NAS-132233 / 24.10.1 / Cherry-pick NFS-related fixes

fs/nfs/callback_xdr.c

@@ -372,6 +372,8 @@ static __be32 decode_rc_list(struct xdr_stream *xdr,
 
 	rc_list->rcl_nrefcalls = ntohl(*p++);
 	if (rc_list->rcl_nrefcalls) {
+		if (unlikely(rc_list->rcl_nrefcalls > xdr->buf->len))
+			goto out;
 		p = xdr_inline_decode(xdr,
 			     rc_list->rcl_nrefcalls * 2 * sizeof(uint32_t));
 		if (unlikely(p == NULL))

fs/nfs/client.c

@@ -987,6 +987,7 @@ struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->layouts);
 	INIT_LIST_HEAD(&server->state_owners_lru);
 	INIT_LIST_HEAD(&server->ss_copies);
+	INIT_LIST_HEAD(&server->ss_src_copies);
 
 	atomic_set(&server->active, 0);
 

fs/nfs/delegation.c

@@ -627,6 +627,9 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
 				prev = delegation;
 			continue;
 		}
+		inode = nfs_delegation_grab_inode(delegation);
+		if (inode == NULL)
+			continue;
 
 		if (prev) {
 			struct inode *tmp = nfs_delegation_grab_inode(prev);
@@ -637,12 +640,6 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
 			}
 		}
 
-		inode = nfs_delegation_grab_inode(delegation);
-		if (inode == NULL) {
-			rcu_read_unlock();
-			iput(to_put);
-			goto restart;
-		}
 		delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 		rcu_read_unlock();
 
@@ -1164,7 +1161,6 @@ static int nfs_server_reap_unclaimed_delegations(struct nfs_server *server,
 	struct inode *inode;
 restart:
 	rcu_read_lock();
-restart_locked:
 	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
 		if (test_bit(NFS_DELEGATION_INODE_FREEING,
 					&delegation->flags) ||
@@ -1175,7 +1171,7 @@ static int nfs_server_reap_unclaimed_delegations(struct nfs_server *server,
 			continue;
 		inode = nfs_delegation_grab_inode(delegation);
 		if (inode == NULL)
-			goto restart_locked;
+			continue;
 		delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 		rcu_read_unlock();
 		if (delegation != NULL) {
@@ -1296,7 +1292,6 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
 	nfs4_stateid stateid;
 restart:
 	rcu_read_lock();
-restart_locked:
 	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
 		if (test_bit(NFS_DELEGATION_INODE_FREEING,
 					&delegation->flags) ||
@@ -1307,7 +1302,7 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
 			continue;
 		inode = nfs_delegation_grab_inode(delegation);
 		if (inode == NULL)
-			goto restart_locked;
+			continue;
 		spin_lock(&delegation->lock);
 		cred = get_cred_rcu(delegation->cred);
 		nfs4_stateid_copy(&stateid, &delegation->stateid);

fs/nfs/nfs42proc.c

@@ -218,7 +218,7 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 
 	if (dst_server != src_server) {
 		spin_lock(&src_server->nfs_client->cl_lock);
-		list_add_tail(&copy->src_copies, &src_server->ss_copies);
+		list_add_tail(&copy->src_copies, &src_server->ss_src_copies);
 		spin_unlock(&src_server->nfs_client->cl_lock);
 	}
 

fs/nfs/nfs4state.c

@@ -1597,7 +1597,7 @@ static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state
 			complete(&copy->completion);
 		}
 	}
-	list_for_each_entry(copy, &sp->so_server->ss_copies, src_copies) {
+	list_for_each_entry(copy, &sp->so_server->ss_src_copies, src_copies) {
 		if ((test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags) &&
 				!nfs4_stateid_match_other(&state->stateid,
 				&copy->parent_src_state->stateid)))
@@ -1957,6 +1957,7 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
 				set_bit(ops->owner_flag_bit, &sp->so_flags);
 				nfs4_put_state_owner(sp);
 				status = nfs4_recovery_handle_error(clp, status);
+				nfs4_free_state_owners(&freeme);
 				return (status != 0) ? status : -EAGAIN;
 			}
 

fs/nfs/super.c

@@ -47,6 +47,7 @@
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 #include <net/ipv6.h>
 #include <linux/netdevice.h>
@@ -223,6 +224,7 @@ static int __nfs_list_for_each_server(struct list_head *head,
 		ret = fn(server, data);
 		if (ret)
 			goto out;
+		cond_resched();
 		rcu_read_lock();
 	}
 	rcu_read_unlock();

fs/nfsd/filecache.c

@@ -1056,6 +1056,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			status = nfserr_jukebox;
 			goto construction_err;
 		}
+		nfsd_file_put(nf);
 		open_retry = false;
 		fh_put(fhp);
 		goto retry;

fs/nfsd/nfs4recover.c

@@ -806,6 +806,10 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
 			ci = &cmsg->cm_u.cm_clntinfo;
 			if (get_user(namelen, &ci->cc_name.cn_len))
 				return -EFAULT;
+			if (!namelen) {
+				dprintk("%s: namelen should not be zero", __func__);
+				return -EINVAL;
+			}
 			name.data = memdup_user(&ci->cc_name.cn_id, namelen);
 			if (IS_ERR(name.data))
 				return PTR_ERR(name.data);
@@ -828,6 +832,10 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
 			cnm = &cmsg->cm_u.cm_name;
 			if (get_user(namelen, &cnm->cn_len))
 				return -EFAULT;
+			if (!namelen) {
+				dprintk("%s: namelen should not be zero", __func__);
+				return -EINVAL;
+			}
 			name.data = memdup_user(&cnm->cn_id, namelen);
 			if (IS_ERR(name.data))
 				return PTR_ERR(name.data);

fs/nfsd/nfs4state.c

@@ -1087,7 +1087,8 @@ static void nfs4_free_deleg(struct nfs4_stid *stid)
  * When a delegation is recalled, the filehandle is stored in the "new"
  * filter.
  * Every 30 seconds we swap the filters and clear the "new" one,
- * unless both are empty of course.
+ * unless both are empty of course.  This results in delegations for a
+ * given filehandle being blocked for between 30 and 60 seconds.
  *
  * Each filter is 256 bits.  We hash the filehandle to 32bit and use the
  * low 3 bytes as hash-table indices.
@@ -1116,9 +1117,9 @@ static int delegation_blocked(struct knfsd_fh *fh)
 		if (ktime_get_seconds() - bd->swap_time > 30) {
 			bd->entries -= bd->old_entries;
 			bd->old_entries = bd->entries;
+			bd->new = 1-bd->new;
 			memset(bd->set[bd->new], 0,
 			       sizeof(bd->set[0]));
-			bd->new = 1-bd->new;
 			bd->swap_time = ktime_get_seconds();
 		}
 		spin_unlock(&blocked_delegations_lock);

fs/nfsd/nfs4xdr.c

@@ -1287,14 +1287,6 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u)
 	return nfs_ok;
 }
 
-static __be32
-nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p)
-{
-	if (argp->minorversion == 0)
-		return nfs_ok;
-	return nfserr_notsupp;
-}
-
 static __be32
 nfsd4_decode_read(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u)
 {
@@ -2387,7 +2379,7 @@ static const nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_OPEN_CONFIRM]	= nfsd4_decode_open_confirm,
 	[OP_OPEN_DOWNGRADE]	= nfsd4_decode_open_downgrade,
 	[OP_PUTFH]		= nfsd4_decode_putfh,
-	[OP_PUTPUBFH]		= nfsd4_decode_putpubfh,
+	[OP_PUTPUBFH]		= nfsd4_decode_noop,
 	[OP_PUTROOTFH]		= nfsd4_decode_noop,
 	[OP_READ]		= nfsd4_decode_read,
 	[OP_READDIR]		= nfsd4_decode_readdir,

fs/nfsd/nfssvc.c

@@ -572,7 +572,6 @@ void nfsd_last_thread(struct net *net)
 		return;
 
 	nfsd_shutdown_net(net);
-	pr_info("nfsd: last server has exited, flushing export cache\n");
 	nfsd_export_flush(net);
 }
 
@@ -787,7 +786,6 @@ int
 nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 {
 	int	error;
-	bool	nfsd_up_before;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct svc_serv *serv;
 
@@ -807,26 +805,22 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 	error = nfsd_create_serv(net);
 	if (error)
 		goto out;
-
-	nfsd_up_before = nn->nfsd_net_up;
 	serv = nn->nfsd_serv;
 
 	error = nfsd_startup_net(net, cred);
 	if (error)
 		goto out_put;
 	error = svc_set_num_threads(serv, NULL, nrservs);
 	if (error)
-		goto out_shutdown;
+		goto out_put;
 	error = serv->sv_nrthreads;
-	if (error == 0)
-		nfsd_last_thread(net);
-out_shutdown:
-	if (error < 0 && !nfsd_up_before)
-		nfsd_shutdown_net(net);
 out_put:
 	/* Threads now hold service active */
 	if (xchg(&nn->keep_active, 0))
 		svc_put(serv);
+
+	if (serv->sv_nrthreads == 0)
+		nfsd_last_thread(net);
 	svc_put(serv);
 out:
 	mutex_unlock(&nfsd_mutex);

include/linux/nfs_fs_sb.h

@@ -238,6 +238,7 @@ struct nfs_server {
 	struct list_head	layouts;
 	struct list_head	delegations;
 	struct list_head	ss_copies;
+	struct list_head	ss_src_copies;
 
 	unsigned long		mig_gen;
 	unsigned long		mig_status;

net/sunrpc/sched.c

@@ -369,8 +369,10 @@ static void rpc_make_runnable(struct workqueue_struct *wq,
 	if (RPC_IS_ASYNC(task)) {
 		INIT_WORK(&task->u.tk_work, rpc_async_schedule);
 		queue_work(wq, &task->u.tk_work);
-	} else
+	} else {
+		smp_mb__after_atomic();
 		wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED);
+	}
 }
 
 /*