NFS4: Trace state recovery operation

[ Upstream commit 511ba52e4c01fd1878140774e6215e0de6c2f36f ]

Add a trace point in the main state manager loop to observe state
recovery operation. Help track down state recovery bugs.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Stable-dep-of: ed1cc05aa1f7 ("NFSv4: Fix a nfs4_state_manager() race")
Signed-off-by: Sasha Levin <sashal@kernel.org>

2 files changed, 96 insertions, 0 deletions

diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 01b185670594..04aa8e34d112 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -61,6 +61,7 @@
 #include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
+#include "nfs4trace.h"
 
 #define NFSDBG_FACILITY		NFSDBG_STATE
 
@@ -2525,6 +2526,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 	/* Ensure exclusive access to NFSv4 state */
 	do {
+		trace_nfs4_state_mgr(clp);
 		clear_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
 		if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
 			section = "purge state";
@@ -2641,6 +2643,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 out_error:
 	if (strlen(section))
 		section_sep = ": ";
+	trace_nfs4_state_mgr_failed(clp, section, status);
 	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
 			" with error %d\n", section_sep, section,
 			clp->cl_hostname, -status);
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 2295a934a154..010ee5e6fa32 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -563,6 +563,99 @@ TRACE_EVENT(nfs4_setup_sequence,
 		)
 );
 
+TRACE_DEFINE_ENUM(NFS4CLNT_MANAGER_RUNNING);
+TRACE_DEFINE_ENUM(NFS4CLNT_CHECK_LEASE);
+TRACE_DEFINE_ENUM(NFS4CLNT_LEASE_EXPIRED);
+TRACE_DEFINE_ENUM(NFS4CLNT_RECLAIM_REBOOT);
+TRACE_DEFINE_ENUM(NFS4CLNT_RECLAIM_NOGRACE);
+TRACE_DEFINE_ENUM(NFS4CLNT_DELEGRETURN);
+TRACE_DEFINE_ENUM(NFS4CLNT_SESSION_RESET);
+TRACE_DEFINE_ENUM(NFS4CLNT_LEASE_CONFIRM);
+TRACE_DEFINE_ENUM(NFS4CLNT_SERVER_SCOPE_MISMATCH);
+TRACE_DEFINE_ENUM(NFS4CLNT_PURGE_STATE);
+TRACE_DEFINE_ENUM(NFS4CLNT_BIND_CONN_TO_SESSION);
+TRACE_DEFINE_ENUM(NFS4CLNT_MOVED);
+TRACE_DEFINE_ENUM(NFS4CLNT_LEASE_MOVED);
+TRACE_DEFINE_ENUM(NFS4CLNT_DELEGATION_EXPIRED);
+TRACE_DEFINE_ENUM(NFS4CLNT_RUN_MANAGER);
+TRACE_DEFINE_ENUM(NFS4CLNT_DELEGRETURN_RUNNING);
+
+#define show_nfs4_clp_state(state) \
+	__print_flags(state, "|", \
+		{ NFS4CLNT_MANAGER_RUNNING,	"MANAGER_RUNNING" }, \
+		{ NFS4CLNT_CHECK_LEASE,		"CHECK_LEASE" }, \
+		{ NFS4CLNT_LEASE_EXPIRED,	"LEASE_EXPIRED" }, \
+		{ NFS4CLNT_RECLAIM_REBOOT,	"RECLAIM_REBOOT" }, \
+		{ NFS4CLNT_RECLAIM_NOGRACE,	"RECLAIM_NOGRACE" }, \
+		{ NFS4CLNT_DELEGRETURN,		"DELEGRETURN" }, \
+		{ NFS4CLNT_SESSION_RESET,	"SESSION_RESET" }, \
+		{ NFS4CLNT_LEASE_CONFIRM,	"LEASE_CONFIRM" }, \
+		{ NFS4CLNT_SERVER_SCOPE_MISMATCH, \
+						"SERVER_SCOPE_MISMATCH" }, \
+		{ NFS4CLNT_PURGE_STATE,		"PURGE_STATE" }, \
+		{ NFS4CLNT_BIND_CONN_TO_SESSION, \
+						"BIND_CONN_TO_SESSION" }, \
+		{ NFS4CLNT_MOVED,		"MOVED" }, \
+		{ NFS4CLNT_LEASE_MOVED,		"LEASE_MOVED" }, \
+		{ NFS4CLNT_DELEGATION_EXPIRED,	"DELEGATION_EXPIRED" }, \
+		{ NFS4CLNT_RUN_MANAGER,		"RUN_MANAGER" }, \
+		{ NFS4CLNT_DELEGRETURN_RUNNING,	"DELEGRETURN_RUNNING" })
+
+TRACE_EVENT(nfs4_state_mgr,
+		TP_PROTO(
+			const struct nfs_client *clp
+		),
+
+		TP_ARGS(clp),
+
+		TP_STRUCT__entry(
+			__field(unsigned long, state)
+			__string(hostname, clp->cl_hostname)
+		),
+
+		TP_fast_assign(
+			__entry->state = clp->cl_state;
+			__assign_str(hostname, clp->cl_hostname)
+		),
+
+		TP_printk(
+			"hostname=%s clp state=%s", __get_str(hostname),
+			show_nfs4_clp_state(__entry->state)
+		)
+)
+
+TRACE_EVENT(nfs4_state_mgr_failed,
+		TP_PROTO(
+			const struct nfs_client *clp,
+			const char *section,
+			int status
+		),
+
+		TP_ARGS(clp, section, status),
+
+		TP_STRUCT__entry(
+			__field(unsigned long, error)
+			__field(unsigned long, state)
+			__string(hostname, clp->cl_hostname)
+			__string(section, section)
+		),
+
+		TP_fast_assign(
+			__entry->error = status;
+			__entry->state = clp->cl_state;
+			__assign_str(hostname, clp->cl_hostname);
+			__assign_str(section, section);
+		),
+
+		TP_printk(
+			"hostname=%s clp state=%s error=%ld (%s) section=%s",
+			__get_str(hostname),
+			show_nfs4_clp_state(__entry->state), -__entry->error,
+			show_nfsv4_errors(__entry->error), __get_str(section)
+
+		)
+)
+
 TRACE_EVENT(nfs4_xdr_status,
 		TP_PROTO(
 			const struct xdr_stream *xdr,