aboutsummaryrefslogtreecommitdiffstats
path: root/fs/nfsd/nfs4state.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfsd/nfs4state.c')
-rw-r--r--fs/nfsd/nfs4state.c768
1 files changed, 617 insertions, 151 deletions
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 1956d377d1a6..836bd825ca4a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -125,6 +125,23 @@ static void free_session(struct nfsd4_session *);
static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;
+static struct workqueue_struct *laundry_wq;
+
+int nfsd4_create_laundry_wq(void)
+{
+ int rc = 0;
+
+ laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4");
+ if (laundry_wq == NULL)
+ rc = -ENOMEM;
+ return rc;
+}
+
+void nfsd4_destroy_laundry_wq(void)
+{
+ destroy_workqueue(laundry_wq);
+}
+
static bool is_session_dead(struct nfsd4_session *ses)
{
return ses->se_flags & NFS4_SESSION_DEAD;
@@ -143,6 +160,13 @@ static bool is_client_expired(struct nfs4_client *clp)
return clp->cl_time == 0;
}
+static void nfsd4_dec_courtesy_client_count(struct nfsd_net *nn,
+ struct nfs4_client *clp)
+{
+ if (clp->cl_state != NFSD4_ACTIVE)
+ atomic_add_unless(&nn->nfsd_courtesy_clients, -1, 0);
+}
+
static __be32 get_client_locked(struct nfs4_client *clp)
{
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
@@ -152,6 +176,8 @@ static __be32 get_client_locked(struct nfs4_client *clp)
if (is_client_expired(clp))
return nfserr_expired;
atomic_inc(&clp->cl_rpc_users);
+ nfsd4_dec_courtesy_client_count(nn, clp);
+ clp->cl_state = NFSD4_ACTIVE;
return nfs_ok;
}
@@ -172,6 +198,8 @@ renew_client_locked(struct nfs4_client *clp)
list_move_tail(&clp->cl_lru, &nn->client_lru);
clp->cl_time = ktime_get_boottime_seconds();
+ nfsd4_dec_courtesy_client_count(nn, clp);
+ clp->cl_state = NFSD4_ACTIVE;
}
static void put_client_renew_locked(struct nfs4_client *clp)
@@ -246,6 +274,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
list_for_each_entry(cur, &lo->lo_blocked, nbl_list) {
if (fh_match(fh, &cur->nbl_fh)) {
list_del_init(&cur->nbl_list);
+ WARN_ON(list_empty(&cur->nbl_lru));
list_del_init(&cur->nbl_lru);
found = cur;
break;
@@ -271,6 +300,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
INIT_LIST_HEAD(&nbl->nbl_lru);
fh_copy_shallow(&nbl->nbl_fh, fh);
locks_init_lock(&nbl->nbl_lock);
+ kref_init(&nbl->nbl_kref);
nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client,
&nfsd4_cb_notify_lock_ops,
NFSPROC4_CLNT_CB_NOTIFY_LOCK);
@@ -280,11 +310,20 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
}
static void
+free_nbl(struct kref *kref)
+{
+ struct nfsd4_blocked_lock *nbl;
+
+ nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref);
+ kfree(nbl);
+}
+
+static void
free_blocked_lock(struct nfsd4_blocked_lock *nbl)
{
locks_delete_block(&nbl->nbl_lock);
locks_release_private(&nbl->nbl_lock);
- kfree(nbl);
+ kref_put(&nbl->nbl_kref, free_nbl);
}
static void
@@ -302,6 +341,7 @@ remove_blocked_locks(struct nfs4_lockowner *lo)
struct nfsd4_blocked_lock,
nbl_list);
list_del_init(&nbl->nbl_list);
+ WARN_ON(list_empty(&nbl->nbl_lru));
list_move(&nbl->nbl_lru, &reaplist);
}
spin_unlock(&nn->blocked_locks_lock);
@@ -326,6 +366,8 @@ nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb)
static int
nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task)
{
+ trace_nfsd_cb_notify_lock_done(&zero_stateid, task);
+
/*
* Since this is just an optimization, we don't try very hard if it
* turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and
@@ -360,11 +402,13 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
* st_{access,deny}_bmap field of the stateid, in order to track not
* only what share bits are currently in force, but also what
* combinations of share bits previous opens have used. This allows us
- * to enforce the recommendation of rfc 3530 14.2.19 that the server
- * return an error if the client attempt to downgrade to a combination
- * of share bits not explicable by closing some of its previous opens.
+ * to enforce the recommendation in
+ * https://datatracker.ietf.org/doc/html/rfc7530#section-16.19.4 that
+ * the server return an error if the client attempt to downgrade to a
+ * combination of share bits not explicable by closing some of its
+ * previous opens.
*
- * XXX: This enforcement is actually incomplete, since we don't keep
+ * This enforcement is arguably incomplete, since we don't keep
* track of access/deny bit combinations; so, e.g., we allow:
*
* OPEN allow read, deny write
@@ -372,6 +416,10 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
* DOWNGRADE allow read, deny none
*
* which we should reject.
+ *
+ * But you could also argue that our current code is already overkill,
+ * since it only exists to return NFS4ERR_INVAL on incorrect client
+ * behavior.
*/
static unsigned int
bmap_to_share_mode(unsigned long bmap)
@@ -672,6 +720,57 @@ static unsigned int file_hashval(struct svc_fh *fh)
static struct hlist_head file_hashtbl[FILE_HASH_SIZE];
+/*
+ * Check if courtesy clients have conflicting access and resolve it if possible
+ *
+ * access: is op_share_access if share_access is true.
+ * Check if access mode, op_share_access, would conflict with
+ * the current deny mode of the file 'fp'.
+ * access: is op_share_deny if share_access is false.
+ * Check if the deny mode, op_share_deny, would conflict with
+ * current access of the file 'fp'.
+ * stp: skip checking this entry.
+ * new_stp: normal open, not open upgrade.
+ *
+ * Function returns:
+ * false - access/deny mode conflict with normal client.
+ * true - no conflict or conflict with courtesy client(s) is resolved.
+ */
+static bool
+nfs4_resolve_deny_conflicts_locked(struct nfs4_file *fp, bool new_stp,
+ struct nfs4_ol_stateid *stp, u32 access, bool share_access)
+{
+ struct nfs4_ol_stateid *st;
+ bool resolvable = true;
+ unsigned char bmap;
+ struct nfsd_net *nn;
+ struct nfs4_client *clp;
+
+ lockdep_assert_held(&fp->fi_lock);
+ list_for_each_entry(st, &fp->fi_stateids, st_perfile) {
+ /* ignore lock stateid */
+ if (st->st_openstp)
+ continue;
+ if (st == stp && new_stp)
+ continue;
+ /* check file access against deny mode or vice versa */
+ bmap = share_access ? st->st_deny_bmap : st->st_access_bmap;
+ if (!(access & bmap_to_share_mode(bmap)))
+ continue;
+ clp = st->st_stid.sc_client;
+ if (try_to_expire_client(clp))
+ continue;
+ resolvable = false;
+ break;
+ }
+ if (resolvable) {
+ clp = stp->st_stid.sc_client;
+ nn = net_generic(clp->net, nfsd_net_id);
+ mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
+ }
+ return resolvable;
+}
+
static void
__nfs4_file_get_access(struct nfs4_file *fp, u32 access)
{
@@ -732,9 +831,9 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
swap(f2, fp->fi_fds[O_RDWR]);
spin_unlock(&fp->fi_lock);
if (f1)
- nfsd_file_put(f1);
+ nfsd_file_close(f1);
if (f2)
- nfsd_file_put(f2);
+ nfsd_file_close(f2);
}
}
@@ -875,19 +974,19 @@ out_free:
* Create a unique stateid_t to represent each COPY.
*/
static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
- unsigned char sc_type)
+ unsigned char cs_type)
{
int new_id;
- stid->stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
- stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
- stid->sc_type = sc_type;
+ stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
+ stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
+ stid->cs_type = cs_type;
idr_preload(GFP_KERNEL);
spin_lock(&nn->s2s_cp_lock);
new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT);
- stid->stid.si_opaque.so_id = new_id;
- stid->stid.si_generation = 1;
+ stid->cs_stid.si_opaque.so_id = new_id;
+ stid->cs_stid.si_generation = 1;
spin_unlock(&nn->s2s_cp_lock);
idr_preload_end();
if (new_id < 0)
@@ -909,7 +1008,7 @@ struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
if (!cps)
return NULL;
cps->cpntf_time = ktime_get_boottime_seconds();
- refcount_set(&cps->cp_stateid.sc_count, 1);
+ refcount_set(&cps->cp_stateid.cs_count, 1);
if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID))
goto out_free;
spin_lock(&nn->s2s_cp_lock);
@@ -925,11 +1024,11 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy)
{
struct nfsd_net *nn;
- WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID);
+ WARN_ON_ONCE(copy->cp_stateid.cs_type != NFS4_COPY_STID);
nn = net_generic(copy->cp_clp->net, nfsd_net_id);
spin_lock(&nn->s2s_cp_lock);
idr_remove(&nn->s2s_cp_stateids,
- copy->cp_stateid.stid.si_opaque.so_id);
+ copy->cp_stateid.cs_stid.si_opaque.so_id);
spin_unlock(&nn->s2s_cp_lock);
}
@@ -961,6 +1060,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
static void nfs4_free_deleg(struct nfs4_stid *stid)
{
+ struct nfs4_delegation *dp = delegstateid(stid);
+
+ WARN_ON_ONCE(!list_empty(&stid->sc_cp_list));
+ WARN_ON_ONCE(!list_empty(&dp->dl_perfile));
+ WARN_ON_ONCE(!list_empty(&dp->dl_perclnt));
+ WARN_ON_ONCE(!list_empty(&dp->dl_recall_lru));
kmem_cache_free(deleg_slab, stid);
atomic_long_dec(&num_delegations);
}
@@ -1043,7 +1148,6 @@ static void block_delegations(struct knfsd_fh *fh)
static struct nfs4_delegation *
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
- struct svc_fh *current_fh,
struct nfs4_clnt_odstate *odstate)
{
struct nfs4_delegation *dp;
@@ -1053,7 +1157,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
n = atomic_long_inc_return(&num_delegations);
if (n < 0 || n > max_delegations)
goto out_dec;
- if (delegation_blocked(&current_fh->fh_handle))
+ if (delegation_blocked(&fp->fi_fhandle))
goto out_dec;
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg));
if (dp == NULL)
@@ -1072,6 +1176,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
get_clnt_odstate(odstate);
dp->dl_type = NFS4_OPEN_DELEGATE_READ;
dp->dl_retries = 1;
+ dp->dl_recalled = false;
nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
&nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
get_nfs4_file(fp);
@@ -1374,6 +1479,7 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid)
release_all_access(stp);
if (stp->st_stateowner)
nfs4_put_stateowner(stp->st_stateowner);
+ WARN_ON(!list_empty(&stid->sc_cp_list));
kmem_cache_free(stateid_slab, stid);
}
@@ -1964,11 +2070,16 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
* This type of memory management is somewhat inefficient, but we use it
* anyway since SETCLIENTID is not a common operation.
*/
-static struct nfs4_client *alloc_client(struct xdr_netobj name)
+static struct nfs4_client *alloc_client(struct xdr_netobj name,
+ struct nfsd_net *nn)
{
struct nfs4_client *clp;
int i;
+ if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) {
+ mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
+ return NULL;
+ }
clp = kmem_cache_zalloc(client_slab, GFP_KERNEL);
if (clp == NULL)
return NULL;
@@ -1986,6 +2097,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
idr_init(&clp->cl_stateids);
atomic_set(&clp->cl_rpc_users, 0);
clp->cl_cb_state = NFSD4_CB_UNKNOWN;
+ clp->cl_state = NFSD4_ACTIVE;
+ atomic_inc(&nn->nfs4_client_count);
+ atomic_set(&clp->cl_delegs_in_recall, 0);
INIT_LIST_HEAD(&clp->cl_idhash);
INIT_LIST_HEAD(&clp->cl_openowners);
INIT_LIST_HEAD(&clp->cl_delegations);
@@ -2092,6 +2206,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp)
static void
__destroy_client(struct nfs4_client *clp)
{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
int i;
struct nfs4_openowner *oo;
struct nfs4_delegation *dp;
@@ -2135,6 +2250,8 @@ __destroy_client(struct nfs4_client *clp)
nfsd4_shutdown_callback(clp);
if (clp->cl_cb_conn.cb_xprt)
svc_xprt_put(clp->cl_cb_conn.cb_xprt);
+ atomic_add_unless(&nn->nfs4_client_count, -1, 0);
+ nfsd4_dec_courtesy_client_count(nn, clp);
free_client(clp);
wake_up_all(&expiry_wq);
}
@@ -2380,7 +2497,7 @@ static const char *cb_state2str(int state)
static int client_info_show(struct seq_file *m, void *v)
{
- struct inode *inode = m->private;
+ struct inode *inode = file_inode(m->file);
struct nfs4_client *clp;
u64 clid;
@@ -2390,10 +2507,17 @@ static int client_info_show(struct seq_file *m, void *v)
memcpy(&clid, &clp->cl_clientid, sizeof(clid));
seq_printf(m, "clientid: 0x%llx\n", clid);
seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr);
- if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
+
+ if (clp->cl_state == NFSD4_COURTESY)
+ seq_puts(m, "status: courtesy\n");
+ else if (clp->cl_state == NFSD4_EXPIRABLE)
+ seq_puts(m, "status: expirable\n");
+ else if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
seq_puts(m, "status: confirmed\n");
else
seq_puts(m, "status: unconfirmed\n");
+ seq_printf(m, "seconds from last renew: %lld\n",
+ ktime_get_boottime_seconds() - clp->cl_time);
seq_printf(m, "name: ");
seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len);
seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion);
@@ -2413,17 +2537,7 @@ static int client_info_show(struct seq_file *m, void *v)
return 0;
}
-static int client_info_open(struct inode *inode, struct file *file)
-{
- return single_open(file, client_info_show, inode);
-}
-
-static const struct file_operations client_info_fops = {
- .open = client_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(client_info);
static void *states_start(struct seq_file *s, loff_t *pos)
__acquires(&clp->cl_lock)
@@ -2466,7 +2580,7 @@ static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f)
static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f)
{
- struct inode *inode = f->nf_inode;
+ struct inode *inode = file_inode(f->nf_file);
seq_printf(s, "superblock: \"%02x:%02x:%ld\"",
MAJOR(inode->i_sb->s_dev),
@@ -2750,7 +2864,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct dentry *dentries[ARRAY_SIZE(client_files)];
- clp = alloc_client(name);
+ clp = alloc_client(name, nn);
if (clp == NULL)
return NULL;
@@ -4112,8 +4226,10 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
status = nfserr_clid_inuse;
if (client_has_state(old)
&& !same_creds(&unconf->cl_cred,
- &old->cl_cred))
+ &old->cl_cred)) {
+ old = NULL;
goto out;
+ }
status = mark_client_expired_locked(old);
if (status) {
old = NULL;
@@ -4230,6 +4346,59 @@ out:
return -ENOMEM;
}
+static unsigned long
+nfsd_courtesy_client_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ int cnt;
+ struct nfsd_net *nn = container_of(shrink,
+ struct nfsd_net, nfsd_client_shrinker);
+
+ cnt = atomic_read(&nn->nfsd_courtesy_clients);
+ if (cnt > 0)
+ mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
+ return (unsigned long)cnt;
+}
+
+static unsigned long
+nfsd_courtesy_client_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+ return SHRINK_STOP;
+}
+
+int
+nfsd4_init_leases_net(struct nfsd_net *nn)
+{
+ struct sysinfo si;
+ u64 max_clients;
+
+ nn->nfsd4_lease = 90; /* default lease time */
+ nn->nfsd4_grace = 90;
+ nn->somebody_reclaimed = false;
+ nn->track_reclaim_completes = false;
+ nn->clverifier_counter = get_random_u32();
+ nn->clientid_base = get_random_u32();
+ nn->clientid_counter = nn->clientid_base + 1;
+ nn->s2s_cp_cl_id = nn->clientid_counter++;
+
+ atomic_set(&nn->nfs4_client_count, 0);
+ si_meminfo(&si);
+ max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024);
+ max_clients *= NFS4_CLIENTS_PER_GB;
+ nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
+
+ atomic_set(&nn->nfsd_courtesy_clients, 0);
+ nn->nfsd_client_shrinker.scan_objects = nfsd_courtesy_client_scan;
+ nn->nfsd_client_shrinker.count_objects = nfsd_courtesy_client_count;
+ nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
+ return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
+}
+
+void
+nfsd4_leases_net_shutdown(struct nfsd_net *nn)
+{
+ unregister_shrinker(&nn->nfsd_client_shrinker);
+}
+
static void init_nfs4_replay(struct nfs4_replay *rp)
{
rp->rp_status = nfserr_serverfault;
@@ -4587,6 +4756,35 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
return ret;
}
+static bool nfsd4_deleg_present(const struct inode *inode)
+{
+ struct file_lock_context *ctx = smp_load_acquire(&inode->i_flctx);
+
+ return ctx && !list_empty_careful(&ctx->flc_lease);
+}
+
+/**
+ * nfsd_wait_for_delegreturn - wait for delegations to be returned
+ * @rqstp: the RPC transaction being executed
+ * @inode: in-core inode of the file being waited for
+ *
+ * The timeout prevents deadlock if all nfsd threads happen to be
+ * tied up waiting for returning delegations.
+ *
+ * Return values:
+ * %true: delegation was returned
+ * %false: timed out waiting for delegreturn
+ */
+bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode)
+{
+ long __maybe_unused timeo;
+
+ timeo = wait_var_event_timeout(inode, !nfsd4_deleg_present(inode),
+ NFSD_DELEGRETURN_TIMEOUT);
+ trace_nfsd_delegret_wakeup(rqstp, inode, timeo);
+ return timeo > 0;
+}
+
static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
{
struct nfs4_delegation *dp = cb_to_delegation(cb);
@@ -4615,6 +4813,8 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
{
struct nfs4_delegation *dp = cb_to_delegation(cb);
+ trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task);
+
if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID ||
dp->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID)
return 1;
@@ -4660,23 +4860,31 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
* We're assuming the state code never drops its reference
* without first removing the lease. Since we're in this lease
* callback (and since the lease code is serialized by the
- * i_lock) we know the server hasn't removed the lease yet, and
+ * flc_lock) we know the server hasn't removed the lease yet, and
* we know it's safe to take a reference.
*/
refcount_inc(&dp->dl_stid.sc_count);
- nfsd4_run_cb(&dp->dl_recall);
+ WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall));
}
-/* Called from break_lease() with i_lock held. */
+/* Called from break_lease() with flc_lock held. */
static bool
nfsd_break_deleg_cb(struct file_lock *fl)
{
- bool ret = false;
struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
struct nfs4_file *fp = dp->dl_stid.sc_file;
+ struct nfs4_client *clp = dp->dl_stid.sc_client;
+ struct nfsd_net *nn;
trace_nfsd_cb_recall(&dp->dl_stid);
+ dp->dl_recalled = true;
+ atomic_inc(&clp->cl_delegs_in_recall);
+ if (try_to_expire_client(clp)) {
+ nn = net_generic(clp->net, nfsd_net_id);
+ mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
+ }
+
/*
* We don't want the locks code to timeout the lease for us;
* we'll remove it ourself if a delegation isn't returned
@@ -4688,9 +4896,17 @@ nfsd_break_deleg_cb(struct file_lock *fl)
fp->fi_had_conflict = true;
nfsd_break_one_deleg(dp);
spin_unlock(&fp->fi_lock);
- return ret;
+ return false;
}
+/**
+ * nfsd_breaker_owns_lease - Check if lease conflict was resolved
+ * @fl: Lock state to check
+ *
+ * Return values:
+ * %true: Lease conflict was resolved
+ * %false: Lease conflict was not resolved.
+ */
static bool nfsd_breaker_owns_lease(struct file_lock *fl)
{
struct nfs4_delegation *dl = fl->fl_owner;
@@ -4698,11 +4914,11 @@ static bool nfsd_breaker_owns_lease(struct file_lock *fl)
struct nfs4_client *clp;
if (!i_am_nfsd())
- return NULL;
+ return false;
rqst = kthread_data(current);
/* Note rq_prog == NFS_ACL_PROGRAM is also possible: */
if (rqst->rq_prog != NFS_PROGRAM || rqst->rq_vers < 4)
- return NULL;
+ return false;
clp = *(rqst->rq_lease_breaker);
return dl->dl_stid.sc_client == clp;
}
@@ -4711,9 +4927,14 @@ static int
nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
struct list_head *dispose)
{
- if (arg & F_UNLCK)
+ struct nfs4_delegation *dp = (struct nfs4_delegation *)onlist->fl_owner;
+ struct nfs4_client *clp = dp->dl_stid.sc_client;
+
+ if (arg & F_UNLCK) {
+ if (dp->dl_recalled)
+ atomic_dec(&clp->cl_delegs_in_recall);
return lease_modify(onlist, arg, dispose);
- else
+ } else
return -EAGAIN;
}
@@ -4910,16 +5131,19 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
.ia_valid = ATTR_SIZE,
.ia_size = 0,
};
+ struct nfsd_attrs attrs = {
+ .na_iattr = &iattr,
+ };
if (!open->op_truncate)
return 0;
if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
return nfserr_inval;
- return nfsd_setattr(rqstp, fh, &iattr, 0, (time64_t)0);
+ return nfsd_setattr(rqstp, fh, &attrs, 0, (time64_t)0);
}
static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp,
- struct nfsd4_open *open)
+ struct nfsd4_open *open, bool new_stp)
{
struct nfsd_file *nf = NULL;
__be32 status;
@@ -4935,6 +5159,13 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
*/
status = nfs4_file_check_deny(fp, open->op_share_deny);
if (status != nfs_ok) {
+ if (status != nfserr_share_denied) {
+ spin_unlock(&fp->fi_lock);
+ goto out;
+ }
+ if (nfs4_resolve_deny_conflicts_locked(fp, new_stp,
+ stp, open->op_share_deny, false))
+ status = nfserr_jukebox;
spin_unlock(&fp->fi_lock);
goto out;
}
@@ -4942,6 +5173,13 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
/* set access to the file */
status = nfs4_file_get_access(fp, open->op_share_access);
if (status != nfs_ok) {
+ if (status != nfserr_share_denied) {
+ spin_unlock(&fp->fi_lock);
+ goto out;
+ }
+ if (nfs4_resolve_deny_conflicts_locked(fp, new_stp,
+ stp, open->op_share_access, true))
+ status = nfserr_jukebox;
spin_unlock(&fp->fi_lock);
goto out;
}
@@ -4957,9 +5195,20 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
if (!fp->fi_fds[oflag]) {
spin_unlock(&fp->fi_lock);
- status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
- if (status)
- goto out_put_access;
+
+ if (!open->op_filp) {
+ status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
+ if (status != nfs_ok)
+ goto out_put_access;
+ } else {
+ status = nfsd_file_create(rqstp, cur_fh, access, &nf);
+ if (status != nfs_ok)
+ goto out_put_access;
+ nf->nf_file = open->op_filp;
+ open->op_filp = NULL;
+ trace_nfsd_file_create(rqstp, access, nf);
+ }
+
spin_lock(&fp->fi_lock);
if (!fp->fi_fds[oflag]) {
fp->fi_fds[oflag] = nf;
@@ -4988,21 +5237,29 @@ out_put_access:
}
static __be32
-nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open)
+nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp,
+ struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp,
+ struct nfsd4_open *open)
{
__be32 status;
unsigned char old_deny_bmap = stp->st_deny_bmap;
if (!test_access(open->op_share_access, stp))
- return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open);
+ return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open, false);
/* test and set deny mode */
spin_lock(&fp->fi_lock);
status = nfs4_file_check_deny(fp, open->op_share_deny);
if (status == nfs_ok) {
- set_deny(open->op_share_deny, stp);
- fp->fi_share_deny |=
+ if (status != nfserr_share_denied) {
+ set_deny(open->op_share_deny, stp);
+ fp->fi_share_deny |=
(open->op_share_deny & NFS4_SHARE_DENY_BOTH);
+ } else {
+ if (nfs4_resolve_deny_conflicts_locked(fp, false,
+ stp, open->op_share_deny, false))
+ status = nfserr_jukebox;
+ }
}
spin_unlock(&fp->fi_lock);
@@ -5105,11 +5362,42 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
return 0;
}
+/*
+ * It's possible that between opening the dentry and setting the delegation,
+ * that it has been renamed or unlinked. Redo the lookup to verify that this
+ * hasn't happened.
+ */
+static int
+nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp,
+ struct svc_fh *parent)
+{
+ struct svc_export *exp;
+ struct dentry *child;
+ __be32 err;
+
+ err = nfsd_lookup_dentry(open->op_rqstp, parent,
+ open->op_fname, open->op_fnamelen,
+ &exp, &child);
+
+ if (err)
+ return -EAGAIN;
+
+ exp_put(exp);
+ dput(child);
+ if (child != file_dentry(fp->fi_deleg_file->nf_file))
+ return -EAGAIN;
+
+ return 0;
+}
+
static struct nfs4_delegation *
-nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
- struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
+nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
+ struct svc_fh *parent)
{
int status = 0;
+ struct nfs4_client *clp = stp->st_stid.sc_client;
+ struct nfs4_file *fp = stp->st_stid.sc_file;
+ struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate;
struct nfs4_delegation *dp;
struct nfsd_file *nf;
struct file_lock *fl;
@@ -5151,7 +5439,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
return ERR_PTR(status);
status = -ENOMEM;
- dp = alloc_init_deleg(clp, fp, fh, odstate);
+ dp = alloc_init_deleg(clp, fp, odstate);
if (!dp)
goto out_delegees;
@@ -5164,6 +5452,13 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
locks_free_lock(fl);
if (status)
goto out_clnt_odstate;
+
+ if (parent) {
+ status = nfsd4_verify_deleg_dentry(open, fp, parent);
+ if (status)
+ goto out_unlock;
+ }
+
status = nfsd4_check_conflicting_opens(clp, fp);
if (status)
goto out_unlock;
@@ -5219,12 +5514,13 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
* proper support for them.
*/
static void
-nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
- struct nfs4_ol_stateid *stp)
+nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
+ struct svc_fh *currentfh)
{
struct nfs4_delegation *dp;
struct nfs4_openowner *oo = openowner(stp->st_stateowner);
struct nfs4_client *clp = stp->st_stid.sc_client;
+ struct svc_fh *parent = NULL;
int cb_up;
int status = 0;
@@ -5238,6 +5534,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
goto out_no_deleg;
break;
case NFS4_OPEN_CLAIM_NULL:
+ parent = currentfh;
+ fallthrough;
case NFS4_OPEN_CLAIM_FH:
/*
* Let's not give out any delegations till everyone's
@@ -5252,7 +5550,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
default:
goto out_no_deleg;
}
- dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file, stp->st_clnt_odstate);
+ dp = nfs4_set_delegation(open, stp, parent);
if (IS_ERR(dp))
goto out_no_deleg;
@@ -5294,6 +5592,18 @@ static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open,
*/
}
+/**
+ * nfsd4_process_open2 - finish open processing
+ * @rqstp: the RPC transaction being executed
+ * @current_fh: NFSv4 COMPOUND's current filehandle
+ * @open: OPEN arguments
+ *
+ * If successful, (1) truncate the file if open->op_truncate was
+ * set, (2) set open->op_stateid, (3) set open->op_delegation.
+ *
+ * Returns %nfs_ok on success; otherwise an nfs4stat value in
+ * network byte order is returned.
+ */
__be32
nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
@@ -5343,7 +5653,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
goto out;
}
} else {
- status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
+ status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open, true);
if (status) {
stp->st_stid.sc_type = NFS4_CLOSED_STID;
release_open_stateid(stp);
@@ -5372,7 +5682,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
* Attempt to hand out a delegation. No error return, because the
* OPEN succeeds even if we fail.
*/
- nfs4_open_delegation(current_fh, open, stp);
+ nfs4_open_delegation(open, stp, &resp->cstate.current_fh);
nodeleg:
status = nfs_ok;
trace_nfsd_open(&stp->st_stid.sc_stateid);
@@ -5577,10 +5887,131 @@ 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;
+
+ if (atomic_read(&clp->cl_delegs_in_recall))
+ return true;
+ 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)
+{
+ unsigned int maxreap, reapcnt = 0;
+ struct list_head *pos, *next;
+ struct nfs4_client *clp;
+
+ maxreap = (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) ?
+ NFSD_CLIENT_MAX_TRIM_PER_RUN : 0;
+ INIT_LIST_HEAD(reaplist);
+ spin_lock(&nn->client_lock);
+ list_for_each_safe(pos, next, &nn->client_lru) {
+ clp = list_entry(pos, struct nfs4_client, cl_lru);
+ if (clp->cl_state == NFSD4_EXPIRABLE)
+ goto exp_client;
+ if (!state_expired(lt, clp->cl_time))
+ break;
+ if (!atomic_read(&clp->cl_rpc_users)) {
+ if (clp->cl_state == NFSD4_ACTIVE)
+ atomic_inc(&nn->nfsd_courtesy_clients);
+ clp->cl_state = NFSD4_COURTESY;
+ }
+ if (!client_has_state(clp))
+ goto exp_client;
+ if (!nfs4_anylock_blockers(clp))
+ if (reapcnt >= maxreap)
+ continue;
+exp_client:
+ if (!mark_client_expired_locked(clp)) {
+ list_add(&clp->cl_lru, reaplist);
+ reapcnt++;
+ }
+ }
+ spin_unlock(&nn->client_lock);
+}
+
+static void
+nfs4_get_courtesy_client_reaplist(struct nfsd_net *nn,
+ struct list_head *reaplist)
+{
+ unsigned int maxreap = 0, reapcnt = 0;
+ struct list_head *pos, *next;
+ struct nfs4_client *clp;
+
+ maxreap = NFSD_CLIENT_MAX_TRIM_PER_RUN;
+ INIT_LIST_HEAD(reaplist);
+
+ spin_lock(&nn->client_lock);
+ list_for_each_safe(pos, next, &nn->client_lru) {
+ clp = list_entry(pos, struct nfs4_client, cl_lru);
+ if (clp->cl_state == NFSD4_ACTIVE)
+ break;
+ if (reapcnt >= maxreap)
+ break;
+ if (!mark_client_expired_locked(clp)) {
+ list_add(&clp->cl_lru, reaplist);
+ reapcnt++;
+ }
+ }
+ spin_unlock(&nn->client_lock);
+}
+
+static void
+nfs4_process_client_reaplist(struct list_head *reaplist)
+{
+ struct list_head *pos, *next;
+ struct nfs4_client *clp;
+
+ list_for_each_safe(pos, next, reaplist) {
+ clp = list_entry(pos, struct nfs4_client, cl_lru);
+ trace_nfsd_clid_purged(&clp->cl_clientid);
+ list_del_init(&clp->cl_lru);
+ expire_client(clp);
+ }
+}
+
static time64_t
nfs4_laundromat(struct nfsd_net *nn)
{
- struct nfs4_client *clp;
struct nfs4_openowner *oo;
struct nfs4_delegation *dp;
struct nfs4_ol_stateid *stp;
@@ -5599,33 +6030,18 @@ nfs4_laundromat(struct nfsd_net *nn)
goto out;
}
nfsd4_end_grace(nn);
- INIT_LIST_HEAD(&reaplist);
spin_lock(&nn->s2s_cp_lock);
idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
- if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
+ if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID &&
state_expired(&lt, cps->cpntf_time))
_free_cpntf_state_locked(nn, cps);
}
spin_unlock(&nn->s2s_cp_lock);
+ nfs4_get_client_reaplist(nn, &reaplist, &lt);
+ nfs4_process_client_reaplist(&reaplist);
- 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))
- continue;
- list_add(&clp->cl_lru, &reaplist);
- }
- spin_unlock(&nn->client_lock);
- list_for_each_safe(pos, next, &reaplist) {
- clp = list_entry(pos, struct nfs4_client, cl_lru);
- trace_nfsd_clid_purged(&clp->cl_clientid);
- list_del_init(&clp->cl_lru);
- expire_client(clp);
- }
spin_lock(&state_lock);
list_for_each_safe(pos, next, &nn->del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
@@ -5694,7 +6110,6 @@ out:
return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
}
-static struct workqueue_struct *laundry_wq;
static void laundromat_main(struct work_struct *);
static void
@@ -5709,6 +6124,18 @@ laundromat_main(struct work_struct *laundry)
queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
}
+static void
+courtesy_client_reaper(struct work_struct *reaper)
+{
+ struct list_head reaplist;
+ struct delayed_work *dwork = to_delayed_work(reaper);
+ struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+ nfsd_shrinker_work);
+
+ nfs4_get_courtesy_client_reaplist(nn, &reaplist);
+ nfs4_process_client_reaplist(&reaplist);
+}
+
static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
{
if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
@@ -5844,6 +6271,7 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
struct nfs4_stid **s, struct nfsd_net *nn)
{
__be32 status;
+ struct nfs4_stid *stid;
bool return_revoked = false;
/*
@@ -5866,15 +6294,16 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
}
if (status)
return status;
- *s = find_stateid_by_type(cstate->clp, stateid, typemask);
- if (!*s)
+ stid = find_stateid_by_type(cstate->clp, stateid, typemask);
+ if (!stid)
return nfserr_bad_stateid;
- if (((*s)->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
- nfs4_put_stid(*s);
+ if ((stid->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
+ nfs4_put_stid(stid);
if (cstate->minorversion)
return nfserr_deleg_revoked;
return nfserr_bad_stateid;
}
+ *s = stid;
return nfs_ok;
}
@@ -5939,12 +6368,12 @@ out:
static void
_free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
{
- WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID);
- if (!refcount_dec_and_test(&cps->cp_stateid.sc_count))
+ WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID);
+ if (!refcount_dec_and_test(&cps->cp_stateid.cs_count))
return;
list_del(&cps->cp_list);
idr_remove(&nn->s2s_cp_stateids,
- cps->cp_stateid.stid.si_opaque.so_id);
+ cps->cp_stateid.cs_stid.si_opaque.so_id);
kfree(cps);
}
/*
@@ -5966,12 +6395,12 @@ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
if (cps_t) {
state = container_of(cps_t, struct nfs4_cpntf_state,
cp_stateid);
- if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID) {
+ if (state->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID) {
state = NULL;
goto unlock;
}
if (!clp)
- refcount_inc(&state->cp_stateid.sc_count);
+ refcount_inc(&state->cp_stateid.cs_count);
else
_free_cpntf_state_locked(nn, state);
}
@@ -6040,7 +6469,11 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
*nfp = NULL;
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) {
- status = check_special_stateids(net, fhp, stateid, flags);
+ if (cstid)
+ status = nfserr_bad_stateid;
+ else
+ status = check_special_stateids(net, fhp, stateid,
+ flags);
goto done;
}
@@ -6375,6 +6808,7 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
struct nfs4_client *clp = s->st_stid.sc_client;
bool unhashed;
LIST_HEAD(reaplist);
+ struct nfs4_ol_stateid *stp;
spin_lock(&clp->cl_lock);
unhashed = unhash_open_stateid(s, &reaplist);
@@ -6383,6 +6817,8 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
if (unhashed)
put_ol_stateid_locked(s, &reaplist);
spin_unlock(&clp->cl_lock);
+ list_for_each_entry(stp, &reaplist, st_locks)
+ nfs4_free_cpntf_statelist(clp->net, &stp->st_stid);
free_ol_stateid_reaplist(&reaplist);
} else {
spin_unlock(&clp->cl_lock);
@@ -6466,6 +6902,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto put_stateid;
+ wake_up_var(d_inode(cstate->current_fh.fh_dentry));
destroy_delegation(dp);
put_stateid:
nfs4_put_stid(&dp->dl_stid);
@@ -6502,7 +6939,7 @@ nfs4_transform_lock_offset(struct file_lock *lock)
}
static fl_owner_t
-nfsd4_fl_get_owner(fl_owner_t owner)
+nfsd4_lm_get_owner(fl_owner_t owner)
{
struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner;
@@ -6511,7 +6948,7 @@ nfsd4_fl_get_owner(fl_owner_t owner)
}
static void
-nfsd4_fl_put_owner(fl_owner_t owner)
+nfsd4_lm_put_owner(fl_owner_t owner)
{
struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner;
@@ -6519,6 +6956,29 @@ nfsd4_fl_put_owner(fl_owner_t owner)
nfs4_put_stateowner(&lo->lo_owner);
}
+/* return pointer to struct nfs4_client if client is expirable */
+static bool
+nfsd4_lm_lock_expirable(struct file_lock *cfl)
+{
+ struct nfs4_lockowner *lo = (struct nfs4_lockowner *)cfl->fl_owner;
+ struct nfs4_client *clp = lo->lo_owner.so_client;
+ struct nfsd_net *nn;
+
+ if (try_to_expire_client(clp)) {
+ nn = net_generic(clp->net, nfsd_net_id);
+ mod_delayed_work(laundry_wq, &nn->laundromat_work, 0);
+ return true;
+ }
+ return false;
+}
+
+/* schedule laundromat to run immediately and wait for it to complete */
+static void
+nfsd4_lm_expire_lock(void)
+{
+ flush_workqueue(laundry_wq);
+}
+
static void
nfsd4_lm_notify(struct file_lock *fl)
{
@@ -6545,9 +7005,12 @@ nfsd4_lm_notify(struct file_lock *fl)
}
static const struct lock_manager_operations nfsd_posix_mng_ops = {
+ .lm_mod_owner = THIS_MODULE,
.lm_notify = nfsd4_lm_notify,
- .lm_get_owner = nfsd4_fl_get_owner,
- .lm_put_owner = nfsd4_fl_put_owner,
+ .lm_get_owner = nfsd4_lm_get_owner,
+ .lm_put_owner = nfsd4_lm_put_owner,
+ .lm_lock_expirable = nfsd4_lm_lock_expirable,
+ .lm_expire_lock = nfsd4_lm_expire_lock,
};
static inline void
@@ -6836,7 +7299,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_blocked_lock *nbl = NULL;
struct file_lock *file_lock = NULL;
struct file_lock *conflock = NULL;
- struct super_block *sb;
__be32 status = 0;
int lkflg;
int err;
@@ -6858,7 +7320,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
dprintk("NFSD: nfsd4_lock: permission denied!\n");
return status;
}
- sb = cstate->current_fh.fh_dentry->d_sb;
if (lock->lk_is_new) {
if (nfsd4_has_session(cstate))
@@ -6910,8 +7371,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
fp = lock_stp->st_stid.sc_file;
switch (lock->lk_type) {
case NFS4_READW_LT:
- if (nfsd4_has_session(cstate) &&
- !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS))
+ if (nfsd4_has_session(cstate))
fl_flags |= FL_SLEEP;
fallthrough;
case NFS4_READ_LT:
@@ -6923,8 +7383,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
fl_type = F_RDLCK;
break;
case NFS4_WRITEW_LT:
- if (nfsd4_has_session(cstate) &&
- !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS))
+ if (nfsd4_has_session(cstate))
fl_flags |= FL_SLEEP;
fallthrough;
case NFS4_WRITE_LT:
@@ -6945,6 +7404,16 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
}
+ /*
+ * Most filesystems with their own ->lock operations will block
+ * the nfsd thread waiting to acquire the lock. That leads to
+ * deadlocks (we don't want every nfsd thread tied up waiting
+ * for file locks), so don't attempt blocking lock notifications
+ * on those filesystems:
+ */
+ if (nf->nf_file->f_op->lock)
+ fl_flags &= ~FL_SLEEP;
+
nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn);
if (!nbl) {
dprintk("NFSD: %s: unable to allocate block!\n", __func__);
@@ -6975,6 +7444,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
spin_lock(&nn->blocked_locks_lock);
list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru);
+ kref_get(&nbl->nbl_kref);
spin_unlock(&nn->blocked_locks_lock);
}
@@ -6987,6 +7457,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nn->somebody_reclaimed = true;
break;
case FILE_LOCK_DEFERRED:
+ kref_put(&nbl->nbl_kref, free_nbl);
nbl = NULL;
fallthrough;
case -EAGAIN: /* conflock holds conflicting lock */
@@ -7007,8 +7478,13 @@ out:
/* dequeue it if we queued it before */
if (fl_flags & FL_SLEEP) {
spin_lock(&nn->blocked_locks_lock);
- list_del_init(&nbl->nbl_list);
- list_del_init(&nbl->nbl_lru);
+ if (!list_empty(&nbl->nbl_list) &&
+ !list_empty(&nbl->nbl_lru)) {
+ list_del_init(&nbl->nbl_list);
+ list_del_init(&nbl->nbl_lru);
+ kref_put(&nbl->nbl_kref, free_nbl);
+ }
+ /* nbl can use one of lists to be linked to reaplist */
spin_unlock(&nn->blocked_locks_lock);
}
free_blocked_lock(nbl);
@@ -7049,21 +7525,22 @@ out:
static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock)
{
struct nfsd_file *nf;
+ struct inode *inode;
__be32 err;
err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf);
if (err)
return err;
- fh_lock(fhp); /* to block new leases till after test_lock: */
- err = nfserrno(nfsd_open_break_lease(fhp->fh_dentry->d_inode,
- NFSD_MAY_READ));
+ inode = fhp->fh_dentry->d_inode;
+ inode_lock(inode); /* to block new leases till after test_lock: */
+ err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
if (err)
goto out;
lock->fl_file = nf->nf_file;
err = nfserrno(vfs_test_lock(nf->nf_file, lock));
lock->fl_file = NULL;
out:
- fh_unlock(fhp);
+ inode_unlock(inode);
nfsd_file_put(nf);
return err;
}
@@ -7252,22 +7729,36 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
return status;
}
+/**
+ * nfsd4_release_lockowner - process NFSv4.0 RELEASE_LOCKOWNER operations
+ * @rqstp: RPC transaction
+ * @cstate: NFSv4 COMPOUND state
+ * @u: RELEASE_LOCKOWNER arguments
+ *
+ * The lockowner's so_count is bumped when a lock record is added
+ * or when copying a conflicting lock. The latter case is brief,
+ * but can lead to fleeting false positives when looking for
+ * locks-in-use.
+ *
+ * Return values:
+ * %nfs_ok: lockowner released or not found
+ * %nfserr_locks_held: lockowner still in use
+ * %nfserr_stale_clientid: clientid no longer active
+ * %nfserr_expired: clientid not recognized
+ */
__be32
nfsd4_release_lockowner(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
union nfsd4_op_u *u)
{
struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
clientid_t *clid = &rlockowner->rl_clientid;
- struct nfs4_stateowner *sop;
- struct nfs4_lockowner *lo = NULL;
struct nfs4_ol_stateid *stp;
- struct xdr_netobj *owner = &rlockowner->rl_owner;
- unsigned int hashval = ownerstr_hashval(owner);
- __be32 status;
- struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct nfs4_lockowner *lo;
struct nfs4_client *clp;
- LIST_HEAD (reaplist);
+ LIST_HEAD(reaplist);
+ __be32 status;
dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
clid->cl_boot, clid->cl_id);
@@ -7275,34 +7766,19 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
status = set_client(clid, cstate, nn);
if (status)
return status;
-
clp = cstate->clp;
- /* Find the matching lock stateowner */
- spin_lock(&clp->cl_lock);
- list_for_each_entry(sop, &clp->cl_ownerstr_hashtbl[hashval],
- so_strhash) {
- if (sop->so_is_open_owner || !same_owner_str(sop, owner))
- continue;
-
- /* see if there are still any locks associated with it */
- lo = lockowner(sop);
- list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) {
- if (check_for_locks(stp->st_stid.sc_file, lo)) {
- status = nfserr_locks_held;
- spin_unlock(&clp->cl_lock);
- return status;
- }
- }
-
- nfs4_get_stateowner(sop);
- break;
- }
+ spin_lock(&clp->cl_lock);
+ lo = find_lockowner_str_locked(clp, &rlockowner->rl_owner);
if (!lo) {
spin_unlock(&clp->cl_lock);
- return status;
+ return nfs_ok;
+ }
+ if (atomic_read(&lo->lo_owner.so_count) != 2) {
+ spin_unlock(&clp->cl_lock);
+ nfs4_put_stateowner(&lo->lo_owner);
+ return nfserr_locks_held;
}
-
unhash_lockowner_locked(lo);
while (!list_empty(&lo->lo_owner.so_stateids)) {
stp = list_first_entry(&lo->lo_owner.so_stateids,
@@ -7312,11 +7788,11 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
put_ol_stateid_locked(stp, &reaplist);
}
spin_unlock(&clp->cl_lock);
+
free_ol_stateid_reaplist(&reaplist);
remove_blocked_locks(lo);
nfs4_put_stateowner(&lo->lo_owner);
-
- return status;
+ return nfs_ok;
}
static inline struct nfs4_client_reclaim *
@@ -7482,6 +7958,7 @@ static int nfs4_state_create_net(struct net *net)
INIT_LIST_HEAD(&nn->blocked_locks_lru);
INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
+ INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, courtesy_client_reaper);
get_net(net);
return 0;
@@ -7557,22 +8034,12 @@ nfs4_state_start(void)
{
int ret;
- laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4");
- if (laundry_wq == NULL) {
- ret = -ENOMEM;
- goto out;
- }
ret = nfsd4_create_callback_queue();
if (ret)
- goto out_free_laundry;
+ return ret;
set_max_delegations();
return 0;
-
-out_free_laundry:
- destroy_workqueue(laundry_wq);
-out:
- return ret;
}
void
@@ -7609,7 +8076,6 @@ nfs4_state_shutdown_net(struct net *net)
void
nfs4_state_shutdown(void)
{
- destroy_workqueue(laundry_wq);
nfsd4_destroy_callback_queue();
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.