Merge tag 'nfsd-4.18' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "A relatively quiet cycle for nfsd.

  The largest piece is an RDMA update from Chuck Lever with new trace
  points, miscellaneous cleanups, and streamlining of the send and
  receive paths.

  Other than that, some miscellaneous bugfixes"

* tag 'nfsd-4.18' of git://linux-nfs.org/~bfields/linux: (26 commits)
  nfsd: fix error handling in nfs4_set_delegation()
  nfsd: fix potential use-after-free in nfsd4_decode_getdeviceinfo
  Fix 16-byte memory leak in gssp_accept_sec_context_upcall
  svcrdma: Fix incorrect return value/type in svc_rdma_post_recvs
  svcrdma: Remove unused svc_rdma_op_ctxt
  svcrdma: Persistently allocate and DMA-map Send buffers
  svcrdma: Simplify svc_rdma_send()
  svcrdma: Remove post_send_wr
  svcrdma: Don't overrun the SGE array in svc_rdma_send_ctxt
  svcrdma: Introduce svc_rdma_send_ctxt
  svcrdma: Clean up Send SGE accounting
  svcrdma: Refactor svc_rdma_dma_map_buf
  svcrdma: Allocate recv_ctxt's on CPU handling Receives
  svcrdma: Persistently allocate and DMA-map Receive buffers
  svcrdma: Preserve Receive buffer until svc_rdma_sendto
  svcrdma: Simplify svc_rdma_recv_ctxt_put
  svcrdma: Remove sc_rq_depth
  svcrdma: Introduce svc_rdma_recv_ctxt
  svcrdma: Trace key RDMA API events
  svcrdma: Trace key RPC/RDMA protocol events
  ...

1 files changed, 583 insertions, 1 deletions

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 50ed3f8bf534..094a676d92a7 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 +887,586 @@ 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);
+
+/**
+ ** 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 <trace/define_trace.h>