Commit 774d5f14 authored by Andy Adamson's avatar Andy Adamson Committed by Trond Myklebust
Browse files

NFSv4.1 Fix a pNFS session draining deadlock 



On a CB_RECALL the callback service thread flushes the inode using
filemap_flush prior to scheduling the state manager thread to return the
delegation. When pNFS is used and I/O has not yet gone to the data server
servicing the inode, a LAYOUTGET can preceed the I/O. Unlike the async
filemap_flush call, the LAYOUTGET must proceed to completion.

If the state manager starts to recover data while the inode flush is sending
the LAYOUTGET, a deadlock occurs as the callback service thread holds the
single callback session slot until the flushing is done which blocks the state
manager thread, and the state manager thread has set the session draining bit
which puts the inode flush LAYOUTGET RPC to sleep on the forechannel slot
table waitq.

Separate the draining of the back channel from the draining of the fore channel
by moving the NFS4_SESSION_DRAINING bit from session scope into the fore
and back slot tables.  Drain the back channel first allowing the LAYOUTGET
call to proceed (and fail) so the callback service thread frees the callback
slot. Then proceed with draining the forechannel.

Signed-off-by: default avatarAndy Adamson <andros@netapp.com>
Signed-off-by: default avatarTrond Myklebust <Trond.Myklebust@netapp.com>
parent 2aed8b47

fs/nfs/callback_proc.c

+1 −1
Original line number Diff line number Diff line
@@ -414,7 +414,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, 


	spin_lock(&tbl->slot_tbl_lock);

	/* state manager is resetting the session */

	if (test_bit(NFS4_SESSION_DRAINING, &clp->cl_session->session_state)) {

	if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {

		spin_unlock(&tbl->slot_tbl_lock);

		status = htonl(NFS4ERR_DELAY);

		/* Return NFS4ERR_BADSESSION if we're draining the session

fs/nfs/callback_xdr.c

+1 −1
Original line number Diff line number Diff line
@@ -763,7 +763,7 @@ static void nfs4_callback_free_slot(struct nfs4_session *session) 
	 * A single slot, so highest used slotid is either 0 or -1

	 */

	tbl->highest_used_slotid = NFS4_NO_SLOT;

	nfs4_session_drain_complete(session, tbl);

	nfs4_slot_tbl_drain_complete(tbl);

	spin_unlock(&tbl->slot_tbl_lock);

}

fs/nfs/nfs4proc.c

+1 −1
Original line number Diff line number Diff line
@@ -572,7 +572,7 @@ int nfs41_setup_sequence(struct nfs4_session *session, 
	task->tk_timeout = 0;



	spin_lock(&tbl->slot_tbl_lock);

	if (test_bit(NFS4_SESSION_DRAINING, &session->session_state) &&

	if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state) &&

	    !args->sa_privileged) {

		/* The state manager will wait until the slot table is empty */

		dprintk("%s session is draining\n", __func__);

fs/nfs/nfs4session.c

+2 −2
Original line number Diff line number Diff line
@@ -73,7 +73,7 @@ void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot) 
			tbl->highest_used_slotid = new_max;

		else {

			tbl->highest_used_slotid = NFS4_NO_SLOT;

			nfs4_session_drain_complete(tbl->session, tbl);

			nfs4_slot_tbl_drain_complete(tbl);

		}

	}

	dprintk("%s: slotid %u highest_used_slotid %d\n", __func__,
@@ -226,7 +226,7 @@ static bool nfs41_assign_slot(struct rpc_task *task, void *pslot) 
	struct nfs4_slot *slot = pslot;

	struct nfs4_slot_table *tbl = slot->table;



	if (nfs4_session_draining(tbl->session) && !args->sa_privileged)

	if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged)

		return false;

	slot->generation = tbl->generation;

	args->sa_slot = slot;

fs/nfs/nfs4session.h

+8 −5
Original line number Diff line number Diff line
@@ -25,6 +25,10 @@ struct nfs4_slot { 
};



/* Sessions */

enum nfs4_slot_tbl_state {

	NFS4_SLOT_TBL_DRAINING,

};



#define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long))

struct nfs4_slot_table {

	struct nfs4_session *session;		/* Parent session */
@@ -43,6 +47,7 @@ struct nfs4_slot_table { 
	unsigned long	generation;		/* Generation counter for

						   target_highest_slotid */

	struct completion complete;

	unsigned long	slot_tbl_state;

};



/*
@@ -68,7 +73,6 @@ struct nfs4_session { 


enum nfs4_session_state {

	NFS4_SESSION_INITING,

	NFS4_SESSION_DRAINING,

};



#if defined(CONFIG_NFS_V4_1)
@@ -88,12 +92,11 @@ extern void nfs4_destroy_session(struct nfs4_session *session); 
extern int nfs4_init_session(struct nfs_server *server);

extern int nfs4_init_ds_session(struct nfs_client *, unsigned long);



extern void nfs4_session_drain_complete(struct nfs4_session *session,

		struct nfs4_slot_table *tbl);

extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);



static inline bool nfs4_session_draining(struct nfs4_session *session)

static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl)

{

	return !!test_bit(NFS4_SESSION_DRAINING, &session->session_state);

	return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);

}



bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,

CRA Git | Maintained and supported by SUSTech CRA and CCSE