + const void *cqe, + int sqecount, + int status + ), + + TP_ARGS(cqe, sqecount, status), + + TP_STRUCT__entry( + __field(const void *, cqe) + __field(int, sqecount) + __field(int, status) + ), + + TP_fast_assign( + __entry->cqe = cqe; + __entry->sqecount = sqecount; + __entry->status = status; + ), + + TP_printk("cqe=%p sqecount=%d status=%d", + __entry->cqe, __entry->sqecount, __entry->status + ) +); + +DEFINE_SENDCOMP_EVENT(read); +DEFINE_SENDCOMP_EVENT(write); + +TRACE_EVENT(svcrdma_cm_event, + TP_PROTO( + const struct rdma_cm_event *event, + const struct sockaddr *sap + ), + + TP_ARGS(event, sap), + + TP_STRUCT__entry( + __field(unsigned int, event) + __field(int, status) + __array(__u8, addr, INET6_ADDRSTRLEN + 10) + ), + + TP_fast_assign( + __entry->event = event->event; + __entry->status = event->status; + snprintf(__entry->addr, sizeof(__entry->addr) - 1, + "%pISpc", sap); + ), + + TP_printk("addr=%s event=%s (%u/%d)", + __entry->addr, + rdma_show_cm_event(__entry->event), + __entry->event, __entry->status + ) +); + +TRACE_EVENT(svcrdma_qp_error, + TP_PROTO( + const struct ib_event *event, + const struct sockaddr *sap + ), + + TP_ARGS(event, sap), + + TP_STRUCT__entry( + __field(unsigned int, event) + __string(device, event->device->name) + __array(__u8, addr, INET6_ADDRSTRLEN + 10) + ), + + TP_fast_assign( + __entry->event = event->event; + __assign_str(device, event->device->name); + snprintf(__entry->addr, sizeof(__entry->addr) - 1, + "%pISpc", sap); + ), + + TP_printk("addr=%s dev=%s event=%s (%u)", + __entry->addr, __get_str(device), + rdma_show_ib_event(__entry->event), __entry->event + ) +); + +DECLARE_EVENT_CLASS(svcrdma_sendqueue_event, + TP_PROTO( + const struct svcxprt_rdma *rdma + ), + + TP_ARGS(rdma), + + TP_STRUCT__entry( + __field(int, avail) + __field(int, depth) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->avail = atomic_read(&rdma->sc_sq_avail); + __entry->depth = rdma->sc_sq_depth; + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s sc_sq_avail=%d/%d", + __get_str(addr), __entry->avail, __entry->depth + ) +); + +#define DEFINE_SQ_EVENT(name) \ + DEFINE_EVENT(svcrdma_sendqueue_event, svcrdma_sq_##name,\ + TP_PROTO( \ + const struct svcxprt_rdma *rdma \ + ), \ + TP_ARGS(rdma)) + +DEFINE_SQ_EVENT(full); +DEFINE_SQ_EVENT(retry); + #endif /* _TRACE_RPCRDMA_H */ #include diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 05c69aca3996..dbedc872ec10 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "xprt_rdma.h" #include diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 08de7dad8abe..c74b41561495 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -20,6 +20,8 @@ * verb (fmr_op_unmap). */ +#include + #include "xprt_rdma.h" #include diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index f8312e30fade..5d6c01ce3c45 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -71,6 +71,7 @@ */ #include +#include #include "xprt_rdma.h" #include diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index f358d1e40a57..b942d7e0aef5 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -48,6 +48,8 @@ #include +#include + #include "xprt_rdma.h" #include diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index a73632ca9048..d50152163190 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -6,8 +6,11 @@ */ #include + #include + #include "xprt_rdma.h" +#include #define RPCDBG_FACILITY RPCDBG_SVCXPRT diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 78ca5806ff0a..330d542fd96e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -432,8 +432,6 @@ static void svc_rdma_send_error(struct svcxprt_rdma *xprt, ret = svc_rdma_post_send_wr(xprt, ctxt, 1, 0); if (ret) { - dprintk("svcrdma: Error %d posting send for protocol error\n", - ret); svc_rdma_unmap_dma(ctxt); svc_rdma_put_context(ctxt, 1); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 4b9cb54cf58b..887ceef125b2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -208,6 +208,8 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) struct svc_rdma_write_info *info = container_of(cc, struct svc_rdma_write_info, wi_cc); + trace_svcrdma_wc_write(wc); + atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); wake_up(&rdma->sc_send_wait); @@ -269,6 +271,8 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) struct svc_rdma_read_info *info = container_of(cc, struct svc_rdma_read_info, ri_cc); + trace_svcrdma_wc_read(wc); + atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); wake_up(&rdma->sc_send_wait); @@ -326,18 +330,20 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) if (atomic_sub_return(cc->cc_sqecount, &rdma->sc_sq_avail) > 0) { ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr); + trace_svcrdma_post_rw(&cc->cc_cqe, + cc->cc_sqecount, ret); if (ret) break; return 0; } - atomic_inc(&rdma_stat_sq_starve); + trace_svcrdma_sq_full(rdma); atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); wait_event(rdma->sc_send_wait, atomic_read(&rdma->sc_sq_avail) > cc->cc_sqecount); + trace_svcrdma_sq_retry(rdma); } while (1); - pr_err("svcrdma: ib_post_send failed (%d)\n", ret); set_bit(XPT_CLOSE, &xprt->xpt_flags); /* If even one was posted, there will be a completion. */ @@ -466,7 +472,7 @@ out_noctx: out_initerr: svc_rdma_put_rw_ctxt(rdma, ctxt); - pr_err("svcrdma: failed to map pagelist (%d)\n", ret); + trace_svcrdma_dma_map_rwctx(rdma, ret); return -EIO; } @@ -661,8 +667,8 @@ out_overrun: return -EINVAL; out_initerr: + trace_svcrdma_dma_map_rwctx(cc->cc_rdma, ret); svc_rdma_put_rw_ctxt(cc->cc_rdma, ctxt); - pr_err("svcrdma: failed to map pagelist (%d)\n", ret); return -EIO; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 4c580833ec2e..fed28de78d37 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -353,7 +353,7 @@ static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, return 0; out_maperr: - pr_err("svcrdma: failed to map page\n"); + trace_svcrdma_dma_map_page(rdma, page); return -EIO; } @@ -597,7 +597,6 @@ static int svc_rdma_send_error_msg(struct svcxprt_rdma *rdma, return 0; err: - pr_err("svcrdma: failed to post Send WR (%d)\n", ret); svc_rdma_unmap_dma(ctxt); svc_rdma_put_context(ctxt, 1); return ret; @@ -690,8 +689,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) err1: put_page(res_page); err0: - pr_err("svcrdma: Could not send reply, err=%d. Closing transport.\n", - ret); + trace_svcrdma_send_failed(rqstp, ret); set_bit(XPT_CLOSE, &xprt->xpt_flags); return -ENOTCONN; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index d2cdffa9fccb..05edb18f8ca3 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -275,16 +275,15 @@ static void qp_event_handler(struct ib_event *event, void *context) { struct svc_xprt *xprt = context; + trace_svcrdma_qp_error(event, (struct sockaddr *)&xprt->xpt_remote); switch (event->event) { /* These are considered benign events */ case IB_EVENT_PATH_MIG: case IB_EVENT_COMM_EST: case IB_EVENT_SQ_DRAINED: case IB_EVENT_QP_LAST_WQE_REACHED: - dprintk("svcrdma: QP event %s (%d) received for QP=%p\n", - ib_event_msg(event->event), event->event, - event->element.qp); break; + /* These are considered fatal events */ case IB_EVENT_PATH_MIG_ERR: case IB_EVENT_QP_FATAL: @@ -292,10 +291,6 @@ static void qp_event_handler(struct ib_event *event, void *context) case IB_EVENT_QP_ACCESS_ERR: case IB_EVENT_DEVICE_FATAL: default: - dprintk("svcrdma: QP ERROR event %s (%d) received for QP=%p, " - "closing transport\n", - ib_event_msg(event->event), event->event, - event->element.qp); set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); break; @@ -314,6 +309,8 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_op_ctxt *ctxt; + trace_svcrdma_wc_receive(wc); + /* WARNING: Only wc->wr_cqe and wc->status are reliable */ ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe); svc_rdma_unmap_dma(ctxt); @@ -360,6 +357,8 @@ void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_op_ctxt *ctxt; + trace_svcrdma_wc_send(wc); + atomic_inc(&xprt->sc_sq_avail); wake_up(&xprt->sc_send_wait); @@ -455,6 +454,7 @@ svc_rdma_post_recv(struct svcxprt_rdma *xprt) svc_xprt_get(&xprt->sc_xprt); ret = ib_post_recv(xprt->sc_qp, &recv_wr, &bad_recv_wr); + trace_svcrdma_post_recv(&recv_wr, ret); if (ret) { svc_rdma_unmap_dma(ctxt); svc_rdma_put_context(ctxt, 1); @@ -513,8 +513,6 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id, return; newxprt->sc_cm_id = new_cma_id; new_cma_id->context = newxprt; - dprintk("svcrdma: Creating newxprt=%p, cm_id=%p, listenxprt=%p\n", - newxprt, newxprt->sc_cm_id, listen_xprt); svc_rdma_parse_connect_private(newxprt, param); /* Save client advertised inbound read limit for use later in accept. */ @@ -545,9 +543,11 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id, static int rdma_listen_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { - struct svcxprt_rdma *xprt = cma_id->context; + struct sockaddr *sap = (struct sockaddr *)&cma_id->route.addr.src_addr; int ret = 0; + trace_svcrdma_cm_event(event, sap); + switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: dprintk("svcrdma: Connect request on cma_id=%p, xprt = %p, " @@ -555,23 +555,8 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, rdma_event_msg(event->event), event->event); handle_connect_req(cma_id, &event->param.conn); break; - - case RDMA_CM_EVENT_ESTABLISHED: - /* Accept complete */ - dprintk("svcrdma: Connection completed on LISTEN xprt=%p, " - "cm_id=%p\n", xprt, cma_id); - break; - - case RDMA_CM_EVENT_DEVICE_REMOVAL: - dprintk("svcrdma: Device removal xprt=%p, cm_id=%p\n", - xprt, cma_id); - if (xprt) { - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - svc_xprt_enqueue(&xprt->sc_xprt); - } - break; - default: + /* NB: No device removal upcall for INADDR_ANY listeners */ dprintk("svcrdma: Unexpected event on listening endpoint %p, " "event = %s (%d)\n", cma_id, rdma_event_msg(event->event), event->event); @@ -584,9 +569,12 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, static int rdma_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { - struct svc_xprt *xprt = cma_id->context; - struct svcxprt_rdma *rdma = - container_of(xprt, struct svcxprt_rdma, sc_xprt); + struct sockaddr *sap = (struct sockaddr *)&cma_id->route.addr.dst_addr; + struct svcxprt_rdma *rdma = cma_id->context; + struct svc_xprt *xprt = &rdma->sc_xprt; + + trace_svcrdma_cm_event(event, sap); + switch (event->event) { case RDMA_CM_EVENT_ESTABLISHED: /* Accept complete */ @@ -599,21 +587,17 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, case RDMA_CM_EVENT_DISCONNECTED: dprintk("svcrdma: Disconnect on DTO xprt=%p, cm_id=%p\n", xprt, cma_id); - if (xprt) { - set_bit(XPT_CLOSE, &xprt->xpt_flags); - svc_xprt_enqueue(xprt); - svc_xprt_put(xprt); - } + set_bit(XPT_CLOSE, &xprt->xpt_flags); + svc_xprt_enqueue(xprt); + svc_xprt_put(xprt); break; case RDMA_CM_EVENT_DEVICE_REMOVAL: dprintk("svcrdma: Device removal cma_id=%p, xprt = %p, " "event = %s (%d)\n", cma_id, xprt, rdma_event_msg(event->event), event->event); - if (xprt) { - set_bit(XPT_CLOSE, &xprt->xpt_flags); - svc_xprt_enqueue(xprt); - svc_xprt_put(xprt); - } + set_bit(XPT_CLOSE, &xprt->xpt_flags); + svc_xprt_enqueue(xprt); + svc_xprt_put(xprt); break; default: dprintk("svcrdma: Unexpected event on DTO endpoint %p, " @@ -1022,13 +1006,13 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) while (1) { if ((atomic_sub_return(wr_count, &xprt->sc_sq_avail) < 0)) { atomic_inc(&rdma_stat_sq_starve); - - /* Wait until SQ WR available if SQ still full */ + trace_svcrdma_sq_full(xprt); atomic_add(wr_count, &xprt->sc_sq_avail); wait_event(xprt->sc_send_wait, atomic_read(&xprt->sc_sq_avail) > wr_count); if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags)) return -ENOTCONN; + trace_svcrdma_sq_retry(xprt); continue; } /* Take a transport ref for each WR posted */ @@ -1037,6 +1021,7 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) /* Bump used SQ WR count and post */ ret = ib_post_send(xprt->sc_qp, wr, &bad_wr); + trace_svcrdma_post_send(wr, ret); if (ret) { set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); for (i = 0; i < wr_count; i ++) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 3d1b27748aba..caca977e3755 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -51,7 +51,10 @@ #include #include #include +#include + #include +#include #include "xprt_rdma.h" #include -- cgit v1.2.3 From 8335640cf89faa0f4e39e73e314f3f3a22d776f3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 May 2018 15:36:02 -0400 Subject: xprtrdma: Add trace_xprtrdma_dma_map(mr) Matches trace_xprtrdma_dma_unmap(mr). Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 1 + net/sunrpc/xprtrdma/fmr_ops.c | 1 + net/sunrpc/xprtrdma/frwr_ops.c | 1 + 3 files changed, 3 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index ac82849954e4..c4494a2b3ecd 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -650,6 +650,7 @@ DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li); DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li_wake); DEFINE_MR_EVENT(xprtrdma_localinv); +DEFINE_MR_EVENT(xprtrdma_dma_map); DEFINE_MR_EVENT(xprtrdma_dma_unmap); DEFINE_MR_EVENT(xprtrdma_remoteinv); DEFINE_MR_EVENT(xprtrdma_recover_mr); diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 592d1e8e27c3..d2bc82f577b0 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -244,6 +244,7 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, mr->mr_sg, i, mr->mr_dir); if (!mr->mr_nents) goto out_dmamap_err; + trace_xprtrdma_dma_map(mr); for (i = 0, dma_pages = mr->fmr.fm_physaddrs; i < mr->mr_nents; i++) dma_pages[i] = sg_dma_address(&mr->mr_sg[i]); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 0f2e108d387e..3056dc901be0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -418,6 +418,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, mr->mr_nents = ib_dma_map_sg(ia->ri_device, mr->mr_sg, i, mr->mr_dir); if (!mr->mr_nents) goto out_dmamap_err; + trace_xprtrdma_dma_map(mr); ibmr = frwr->fr_mr; n = ib_map_mr_sg(ibmr, mr->mr_sg, mr->mr_nents, NULL, PAGE_SIZE); -- cgit v1.2.3