Merge tag 'nfs-for-6.11-2' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client fixes from Anna Schumaker:

 - Fix rpcrdma refcounting in xa_alloc

 - Fix rpcrdma usage of XA_FLAGS_ALLOC

 - Fix requesting FATTR4_WORD2_OPEN_ARGUMENTS

 - Fix attribute bitmap decoder to handle a 3rd word

 - Add reschedule points when returning delegations to avoid soft lockups

 - Fix clearing layout segments in layoutreturn

 - Avoid unnecessary rescanning of the per-server delegation list

* tag 'nfs-for-6.11-2' of git://git.linux-nfs.org/projects/anna/linux-nfs:
  NFS: Avoid unnecessary rescanning of the per-server delegation list
  NFSv4: Fix clearing of layout segments in layoutreturn
  NFSv4: Add missing rescheduling points in nfs_client_return_marked_delegations
  nfs: fix bitmap decoder to handle a 3rd word
  nfs: fix the fetch of FATTR4_OPEN_ARGUMENTS
  rpcrdma: Trace connection registration and unregistration
  rpcrdma: Use XA_FLAGS_ALLOC instead of XA_FLAGS_ALLOC1
  rpcrdma: Device kref is over-incremented on error from xa_alloc

fs/nfs/callback_xdr.c

@@ -118,7 +118,9 @@ static __be32 decode_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
 	if (likely(attrlen > 0))
 		bitmap[0] = ntohl(*p++);
 	if (attrlen > 1)
-		bitmap[1] = ntohl(*p);
+		bitmap[1] = ntohl(*p++);
+	if (attrlen > 2)
+		bitmap[2] = ntohl(*p);
 	return 0;
 }
 
@@ -446,7 +448,7 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp,
 				      void *argp)
 {
 	struct cb_recallanyargs *args = argp;
-	uint32_t bitmap[2];
+	uint32_t bitmap[3];
 	__be32 *p, status;
 
 	p = xdr_inline_decode(xdr, 4);

fs/nfs/delegation.c

@@ -647,6 +647,9 @@ 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);
@@ -657,12 +660,6 @@ 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();
 
@@ -1184,7 +1181,6 @@ 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) ||
@@ -1195,7 +1191,7 @@ 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) {
@@ -1318,7 +1314,6 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
 
 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) ||
@@ -1330,7 +1325,7 @@ 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/nfs4proc.c

@@ -3931,7 +3931,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 		     FATTR4_WORD0_CASE_INSENSITIVE |
 		     FATTR4_WORD0_CASE_PRESERVING;
 	if (minorversion)
-		bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT;
+		bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT |
+			     FATTR4_WORD2_OPEN_ARGUMENTS;
 
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
 	if (status == 0) {
@@ -9997,6 +9998,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		fallthrough;
 	default:
 		task->tk_status = 0;
+		lrp->res.lrs_present = 0;
 		fallthrough;
 	case 0:
 		break;
@@ -10010,9 +10012,11 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		task->tk_status = 0;
 		break;
 	case -NFS4ERR_DELAY:
-		if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
-			break;
+		if (nfs4_async_handle_error(task, server, NULL, NULL) ==
+		    -EAGAIN)
 			goto out_restart;
+		lrp->res.lrs_present = 0;
+		break;
 	}
 	return;
 out_restart:

fs/nfs/pnfs.c

@@ -1284,10 +1284,9 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
 	LIST_HEAD(freeme);
 
 	spin_lock(&inode->i_lock);
-	if (!pnfs_layout_is_valid(lo) ||
-	    !nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
+	if (!nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
 		goto out_unlock;
-	if (stateid) {
+	if (stateid && pnfs_layout_is_valid(lo)) {
 		u32 seq = be32_to_cpu(arg_stateid->seqid);
 
 		pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq);

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>
@@ -228,6 +229,7 @@ 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();

include/trace/events/rpcrdma.h

@@ -2277,6 +2277,42 @@ DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one);
 DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_wait_on);
 DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one_done);
 
+DECLARE_EVENT_CLASS(rpcrdma_client_register_class,
+	TP_PROTO(
+		const struct ib_device *device,
+		const struct rpcrdma_notification *rn
+	),
+
+	TP_ARGS(device, rn),
+
+	TP_STRUCT__entry(
+		__string(name, device->name)
+		__field(void *, callback)
+		__field(u32, index)
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		__entry->callback = rn->rn_done;
+		__entry->index = rn->rn_index;
+	),
+
+	TP_printk("device=%s index=%u done callback=%pS\n",
+		__get_str(name), __entry->index, __entry->callback
+	)
+);
+
+#define DEFINE_CLIENT_REGISTER_EVENT(name)				\
+	DEFINE_EVENT(rpcrdma_client_register_class, name,		\
+	TP_PROTO(							\
+		const struct ib_device *device,				\
+		const struct rpcrdma_notification *rn			\
+	),								\
+	TP_ARGS(device, rn))
+
+DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_register);
+DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_unregister);
+
 #endif /* _TRACE_RPCRDMA_H */
 
 #include <trace/define_trace.h>

net/sunrpc/xprtrdma/ib_client.c

@@ -62,10 +62,11 @@ int rpcrdma_rn_register(struct ib_device *device,
 	if (!rd || test_bit(RPCRDMA_RD_F_REMOVING, &rd->rd_flags))
 		return -ENETUNREACH;
 
-	kref_get(&rd->rd_kref);
 	if (xa_alloc(&rd->rd_xa, &rn->rn_index, rn, xa_limit_32b, GFP_KERNEL) < 0)
 		return -ENOMEM;
+	kref_get(&rd->rd_kref);
 	rn->rn_done = done;
+	trace_rpcrdma_client_register(device, rn);
 	return 0;
 }
 
@@ -91,6 +92,7 @@ void rpcrdma_rn_unregister(struct ib_device *device,
 	if (!rd)
 		return;
 
+	trace_rpcrdma_client_unregister(device, rn);
 	xa_erase(&rd->rd_xa, rn->rn_index);
 	kref_put(&rd->rd_kref, rpcrdma_rn_release);
 }
@@ -111,7 +113,7 @@ static int rpcrdma_add_one(struct ib_device *device)
 		return -ENOMEM;
 
 	kref_init(&rd->rd_kref);
-	xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC1);
+	xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC);
 	rd->rd_device = device;
 	init_completion(&rd->rd_done);
 	ib_set_client_data(device, &rpcrdma_ib_client, rd);