NFS4: Trace lock reclaims

One of the most frustrating messages our sustaining team sees is
the "Lock reclaim failed!" message. Add some observability in the
client's lock reclaim logic so we can capture better data the
first time a problem occurs.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

1 files changed, 82 insertions, 0 deletions

diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 0c298dc5e4b2..e60b6fbd5ada 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -1022,6 +1022,88 @@ TRACE_EVENT(nfs4_set_lock,
 		)
 );
 
+TRACE_DEFINE_ENUM(LK_STATE_IN_USE);
+TRACE_DEFINE_ENUM(NFS_DELEGATED_STATE);
+TRACE_DEFINE_ENUM(NFS_OPEN_STATE);
+TRACE_DEFINE_ENUM(NFS_O_RDONLY_STATE);
+TRACE_DEFINE_ENUM(NFS_O_WRONLY_STATE);
+TRACE_DEFINE_ENUM(NFS_O_RDWR_STATE);
+TRACE_DEFINE_ENUM(NFS_STATE_RECLAIM_REBOOT);
+TRACE_DEFINE_ENUM(NFS_STATE_RECLAIM_NOGRACE);
+TRACE_DEFINE_ENUM(NFS_STATE_POSIX_LOCKS);
+TRACE_DEFINE_ENUM(NFS_STATE_RECOVERY_FAILED);
+TRACE_DEFINE_ENUM(NFS_STATE_MAY_NOTIFY_LOCK);
+TRACE_DEFINE_ENUM(NFS_STATE_CHANGE_WAIT);
+TRACE_DEFINE_ENUM(NFS_CLNT_DST_SSC_COPY_STATE);
+TRACE_DEFINE_ENUM(NFS_CLNT_SRC_SSC_COPY_STATE);
+TRACE_DEFINE_ENUM(NFS_SRV_SSC_COPY_STATE);
+
+#define show_nfs4_state_flags(flags) \
+	__print_flags(flags, "|", \
+		{ LK_STATE_IN_USE,		"IN_USE" }, \
+		{ NFS_DELEGATED_STATE,		"DELEGATED" }, \
+		{ NFS_OPEN_STATE,		"OPEN" }, \
+		{ NFS_O_RDONLY_STATE,		"O_RDONLY" }, \
+		{ NFS_O_WRONLY_STATE,		"O_WRONLY" }, \
+		{ NFS_O_RDWR_STATE,		"O_RDWR" }, \
+		{ NFS_STATE_RECLAIM_REBOOT,	"RECLAIM_REBOOT" }, \
+		{ NFS_STATE_RECLAIM_NOGRACE,	"RECLAIM_NOGRACE" }, \
+		{ NFS_STATE_POSIX_LOCKS,	"POSIX_LOCKS" }, \
+		{ NFS_STATE_RECOVERY_FAILED,	"RECOVERY_FAILED" }, \
+		{ NFS_STATE_MAY_NOTIFY_LOCK,	"MAY_NOTIFY_LOCK" }, \
+		{ NFS_STATE_CHANGE_WAIT,	"CHANGE_WAIT" }, \
+		{ NFS_CLNT_DST_SSC_COPY_STATE,	"CLNT_DST_SSC_COPY" }, \
+		{ NFS_CLNT_SRC_SSC_COPY_STATE,	"CLNT_SRC_SSC_COPY" }, \
+		{ NFS_SRV_SSC_COPY_STATE,	"SRV_SSC_COPY" })
+
+#define show_nfs4_lock_flags(flags) \
+	__print_flags(flags, "|", \
+		{ BIT(NFS_LOCK_INITIALIZED),	"INITIALIZED" }, \
+		{ BIT(NFS_LOCK_LOST),		"LOST" })
+
+TRACE_EVENT(nfs4_state_lock_reclaim,
+		TP_PROTO(
+			const struct nfs4_state *state,
+			const struct nfs4_lock_state *lock
+		),
+
+		TP_ARGS(state, lock),
+
+		TP_STRUCT__entry(
+			__field(dev_t, dev)
+			__field(u32, fhandle)
+			__field(u64, fileid)
+			__field(unsigned long, state_flags)
+			__field(unsigned long, lock_flags)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
+		),
+
+		TP_fast_assign(
+			const struct inode *inode = state->inode;
+
+			__entry->dev = inode->i_sb->s_dev;
+			__entry->fileid = NFS_FILEID(inode);
+			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+			__entry->state_flags = state->flags;
+			__entry->lock_flags = lock->ls_flags;
+			__entry->stateid_seq =
+				be32_to_cpu(state->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&state->stateid);
+		),
+
+		TP_printk(
+			"fileid=%02x:%02x:%llu fhandle=0x%08x "
+			"stateid=%d:0x%08x state_flags=%s lock_flags=%s",
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->fileid, __entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash,
+			show_nfs4_state_flags(__entry->state_flags),
+			show_nfs4_lock_flags(__entry->lock_flags)
+		)
+)
+
 DECLARE_EVENT_CLASS(nfs4_set_delegation_event,
 		TP_PROTO(
 			const struct inode *inode,