nfsd: add trace events

For now just a few simple events to trace the layout stateid lifetime, but
these already were enough to find several bugs in the Linux client layout
stateid handling.

Signed-off-by: Christoph Hellwig <hch@lst.de>

5 files changed, 85 insertions, 3 deletions

diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index 5806270a8567..6cba933880c5 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -2,9 +2,14 @@
 # Makefile for the Linux nfs server
 #
 
+ccflags-y += -I$(src)                   # needed for trace events
+
 obj-$(CONFIG_NFSD)      += nfsd.o
 
-nfsd-y                  := nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
+# this one should be compiled first, as the tracing macros can easily blow up
+nfsd-y                  += trace.o
+
+nfsd-y                  += nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
                            export.o auth.o lockd.o nfscache.o nfsxdr.o stats.o
 nfsd-$(CONFIG_NFSD_FAULT_INJECTION) += fault_inject.o
 nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index d926865df94f..60137c54b2f7 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -9,6 +9,7 @@
 
 #include "pnfs.h"
 #include "netns.h"
+#include "trace.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PNFS
 
@@ -125,6 +126,8 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid)
         struct nfs4_client *clp = ls->ls_stid.sc_client;
         struct nfs4_file *fp = ls->ls_stid.sc_file;
 
+        trace_layoutstate_free(&ls->ls_stid.sc_stateid);
+
         spin_lock(&clp->cl_lock);
         list_del_init(&ls->ls_perclnt);
         spin_unlock(&clp->cl_lock);
@@ -215,6 +218,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
         list_add(&ls->ls_perfile, &fp->fi_lo_states);
         spin_unlock(&fp->fi_lock);
 
+        trace_layoutstate_alloc(&ls->ls_stid.sc_stateid);
         return ls;
 }
 
@@ -280,6 +284,8 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls)
         if (list_empty(&ls->ls_layouts))
                 goto out_unlock;
 
+        trace_layout_recall(&ls->ls_stid.sc_stateid);
+
         atomic_inc(&ls->ls_stid.sc_count);
         update_stateid(&ls->ls_stid.sc_stateid);
         memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
@@ -454,8 +460,10 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp,
         nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid,
                                                 false, lrp->lr_layout_type,
                                                 &ls);
-        if (nfserr)
+        if (nfserr) {
+                trace_layout_return_lookup_fail(&lrp->lr_sid);
                 return nfserr;
+        }
 
         spin_lock(&ls->ls_lock);
         list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) {
@@ -472,6 +480,7 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp,
                 }
                 lrp->lrs_present = 1;
         } else {
+                trace_layoutstate_unhash(&ls->ls_stid.sc_stateid);
                 nfs4_unhash_stid(&ls->ls_stid);
                 lrp->lrs_present = 0;
         }
@@ -570,6 +579,8 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 
         rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
 
+        nfsd4_cb_layout_fail(ls);
+
         printk(KERN_WARNING
                 "nfsd: client %s failed to respond to layout recall. "
                 "  Fencing..\n", addr_str);
@@ -597,6 +608,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
         case 0:
                 return 1;
         case -NFS4ERR_NOMATCHING_LAYOUT:
+                trace_layout_recall_done(&ls->ls_stid.sc_stateid);
                 task->tk_status = 0;
                 return 1;
         case -NFS4ERR_DELAY:
@@ -624,6 +636,8 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb)
                 container_of(cb, struct nfs4_layout_stateid, ls_recall);
         LIST_HEAD(reaplist);
 
+        trace_layout_recall_release(&ls->ls_stid.sc_stateid);
+
         nfsd4_return_all_layouts(ls, &reaplist);
         nfsd4_free_layouts(&reaplist);
         nfs4_put_stid(&ls->ls_stid);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index fa14359eb956..d30bea8d0277 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -44,6 +44,7 @@
 #include "netns.h"
 #include "acl.h"
 #include "pnfs.h"
+#include "trace.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -1298,8 +1299,10 @@ nfsd4_layoutget(struct svc_rqst *rqstp,
 
         nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid,
                                                 true, lgp->lg_layout_type, &ls);
-        if (nfserr)
+        if (nfserr) {
+                trace_layout_get_lookup_fail(&lgp->lg_sid);
                 goto out;
+        }
 
         nfserr = nfserr_recallconflict;
         if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls))
@@ -1359,6 +1362,7 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp,
                                                 false, lcp->lc_layout_type,
                                                 &ls);
         if (nfserr) {
+                trace_layout_commit_lookup_fail(&lcp->lc_sid);
                 /* fixup error code as per RFC5661 */
                 if (nfserr == nfserr_bad_stateid)
                         nfserr = nfserr_badlayout;
diff --git a/fs/nfsd/trace.c b/fs/nfsd/trace.c
new file mode 100644
index 000000000000..82f89070594c
--- /dev/null
+++ b/fs/nfsd/trace.c
@@ -0,0 +1,5 @@
+
+#include "state.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
new file mode 100644
index 000000000000..c668520c344b
--- /dev/null
+++ b/fs/nfsd/trace.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nfsd
+
+#if !defined(_NFSD_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _NFSD_TRACE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(nfsd_stateid_class,
+        TP_PROTO(stateid_t *stp),
+        TP_ARGS(stp),
+        TP_STRUCT__entry(
+                __field(u32, cl_boot)
+                __field(u32, cl_id)
+                __field(u32, si_id)
+                __field(u32, si_generation)
+        ),
+        TP_fast_assign(