Re: [PATCH RFC v17 10/11] NFSD: Update laundromat to handle courtesy clients

[dai.ngo@oracle.com]

On 3/17/22 8:03 AM, Chuck Lever III wrote:
>
>> On Mar 17, 2022, at 3:43 AM, Dai Ngo <dai.ngo@oracle.com> wrote:
>>
>> Add nfs4_anylock_blocker and nfs4_lockowner_has_blockers to check
>> if an expired client has any lock blockers
>>
>> Update nfs4_get_client_reaplist to:
>> . add courtesy client in CLIENT_EXPIRED state to reaplist.
>> . detect if expired client still has state and no blockers then
>>    transit it to courtesy client by setting CLIENT_COURTESY state
>>    and removing the client record.
>>
>> Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
>> ---
>> fs/nfsd/nfs4state.c | 93 +++++++++++++++++++++++++++++++++++++++++++++++++++--
>> 1 file changed, 91 insertions(+), 2 deletions(-)
>>
>> diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
>> index b4b976e00ce6..d5758c7101dc 100644
>> --- a/fs/nfsd/nfs4state.c
>> +++ b/fs/nfsd/nfs4state.c
>> @@ -5755,24 +5755,106 @@ static void nfsd4_ssc_expire_umount(struct nfsd_net *nn)
>> }
>> #endif
>>
>> +/* Check if any lock belonging to this lockowner has any blockers */
>> +static bool
>> +nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo)
>> +{
>> +	struct file_lock_context *ctx;
>> +	struct nfs4_ol_stateid *stp;
>> +	struct nfs4_file *nf;
>> +
>> +	list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) {
>> +		nf = stp->st_stid.sc_file;
>> +		ctx = nf->fi_inode->i_flctx;
>> +		if (!ctx)
>> +			continue;
>> +		if (locks_owner_has_blockers(ctx, lo))
>> +			return true;
>> +	}
>> +	return false;
>> +}
>> +
>> +static bool
>> +nfs4_anylock_blockers(struct nfs4_client *clp)
>> +{
>> +	int i;
>> +	struct nfs4_stateowner *so;
>> +	struct nfs4_lockowner *lo;
>> +
>> +	spin_lock(&clp->cl_lock);
>> +	for (i = 0; i < OWNER_HASH_SIZE; i++) {
>> +		list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[i],
>> +				so_strhash) {
>> +			if (so->so_is_open_owner)
>> +				continue;
>> +			lo = lockowner(so);
>> +			if (nfs4_lockowner_has_blockers(lo)) {
>> +				spin_unlock(&clp->cl_lock);
>> +				return true;
>> +			}
>> +		}
>> +	}
>> +	spin_unlock(&clp->cl_lock);
>> +	return false;
>> +}
>> +
>> static void
>> nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist,
>> 				struct laundry_time *lt)
>> {
>> 	struct list_head *pos, *next;
>> 	struct nfs4_client *clp;
>> +	bool cour;
>> +	struct list_head cslist;
>>
>> 	INIT_LIST_HEAD(reaplist);
>> +	INIT_LIST_HEAD(&cslist);
>> 	spin_lock(&nn->client_lock);
>> 	list_for_each_safe(pos, next, &nn->client_lru) {
>> 		clp = list_entry(pos, struct nfs4_client, cl_lru);
>> 		if (!state_expired(lt, clp->cl_time))
>> 			break;
>> -		if (mark_client_expired_locked(clp))
>> +
>> +		if (!client_has_state(clp))
>> +			goto exp_client;
>> +
>> +		if (clp->cl_cs_client_state == NFSD4_CLIENT_EXPIRED)
>> +			goto exp_client;
>> +		cour = (clp->cl_cs_client_state == NFSD4_CLIENT_COURTESY);
> I've forgotten: why don't you need to hold clp->cl_cs_lock while
> checking cs_client_state here?

The CLIENT_EXPIRED can be set when either the client is reconnecting
or when a thread tries to resolve the conflict with the courtesy
client. The reconnecting client and the laundromat are synced by
nn->client_lock. For thread that tries to resolve conflict and set
CLIENT_EXPIRED, if the laundromat misses detecting CLIENT_EXPIRED
then it will get it the next time it runs.

The CLIENT_COURTESY state is only set by the laundromat so there is
no need for any lock when checking it here.

-Dai

>
>
>> +		if (cour && ktime_get_boottime_seconds() >=
>> +				(clp->cl_time + NFSD_COURTESY_CLIENT_TIMEOUT))
>> +			goto exp_client;
>> +		if (nfs4_anylock_blockers(clp)) {
>> +exp_client:
>> +			if (mark_client_expired_locked(clp))
>> +				continue;
>> +			list_add(&clp->cl_lru, reaplist);
>> 			continue;
>> -		list_add(&clp->cl_lru, reaplist);
>> +		}
>> +		if (!cour) {
>> +			spin_lock(&clp->cl_cs_lock);
>> +			clp->cl_cs_client_state = NFSD4_CLIENT_COURTESY;
>> +			spin_unlock(&clp->cl_cs_lock);
>> +			list_add(&clp->cl_cs_list, &cslist);
>> +		}
>> 	}
>> 	spin_unlock(&nn->client_lock);
>> +
>> +	while (!list_empty(&cslist)) {
>> +		clp = list_first_entry(&cslist, struct nfs4_client, cl_cs_list);
>> +		list_del_init(&clp->cl_cs_list);
>> +		spin_lock(&clp->cl_cs_lock);
>> +		/*
>> +		 * Client might have re-connected. Make sure it's
>> +		 * still in courtesy state before removing its record.
>> +		 */
>> +		if (clp->cl_cs_client_state != NFSD4_CLIENT_COURTESY) {
>> +			spin_unlock(&clp->cl_cs_lock);
>> +			continue;
>> +		}
>> +		spin_unlock(&clp->cl_cs_lock);
>> +		nfsd4_client_record_remove(clp);
>> +	}
>> }
>>
>> static time64_t
>> @@ -5818,6 +5900,13 @@ nfs4_laundromat(struct nfsd_net *nn)
>> 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
>> 		if (!state_expired(&lt, dp->dl_time))
>> 			break;
>> +		spin_lock(&clp->cl_cs_lock);
>> +		if (clp->cl_cs_client_state == NFSD4_CLIENT_COURTESY) {
>> +			clp->cl_cs_client_state = NFSD4_CLIENT_EXPIRED;
>> +			spin_unlock(&clp->cl_cs_lock);
>> +			continue;
>> +		}
>> +		spin_unlock(&clp->cl_cs_lock);
>> 		WARN_ON(!unhash_delegation_locked(dp));
>> 		list_add(&dp->dl_recall_lru, &reaplist);
>> 	}
>> -- 
>> 2.9.5
>>
> --
> Chuck Lever
>
>
>