Merge branch 'linux-next' of git://git.linux-nfs.org/projects/anna/linux-nfs.git

26 files changed, 181 insertions, 123 deletions

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 943aeea1eb160f..6be13e0ec170d1 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -580,6 +580,8 @@ retry:
 		nfs4_delete_deviceid(node->ld, node->nfs_client, id);
 		goto retry;
 	}
+
+	nfs4_put_deviceid_node(node);
 	return ERR_PTR(-ENODEV);
 }
 
@@ -893,10 +895,9 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 	}
 
 	if (pgio->pg_dreq == NULL)
-		wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
-					      req->wb_index);
+		wb_size = pnfs_num_cont_bytes(pgio->pg_inode, req->wb_index);
 	else
-		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq, req_offset(req));
 
 	pnfs_generic_pg_init_write(pgio, req, wb_size);
 
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index f318a05a80e17a..c97ebc42ec0fee 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -351,6 +351,9 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 	d->map = bl_map_simple;
 	d->pr_key = v->scsi.pr_key;
 
+	if (d->len == 0)
+		return -ENODEV;
+
 	pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
 		d->bdev_handle->bdev->bd_disk->disk_name, d->pr_key);
 
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index 6c977288cc2881..d8d50a88de04f2 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -75,7 +75,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 	msg->len = sizeof(*bl_msg) + b->simple.len;
 	msg->data = kzalloc(msg->len, gfp_mask);
 	if (!msg->data)
-		goto out_free_data;
+		goto out_unlock;
 
 	bl_msg = msg->data;
 	bl_msg->type = BL_DEVICE_MOUNT;
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index ccd4f245cae240..cc1b6620a0c22f 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -40,11 +40,12 @@ enum nfs4_callback_opnum {
 
 struct nfs4_slot;
 struct cb_process_state {
-	__be32			drc_status;
 	struct nfs_client	*clp;
 	struct nfs4_slot	*slot;
-	u32			minorversion;
 	struct net		*net;
+	u32			minorversion;
+	__be32			drc_status;
+	unsigned int		referring_calls;
 };
 
 struct cb_compound_hdr_arg {
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 96a4923080ae28..76cea34477ae6f 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -207,7 +207,8 @@ static struct inode *nfs_layout_find_inode(struct nfs_client *clp,
  * Enforce RFC5661 section 12.5.5.2.1. (Layout Recall and Return Sequencing)
  */
 static u32 pnfs_check_callback_stateid(struct pnfs_layout_hdr *lo,
-					const nfs4_stateid *new)
+					const nfs4_stateid *new,
+					struct cb_process_state *cps)
 {
 	u32 oldseq, newseq;
 
@@ -221,28 +222,29 @@ static u32 pnfs_check_callback_stateid(struct pnfs_layout_hdr *lo,
 
 	newseq = be32_to_cpu(new->seqid);
 	/* Are we already in a layout recall situation? */
-	if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) &&
-	    lo->plh_return_seq != 0) {
-		if (newseq < lo->plh_return_seq)
-			return NFS4ERR_OLD_STATEID;
-		if (newseq > lo->plh_return_seq)
-			return NFS4ERR_DELAY;
-		goto out;
-	}
+	if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return NFS4ERR_DELAY;
 
-	/* Check that the stateid matches what we think it should be. */
+	/*
+	 * Check that the stateid matches what we think it should be.
+	 * Note that if the server sent us a list of referring calls,
+	 * and we know that those have completed, then we trust the
+	 * stateid argument is correct.
+	 */
 	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
-	if (newseq > oldseq + 1)
+	if (newseq > oldseq + 1 && !cps->referring_calls)
 		return NFS4ERR_DELAY;
+
 	/* Crazy server! */
 	if (newseq <= oldseq)
 		return NFS4ERR_OLD_STATEID;
-out:
+
 	return NFS_OK;
 }
 
 static u32 initiate_file_draining(struct nfs_client *clp,
-				  struct cb_layoutrecallargs *args)
+				  struct cb_layoutrecallargs *args,
+				  struct cb_process_state *cps)
 {
 	struct inode *ino;
 	struct pnfs_layout_hdr *lo;
@@ -266,7 +268,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 		goto out;
 	}
 	pnfs_get_layout_hdr(lo);
-	rv = pnfs_check_callback_stateid(lo, &args->cbl_stateid);
+	rv = pnfs_check_callback_stateid(lo, &args->cbl_stateid, cps);
 	if (rv != NFS_OK)
 		goto unlock;
 
@@ -326,10 +328,11 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 }
 
 static u32 do_callback_layoutrecall(struct nfs_client *clp,
-				    struct cb_layoutrecallargs *args)
+				    struct cb_layoutrecallargs *args,
+				    struct cb_process_state *cps)
 {
 	if (args->cbl_recall_type == RETURN_FILE)
-		return initiate_file_draining(clp, args);
+		return initiate_file_draining(clp, args, cps);
 	return initiate_bulk_draining(clp, args);
 }
 
@@ -340,11 +343,12 @@ __be32 nfs4_callback_layoutrecall(void *argp, void *resp,
 	u32 res = NFS4ERR_OP_NOT_IN_SESSION;
 
 	if (cps->clp)
-		res = do_callback_layoutrecall(cps->clp, args);
+		res = do_callback_layoutrecall(cps->clp, args, cps);
 	return cpu_to_be32(res);
 }
 
-static void pnfs_recall_all_layouts(struct nfs_client *clp)
+static void pnfs_recall_all_layouts(struct nfs_client *clp,
+				    struct cb_process_state *cps)
 {
 	struct cb_layoutrecallargs args;
 
@@ -352,7 +356,7 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp)
 	memset(&args, 0, sizeof(args));
 	args.cbl_recall_type = RETURN_ALL;
 	/* FIXME we ignore errors, what should we do? */
-	do_callback_layoutrecall(clp, &args);
+	do_callback_layoutrecall(clp, &args, cps);
 }
 
 __be32 nfs4_callback_devicenotify(void *argp, void *resp,
@@ -450,6 +454,7 @@ static int referring_call_exists(struct nfs_client *clp,
 	__acquires(lock)
 {
 	int status = 0;
+	int found = 0;
 	int i, j;
 	struct nfs4_session *session;
 	struct nfs4_slot_table *tbl;
@@ -478,11 +483,12 @@ static int referring_call_exists(struct nfs_client *clp,
 			spin_lock(lock);
 			if (status)
 				goto out;
+			found++;
 		}
 	}
 
 out:
-	return status;
+	return status < 0 ? status : found;
 }
 
 __be32 nfs4_callback_sequence(void *argp, void *resp,
@@ -493,6 +499,7 @@ __be32 nfs4_callback_sequence(void *argp, void *resp,
 	struct nfs4_slot_table *tbl;
 	struct nfs4_slot *slot;
 	struct nfs_client *clp;
+	int ret;
 	int i;
 	__be32 status = htonl(NFS4ERR_BADSESSION);
 
@@ -552,11 +559,13 @@ __be32 nfs4_callback_sequence(void *argp, void *resp,
 	 * related callback was received before the response to the original
 	 * call.
 	 */
-	if (referring_call_exists(clp, args->csa_nrclists, args->csa_rclists,
-				&tbl->slot_tbl_lock) < 0) {
+	ret = referring_call_exists(clp, args->csa_nrclists, args->csa_rclists,
+				    &tbl->slot_tbl_lock);
+	if (ret < 0) {
 		status = htonl(NFS4ERR_DELAY);
 		goto out_unlock;
 	}
+	cps->referring_calls = ret;
 
 	/*
 	 * RFC5661 20.9.3
@@ -617,7 +626,7 @@ __be32 nfs4_callback_recallany(void *argp, void *resp,
 		nfs_expire_unused_delegation_types(cps->clp, flags);
 
 	if (args->craa_type_mask & BIT(RCA4_TYPE_MASK_FILE_LAYOUT))
-		pnfs_recall_all_layouts(cps->clp);
+		pnfs_recall_all_layouts(cps->clp, cps);
 
 	if (args->craa_type_mask & BIT(PNFS_FF_RCA4_TYPE_MASK_READ)) {
 		set_bit(NFS4CLNT_RECALL_ANY_LAYOUT_READ, &cps->clp->cl_state);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 321af81c456e2a..9369488f2ed453 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -967,6 +967,11 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 		nops--;
 	}
 
+	if (svc_is_backchannel(rqstp) && cps.clp) {
+		rqstp->bc_to_initval = cps.clp->cl_rpcclient->cl_timeout->to_initval;
+		rqstp->bc_to_retries = cps.clp->cl_rpcclient->cl_timeout->to_retries;
+	}
+
 	*hdr_res.status = status;
 	*hdr_res.nops = htonl(nops);
 	nfs4_cb_free_slot(&cps);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 13dffe4201e6e9..c8ecbe99905960 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2194,6 +2194,8 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 {
 	struct inode *inode;
 
+	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
+
 	if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
 		goto full_reval;
 	if (d_mountpoint(dentry))
@@ -2963,7 +2965,7 @@ static u64 nfs_access_login_time(const struct task_struct *task,
 	rcu_read_lock();
 	for (;;) {
 		parent = rcu_dereference(task->real_parent);
-		pcred = rcu_dereference(parent->cred);
+		pcred = __task_cred(parent);
 		if (parent == task || cred_fscmp(pcred, cred) != 0)
 			break;
 		task = parent;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index f6c74f4246917f..c03926a1cc73bc 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -205,9 +205,10 @@ static void nfs_direct_req_release(struct nfs_direct_req *dreq)
 	kref_put(&dreq->kref, nfs_direct_req_free);
 }
 
-ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq)
+ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset)
 {
-	return dreq->bytes_left;
+	loff_t start = offset - dreq->io_start;
+	return dreq->max_count - start;
 }
 EXPORT_SYMBOL_GPL(nfs_dreq_bytes_left);
 
@@ -368,7 +369,6 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 			bytes -= req_len;
 			requested_bytes += req_len;
 			pos += req_len;
-			dreq->bytes_left -= req_len;
 		}
 		nfs_direct_release_pages(pagevec, npages);
 		kvfree(pagevec);
@@ -440,7 +440,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 		goto out;
 
 	dreq->inode = inode;
-	dreq->bytes_left = dreq->max_count = count;
+	dreq->max_count = count;
 	dreq->io_start = iocb->ki_pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
@@ -873,7 +873,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 			bytes -= req_len;
 			requested_bytes += req_len;
 			pos += req_len;
-			dreq->bytes_left -= req_len;
 
 			if (defer) {
 				nfs_mark_request_commit(req, NULL, &cinfo, 0);
@@ -980,7 +979,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
 		goto out;
 
 	dreq->inode = inode;
-	dreq->bytes_left = dreq->max_count = count;
+	dreq->max_count = count;
 	dreq->io_start = pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index e8cccb94b9277e..8577ccf621f5be 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -558,7 +558,6 @@ const struct address_space_operations nfs_file_aops = {
 	.read_folio = nfs_read_folio,
 	.readahead = nfs_readahead,
 	.dirty_folio = filemap_dirty_folio,
-	.writepage = nfs_writepage,
 	.writepages = nfs_writepages,
 	.write_begin = nfs_write_begin,
 	.write_end = nfs_write_end,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9c9cf764f6000d..e3722ce6722e24 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -655,7 +655,7 @@ extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
 /* direct.c */
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 			      struct nfs_direct_req *dreq);
-extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
+extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset);
 
 /* nfs4proc.c */
 extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
@@ -936,7 +936,6 @@ struct nfs_direct_req {
 	loff_t			io_start;	/* Start offset for I/O */
 	ssize_t			count,		/* bytes actually processed */
 				max_count,	/* max expected count */
-				bytes_left,	/* bytes left to be sent */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8a943fffaad561..23819a75650857 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -170,6 +170,7 @@ static int nfs4_map_errors(int err)
 	case -NFS4ERR_RESOURCE:
 	case -NFS4ERR_LAYOUTTRYLATER:
 	case -NFS4ERR_RECALLCONFLICT:
+	case -NFS4ERR_RETURNCONFLICT:
 		return -EREMOTEIO;
 	case -NFS4ERR_WRONGSEC:
 	case -NFS4ERR_WRONG_CRED:
@@ -558,6 +559,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_LAYOUTTRYLATER:
 		case -NFS4ERR_RECALLCONFLICT:
+		case -NFS4ERR_RETURNCONFLICT:
 			exception->delay = 1;
 			return 0;
 
@@ -9691,6 +9693,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 		status = -EBUSY;
 		break;
 	case -NFS4ERR_RECALLCONFLICT:
+	case -NFS4ERR_RETURNCONFLICT:
 		status = -ERECALLCONFLICT;
 		break;
 	case -NFS4ERR_DELEG_REVOKED:
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index deec76cf5afeaf..69406e60f391e2 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1602,7 +1602,8 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_pgio_args *args
 static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg *readdir, struct rpc_rqst *req, struct compound_hdr *hdr)
 {
 	uint32_t attrs[3] = {
-		FATTR4_WORD0_RDATTR_ERROR,
+		FATTR4_WORD0_TYPE
+		| FATTR4_WORD0_RDATTR_ERROR,
 		FATTR4_WORD1_MOUNTED_ON_FILEID,
 	};
 	uint32_t dircount = readdir->count;
@@ -1612,12 +1613,20 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
 	unsigned int i;
 
 	if (readdir->plus) {
-		attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE|
-			FATTR4_WORD0_FSID|FATTR4_WORD0_FILEHANDLE|FATTR4_WORD0_FILEID;
-		attrs[1] |= FATTR4_WORD1_MODE|FATTR4_WORD1_NUMLINKS|FATTR4_WORD1_OWNER|
-			FATTR4_WORD1_OWNER_GROUP|FATTR4_WORD1_RAWDEV|
-			FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS|
-			FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
+		attrs[0] |= FATTR4_WORD0_CHANGE
+			| FATTR4_WORD0_SIZE
+			| FATTR4_WORD0_FSID
+			| FATTR4_WORD0_FILEHANDLE
+			| FATTR4_WORD0_FILEID;
+		attrs[1] |= FATTR4_WORD1_MODE
+			| FATTR4_WORD1_NUMLINKS
+			| FATTR4_WORD1_OWNER
+			| FATTR4_WORD1_OWNER_GROUP
+			| FATTR4_WORD1_RAWDEV
+			| FATTR4_WORD1_SPACE_USED
+			| FATTR4_WORD1_TIME_ACCESS
+			| FATTR4_WORD1_TIME_METADATA
+			| FATTR4_WORD1_TIME_MODIFY;
 		attrs[2] |= FATTR4_WORD2_SECURITY_LABEL;
 	}
 	/* Use mounted_on_fileid only if the server supports it */
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 4e90ca531176d9..afedb449b54fd3 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -400,6 +400,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event,
 			__field(unsigned long, flags)
 			__field(dev_t, dev)
 			__field(u64, dir)
+			__field(u64, fileid)
 			__string(name, dentry->d_name.name)
 		),
 
@@ -407,16 +408,18 @@ DECLARE_EVENT_CLASS(nfs_lookup_event,
 			__entry->dev = dir->i_sb->s_dev;
 			__entry->dir = NFS_FILEID(dir);
 			__entry->flags = flags;
+			__entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry));
 			__assign_str(name, dentry->d_name.name);
 		),
 
 		TP_printk(
-			"flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
+			"flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu",
 			__entry->flags,
 			show_fs_lookup_flags(__entry->flags),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->dir,
-			__get_str(name)
+			__get_str(name),
+			__entry->fileid
 		)
 );
 
@@ -444,6 +447,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done,
 			__field(unsigned long, flags)
 			__field(dev_t, dev)
 			__field(u64, dir)
+			__field(u64, fileid)
 			__string(name, dentry->d_name.name)
 		),
 
@@ -452,17 +456,19 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done,
 			__entry->dir = NFS_FILEID(dir);
 			__entry->error = error < 0 ? -error : 0;
 			__entry->flags = flags;
+			__entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry));
 			__assign_str(name, dentry->d_name.name);
 		),
 
 		TP_printk(
-			"error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s",
+			"error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu",
 			-__entry->error, show_nfs_status(__entry->error),
 			__entry->flags,
 			show_fs_lookup_flags(__entry->flags),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->dir,
-			__get_str(name)
+			__get_str(name),
+			__entry->fileid
 		)
 );
 
@@ -893,7 +899,7 @@ DECLARE_EVENT_CLASS(nfs_rename_event_done,
 DEFINE_NFS_RENAME_EVENT(nfs_rename_enter);
 DEFINE_NFS_RENAME_EVENT_DONE(nfs_rename_exit);
 
-DEFINE_NFS_RENAME_EVENT_DONE(nfs_sillyrename_rename);
+DEFINE_NFS_RENAME_EVENT_DONE(nfs_async_rename_done);
 
 TRACE_EVENT(nfs_sillyrename_unlink,
 		TP_PROTO(
@@ -1539,7 +1545,6 @@ DECLARE_EVENT_CLASS(nfs_direct_req_class,
 			__field(u32, fhandle)
 			__field(loff_t, offset)
 			__field(ssize_t, count)
-			__field(ssize_t, bytes_left)
 			__field(ssize_t, error)
 			__field(int, flags)
 		),
@@ -1554,19 +1559,18 @@ DECLARE_EVENT_CLASS(nfs_direct_req_class,
 			__entry->fhandle = nfs_fhandle_hash(fh);
 			__entry->offset = dreq->io_start;
 			__entry->count = dreq->count;
-			__entry->bytes_left = dreq->bytes_left;
 			__entry->error = dreq->error;
 			__entry->flags = dreq->flags;
 		),
 
 		TP_printk(
 			"error=%zd fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld count=%zd bytes_left=%zd flags=%s",
+			"offset=%lld count=%zd flags=%s",
 			__entry->error, MAJOR(__entry->dev),
 			MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle, __entry->offset,
-			__entry->count, __entry->bytes_left,
+			__entry->count,
 			nfs_show_direct_req_flags(__entry->flags)
 		)
 );
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 21a365357629c7..0c0fed1ecd0bf0 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2733,7 +2733,8 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 		if (pgio->pg_dreq == NULL)
 			rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
 		else
-			rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+			rd_size = nfs_dreq_bytes_left(pgio->pg_dreq,
+						      req_offset(req));
 
 		pgio->pg_lseg =
 			pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req),
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 150a953a8be946..0110299643a248 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -267,7 +267,7 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
 	struct inode *new_dir = data->new_dir;
 	struct dentry *old_dentry = data->old_dentry;
 
-	trace_nfs_sillyrename_rename(old_dir, old_dentry,
+	trace_nfs_async_rename_done(old_dir, old_dentry,
 			new_dir, data->new_dentry, task->tk_status);
 	if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
 		rpc_restart_call_prepare(task);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index b664caea8b4e67..0b4fdad511d924 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -680,17 +680,6 @@ static int nfs_writepage_locked(struct folio *folio,
 	return err;
 }
 
-int nfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-	int ret;
-
-	ret = nfs_writepage_locked(folio, wbc);
-	if (ret != AOP_WRITEPAGE_ACTIVATE)
-		unlock_page(page);
-	return ret;
-}
-
 static int nfs_writepages_callback(struct folio *folio,
 				   struct writeback_control *wbc, void *data)
 {
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 279262057a9258..f5ce7b10114613 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -595,7 +595,6 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
  * linux/fs/nfs/write.c
  */
 extern int  nfs_congestion_kb;
-extern int  nfs_writepage(struct page *page, struct writeback_control *wbc);
 extern int  nfs_writepages(struct address_space *, struct writeback_control *);
 extern int  nfs_flush_incompatible(struct file *file, struct folio *folio);
 extern int  nfs_update_folio(struct file *file, struct folio *folio,
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index db30a159f9d5f5..f22bf915dcf6e6 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -20,7 +20,8 @@
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid);
 void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied);
-void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task);
+void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task,
+		const struct rpc_timeout *to);
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
 void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index e9d4377d03c6e7..5e9d1469c6faea 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -252,7 +252,6 @@ void		rpc_clnt_probe_trunked_xprts(struct rpc_clnt *,
 
 const char *rpc_proc_name(const struct rpc_task *task);
 
-void rpc_clnt_xprt_switch_put(struct rpc_clnt *);
 void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *);
 void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *, struct rpc_xprt *);
 bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt,
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 8ada7dc802d305..2d61987b354564 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -38,6 +38,17 @@ struct rpc_wait {
 };
 
 /*
+ * This describes a timeout strategy
+ */
+struct rpc_timeout {
+	unsigned long		to_initval,		/* initial timeout */
+				to_maxval,		/* max timeout */
+				to_increment;		/* if !exponential */
+	unsigned int		to_retries;		/* max # of retries */
+	unsigned char		to_exponential;
+};
+
+/*
  * This is the RPC task struct
  */
 struct rpc_task {
@@ -205,7 +216,8 @@ struct rpc_wait_queue {
  */
 struct rpc_task *rpc_new_task(const struct rpc_task_setup *);
 struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req);
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
+		struct rpc_timeout *timeout);
 void		rpc_put_task(struct rpc_task *);
 void		rpc_put_task_async(struct rpc_task *);
 bool		rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index b10f987509cc80..3331a1c2b47e64 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -250,6 +250,8 @@ struct svc_rqst {
 	struct net		*rq_bc_net;	/* pointer to backchannel's
 						 * net namespace
 						 */
+	unsigned long	bc_to_initval;
+	unsigned int	bc_to_retries;
 	void **			rq_lease_breaker; /* The v4 client breaking a lease */
 	unsigned int		rq_status_counter; /* RPC processing counter */
 };
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index f85d3a0daca26f..464f6a9492ab7e 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -30,17 +30,6 @@
 #define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
 #define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
 
-/*
- * This describes a timeout strategy
- */
-struct rpc_timeout {
-	unsigned long		to_initval,		/* initial timeout */
-				to_maxval,		/* max timeout */
-				to_increment;		/* if !exponential */
-	unsigned int		to_retries;		/* max # of retries */
-	unsigned char		to_exponential;
-};
-
 enum rpc_display_format_t {
 	RPC_DISPLAY_ADDR = 0,
 	RPC_DISPLAY_PORT,
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index daa9582ec861aa..19437b15ffc7bf 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -797,15 +797,24 @@ out_revert:
 }
 EXPORT_SYMBOL_GPL(rpc_switch_client_transport);
 
-static
-int _rpc_clnt_xprt_iter_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi,
-			     void func(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps))
+static struct rpc_xprt_switch *rpc_clnt_xprt_switch_get(struct rpc_clnt *clnt)
 {
 	struct rpc_xprt_switch *xps;
 
 	rcu_read_lock();
 	xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
 	rcu_read_unlock();
+
+	return xps;
+}
+
+static
+int _rpc_clnt_xprt_iter_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi,
+			     void func(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps))
+{
+	struct rpc_xprt_switch *xps;
+
+	xps = rpc_clnt_xprt_switch_get(clnt);
 	if (xps == NULL)
 		return -EAGAIN;
 	func(xpi, xps);
@@ -1302,8 +1311,10 @@ static void call_bc_encode(struct rpc_task *task);
  * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run
  * rpc_execute against it
  * @req: RPC request
+ * @timeout: timeout values to use for this task
  */
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req)
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
+		struct rpc_timeout *timeout)
 {
 	struct rpc_task *task;
 	struct rpc_task_setup task_setup_data = {
@@ -1322,7 +1333,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req)
 		return task;
 	}
 
-	xprt_init_bc_request(req, task);
+	xprt_init_bc_request(req, task, timeout);
 
 	task->tk_action = call_bc_encode;
 	atomic_inc(&task->tk_count);
@@ -2206,9 +2217,7 @@ call_connect_status(struct rpc_task *task)
 			struct rpc_xprt *saved = task->tk_xprt;
 			struct rpc_xprt_switch *xps;
 
-			rcu_read_lock();
-			xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
-			rcu_read_unlock();
+			xps = rpc_clnt_xprt_switch_get(clnt);
 			if (xps->xps_nxprts > 1) {
 				long value;
 
@@ -3116,7 +3125,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt,
 				  struct rpc_xprt *xprt,
 				  struct rpc_add_xprt_test *data)
 {
-	struct rpc_xprt_switch *xps;
 	struct rpc_xprt *main_xprt;
 	int status = 0;
 
@@ -3124,7 +3132,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt,
 
 	rcu_read_lock();
 	main_xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
-	xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
 	status = rpc_cmp_addr_port((struct sockaddr *)&xprt->addr,
 				   (struct sockaddr *)&main_xprt->addr);
 	rcu_read_unlock();
@@ -3135,7 +3142,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt,
 	status = rpc_clnt_add_xprt_helper(clnt, xprt, data);
 out:
 	xprt_put(xprt);
-	xprt_switch_put(xps);
 	return status;
 }
 
@@ -3250,34 +3256,27 @@ rpc_set_connect_timeout(struct rpc_clnt *clnt,
 }
 EXPORT_SYMBOL_GPL(rpc_set_connect_timeout);
 
-void rpc_clnt_xprt_switch_put(struct rpc_clnt *clnt)
-{
-	rcu_read_lock();
-	xprt_switch_put(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_put);
-
 void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
 {
 	struct rpc_xprt_switch *xps;
 
-	rcu_read_lock();
-	xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
-	rcu_read_unlock();
+	xps = rpc_clnt_xprt_switch_get(clnt);
 	xprt_set_online_locked(xprt, xps);
+	xprt_switch_put(xps);
 }
 
 void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
 {
+	struct rpc_xprt_switch *xps;
+
 	if (rpc_clnt_xprt_switch_has_addr(clnt,
 		(const struct sockaddr *)&xprt->addr)) {
 		return rpc_clnt_xprt_set_online(clnt, xprt);
 	}
-	rcu_read_lock();
-	rpc_xprt_switch_add_xprt(rcu_dereference(clnt->cl_xpi.xpi_xpswitch),
-				 xprt);
-	rcu_read_unlock();
+
+	xps = rpc_clnt_xprt_switch_get(clnt);
+	rpc_xprt_switch_add_xprt(xps, xprt);
+	xprt_switch_put(xps);
 }
 EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_add_xprt);
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 3f2ea7a0496fdc..3f714d33624be3 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1557,6 +1557,7 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 {
 	struct rpc_task *task;
 	int proc_error;
+	struct rpc_timeout timeout;
 
 	/* Build the svc_rqst used by the common processing routine */
 	rqstp->rq_xid = req->rq_xid;
@@ -1602,8 +1603,16 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 		return;
 	}
 	/* Finally, send the reply synchronously */
+	if (rqstp->bc_to_initval > 0) {
+		timeout.to_initval = rqstp->bc_to_initval;
+		timeout.to_retries = rqstp->bc_to_initval;
+	} else {
+		timeout.to_initval = req->rq_xprt->timeout->to_initval;
+		timeout.to_initval = req->rq_xprt->timeout->to_retries;
+	}
 	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
-	task = rpc_run_bc_task(req);
+	task = rpc_run_bc_task(req, &timeout);
+
 	if (IS_ERR(task))
 		return;
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 2364c485540c66..af13fdfa667214 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -651,9 +651,9 @@ static unsigned long xprt_abs_ktime_to_jiffies(ktime_t abstime)
 		jiffies + nsecs_to_jiffies(-delta);
 }
 
-static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req)
+static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req,
+		const struct rpc_timeout *to)
 {
-	const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
 	unsigned long majortimeo = req->rq_timeout;
 
 	if (to->to_exponential)
@@ -665,9 +665,10 @@ static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req)
 	return majortimeo;
 }
 
-static void xprt_reset_majortimeo(struct rpc_rqst *req)
+static void xprt_reset_majortimeo(struct rpc_rqst *req,
+		const struct rpc_timeout *to)
 {
-	req->rq_majortimeo += xprt_calc_majortimeo(req);
+	req->rq_majortimeo += xprt_calc_majortimeo(req, to);
 }
 
 static void xprt_reset_minortimeo(struct rpc_rqst *req)
@@ -675,7 +676,8 @@ static void xprt_reset_minortimeo(struct rpc_rqst *req)
 	req->rq_minortimeo += req->rq_timeout;
 }
 
-static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
+static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req,
+		const struct rpc_timeout *to)
 {
 	unsigned long time_init;
 	struct rpc_xprt *xprt = req->rq_xprt;
@@ -684,8 +686,9 @@ static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
 		time_init = jiffies;
 	else
 		time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
-	req->rq_timeout = task->tk_client->cl_timeout->to_initval;
-	req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
+
+	req->rq_timeout = to->to_initval;
+	req->rq_majortimeo = time_init + xprt_calc_majortimeo(req, to);
 	req->rq_minortimeo = time_init + req->rq_timeout;
 }
 
@@ -713,7 +716,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
 	} else {
 		req->rq_timeout = to->to_initval;
 		req->rq_retries = 0;
-		xprt_reset_majortimeo(req);
+		xprt_reset_majortimeo(req, to);
 		/* Reset the RTT counters == "slow start" */
 		spin_lock(&xprt->transport_lock);
 		rpc_init_rtt(req->rq_task->tk_client->cl_rtt, to->to_initval);
@@ -1886,7 +1889,7 @@ xprt_request_init(struct rpc_task *task)
 	req->rq_snd_buf.bvec = NULL;
 	req->rq_rcv_buf.bvec = NULL;
 	req->rq_release_snd_buf = NULL;
-	xprt_init_majortimeo(task, req);
+	xprt_init_majortimeo(task, req, task->tk_client->cl_timeout);
 
 	trace_xprt_reserve(req);
 }
@@ -1983,7 +1986,8 @@ void xprt_release(struct rpc_task *task)
 
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 void
-xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task)
+xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task,
+		const struct rpc_timeout *to)
 {
 	struct xdr_buf *xbufp = &req->rq_snd_buf;
 
@@ -1996,6 +2000,13 @@ xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task)
 	 */
 	xbufp->len = xbufp->head[0].iov_len + xbufp->page_len +
 		xbufp->tail[0].iov_len;
+	/*
+	 * Backchannel Replies are sent with !RPC_TASK_SOFT and
+	 * RPC_TASK_NO_RETRANS_TIMEOUT. The major timeout setting
+	 * affects only how long each Reply waits to be sent when
+	 * a transport connection cannot be established.
+	 */
+	xprt_init_majortimeo(task, req, to);
 }
 #endif
 
diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c
index 701250b305dba9..720d3ba742ec02 100644
--- a/net/sunrpc/xprtmultipath.c
+++ b/net/sunrpc/xprtmultipath.c
@@ -284,7 +284,7 @@ struct rpc_xprt *_xprt_switch_find_current_entry(struct list_head *head,
 		if (cur == pos)
 			found = true;
 		if (found && ((find_active && xprt_is_active(pos)) ||
-			      (!find_active && xprt_is_active(pos))))
+			      (!find_active && !xprt_is_active(pos))))
 			return pos;
 	}
 	return NULL;
@@ -336,8 +336,9 @@ struct rpc_xprt *xprt_iter_current_entry_offline(struct rpc_xprt_iter *xpi)
 			xprt_switch_find_current_entry_offline);
 }
 
-bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
-			      const struct sockaddr *sap)
+static
+bool __rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
+				const struct sockaddr *sap)
 {
 	struct list_head *head;
 	struct rpc_xprt *pos;
@@ -356,6 +357,18 @@ bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
 	return false;
 }
 
+bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
+			      const struct sockaddr *sap)
+{
+	bool res;
+
+	rcu_read_lock();
+	res = __rpc_xprt_switch_has_addr(xps, sap);
+	rcu_read_unlock();
+
+	return res;
+}
+
 static
 struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head,
 		const struct rpc_xprt *cur, bool check_active)