summaryrefslogtreecommitdiff
path: root/fs/nfsd/nfs4state.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfsd/nfs4state.c')
-rw-r--r--fs/nfsd/nfs4state.c279
1 files changed, 183 insertions, 96 deletions
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b82817767b9d..b29b5a185a2c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -63,12 +63,16 @@ static const stateid_t zero_stateid = {
static const stateid_t currentstateid = {
.si_generation = 1,
};
+static const stateid_t close_stateid = {
+ .si_generation = 0xffffffffU,
+};
static u64 current_sessionid = 1;
#define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t)))
#define ONE_STATEID(stateid) (!memcmp((stateid), &one_stateid, sizeof(stateid_t)))
#define CURRENT_STATEID(stateid) (!memcmp((stateid), &currentstateid, sizeof(stateid_t)))
+#define CLOSE_STATEID(stateid) (!memcmp((stateid), &close_stateid, sizeof(stateid_t)))
/* forward declarations */
static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner);
@@ -83,6 +87,11 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid);
*/
static DEFINE_SPINLOCK(state_lock);
+enum nfsd4_st_mutex_lock_subclass {
+ OPEN_STATEID_MUTEX = 0,
+ LOCK_STATEID_MUTEX = 1,
+};
+
/*
* A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for
* the refcount on the open stateid to drop.
@@ -3562,7 +3571,9 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
/* ignore lock owners */
if (local->st_stateowner->so_is_open_owner == 0)
continue;
- if (local->st_stateowner == &oo->oo_owner) {
+ if (local->st_stateowner != &oo->oo_owner)
+ continue;
+ if (local->st_stid.sc_type == NFS4_OPEN_STID) {
ret = local;
refcount_inc(&ret->st_stid.sc_count);
break;
@@ -3571,6 +3582,52 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
return ret;
}
+static __be32
+nfsd4_verify_open_stid(struct nfs4_stid *s)
+{
+ __be32 ret = nfs_ok;
+
+ switch (s->sc_type) {
+ default:
+ break;
+ case NFS4_CLOSED_STID:
+ case NFS4_CLOSED_DELEG_STID:
+ ret = nfserr_bad_stateid;
+ break;
+ case NFS4_REVOKED_DELEG_STID:
+ ret = nfserr_deleg_revoked;
+ }
+ return ret;
+}
+
+/* Lock the stateid st_mutex, and deal with races with CLOSE */
+static __be32
+nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp)
+{
+ __be32 ret;
+
+ mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX);
+ ret = nfsd4_verify_open_stid(&stp->st_stid);
+ if (ret != nfs_ok)
+ mutex_unlock(&stp->st_mutex);
+ return ret;
+}
+
+static struct nfs4_ol_stateid *
+nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
+{
+ struct nfs4_ol_stateid *stp;
+ for (;;) {
+ spin_lock(&fp->fi_lock);
+ stp = nfsd4_find_existing_open(fp, open);
+ spin_unlock(&fp->fi_lock);
+ if (!stp || nfsd4_lock_ol_stateid(stp) == nfs_ok)
+ break;
+ nfs4_put_stid(&stp->st_stid);
+ }
+ return stp;
+}
+
static struct nfs4_openowner *
alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
struct nfsd4_compound_state *cstate)
@@ -3613,8 +3670,9 @@ init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
stp = open->op_stp;
/* We are moving these outside of the spinlocks to avoid the warnings */
mutex_init(&stp->st_mutex);
- mutex_lock(&stp->st_mutex);
+ mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);
+retry:
spin_lock(&oo->oo_owner.so_client->cl_lock);
spin_lock(&fp->fi_lock);
@@ -3639,7 +3697,11 @@ out_unlock:
spin_unlock(&fp->fi_lock);
spin_unlock(&oo->oo_owner.so_client->cl_lock);
if (retstp) {
- mutex_lock(&retstp->st_mutex);
+ /* Handle races with CLOSE */
+ if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+ nfs4_put_stid(&retstp->st_stid);
+ goto retry;
+ }
/* To keep mutex tracking happy */
mutex_unlock(&stp->st_mutex);
stp = retstp;
@@ -4449,6 +4511,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
struct nfs4_ol_stateid *stp = NULL;
struct nfs4_delegation *dp = NULL;
__be32 status;
+ bool new_stp = false;
/*
* Lookup file; if found, lookup stateid and check open request,
@@ -4460,9 +4523,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
status = nfs4_check_deleg(cl, open, &dp);
if (status)
goto out;
- spin_lock(&fp->fi_lock);
- stp = nfsd4_find_existing_open(fp, open);
- spin_unlock(&fp->fi_lock);
+ stp = nfsd4_find_and_lock_existing_open(fp, open);
} else {
open->op_file = NULL;
status = nfserr_bad_stateid;
@@ -4470,35 +4531,31 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
goto out;
}
+ if (!stp) {
+ stp = init_open_stateid(fp, open);
+ if (!open->op_stp)
+ new_stp = true;
+ }
+
/*
* OPEN the file, or upgrade an existing OPEN.
* If truncate fails, the OPEN fails.
+ *
+ * stp is already locked.
*/
- if (stp) {
+ if (!new_stp) {
/* Stateid was found, this is an OPEN upgrade */
- mutex_lock(&stp->st_mutex);
status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
if (status) {
mutex_unlock(&stp->st_mutex);
goto out;
}
} else {
- /* stp is returned locked. */
- stp = init_open_stateid(fp, open);
- /* See if we lost the race to some other thread */
- if (stp->st_access_bmap != 0) {
- status = nfs4_upgrade_open(rqstp, fp, current_fh,
- stp, open);
- if (status) {
- mutex_unlock(&stp->st_mutex);
- goto out;
- }
- goto upgrade_out;
- }
status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
if (status) {
- mutex_unlock(&stp->st_mutex);
+ stp->st_stid.sc_type = NFS4_CLOSED_STID;
release_open_stateid(stp);
+ mutex_unlock(&stp->st_mutex);
goto out;
}
@@ -4507,7 +4564,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
if (stp->st_clnt_odstate == open->op_odstate)
open->op_odstate = NULL;
}
-upgrade_out:
+
nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
mutex_unlock(&stp->st_mutex);
@@ -4734,7 +4791,7 @@ nfs4_laundromat(struct nfsd_net *nn)
spin_unlock(&nn->blocked_locks_lock);
while (!list_empty(&reaplist)) {
- nbl = list_first_entry(&nn->blocked_locks_lru,
+ nbl = list_first_entry(&reaplist,
struct nfsd4_blocked_lock, nbl_lru);
list_del_init(&nbl->nbl_lru);
posix_unblock_lock(&nbl->nbl_lock);
@@ -4855,6 +4912,18 @@ static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_s
return nfserr_old_stateid;
}
+static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_stid *s, bool has_session)
+{
+ __be32 ret;
+
+ spin_lock(&s->sc_lock);
+ ret = nfsd4_verify_open_stid(s);
+ if (ret == nfs_ok)
+ ret = check_stateid_generation(in, &s->sc_stateid, has_session);
+ spin_unlock(&s->sc_lock);
+ return ret;
+}
+
static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols)
{
if (ols->st_stateowner->so_is_open_owner &&
@@ -4868,7 +4937,8 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
struct nfs4_stid *s;
__be32 status = nfserr_bad_stateid;
- if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+ if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
+ CLOSE_STATEID(stateid))
return status;
/* Client debugging aid. */
if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) {
@@ -4883,7 +4953,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
s = find_stateid_locked(cl, stateid);
if (!s)
goto out_unlock;
- status = check_stateid_generation(stateid, &s->sc_stateid, 1);
+ status = nfsd4_stid_check_stateid_generation(stateid, s, 1);
if (status)
goto out_unlock;
switch (s->sc_type) {
@@ -4926,7 +4996,8 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
else if (typemask & NFS4_DELEG_STID)
typemask |= NFS4_REVOKED_DELEG_STID;
- if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+ if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
+ CLOSE_STATEID(stateid))
return nfserr_bad_stateid;
status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
if (status == nfserr_stale_clientid) {
@@ -5044,7 +5115,7 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
&s, nn);
if (status)
return status;
- status = check_stateid_generation(stateid, &s->sc_stateid,
+ status = nfsd4_stid_check_stateid_generation(stateid, s,
nfsd4_has_session(cstate));
if (status)
goto out;
@@ -5098,7 +5169,9 @@ nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
struct nfs4_ol_stateid *stp = openlockstateid(s);
__be32 ret;
- mutex_lock(&stp->st_mutex);
+ ret = nfsd4_lock_ol_stateid(stp);
+ if (ret)
+ goto out_put_stid;
ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
if (ret)
@@ -5109,11 +5182,13 @@ nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
lockowner(stp->st_stateowner)))
goto out;
+ stp->st_stid.sc_type = NFS4_CLOSED_STID;
release_lock_stateid(stp);
ret = nfs_ok;
out:
mutex_unlock(&stp->st_mutex);
+out_put_stid:
nfs4_put_stid(s);
return ret;
}
@@ -5133,6 +5208,7 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
s = find_stateid_locked(cl, stateid);
if (!s)
goto out_unlock;
+ spin_lock(&s->sc_lock);
switch (s->sc_type) {
case NFS4_DELEG_STID:
ret = nfserr_locks_held;
@@ -5144,11 +5220,13 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
ret = nfserr_locks_held;
break;
case NFS4_LOCK_STID:
+ spin_unlock(&s->sc_lock);
refcount_inc(&s->sc_count);
spin_unlock(&cl->cl_lock);
ret = nfsd4_free_lock_stateid(stateid, s);
goto out;
case NFS4_REVOKED_DELEG_STID:
+ spin_unlock(&s->sc_lock);
dp = delegstateid(s);
list_del_init(&dp->dl_recall_lru);
spin_unlock(&cl->cl_lock);
@@ -5157,6 +5235,7 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
/* Default falls through and returns nfserr_bad_stateid */
}
+ spin_unlock(&s->sc_lock);
out_unlock:
spin_unlock(&cl->cl_lock);
out:
@@ -5179,15 +5258,9 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
status = nfsd4_check_seqid(cstate, sop, seqid);
if (status)
return status;
- if (stp->st_stid.sc_type == NFS4_CLOSED_STID
- || stp->st_stid.sc_type == NFS4_REVOKED_DELEG_STID)
- /*
- * "Closed" stateid's exist *only* to return
- * nfserr_replay_me from the previous step, and
- * revoked delegations are kept only for free_stateid.
- */
- return nfserr_bad_stateid;
- mutex_lock(&stp->st_mutex);
+ status = nfsd4_lock_ol_stateid(stp);
+ if (status != nfs_ok)
+ return status;
status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
if (status == nfs_ok)
status = nfs4_check_fh(current_fh, &stp->st_stid);
@@ -5367,7 +5440,6 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
bool unhashed;
LIST_HEAD(reaplist);
- s->st_stid.sc_type = NFS4_CLOSED_STID;
spin_lock(&clp->cl_lock);
unhashed = unhash_open_stateid(s, &reaplist);
@@ -5407,10 +5479,17 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfsd4_bump_seqid(cstate, status);
if (status)
goto out;
+
+ stp->st_stid.sc_type = NFS4_CLOSED_STID;
nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
- mutex_unlock(&stp->st_mutex);
nfsd4_close_open_stateid(stp);
+ mutex_unlock(&stp->st_mutex);
+
+ /* See RFC5661 sectionm 18.2.4 */
+ if (stp->st_stid.sc_client->cl_minorversion)
+ memcpy(&close->cl_stateid, &close_stateid,
+ sizeof(close->cl_stateid));
/* put reference from nfs4_preprocess_seqid_op */
nfs4_put_stid(&stp->st_stid);
@@ -5436,7 +5515,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
dp = delegstateid(s);
- status = check_stateid_generation(stateid, &dp->dl_stid.sc_stateid, nfsd4_has_session(cstate));
+ status = nfsd4_stid_check_stateid_generation(stateid, &dp->dl_stid, nfsd4_has_session(cstate));
if (status)
goto put_stateid;
@@ -5642,14 +5721,41 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
return ret;
}
-static void
+static struct nfs4_ol_stateid *
+find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
+{
+ struct nfs4_ol_stateid *lst;
+ struct nfs4_client *clp = lo->lo_owner.so_client;
+
+ lockdep_assert_held(&clp->cl_lock);
+
+ list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
+ if (lst->st_stid.sc_type != NFS4_LOCK_STID)
+ continue;
+ if (lst->st_stid.sc_file == fp) {
+ refcount_inc(&lst->st_stid.sc_count);
+ return lst;
+ }
+ }
+ return NULL;
+}
+
+static struct nfs4_ol_stateid *
init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
struct nfs4_file *fp, struct inode *inode,
struct nfs4_ol_stateid *open_stp)
{
struct nfs4_client *clp = lo->lo_owner.so_client;
+ struct nfs4_ol_stateid *retstp;
- lockdep_assert_held(&clp->cl_lock);
+ mutex_init(&stp->st_mutex);
+ mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);
+retry:
+ spin_lock(&clp->cl_lock);
+ spin_lock(&fp->fi_lock);
+ retstp = find_lock_stateid(lo, fp);
+ if (retstp)
+ goto out_unlock;
refcount_inc(&stp->st_stid.sc_count);
stp->st_stid.sc_type = NFS4_LOCK_STID;
@@ -5659,29 +5765,22 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
- mutex_init(&stp->st_mutex);
list_add(&stp->st_locks, &open_stp->st_locks);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
- spin_lock(&fp->fi_lock);
list_add(&stp->st_perfile, &fp->fi_stateids);
+out_unlock:
spin_unlock(&fp->fi_lock);
-}
-
-static struct nfs4_ol_stateid *
-find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
-{
- struct nfs4_ol_stateid *lst;
- struct nfs4_client *clp = lo->lo_owner.so_client;
-
- lockdep_assert_held(&clp->cl_lock);
-
- list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
- if (lst->st_stid.sc_file == fp) {
- refcount_inc(&lst->st_stid.sc_count);
- return lst;
+ spin_unlock(&clp->cl_lock);
+ if (retstp) {
+ if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+ nfs4_put_stid(&retstp->st_stid);
+ goto retry;
}
+ /* To keep mutex tracking happy */
+ mutex_unlock(&stp->st_mutex);
+ stp = retstp;
}
- return NULL;
+ return stp;
}
static struct nfs4_ol_stateid *
@@ -5694,26 +5793,25 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,
struct nfs4_openowner *oo = openowner(ost->st_stateowner);
struct nfs4_client *clp = oo->oo_owner.so_client;
+ *new = false;
spin_lock(&clp->cl_lock);
lst = find_lock_stateid(lo, fi);
- if (lst == NULL) {
- spin_unlock(&clp->cl_lock);
- ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
- if (ns == NULL)
- return NULL;
-
- spin_lock(&clp->cl_lock);
- lst = find_lock_stateid(lo, fi);
- if (likely(!lst)) {
- lst = openlockstateid(ns);
- init_lock_stateid(lst, lo, fi, inode, ost);
- ns = NULL;
- *new = true;
- }
- }
spin_unlock(&clp->cl_lock);
- if (ns)
+ if (lst != NULL) {
+ if (nfsd4_lock_ol_stateid(lst) == nfs_ok)
+ goto out;
+ nfs4_put_stid(&lst->st_stid);
+ }
+ ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
+ if (ns == NULL)
+ return NULL;
+
+ lst = init_lock_stateid(openlockstateid(ns), lo, fi, inode, ost);
+ if (lst == openlockstateid(ns))
+ *new = true;
+ else
nfs4_put_stid(ns);
+out:
return lst;
}
@@ -5750,7 +5848,6 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
struct nfs4_lockowner *lo;
struct nfs4_ol_stateid *lst;
unsigned int strhashval;
- bool hashed;
lo = find_lockowner_str(cl, &lock->lk_new_owner);
if (!lo) {
@@ -5766,25 +5863,12 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
goto out;
}
-retry:
lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
if (lst == NULL) {
status = nfserr_jukebox;
goto out;
}
- mutex_lock(&lst->st_mutex);
-
- /* See if it's still hashed to avoid race with FREE_STATEID */
- spin_lock(&cl->cl_lock);
- hashed = !list_empty(&lst->st_perfile);
- spin_unlock(&cl->cl_lock);
-
- if (!hashed) {
- mutex_unlock(&lst->st_mutex);
- nfs4_put_stid(&lst->st_stid);
- goto retry;
- }
status = nfs_ok;
*plst = lst;
out:
@@ -5990,14 +6074,16 @@ out:
seqid_mutating_err(ntohl(status)))
lock_sop->lo_owner.so_seqid++;
- mutex_unlock(&lock_stp->st_mutex);
-
/*
* If this is a new, never-before-used stateid, and we are
* returning an error, then just go ahead and release it.
*/
- if (status && new)
+ if (status && new) {
+ lock_stp->st_stid.sc_type = NFS4_CLOSED_STID;
release_lock_stateid(lock_stp);
+ }
+
+ mutex_unlock(&lock_stp->st_mutex);
nfs4_put_stid(&lock_stp->st_stid);
}
@@ -7017,6 +7103,10 @@ static int nfs4_state_create_net(struct net *net)
INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]);
nn->conf_name_tree = RB_ROOT;
nn->unconf_name_tree = RB_ROOT;
+ nn->boot_time = get_seconds();
+ nn->grace_ended = false;
+ nn->nfsd4_manager.block_opens = true;
+ INIT_LIST_HEAD(&nn->nfsd4_manager.list);
INIT_LIST_HEAD(&nn->client_lru);
INIT_LIST_HEAD(&nn->close_lru);
INIT_LIST_HEAD(&nn->del_recall_lru);
@@ -7074,9 +7164,6 @@ nfs4_state_start_net(struct net *net)
ret = nfs4_state_create_net(net);
if (ret)
return ret;
- nn->boot_time = get_seconds();
- nn->grace_ended = false;
- nn->nfsd4_manager.block_opens = true;
locks_start_grace(net, &nn->nfsd4_manager);
nfsd4_client_tracking_init(net);
printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n",
@@ -7153,7 +7240,7 @@ nfs4_state_shutdown_net(struct net *net)
spin_unlock(&nn->blocked_locks_lock);
while (!list_empty(&reaplist)) {
- nbl = list_first_entry(&nn->blocked_locks_lru,
+ nbl = list_first_entry(&reaplist,
struct nfsd4_blocked_lock, nbl_lru);
list_del_init(&nbl->nbl_lru);
posix_unblock_lock(&nbl->nbl_lock);