1 files changed, 1197 insertions, 638 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8c74871e37c9..63b75d214210 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -13,11 +13,13 @@
 #include <linux/iversion.h>
 #include <linux/ktime.h>
 #include <linux/netfs.h>
+#include <trace/events/netfs.h>
 
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
 #include "metric.h"
+#include "crypto.h"
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/striper.h>
 
@@ -78,23 +80,25 @@ static inline struct ceph_snap_context *page_snap_context(struct page *page)
  */
 static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 {
-	struct inode *inode;
+	struct inode *inode = mapping->host;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 	struct ceph_inode_info *ci;
 	struct ceph_snap_context *snapc;
 
 	if (folio_test_dirty(folio)) {
-		dout("%p dirty_folio %p idx %lu -- already dirty\n",
-		     mapping->host, folio, folio->index);
+		doutc(cl, "%llx.%llx %p idx %lu -- already dirty\n",
+		      ceph_vinop(inode), folio, folio->index);
 		VM_BUG_ON_FOLIO(!folio_test_private(folio), folio);
 		return false;
 	}
 
-	inode = mapping->host;
+	atomic64_inc(&mdsc->dirty_folios);
+
 	ci = ceph_inode(inode);
 
 	/* dirty the head */
 	spin_lock(&ci->i_ceph_lock);
-	BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference
 	if (__ceph_have_pending_cap_snap(ci)) {
 		struct ceph_cap_snap *capsnap =
 				list_last_entry(&ci->i_cap_snaps,
@@ -110,12 +114,12 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 	if (ci->i_wrbuffer_ref == 0)
 		ihold(inode);
 	++ci->i_wrbuffer_ref;
-	dout("%p dirty_folio %p idx %lu head %d/%d -> %d/%d "
-	     "snapc %p seq %lld (%d snaps)\n",
-	     mapping->host, folio, folio->index,
-	     ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
-	     ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
-	     snapc, snapc->seq, snapc->num_snaps);
+	doutc(cl, "%llx.%llx %p idx %lu head %d/%d -> %d/%d "
+	      "snapc %p seq %lld (%d snaps)\n",
+	      ceph_vinop(inode), folio, folio->index,
+	      ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
+	      ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
+	      snapc, snapc->seq, snapc->num_snaps);
 	spin_unlock(&ci->i_ceph_lock);
 
 	/*
@@ -136,50 +140,29 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 static void ceph_invalidate_folio(struct folio *folio, size_t offset,
 				size_t length)
 {
-	struct inode *inode;
-	struct ceph_inode_info *ci;
+	struct inode *inode = folio->mapping->host;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_snap_context *snapc;
 
-	inode = folio->mapping->host;
-	ci = ceph_inode(inode);
 
 	if (offset != 0 || length != folio_size(folio)) {
-		dout("%p invalidate_folio idx %lu partial dirty page %zu~%zu\n",
-		     inode, folio->index, offset, length);
+		doutc(cl, "%llx.%llx idx %lu partial dirty page %zu~%zu\n",
+		      ceph_vinop(inode), folio->index, offset, length);
 		return;
 	}
 
 	WARN_ON(!folio_test_locked(folio));
 	if (folio_test_private(folio)) {
-		dout("%p invalidate_folio idx %lu full dirty page\n",
-		     inode, folio->index);
+		doutc(cl, "%llx.%llx idx %lu full dirty page\n",
+		      ceph_vinop(inode), folio->index);
 
 		snapc = folio_detach_private(folio);
 		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
 		ceph_put_snap_context(snapc);
 	}
 
-	folio_wait_fscache(folio);
-}
-
-static bool ceph_release_folio(struct folio *folio, gfp_t gfp)
-{
-	struct inode *inode = folio->mapping->host;
-
-	dout("%llx:%llx release_folio idx %lu (%sdirty)\n",
-	     ceph_vinop(inode),
-	     folio->index, folio_test_dirty(folio) ? "" : "not ");
-
-	if (folio_test_private(folio))
-		return false;
-
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	ceph_fscache_note_page_release(inode);
-	return true;
+	netfs_invalidate_folio(folio, offset, length);
 }
 
 static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
@@ -187,61 +170,103 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
 	struct inode *inode = rreq->inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_layout *lo = &ci->i_layout;
+	unsigned long max_pages = inode->i_sb->s_bdi->ra_pages;
+	loff_t end = rreq->start + rreq->len, new_end;
+	struct ceph_netfs_request_data *priv = rreq->netfs_priv;
+	unsigned long max_len;
 	u32 blockoff;
-	u64 blockno;
 
-	/* Expand the start downward */
-	blockno = div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
-	rreq->start = blockno * lo->stripe_unit;
-	rreq->len += blockoff;
+	if (priv) {
+		/* Readahead is disabled by posix_fadvise POSIX_FADV_RANDOM */
+		if (priv->file_ra_disabled)
+			max_pages = 0;
+		else
+			max_pages = priv->file_ra_pages;
 
-	/* Now, round up the length to the next block */
-	rreq->len = roundup(rreq->len, lo->stripe_unit);
-}
+	}
 
-static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
-{
-	struct inode *inode = subreq->rreq->inode;
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	u64 objno, objoff;
-	u32 xlen;
+	/* Readahead is disabled */
+	if (!max_pages)
+		return;
 
-	/* Truncate the extent at the end of the current block */
-	ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len,
-				      &objno, &objoff, &xlen);
-	subreq->len = min(xlen, fsc->mount_options->rsize);
-	return true;
+	max_len = max_pages << PAGE_SHIFT;
+
+	/*
+	 * Try to expand the length forward by rounding up it to the next
+	 * block, but do not exceed the file size, unless the original
+	 * request already exceeds it.
+	 */
+	new_end = umin(round_up(end, lo->stripe_unit), rreq->i_size);
+	if (new_end > end && new_end <= rreq->start + max_len)
+		rreq->len = new_end - rreq->start;
+
+	/* Try to expand the start downward */
+	div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
+	if (rreq->len + blockoff <= max_len) {
+		rreq->start -= blockoff;
+		rreq->len += blockoff;
+	}
 }
 
 static void finish_netfs_read(struct ceph_osd_request *req)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
+	struct inode *inode = req->r_inode;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
 	struct netfs_io_subrequest *subreq = req->r_priv;
-	int num_pages;
+	struct ceph_osd_req_op *op = &req->r_ops[0];
 	int err = req->r_result;
+	bool sparse = (op->op == CEPH_OSD_OP_SPARSE_READ);
 
 	ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				 req->r_end_latency, osd_data->length, err);
 
-	dout("%s: result %d subreq->len=%zu i_size=%lld\n", __func__, req->r_result,
-	     subreq->len, i_size_read(req->r_inode));
+	doutc(cl, "result %d subreq->len=%zu i_size=%lld\n", req->r_result,
+	      subreq->len, i_size_read(req->r_inode));
 
 	/* no object means success but no data */
-	if (err == -ENOENT)
+	if (err == -ENOENT) {
+		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
 		err = 0;
-	else if (err == -EBLOCKLISTED)
+	} else if (err == -EBLOCKLISTED) {
 		fsc->blocklisted = true;
+	}
 
-	if (err >= 0 && err < subreq->len)
-		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
-
-	netfs_subreq_terminated(subreq, err, false);
+	if (err >= 0) {
+		if (sparse && err > 0)
+			err = ceph_sparse_ext_map_end(op);
+		if (err < subreq->len &&
+		    subreq->rreq->origin != NETFS_UNBUFFERED_READ &&
+		    subreq->rreq->origin != NETFS_DIO_READ)
+			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+		if (IS_ENCRYPTED(inode) && err > 0) {
+			err = ceph_fscrypt_decrypt_extents(inode,
+					osd_data->pages, subreq->start,
+					op->extent.sparse_ext,
+					op->extent.sparse_ext_cnt);
+			if (err > subreq->len)
+				err = subreq->len;
+		}
+		if (err > 0)
+			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	}
 
-	num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
-	ceph_put_page_vector(osd_data->pages, num_pages, false);
+	if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) {
+		ceph_put_page_vector(osd_data->pages,
+				     calc_pages_for(osd_data->alignment,
+					osd_data->length), false);
+	}
+	if (err > 0) {
+		subreq->transferred = err;
+		err = 0;
+	}
+	subreq->error = err;
+	trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress);
+	netfs_read_subreq_terminated(subreq);
 	iput(req->r_inode);
+	ceph_dec_osd_stopping_blocker(fsc->mdsc);
 }
 
 static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
@@ -253,12 +278,13 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct iov_iter iter;
 	ssize_t err = 0;
 	size_t len;
 	int mode;
 
-	__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	if (rreq->origin != NETFS_UNBUFFERED_READ &&
+	    rreq->origin != NETFS_DIO_READ)
+		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 	__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
 
 	if (subreq->start >= inode->i_size)
@@ -275,6 +301,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INLINE_DATA);
 	req->r_num_caps = 2;
 
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	if (err < 0)
 		goto out;
@@ -288,87 +315,177 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	}
 
 	len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len);
-	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
-	err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter);
-	if (err == 0)
+	err = copy_to_iter(iinfo->inline_data + subreq->start, len, &subreq->io_iter);
+	if (err == 0) {
 		err = -EFAULT;
+	} else {
+		subreq->transferred += err;
+		err = 0;
+	}
 
 	ceph_mdsc_put_request(req);
 out:
-	netfs_subreq_terminated(subreq, err, false);
+	subreq->error = err;
+	trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress);
+	netfs_read_subreq_terminated(subreq);
 	return true;
 }
 
+static int ceph_netfs_prepare_read(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *rreq = subreq->rreq;
+	struct inode *inode = rreq->inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	u64 objno, objoff;
+	u32 xlen;
+
+	/* Truncate the extent at the end of the current block */
+	ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len,
+				      &objno, &objoff, &xlen);
+	rreq->io_streams[0].sreq_max_len = umin(xlen, fsc->mount_options->rsize);
+	return 0;
+}
+
 static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *rreq = subreq->rreq;
 	struct inode *inode = rreq->inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_osd_request *req;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
+	struct ceph_osd_request *req = NULL;
 	struct ceph_vino vino = ceph_vino(inode);
-	struct iov_iter iter;
-	struct page **pages;
-	size_t page_off;
-	int err = 0;
-	u64 len = subreq->len;
+	int err;
+	u64 len;
+	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
+	u64 off = subreq->start;
+	int extent_cnt;
+
+	if (ceph_inode_is_shutdown(inode)) {
+		err = -EIO;
+		goto out;
+	}
 
 	if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq))
 		return;
 
-	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
-			0, 1, CEPH_OSD_OP_READ,
-			CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
-			NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
+	// TODO: This rounding here is slightly dodgy.  It *should* work, for
+	// now, as the cache only deals in blocks that are a multiple of
+	// PAGE_SIZE and fscrypt blocks are at most PAGE_SIZE.  What needs to
+	// happen is for the fscrypt driving to be moved into netfslib and the
+	// data in the cache also to be stored encrypted.
+	len = subreq->len;
+	ceph_fscrypt_adjust_off_and_len(inode, &off, &len);
+
+	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino,
+			off, &len, 0, 1, sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ,
+			CEPH_OSD_FLAG_READ, NULL, ci->i_truncate_seq,
+			ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		req = NULL;
 		goto out;
 	}
 
-	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
-	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
-	err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
-	if (err < 0) {
-		dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err);
-		goto out;
+	if (sparse) {
+		extent_cnt = __ceph_sparse_read_ext_count(inode, len);
+		err = ceph_alloc_sparse_ext_map(&req->r_ops[0], extent_cnt);
+		if (err)
+			goto out;
 	}
 
-	/* should always give us a page-aligned read */
-	WARN_ON_ONCE(page_off);
-	len = err;
-	err = 0;
+	doutc(cl, "%llx.%llx pos=%llu orig_len=%zu len=%llu\n",
+	      ceph_vinop(inode), subreq->start, subreq->len, len);
+
+	/*
+	 * FIXME: For now, use CEPH_OSD_DATA_TYPE_PAGES instead of _ITER for
+	 * encrypted inodes. We'd need infrastructure that handles an iov_iter
+	 * instead of page arrays, and we don't have that as of yet. Once the
+	 * dust settles on the write helpers and encrypt/decrypt routines for
+	 * netfs, we should be able to rework this.
+	 */
+	if (IS_ENCRYPTED(inode)) {
+		struct page **pages;
+		size_t page_off;
+
+		/*
+		 * FIXME: io_iter.count needs to be corrected to aligned
+		 * length. Otherwise, iov_iter_get_pages_alloc2() operates
+		 * with the initial unaligned length value. As a result,
+		 * ceph_msg_data_cursor_init() triggers BUG_ON() in the case
+		 * if msg->sparse_read_total > msg->data_length.
+		 */
+		subreq->io_iter.count = len;
 
-	osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
+		err = iov_iter_get_pages_alloc2(&subreq->io_iter, &pages, len, &page_off);
+		if (err < 0) {
+			doutc(cl, "%llx.%llx failed to allocate pages, %d\n",
+			      ceph_vinop(inode), err);
+			goto out;
+		}
+
+		/* should always give us a page-aligned read */
+		WARN_ON_ONCE(page_off);
+		len = err;
+		err = 0;
+
+		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false,
+						 false);
+	} else {
+		osd_req_op_extent_osd_iter(req, 0, &subreq->io_iter);
+	}
+	if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
+		err = -EIO;
+		goto out;
+	}
 	req->r_callback = finish_netfs_read;
 	req->r_priv = subreq;
 	req->r_inode = inode;
 	ihold(inode);
 
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 	ceph_osdc_start_request(req->r_osdc, req);
 out:
 	ceph_osdc_put_request(req);
-	if (err)
-		netfs_subreq_terminated(subreq, err, false);
-	dout("%s: result %d\n", __func__, err);
+	if (err) {
+		subreq->error = err;
+		netfs_read_subreq_terminated(subreq);
+	}
+	doutc(cl, "%llx.%llx result %d\n", ceph_vinop(inode), err);
 }
 
 static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 {
 	struct inode *inode = rreq->inode;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int got = 0, want = CEPH_CAP_FILE_CACHE;
+	struct ceph_netfs_request_data *priv;
 	int ret = 0;
 
+	/* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
+	__set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
+
 	if (rreq->origin != NETFS_READAHEAD)
 		return 0;
 
+	priv = kzalloc(sizeof(*priv), GFP_NOFS);
+	if (!priv)
+		return -ENOMEM;
+
 	if (file) {
 		struct ceph_rw_context *rw_ctx;
 		struct ceph_file_info *fi = file->private_data;
 
+		priv->file_ra_pages = file->f_ra.ra_pages;
+		priv->file_ra_disabled = file->f_mode & FMODE_RANDOM;
+
 		rw_ctx = ceph_find_rw_context(fi);
-		if (rw_ctx)
+		if (rw_ctx) {
+			rreq->netfs_priv = priv;
 			return 0;
+		}
 	}
 
 	/*
@@ -377,47 +494,63 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 	 */
 	ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got);
 	if (ret < 0) {
-		dout("start_read %p, error getting cap\n", inode);
-		return ret;
+		doutc(cl, "%llx.%llx, error getting cap\n", ceph_vinop(inode));
+		goto out;
 	}
 
 	if (!(got & want)) {
-		dout("start_read %p, no cache cap\n", inode);
-		return -EACCES;
+		doutc(cl, "%llx.%llx, no cache cap\n", ceph_vinop(inode));
+		ret = -EACCES;
+		goto out;
+	}
+	if (ret == 0) {
+		ret = -EACCES;
+		goto out;
 	}
-	if (ret == 0)
-		return -EACCES;
 
-	rreq->netfs_priv = (void *)(uintptr_t)got;
-	return 0;
+	priv->caps = got;
+	rreq->netfs_priv = priv;
+	rreq->io_streams[0].sreq_max_len = fsc->mount_options->rsize;
+
+out:
+	if (ret < 0) {
+		if (got)
+			ceph_put_cap_refs(ceph_inode(inode), got);
+		kfree(priv);
+	}
+
+	return ret;
 }
 
 static void ceph_netfs_free_request(struct netfs_io_request *rreq)
 {
-	struct ceph_inode_info *ci = ceph_inode(rreq->inode);
-	int got = (uintptr_t)rreq->netfs_priv;
+	struct ceph_netfs_request_data *priv = rreq->netfs_priv;
+
+	if (!priv)
+		return;
 
-	if (got)
-		ceph_put_cap_refs(ci, got);
+	if (priv->caps)
+		ceph_put_cap_refs(ceph_inode(rreq->inode), priv->caps);
+	kfree(priv);
+	rreq->netfs_priv = NULL;
 }
 
 const struct netfs_request_ops ceph_netfs_ops = {
 	.init_request		= ceph_init_request,
 	.free_request		= ceph_netfs_free_request,
-	.begin_cache_operation	= ceph_begin_cache_operation,
+	.prepare_read		= ceph_netfs_prepare_read,
 	.issue_read		= ceph_netfs_issue_read,
 	.expand_readahead	= ceph_netfs_expand_readahead,
-	.clamp_length		= ceph_netfs_clamp_length,
 	.check_write_begin	= ceph_netfs_check_write_begin,
 };
 
 #ifdef CONFIG_CEPH_FSCACHE
 static void ceph_set_page_fscache(struct page *page)
 {
-	set_page_fscache(page);
+	folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
 }
 
-static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
+static void ceph_fscache_write_terminated(void *priv, ssize_t error)
 {
 	struct inode *inode = priv;
 
@@ -431,7 +564,7 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b
 	struct fscache_cookie *cookie = ceph_fscache_cookie(ci);
 
 	fscache_write_to_cache(cookie, inode->i_mapping, off, len, i_size_read(inode),
-			       ceph_fscache_write_terminated, inode, caching);
+			       ceph_fscache_write_terminated, inode, true, caching);
 }
 #else
 static inline void ceph_set_page_fscache(struct page *page)
@@ -449,7 +582,36 @@ struct ceph_writeback_ctl
 	u64 truncate_size;
 	u32 truncate_seq;
 	bool size_stable;
+
 	bool head_snapc;
+	struct ceph_snap_context *snapc;
+	struct ceph_snap_context *last_snapc;
+
+	bool done;
+	bool should_loop;
+	bool range_whole;
+	pgoff_t start_index;
+	pgoff_t index;
+	pgoff_t end;
+	xa_mark_t tag;
+
+	pgoff_t strip_unit_end;
+	unsigned int wsize;
+	unsigned int nr_folios;
+	unsigned int max_pages;
+	unsigned int locked_pages;
+
+	int op_idx;
+	int num_ops;
+	u64 offset;
+	u64 len;
+
+	struct folio_batch fbatch;
+	unsigned int processed_in_fbatch;
+
+	bool from_pool;
+	struct page **pages;
+	struct page **data_pages;
 };
 
 /*
@@ -461,13 +623,14 @@ get_oldest_context(struct inode *inode, struct ceph_writeback_ctl *ctl,
 		   struct ceph_snap_context *page_snapc)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_snap_context *snapc = NULL;
 	struct ceph_cap_snap *capsnap = NULL;
 
 	spin_lock(&ci->i_ceph_lock);
 	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
-		dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
-		     capsnap->context, capsnap->dirty_pages);
+		doutc(cl, " capsnap %p snapc %p has %d dirty pages\n",
+		      capsnap, capsnap->context, capsnap->dirty_pages);
 		if (!capsnap->dirty_pages)
 			continue;
 
@@ -499,8 +662,8 @@ get_oldest_context(struct inode *inode, struct ceph_writeback_ctl *ctl,
 	}
 	if (!snapc && ci->i_wrbuffer_ref_head) {
 		snapc = ceph_get_snap_context(ci->i_head_snapc);
-		dout(" head snapc %p has %d dirty pages\n",
-		     snapc, ci->i_wrbuffer_ref_head);
+		doutc(cl, " head snapc %p has %d dirty pages\n", snapc,
+		      ci->i_wrbuffer_ref_head);
 		if (ctl) {
 			ctl->i_size = i_size_read(inode);
 			ctl->truncate_size = ci->i_truncate_size;
@@ -517,10 +680,12 @@ static u64 get_writepages_data_length(struct inode *inode,
 				      struct page *page, u64 start)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_snap_context *snapc = page_snap_context(page);
+	struct ceph_snap_context *snapc;
 	struct ceph_cap_snap *capsnap = NULL;
 	u64 end = i_size_read(inode);
+	u64 ret;
 
+	snapc = page_snap_context(ceph_fscrypt_pagecache_page(page));
 	if (snapc != ci->i_head_snapc) {
 		bool found = false;
 		spin_lock(&ci->i_ceph_lock);
@@ -535,56 +700,68 @@ static u64 get_writepages_data_length(struct inode *inode,
 		spin_unlock(&ci->i_ceph_lock);
 		WARN_ON(!found);
 	}
-	if (end > page_offset(page) + thp_size(page))
-		end = page_offset(page) + thp_size(page);
-	return end > start ? end - start : 0;
+	if (end > ceph_fscrypt_page_offset(page) + thp_size(page))
+		end = ceph_fscrypt_page_offset(page) + thp_size(page);
+	ret = end > start ? end - start : 0;
+	if (ret && fscrypt_is_bounce_page(page))
+		ret = round_up(ret, CEPH_FSCRYPT_BLOCK_SIZE);
+	return ret;
 }
 
 /*
- * Write a single page, but leave the page locked.
+ * Write a folio, but leave it locked.
  *
  * If we get a write error, mark the mapping for error, but still adjust the
- * dirty page accounting (i.e., page is no longer dirty).
+ * dirty page accounting (i.e., folio is no longer dirty).
  */
-static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
+static int write_folio_nounlock(struct folio *folio,
+		struct writeback_control *wbc)
 {
-	struct folio *folio = page_folio(page);
-	struct inode *inode = page->mapping->host;
+	struct page *page = &folio->page;
+	struct inode *inode = folio->mapping->host;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_snap_context *snapc, *oldest;
-	loff_t page_off = page_offset(page);
+	loff_t page_off = folio_pos(folio);
 	int err;
-	loff_t len = thp_size(page);
+	loff_t len = folio_size(folio);
+	loff_t wlen;
 	struct ceph_writeback_ctl ceph_wbc;
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_osd_request *req;
 	bool caching = ceph_is_cache_enabled(inode);
+	struct page *bounce_page = NULL;
+
+	doutc(cl, "%llx.%llx folio %p idx %lu\n", ceph_vinop(inode), folio,
+	      folio->index);
 
-	dout("writepage %p idx %lu\n", page, page->index);
+	if (ceph_inode_is_shutdown(inode))
+		return -EIO;
 
 	/* verify this is a writeable snap context */
-	snapc = page_snap_context(page);
+	snapc = page_snap_context(&folio->page);
 	if (!snapc) {
-		dout("writepage %p page %p not dirty?\n", inode, page);
+		doutc(cl, "%llx.%llx folio %p not dirty?\n", ceph_vinop(inode),
+		      folio);
 		return 0;
 	}
 	oldest = get_oldest_context(inode, &ceph_wbc, snapc);
 	if (snapc->seq > oldest->seq) {
-		dout("writepage %p page %p snapc %p not writeable - noop\n",
-		     inode, page, snapc);
+		doutc(cl, "%llx.%llx folio %p snapc %p not writeable - noop\n",
+		      ceph_vinop(inode), folio, snapc);
 		/* we should only noop if called by kswapd */
 		WARN_ON(!(current->flags & PF_MEMALLOC));
 		ceph_put_snap_context(oldest);
-		redirty_page_for_writepage(wbc, page);
+		folio_redirty_for_writepage(wbc, folio);
 		return 0;
 	}
 	ceph_put_snap_context(oldest);
 
 	/* is this a partial page at end of file? */
 	if (page_off >= ceph_wbc.i_size) {
-		dout("folio at %lu beyond eof %llu\n", folio->index,
-				ceph_wbc.i_size);
+		doutc(cl, "%llx.%llx folio at %lu beyond eof %llu\n",
+		      ceph_vinop(inode), folio->index, ceph_wbc.i_size);
 		folio_invalidate(folio, 0, folio_size(folio));
 		return 0;
 	}
@@ -592,39 +769,61 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	if (ceph_wbc.i_size < page_off + len)
 		len = ceph_wbc.i_size - page_off;
 
-	dout("writepage %p page %p index %lu on %llu~%llu snapc %p seq %lld\n",
-	     inode, page, page->index, page_off, len, snapc, snapc->seq);
+	wlen = IS_ENCRYPTED(inode) ? round_up(len, CEPH_FSCRYPT_BLOCK_SIZE) : len;
+	doutc(cl, "%llx.%llx folio %p index %lu on %llu~%llu snapc %p seq %lld\n",
+	      ceph_vinop(inode), folio, folio->index, page_off, wlen, snapc,
+	      snapc->seq);
 
 	if (atomic_long_inc_return(&fsc->writeback_count) >
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
 		fsc->write_congested = true;
 
-	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1,
-				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
-				    ceph_wbc.truncate_seq, ceph_wbc.truncate_size,
-				    true);
+	req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode),
+				    page_off, &wlen, 0, 1, CEPH_OSD_OP_WRITE,
+				    CEPH_OSD_FLAG_WRITE, snapc,
+				    ceph_wbc.truncate_seq,
+				    ceph_wbc.truncate_size, true);
 	if (IS_ERR(req)) {
-		redirty_page_for_writepage(wbc, page);
+		folio_redirty_for_writepage(wbc, folio);
 		return PTR_ERR(req);
 	}
 
-	set_page_writeback(page);
+	if (wlen < len)
+		len = wlen;
+
+	folio_start_writeback(folio);
 	if (caching)
-		ceph_set_page_fscache(page);
+		ceph_set_page_fscache(&folio->page);
 	ceph_fscache_write_to_cache(inode, page_off, len, caching);
 
-	/* it may be a short write due to an object boundary */
-	WARN_ON_ONCE(len > thp_size(page));
-	osd_req_op_extent_osd_data_pages(req, 0, &page, len, 0, false, false);
-	dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len);
+	if (IS_ENCRYPTED(inode)) {
+		bounce_page = fscrypt_encrypt_pagecache_blocks(folio,
+						    CEPH_FSCRYPT_BLOCK_SIZE, 0,
+						    GFP_NOFS);
+		if (IS_ERR(bounce_page)) {
+			folio_redirty_for_writepage(wbc, folio);
+			folio_end_writeback(folio);
+			ceph_osdc_put_request(req);
+			return PTR_ERR(bounce_page);
+		}
+	}
 
-	req->r_mtime = inode->i_mtime;
+	/* it may be a short write due to an object boundary */
+	WARN_ON_ONCE(len > folio_size(folio));
+	osd_req_op_extent_osd_data_pages(req, 0,
+			bounce_page ? &bounce_page : &page, wlen, 0,
+			false, false);
+	doutc(cl, "%llx.%llx %llu~%llu (%llu bytes, %sencrypted)\n",
+	      ceph_vinop(inode), page_off, len, wlen,
+	      IS_ENCRYPTED(inode) ? "" : "not ");
+
+	req->r_mtime = inode_get_mtime(inode);
 	ceph_osdc_start_request(osdc, req);
 	err = ceph_osdc_wait_request(osdc, req);
 
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
-
+	fscrypt_free_bounce_page(bounce_page);
 	ceph_osdc_put_request(req);
 	if (err == 0)
 		err = len;
@@ -635,24 +834,26 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 			wbc = &tmp_wbc;
 		if (err == -ERESTARTSYS) {
 			/* killed by SIGKILL */
-			dout("writepage interrupted page %p\n", page);
-			redirty_page_for_writepage(wbc, page);
-			end_page_writeback(page);
+			doutc(cl, "%llx.%llx interrupted page %p\n",
+			      ceph_vinop(inode), folio);
+			folio_redirty_for_writepage(wbc, folio);
+			folio_end_writeback(folio);
 			return err;
 		}
 		if (err == -EBLOCKLISTED)
 			fsc->blocklisted = true;
-		dout("writepage setting page/mapping error %d %p\n",
-		     err, page);
+		doutc(cl, "%llx.%llx setting mapping error %d %p\n",
+		      ceph_vinop(inode), err, folio);
 		mapping_set_error(&inode->i_data, err);
 		wbc->pages_skipped++;
 	} else {
-		dout("writepage cleaned page %p\n", page);
+		doutc(cl, "%llx.%llx cleaned page %p\n",
+		      ceph_vinop(inode), folio);
 		err = 0;  /* vfs expects us to return 0 */
 	}
-	oldest = detach_page_private(page);
+	oldest = folio_detach_private(folio);
 	WARN_ON_ONCE(oldest != snapc);
-	end_page_writeback(page);
+	folio_end_writeback(folio);
 	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
 	ceph_put_snap_context(snapc);  /* page's reference */
 
@@ -663,30 +864,6 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	return err;
 }
 
-static int ceph_writepage(struct page *page, struct writeback_control *wbc)
-{
-	int err;
-	struct inode *inode = page->mapping->host;
-	BUG_ON(!inode);
-	ihold(inode);
-
-	if (wbc->sync_mode == WB_SYNC_NONE &&
-	    ceph_inode_to_client(inode)->write_congested)
-		return AOP_WRITEPAGE_ACTIVATE;
-
-	wait_on_page_fscache(page);
-
-	err = writepage_nounlock(page, wbc);
-	if (err == -ERESTARTSYS) {
-		/* direct memory reclaimer was killed by SIGKILL. return 0
-		 * to prevent caller from setting mapping/page error */
-		err = 0;
-	}
-	unlock_page(page);
-	iput(inode);
-	return err;
-}
-
 /*
  * async writeback completion handler.
  *
@@ -697,6 +874,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 {
 	struct inode *inode = req->r_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_osd_data *osd_data;
 	struct page *page;
 	int num_pages, total_pages = 0;
@@ -704,11 +882,12 @@ static void writepages_finish(struct ceph_osd_request *req)
 	int rc = req->r_result;
 	struct ceph_snap_context *snapc = req->r_snapc;
 	struct address_space *mapping = inode->i_mapping;
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 	unsigned int len = 0;
 	bool remove_page;
 
-	dout("writepages_finish %p rc %d\n", inode, rc);
+	doutc(cl, "%llx.%llx rc %d\n", ceph_vinop(inode), rc);
 	if (rc < 0) {
 		mapping_set_error(mapping, rc);
 		ceph_set_error_write(ci);
@@ -730,8 +909,10 @@ static void writepages_finish(struct ceph_osd_request *req)
 	/* clean all pages */
 	for (i = 0; i < req->r_num_ops; i++) {
 		if (req->r_ops[i].op != CEPH_OSD_OP_WRITE) {
-			pr_warn("%s incorrect op %d req %p index %d tid %llu\n",
-				__func__, req->r_ops[i].op, req, i, req->r_tid);
+			pr_warn_client(cl,
+				"%llx.%llx incorrect op %d req %p index %d tid %llu\n",
+				ceph_vinop(inode), req->r_ops[i].op, req, i,
+				req->r_tid);
 			break;
 		}
 
@@ -743,6 +924,11 @@ static void writepages_finish(struct ceph_osd_request *req)
 		total_pages += num_pages;
 		for (j = 0; j < num_pages; j++) {
 			page = osd_data->pages[j];
+			if (fscrypt_is_bounce_page(page)) {
+				page = fscrypt_pagecache_page(page);
+				fscrypt_free_bounce_page(osd_data->pages[j]);
+				osd_data->pages[j] = page;
+			}
 			BUG_ON(!page);
 			WARN_ON(!PageUptodate(page));
 
@@ -753,16 +939,23 @@ static void writepages_finish(struct ceph_osd_request *req)
 
 			ceph_put_snap_context(detach_page_private(page));
 			end_page_writeback(page);
-			dout("unlocking %p\n", page);
+
+			if (atomic64_dec_return(&mdsc->dirty_folios) <= 0) {
+				wake_up_all(&mdsc->flush_end_wq);
+				WARN_ON(atomic64_read(&mdsc->dirty_folios) < 0);
+			}
+
+			doutc(cl, "unlocking %p\n", page);
 
 			if (remove_page)
-				generic_error_remove_page(inode->i_mapping,
-							  page);
+				generic_error_remove_folio(inode->i_mapping,
+							  page_folio(page));
 
 			unlock_page(page);
 		}
-		dout("writepages_finish %p wrote %llu bytes cleaned %d pages\n",
-		     inode, osd_data->length, rc >= 0 ? num_pages : 0);
+		doutc(cl, "%llx.%llx wrote %llu bytes cleaned %d pages\n",
+		      ceph_vinop(inode), osd_data->length,
+		      rc >= 0 ? num_pages : 0);
 
 		release_pages(osd_data->pages, num_pages);
 	}
@@ -778,382 +971,748 @@ static void writepages_finish(struct ceph_osd_request *req)
 	else
 		kfree(osd_data->pages);
 	ceph_osdc_put_request(req);
+	ceph_dec_osd_stopping_blocker(fsc->mdsc);
 }
 
-/*
- * initiate async writeback
- */
-static int ceph_writepages_start(struct address_space *mapping,
-				 struct writeback_control *wbc)
+static inline
+bool is_forced_umount(struct address_space *mapping)
 {
 	struct inode *inode = mapping->host;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_vino vino = ceph_vino(inode);
-	pgoff_t index, start_index, end = -1;
-	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
-	struct pagevec pvec;
-	int rc = 0;
-	unsigned int wsize = i_blocksize(inode);
-	struct ceph_osd_request *req = NULL;
-	struct ceph_writeback_ctl ceph_wbc;
-	bool should_loop, range_whole = false;
-	bool done = false;
-	bool caching = ceph_is_cache_enabled(inode);
-
-	if (wbc->sync_mode == WB_SYNC_NONE &&
-	    fsc->write_congested)
-		return 0;
-
-	dout("writepages_start %p (mode=%s)\n", inode,
-	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
-	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 
 	if (ceph_inode_is_shutdown(inode)) {
 		if (ci->i_wrbuffer_ref > 0) {
-			pr_warn_ratelimited(
-				"writepage_start %p %lld forced umount\n",
-				inode, ceph_ino(inode));
+			pr_warn_ratelimited_client(cl,
+				"%llx.%llx %lld forced umount\n",
+				ceph_vinop(inode), ceph_ino(inode));
 		}
 		mapping_set_error(mapping, -EIO);
-		return -EIO; /* we're in a forced umount, don't write! */
+		return true;
 	}
+
+	return false;
+}
+
+static inline
+unsigned int ceph_define_write_size(struct address_space *mapping)
+{
+	struct inode *inode = mapping->host;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	unsigned int wsize = i_blocksize(inode);
+
 	if (fsc->mount_options->wsize < wsize)
 		wsize = fsc->mount_options->wsize;
 
-	pagevec_init(&pvec);
+	return wsize;
+}
+
+static inline
+void ceph_folio_batch_init(struct ceph_writeback_ctl *ceph_wbc)
+{
+	folio_batch_init(&ceph_wbc->fbatch);
+	ceph_wbc->processed_in_fbatch = 0;
+}
+
+static inline
+void ceph_folio_batch_reinit(struct ceph_writeback_ctl *ceph_wbc)
+{
+	folio_batch_release(&ceph_wbc->fbatch);
+	ceph_folio_batch_init(ceph_wbc);
+}
 
-	start_index = wbc->range_cyclic ? mapping->writeback_index : 0;
-	index = start_index;
+static inline
+void ceph_init_writeback_ctl(struct address_space *mapping,
+			     struct writeback_control *wbc,
+			     struct ceph_writeback_ctl *ceph_wbc)
+{
+	ceph_wbc->snapc = NULL;
+	ceph_wbc->last_snapc = NULL;
+
+	ceph_wbc->strip_unit_end = 0;
+	ceph_wbc->wsize = ceph_define_write_size(mapping);
+
+	ceph_wbc->nr_folios = 0;
+	ceph_wbc->max_pages = 0;
+	ceph_wbc->locked_pages = 0;
+
+	ceph_wbc->done = false;
+	ceph_wbc->should_loop = false;
+	ceph_wbc->range_whole = false;
+
+	ceph_wbc->start_index = wbc->range_cyclic ? mapping->writeback_index : 0;
+	ceph_wbc->index = ceph_wbc->start_index;
+	ceph_wbc->end = -1;
+
+	ceph_wbc->tag = wbc_to_tag(wbc);
+
+	ceph_wbc->op_idx = -1;
+	ceph_wbc->num_ops = 0;
+	ceph_wbc->offset = 0;
+	ceph_wbc->len = 0;
+	ceph_wbc->from_pool = false;
+
+	ceph_folio_batch_init(ceph_wbc);
+
+	ceph_wbc->pages = NULL;
+	ceph_wbc->data_pages = NULL;
+}
+
+static inline
+int ceph_define_writeback_range(struct address_space *mapping,
+				struct writeback_control *wbc,
+				struct ceph_writeback_ctl *ceph_wbc)
+{
+	struct inode *inode = mapping->host;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 
-retry:
 	/* find oldest snap context with dirty data */
-	snapc = get_oldest_context(inode, &ceph_wbc, NULL);
-	if (!snapc) {
+	ceph_wbc->snapc = get_oldest_context(inode, ceph_wbc, NULL);
+	if (!ceph_wbc->snapc) {
 		/* hmm, why does writepages get called when there
 		   is no dirty data? */
-		dout(" no snap context with dirty data?\n");
-		goto out;
+		doutc(cl, " no snap context with dirty data?\n");
+		return -ENODATA;
 	}
-	dout(" oldest snapc is %p seq %lld (%d snaps)\n",
-	     snapc, snapc->seq, snapc->num_snaps);
 
-	should_loop = false;
-	if (ceph_wbc.head_snapc && snapc != last_snapc) {
+	doutc(cl, " oldest snapc is %p seq %lld (%d snaps)\n",
+	      ceph_wbc->snapc, ceph_wbc->snapc->seq,
+	      ceph_wbc->snapc->num_snaps);
+
+	ceph_wbc->should_loop = false;
+
+	if (ceph_wbc->head_snapc && ceph_wbc->snapc != ceph_wbc->last_snapc) {
 		/* where to start/end? */
 		if (wbc->range_cyclic) {
-			index = start_index;
-			end = -1;
-			if (index > 0)
-				should_loop = true;
-			dout(" cyclic, start at %lu\n", index);
+			ceph_wbc->index = ceph_wbc->start_index;
+			ceph_wbc->end = -1;
+			if (ceph_wbc->index > 0)
+				ceph_wbc->should_loop = true;
+			doutc(cl, " cyclic, start at %lu\n", ceph_wbc->index);
 		} else {
-			index = wbc->range_start >> PAGE_SHIFT;
-			end = wbc->range_end >> PAGE_SHIFT;
+			ceph_wbc->index = wbc->range_start >> PAGE_SHIFT;
+			ceph_wbc->end = wbc->range_end >> PAGE_SHIFT;
 			if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
-				range_whole = true;
-			dout(" not cyclic, %lu to %lu\n", index, end);
+				ceph_wbc->range_whole = true;
+			doutc(cl, " not cyclic, %lu to %lu\n",
+				ceph_wbc->index, ceph_wbc->end);
 		}
-	} else if (!ceph_wbc.head_snapc) {
+	} else if (!ceph_wbc->head_snapc) {
 		/* Do not respect wbc->range_{start,end}. Dirty pages
 		 * in that range can be associated with newer snapc.
 		 * They are not writeable until we write all dirty pages
 		 * associated with 'snapc' get written */
-		if (index > 0)
-			should_loop = true;
-		dout(" non-head snapc, range whole\n");
+		if (ceph_wbc->index > 0)
+			ceph_wbc->should_loop = true;
+		doutc(cl, " non-head snapc, range whole\n");
 	}
 
-	ceph_put_snap_context(last_snapc);
-	last_snapc = snapc;
+	ceph_put_snap_context(ceph_wbc->last_snapc);
+	ceph_wbc->last_snapc = ceph_wbc->snapc;
 
-	while (!done && index <= end) {
-		int num_ops = 0, op_idx;
-		unsigned i, pvec_pages, max_pages, locked_pages = 0;
-		struct page **pages = NULL, **data_pages;
-		struct page *page;
-		pgoff_t strip_unit_end = 0;
-		u64 offset = 0, len = 0;
-		bool from_pool = false;
+	return 0;
+}
 
-		max_pages = wsize >> PAGE_SHIFT;
+static inline
+bool has_writeback_done(struct ceph_writeback_ctl *ceph_wbc)
+{
+	return ceph_wbc->done && ceph_wbc->index > ceph_wbc->end;
+}
 
-get_more_pages:
-		pvec_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
-						end, PAGECACHE_TAG_DIRTY);
-		dout("pagevec_lookup_range_tag got %d\n", pvec_pages);
-		if (!pvec_pages && !locked_pages)
-			break;
-		for (i = 0; i < pvec_pages && locked_pages < max_pages; i++) {
-			page = pvec.pages[i];
-			dout("? %p idx %lu\n", page, page->index);
-			if (locked_pages == 0)
-				lock_page(page);  /* first page */
-			else if (!trylock_page(page))
-				break;
+static inline
+bool can_next_page_be_processed(struct ceph_writeback_ctl *ceph_wbc,
+				unsigned index)
+{
+	return index < ceph_wbc->nr_folios &&
+		ceph_wbc->locked_pages < ceph_wbc->max_pages;
+}
 
-			/* only dirty pages, or our accounting breaks */
-			if (unlikely(!PageDirty(page)) ||
-			    unlikely(page->mapping != mapping)) {
-				dout("!dirty or !mapping %p\n", page);
-				unlock_page(page);
-				continue;
-			}
-			/* only if matching snap context */
-			pgsnapc = page_snap_context(page);
-			if (pgsnapc != snapc) {
-				dout("page snapc %p %lld != oldest %p %lld\n",
-				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);
-				if (!should_loop &&
-				    !ceph_wbc.head_snapc &&
-				    wbc->sync_mode != WB_SYNC_NONE)
-					should_loop = true;
-				unlock_page(page);
-				continue;
+static
+int ceph_check_page_before_write(struct address_space *mapping,
+				 struct writeback_control *wbc,
+				 struct ceph_writeback_ctl *ceph_wbc,
+				 struct folio *folio)
+{
+	struct inode *inode = mapping->host;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
+	struct ceph_snap_context *pgsnapc;
+
+	/* only dirty folios, or our accounting breaks */
+	if (unlikely(!folio_test_dirty(folio) || folio->mapping != mapping)) {
+		doutc(cl, "!dirty or !mapping %p\n", folio);
+		return -ENODATA;
+	}
+
+	/* only if matching snap context */
+	pgsnapc = page_snap_context(&folio->page);
+	if (pgsnapc != ceph_wbc->snapc) {
+		doutc(cl, "folio snapc %p %lld != oldest %p %lld\n",
+		      pgsnapc, pgsnapc->seq,
+		      ceph_wbc->snapc, ceph_wbc->snapc->seq);
+
+		if (!ceph_wbc->should_loop && !ceph_wbc->head_snapc &&
+		    wbc->sync_mode != WB_SYNC_NONE)
+			ceph_wbc->should_loop = true;
+
+		return -ENODATA;
+	}
+
+	if (folio_pos(folio) >= ceph_wbc->i_size) {
+		doutc(cl, "folio at %lu beyond eof %llu\n",
+		      folio->index, ceph_wbc->i_size);
+
+		if ((ceph_wbc->size_stable ||
+		    folio_pos(folio) >= i_size_read(inode)) &&
+		    folio_clear_dirty_for_io(folio))
+			folio_invalidate(folio, 0, folio_size(folio));
+
+		return -ENODATA;
+	}
+
+	if (ceph_wbc->strip_unit_end &&
+	    (folio->index > ceph_wbc->strip_unit_end)) {
+		doutc(cl, "end of strip unit %p\n", folio);
+		return -E2BIG;
+	}
+
+	return 0;
+}
+
+static inline
+void __ceph_allocate_page_array(struct ceph_writeback_ctl *ceph_wbc,
+				unsigned int max_pages)
+{
+	ceph_wbc->pages = kmalloc_array(max_pages,
+					sizeof(*ceph_wbc->pages),
+					GFP_NOFS);
+	if (!ceph_wbc->pages) {
+		ceph_wbc->from_pool = true;
+		ceph_wbc->pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
+		BUG_ON(!ceph_wbc->pages);
+	}
+}
+
+static inline
+void ceph_allocate_page_array(struct address_space *mapping,
+			      struct ceph_writeback_ctl *ceph_wbc,
+			      struct folio *folio)
+{
+	struct inode *inode = mapping->host;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	u64 objnum;
+	u64 objoff;
+	u32 xlen;
+
+	/* prepare async write request */
+	ceph_wbc->offset = (u64)folio_pos(folio);
+	ceph_calc_file_object_mapping(&ci->i_layout,
+					ceph_wbc->offset, ceph_wbc->wsize,
+					&objnum, &objoff, &xlen);
+
+	ceph_wbc->num_ops = 1;
+	ceph_wbc->strip_unit_end = folio->index + ((xlen - 1) >> PAGE_SHIFT);
+
+	BUG_ON(ceph_wbc->pages);
+	ceph_wbc->max_pages = calc_pages_for(0, (u64)xlen);
+	__ceph_allocate_page_array(ceph_wbc, ceph_wbc->max_pages);
+
+	ceph_wbc->len = 0;
+}
+
+static inline
+bool is_folio_index_contiguous(const struct ceph_writeback_ctl *ceph_wbc,
+			      const struct folio *folio)
+{
+	return folio->index == (ceph_wbc->offset + ceph_wbc->len) >> PAGE_SHIFT;
+}
+
+static inline
+bool is_num_ops_too_big(struct ceph_writeback_ctl *ceph_wbc)
+{
+	return ceph_wbc->num_ops >=
+		(ceph_wbc->from_pool ?  CEPH_OSD_SLAB_OPS : CEPH_OSD_MAX_OPS);
+}
+
+static inline
+bool is_write_congestion_happened(struct ceph_fs_client *fsc)
+{
+	return atomic_long_inc_return(&fsc->writeback_count) >
+		CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb);
+}
+
+static inline int move_dirty_folio_in_page_array(struct address_space *mapping,
+		struct writeback_control *wbc,
+		struct ceph_writeback_ctl *ceph_wbc, struct folio *folio)
+{
+	struct inode *inode = mapping->host;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
+	struct page **pages = ceph_wbc->pages;
+	unsigned int index = ceph_wbc->locked_pages;
+	gfp_t gfp_flags = ceph_wbc->locked_pages ? GFP_NOWAIT : GFP_NOFS;
+
+	if (IS_ENCRYPTED(inode)) {
+		pages[index] = fscrypt_encrypt_pagecache_blocks(folio,
+								PAGE_SIZE,
+								0,
+								gfp_flags);
+		if (IS_ERR(pages[index])) {
+			int err = PTR_ERR(pages[index]);
+
+			if (err == -EINVAL) {
+				pr_err_client(cl, "inode->i_blkbits=%hhu\n",
+						inode->i_blkbits);
 			}
-			if (page_offset(page) >= ceph_wbc.i_size) {
-				struct folio *folio = page_folio(page);
-
-				dout("folio at %lu beyond eof %llu\n",
-				     folio->index, ceph_wbc.i_size);
-				if ((ceph_wbc.size_stable ||
-				    folio_pos(folio) >= i_size_read(inode)) &&
-				    folio_clear_dirty_for_io(folio))
-					folio_invalidate(folio, 0,
-							folio_size(folio));
+
+			/* better not fail on first page! */
+			BUG_ON(ceph_wbc->locked_pages == 0);
+
+			pages[index] = NULL;
+			return err;
+		}
+	} else {
+		pages[index] = &folio->page;
+	}
+
+	ceph_wbc->locked_pages++;
+
+	return 0;
+}
+
+static
+int ceph_process_folio_batch(struct address_space *mapping,
+			     struct writeback_control *wbc,
+			     struct ceph_writeback_ctl *ceph_wbc)
+{
+	struct inode *inode = mapping->host;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
+	struct folio *folio = NULL;
+	unsigned i;
+	int rc = 0;
+
+	for (i = 0; can_next_page_be_processed(ceph_wbc, i); i++) {
+		folio = ceph_wbc->fbatch.folios[i];
+
+		if (!folio)
+			continue;
+
+		doutc(cl, "? %p idx %lu, folio_test_writeback %#x, "
+			"folio_test_dirty %#x, folio_test_locked %#x\n",
+			folio, folio->index, folio_test_writeback(folio),
+			folio_test_dirty(folio),
+			folio_test_locked(folio));
+
+		if (folio_test_writeback(folio) ||
+		    folio_test_private_2(folio) /* [DEPRECATED] */) {
+			doutc(cl, "waiting on writeback %p\n", folio);
+			folio_wait_writeback(folio);
+			folio_wait_private_2(folio); /* [DEPRECATED] */
+			continue;
+		}
+
+		if (ceph_wbc->locked_pages == 0)
+			folio_lock(folio);
+		else if (!folio_trylock(folio))
+			break;
+
+		rc = ceph_check_page_before_write(mapping, wbc,
+						  ceph_wbc, folio);
+		if (rc == -ENODATA) {
+			rc = 0;
+			folio_unlock(folio);
+			ceph_wbc->fbatch.folios[i] = NULL;
+			continue;
+		} else if (rc == -E2BIG) {
+			rc = 0;
+			folio_unlock(folio);
+			ceph_wbc->fbatch.folios[i] = NULL;
+			break;
+		}
+
+		if (!folio_clear_dirty_for_io(folio)) {
+			doutc(cl, "%p !folio_clear_dirty_for_io\n", folio);
+			folio_unlock(folio);
+			ceph_wbc->fbatch.folios[i] = NULL;
+			continue;
+		}
+
+		/*
+		 * We have something to write.  If this is
+		 * the first locked page this time through,
+		 * calculate max possible write size and
+		 * allocate a page array
+		 */
+		if (ceph_wbc->locked_pages == 0) {
+			ceph_allocate_page_array(mapping, ceph_wbc, folio);
+		} else if (!is_folio_index_contiguous(ceph_wbc, folio)) {
+			if (is_num_ops_too_big(ceph_wbc)) {
+				folio_redirty_for_writepage(wbc, folio);
 				folio_unlock(folio);
-				continue;
-			}
-			if (strip_unit_end && (page->index > strip_unit_end)) {
-				dout("end of strip unit %p\n", page);
-				unlock_page(page);
 				break;
 			}
-			if (PageWriteback(page) || PageFsCache(page)) {
-				if (wbc->sync_mode == WB_SYNC_NONE) {
-					dout("%p under writeback\n", page);
-					unlock_page(page);
-					continue;
-				}
-				dout("waiting on writeback %p\n", page);
-				wait_on_page_writeback(page);
-				wait_on_page_fscache(page);
-			}
 
-			if (!clear_page_dirty_for_io(page)) {
-				dout("%p !clear_page_dirty_for_io\n", page);
-				unlock_page(page);
-				continue;
-			}
+			ceph_wbc->num_ops++;
+			ceph_wbc->offset = (u64)folio_pos(folio);
+			ceph_wbc->len = 0;
+		}
 
-			/*
-			 * We have something to write.  If this is
-			 * the first locked page this time through,
-			 * calculate max possinle write size and
-			 * allocate a page array
-			 */
-			if (locked_pages == 0) {
-				u64 objnum;
-				u64 objoff;
-				u32 xlen;
-
-				/* prepare async write request */
-				offset = (u64)page_offset(page);
-				ceph_calc_file_object_mapping(&ci->i_layout,
-							      offset, wsize,
-							      &objnum, &objoff,
-							      &xlen);
-				len = xlen;
-
-				num_ops = 1;
-				strip_unit_end = page->index +
-					((len - 1) >> PAGE_SHIFT);
-
-				BUG_ON(pages);
-				max_pages = calc_pages_for(0, (u64)len);
-				pages = kmalloc_array(max_pages,
-						      sizeof(*pages),
-						      GFP_NOFS);
-				if (!pages) {
-					from_pool = true;
-					pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
-					BUG_ON(!pages);
-				}
-
-				len = 0;
-			} else if (page->index !=
-				   (offset + len) >> PAGE_SHIFT) {
-				if (num_ops >= (from_pool ?  CEPH_OSD_SLAB_OPS :
-							     CEPH_OSD_MAX_OPS)) {
-					redirty_page_for_writepage(wbc, page);
-					unlock_page(page);
-					break;
-				}
-
-				num_ops++;
-				offset = (u64)page_offset(page);
-				len = 0;
-			}
+		/* note position of first page in fbatch */
+		doutc(cl, "%llx.%llx will write folio %p idx %lu\n",
+		      ceph_vinop(inode), folio, folio->index);
 
-			/* note position of first page in pvec */
-			dout("%p will write page %p idx %lu\n",
-			     inode, page, page->index);
+		fsc->write_congested = is_write_congestion_happened(fsc);
 
-			if (atomic_long_inc_return(&fsc->writeback_count) >
-			    CONGESTION_ON_THRESH(
-				    fsc->mount_options->congestion_kb))
-				fsc->write_congested = true;
+		rc = move_dirty_folio_in_page_array(mapping, wbc, ceph_wbc,
+				folio);
+		if (rc) {
+			folio_redirty_for_writepage(wbc, folio);
+			folio_unlock(folio);
+			break;
+		}
 
-			pages[locked_pages++] = page;
-			pvec.pages[i] = NULL;
+		ceph_wbc->fbatch.folios[i] = NULL;
+		ceph_wbc->len += folio_size(folio);
+	}
 
-			len += thp_size(page);
-		}
+	ceph_wbc->processed_in_fbatch = i;
 
-		/* did we get anything? */
-		if (!locked_pages)
-			goto release_pvec_pages;
-		if (i) {
-			unsigned j, n = 0;
-			/* shift unused page to beginning of pvec */
-			for (j = 0; j < pvec_pages; j++) {
-				if (!pvec.pages[j])
-					continue;
-				if (n < j)
-					pvec.pages[n] = pvec.pages[j];
-				n++;
-			}
-			pvec.nr = n;
+	return rc;
+}
 
-			if (pvec_pages && i == pvec_pages &&
-			    locked_pages < max_pages) {
-				dout("reached end pvec, trying for more\n");
-				pagevec_release(&pvec);
-				goto get_more_pages;
-			}
+static inline
+void ceph_shift_unused_folios_left(struct folio_batch *fbatch)
+{
+	unsigned j, n = 0;
+
+	/* shift unused page to beginning of fbatch */
+	for (j = 0; j < folio_batch_count(fbatch); j++) {
+		if (!fbatch->folios[j])
+			continue;
+
+		if (n < j) {
+			fbatch->folios[n] = fbatch->folios[j];
 		}
 
+		n++;
+	}
+
+	fbatch->nr = n;
+}
+
+static
+int ceph_submit_write(struct address_space *mapping,
+			struct writeback_control *wbc,
+			struct ceph_writeback_ctl *ceph_wbc)
+{
+	struct inode *inode = mapping->host;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
+	struct ceph_vino vino = ceph_vino(inode);
+	struct ceph_osd_request *req = NULL;
+	struct page *page = NULL;
+	bool caching = ceph_is_cache_enabled(inode);
+	u64 offset;
+	u64 len;
+	unsigned i;
+
 new_request:
-		offset = page_offset(pages[0]);
-		len = wsize;
+	offset = ceph_fscrypt_page_offset(ceph_wbc->pages[0]);
+	len = ceph_wbc->wsize;
 
+	req = ceph_osdc_new_request(&fsc->client->osdc,
+				    &ci->i_layout, vino,
+				    offset, &len, 0, ceph_wbc->num_ops,
+				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
+				    ceph_wbc->snapc, ceph_wbc->truncate_seq,
+				    ceph_wbc->truncate_size, false);
+	if (IS_ERR(req)) {
 		req = ceph_osdc_new_request(&fsc->client->osdc,
-					&ci->i_layout, vino,
-					offset, &len, 0, num_ops,
-					CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
-					snapc, ceph_wbc.truncate_seq,
-					ceph_wbc.truncate_size, false);
-		if (IS_ERR(req)) {
-			req = ceph_osdc_new_request(&fsc->client->osdc,
-						&ci->i_layout, vino,
-						offset, &len, 0,
-						min(num_ops,
-						    CEPH_OSD_SLAB_OPS),
-						CEPH_OSD_OP_WRITE,
-						CEPH_OSD_FLAG_WRITE,
-						snapc, ceph_wbc.truncate_seq,
-						ceph_wbc.truncate_size, true);
-			BUG_ON(IS_ERR(req));
+					    &ci->i_layout, vino,
+					    offset, &len, 0,
+					    min(ceph_wbc->num_ops,
+						CEPH_OSD_SLAB_OPS),
+					    CEPH_OSD_OP_WRITE,
+					    CEPH_OSD_FLAG_WRITE,
+					    ceph_wbc->snapc,
+					    ceph_wbc->truncate_seq,
+					    ceph_wbc->truncate_size,
+					    true);
+		BUG_ON(IS_ERR(req));
+	}
+
+	page = ceph_wbc->pages[ceph_wbc->locked_pages - 1];
+	BUG_ON(len < ceph_fscrypt_page_offset(page) + thp_size(page) - offset);
+
+	if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
+		for (i = 0; i < folio_batch_count(&ceph_wbc->fbatch); i++) {
+			struct folio *folio = ceph_wbc->fbatch.folios[i];
+
+			if (!folio)
+				continue;
+
+			page = &folio->page;
+			redirty_page_for_writepage(wbc, page);
+			unlock_page(page);
 		}
-		BUG_ON(len < page_offset(pages[locked_pages - 1]) +
-			     thp_size(page) - offset);
-
-		req->r_callback = writepages_finish;
-		req->r_inode = inode;
-
-		/* Format the osd request message and submit the write */
-		len = 0;
-		data_pages = pages;
-		op_idx = 0;
-		for (i = 0; i < locked_pages; i++) {
-			u64 cur_offset = page_offset(pages[i]);
-			/*
-			 * Discontinuity in page range? Ceph can handle that by just passing
-			 * multiple extents in the write op.
-			 */
-			if (offset + len != cur_offset) {
-				/* If it's full, stop here */
-				if (op_idx + 1 == req->r_num_ops)
-					break;
-
-				/* Kick off an fscache write with what we have so far. */
-				ceph_fscache_write_to_cache(inode, offset, len, caching);
-
-				/* Start a new extent */
-				osd_req_op_extent_dup_last(req, op_idx,
-							   cur_offset - offset);
-				dout("writepages got pages at %llu~%llu\n",
-				     offset, len);
-				osd_req_op_extent_osd_data_pages(req, op_idx,
-							data_pages, len, 0,
-							from_pool, false);
-				osd_req_op_extent_update(req, op_idx, len);
-
-				len = 0;
-				offset = cur_offset;
-				data_pages = pages + i;
-				op_idx++;
-			}
 
-			set_page_writeback(pages[i]);
-			if (caching)
-				ceph_set_page_fscache(pages[i]);
-			len += thp_size(page);
+		for (i = 0; i < ceph_wbc->locked_pages; i++) {
+			page = ceph_fscrypt_pagecache_page(ceph_wbc->pages[i]);
+
+			if (!page)
+				continue;
+
+			redirty_page_for_writepage(wbc, page);
+			unlock_page(page);
 		}
-		ceph_fscache_write_to_cache(inode, offset, len, caching);
-
-		if (ceph_wbc.size_stable) {
-			len = min(len, ceph_wbc.i_size - offset);
-		} else if (i == locked_pages) {
-			/* writepages_finish() clears writeback pages
-			 * according to the data length, so make sure
-			 * data length covers all locked pages */
-			u64 min_len = len + 1 - thp_size(page);
-			len = get_writepages_data_length(inode, pages[i - 1],
-							 offset);
-			len = max(len, min_len);
+
+		ceph_osdc_put_request(req);
+		return -EIO;
+	}
+
+	req->r_callback = writepages_finish;
+	req->r_inode = inode;
+
+	/* Format the osd request message and submit the write */
+	len = 0;
+	ceph_wbc->data_pages = ceph_wbc->pages;
+	ceph_wbc->op_idx = 0;
+	for (i = 0; i < ceph_wbc->locked_pages; i++) {
+		u64 cur_offset;
+
+		page = ceph_fscrypt_pagecache_page(ceph_wbc->pages[i]);
+		cur_offset = page_offset(page);
+
+		/*
+		 * Discontinuity in page range? Ceph can handle that by just passing
+		 * multiple extents in the write op.
+		 */
+		if (offset + len != cur_offset) {
+			/* If it's full, stop here */
+			if (ceph_wbc->op_idx + 1 == req->r_num_ops)
+				break;
+
+			/* Kick off an fscache write with what we have so far. */
+			ceph_fscache_write_to_cache(inode, offset, len, caching);
+
+			/* Start a new extent */
+			osd_req_op_extent_dup_last(req, ceph_wbc->op_idx,
+						   cur_offset - offset);
+
+			doutc(cl, "got pages at %llu~%llu\n", offset, len);
+
+			osd_req_op_extent_osd_data_pages(req, ceph_wbc->op_idx,
+							 ceph_wbc->data_pages,
+							 len, 0,
+							 ceph_wbc->from_pool,
+							 false);
+			osd_req_op_extent_update(req, ceph_wbc->op_idx, len);
+
+			len = 0;
+			offset = cur_offset;
+			ceph_wbc->data_pages = ceph_wbc->pages + i;
+			ceph_wbc->op_idx++;
 		}
-		dout("writepages got pages at %llu~%llu\n", offset, len);
-
-		osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
-						 0, from_pool, false);
-		osd_req_op_extent_update(req, op_idx, len);
-
-		BUG_ON(op_idx + 1 != req->r_num_ops);
-
-		from_pool = false;
-		if (i < locked_pages) {
-			BUG_ON(num_ops <= req->r_num_ops);
-			num_ops -= req->r_num_ops;
-			locked_pages -= i;
-
-			/* allocate new pages array for next request */
-			data_pages = pages;
-			pages = kmalloc_array(locked_pages, sizeof(*pages),
-					      GFP_NOFS);
-			if (!pages) {
-				from_pool = true;
-				pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
-				BUG_ON(!pages);
+
+		set_page_writeback(page);
+
+		if (caching)
+			ceph_set_page_fscache(page);
+
+		len += thp_size(page);
+	}
+
+	ceph_fscache_write_to_cache(inode, offset, len, caching);
+
+	if (ceph_wbc->size_stable) {
+		len = min(len, ceph_wbc->i_size - offset);
+	} else if (i == ceph_wbc->locked_pages) {
+		/* writepages_finish() clears writeback pages
+		 * according to the data length, so make sure
+		 * data length covers all locked pages */
+		u64 min_len = len + 1 - thp_size(page);
+		len = get_writepages_data_length(inode,
+						 ceph_wbc->pages[i - 1],
+						 offset);
+		len = max(len, min_len);
+	}
+
+	if (IS_ENCRYPTED(inode))
+		len = round_up(len, CEPH_FSCRYPT_BLOCK_SIZE);
+
+	doutc(cl, "got pages at %llu~%llu\n", offset, len);
+
+	if (IS_ENCRYPTED(inode) &&
+	    ((offset | len) & ~CEPH_FSCRYPT_BLOCK_MASK)) {
+		pr_warn_client(cl,
+			"bad encrypted write offset=%lld len=%llu\n",
+			offset, len);
+	}
+
+	osd_req_op_extent_osd_data_pages(req, ceph_wbc->op_idx,
+					 ceph_wbc->data_pages, len,
+					 0, ceph_wbc->from_pool, false);
+	osd_req_op_extent_update(req, ceph_wbc->op_idx, len);
+
+	BUG_ON(ceph_wbc->op_idx + 1 != req->r_num_ops);
+
+	ceph_wbc->from_pool = false;
+	if (i < ceph_wbc->locked_pages) {
+		BUG_ON(ceph_wbc->num_ops <= req->r_num_ops);
+		ceph_wbc->num_ops -= req->r_num_ops;
+		ceph_wbc->locked_pages -= i;
+
+		/* allocate new pages array for next request */
+		ceph_wbc->data_pages = ceph_wbc->pages;
+		__ceph_allocate_page_array(ceph_wbc, ceph_wbc->locked_pages);
+		memcpy(ceph_wbc->pages, ceph_wbc->data_pages + i,
+			ceph_wbc->locked_pages * sizeof(*ceph_wbc->pages));
+		memset(ceph_wbc->data_pages + i, 0,
+			ceph_wbc->locked_pages * sizeof(*ceph_wbc->pages));
+	} else {
+		BUG_ON(ceph_wbc->num_ops != req->r_num_ops);
+		/* request message now owns the pages array */
+		ceph_wbc->pages = NULL;
+	}
+
+	req->r_mtime = inode_get_mtime(inode);
+	ceph_osdc_start_request(&fsc->client->osdc, req);
+	req = NULL;
+
+	wbc->nr_to_write -= i;
+	if (ceph_wbc->pages)
+		goto new_request;
+
+	return 0;
+}
+
+static
+void ceph_wait_until_current_writes_complete(struct address_space *mapping,
+					     struct writeback_control *wbc,
+					     struct ceph_writeback_ctl *ceph_wbc)
+{
+	struct page *page;
+	unsigned i, nr;
+
+	if (wbc->sync_mode != WB_SYNC_NONE &&
+	    ceph_wbc->start_index == 0 && /* all dirty pages were checked */
+	    !ceph_wbc->head_snapc) {
+		ceph_wbc->index = 0;
+
+		while ((ceph_wbc->index <= ceph_wbc->end) &&
+			(nr = filemap_get_folios_tag(mapping,
+						     &ceph_wbc->index,
+						     (pgoff_t)-1,
+						     PAGECACHE_TAG_WRITEBACK,
+						     &ceph_wbc->fbatch))) {
+			for (i = 0; i < nr; i++) {
+				page = &ceph_wbc->fbatch.folios[i]->page;
+				if (page_snap_context(page) != ceph_wbc->snapc)
+					continue;
+				wait_on_page_writeback(page);
 			}
-			memcpy(pages, data_pages + i,
-			       locked_pages * sizeof(*pages));
-			memset(data_pages + i, 0,
-			       locked_pages * sizeof(*pages));
-		} else {
-			BUG_ON(num_ops != req->r_num_ops);
-			index = pages[i - 1]->index + 1;
-			/* request message now owns the pages array */
-			pages = NULL;
+
+			folio_batch_release(&ceph_wbc->fbatch);
+			cond_resched();
 		}
+	}
+}
 
-		req->r_mtime = inode->i_mtime;
-		ceph_osdc_start_request(&fsc->client->osdc, req);
-		req = NULL;
+/*
+ * initiate async writeback
+ */
+static int ceph_writepages_start(struct address_space *mapping,
+				 struct writeback_control *wbc)
+{
+	struct inode *inode = mapping->host;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
+	struct ceph_writeback_ctl ceph_wbc;
+	int rc = 0;
+
+	if (wbc->sync_mode == WB_SYNC_NONE && fsc->write_congested)
+		return 0;
+
+	doutc(cl, "%llx.%llx (mode=%s)\n", ceph_vinop(inode),
+	      wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
+	      (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
+
+	if (is_forced_umount(mapping)) {
+		/* we're in a forced umount, don't write! */
+		return -EIO;
+	}
+
+	ceph_init_writeback_ctl(mapping, wbc, &ceph_wbc);
+
+	if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
+		rc = -EIO;
+		goto out;
+	}
+
+retry:
+	rc = ceph_define_writeback_range(mapping, wbc, &ceph_wbc);
+	if (rc == -ENODATA) {
+		/* hmm, why does writepages get called when there
+		   is no dirty data? */
+		rc = 0;
+		goto dec_osd_stopping_blocker;
+	}
+
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+		tag_pages_for_writeback(mapping, ceph_wbc.index, ceph_wbc.end);
+
+	while (!has_writeback_done(&ceph_wbc)) {
+		ceph_wbc.locked_pages = 0;
+		ceph_wbc.max_pages = ceph_wbc.wsize >> PAGE_SHIFT;
+
+get_more_pages:
+		ceph_folio_batch_reinit(&ceph_wbc);
+
+		ceph_wbc.nr_folios = filemap_get_folios_tag(mapping,
+							    &ceph_wbc.index,
+							    ceph_wbc.end,
+							    ceph_wbc.tag,
+							    &ceph_wbc.fbatch);
+		doutc(cl, "pagevec_lookup_range_tag for tag %#x got %d\n",
+			ceph_wbc.tag, ceph_wbc.nr_folios);
+
+		if (!ceph_wbc.nr_folios && !ceph_wbc.locked_pages)
+			break;
+
+process_folio_batch:
+		rc = ceph_process_folio_batch(mapping, wbc, &ceph_wbc);
+		ceph_shift_unused_folios_left(&ceph_wbc.fbatch);
+		if (rc)
+			goto release_folios;
 
-		wbc->nr_to_write -= i;
-		if (pages)
-			goto new_request;
+		/* did we get anything? */
+		if (!ceph_wbc.locked_pages)
+			goto release_folios;
+
+		if (ceph_wbc.processed_in_fbatch) {
+			if (folio_batch_count(&ceph_wbc.fbatch) == 0 &&
+			    ceph_wbc.locked_pages < ceph_wbc.max_pages) {
+				doutc(cl, "reached end fbatch, trying for more\n");
+				goto get_more_pages;
+			}
+		}
+
+		rc = ceph_submit_write(mapping, wbc, &ceph_wbc);
+		if (rc)
+			goto release_folios;
+
+		ceph_wbc.locked_pages = 0;
+		ceph_wbc.strip_unit_end = 0;
+
+		if (folio_batch_count(&ceph_wbc.fbatch) > 0) {
+			ceph_wbc.nr_folios =
+				folio_batch_count(&ceph_wbc.fbatch);
+			goto process_folio_batch;
+		}
 
 		/*
 		 * We stop writing back only if we are not doing
@@ -1162,58 +1721,44 @@ new_request:
 		 * we tagged for writeback prior to entering this loop.
 		 */
 		if (wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE)
-			done = true;
+			ceph_wbc.done = true;
 
-release_pvec_pages:
-		dout("pagevec_release on %d pages (%p)\n", (int)pvec.nr,
-		     pvec.nr ? pvec.pages[0] : NULL);
-		pagevec_release(&pvec);
+release_folios:
+		doutc(cl, "folio_batch release on %d folios (%p)\n",
+		      (int)ceph_wbc.fbatch.nr,
+		      ceph_wbc.fbatch.nr ? ceph_wbc.fbatch.folios[0] : NULL);
+		folio_batch_release(&ceph_wbc.fbatch);
 	}
 
-	if (should_loop && !done) {
+	if (ceph_wbc.should_loop && !ceph_wbc.done) {
 		/* more to do; loop back to beginning of file */
-		dout("writepages looping back to beginning of file\n");
-		end = start_index - 1; /* OK even when start_index == 0 */
+		doutc(cl, "looping back to beginning of file\n");
+		/* OK even when start_index == 0 */
+		ceph_wbc.end = ceph_wbc.start_index - 1;
 
 		/* to write dirty pages associated with next snapc,
 		 * we need to wait until current writes complete */
-		if (wbc->sync_mode != WB_SYNC_NONE &&
-		    start_index == 0 && /* all dirty pages were checked */
-		    !ceph_wbc.head_snapc) {
-			struct page *page;
-			unsigned i, nr;
-			index = 0;
-			while ((index <= end) &&
-			       (nr = pagevec_lookup_tag(&pvec, mapping, &index,
-						PAGECACHE_TAG_WRITEBACK))) {
-				for (i = 0; i < nr; i++) {
-					page = pvec.pages[i];
-					if (page_snap_context(page) != snapc)
-						continue;
-					wait_on_page_writeback(page);
-				}
-				pagevec_release(&pvec);
-				cond_resched();
-			}
-		}
+		ceph_wait_until_current_writes_complete(mapping, wbc, &ceph_wbc);
 
-		start_index = 0;
-		index = 0;
+		ceph_wbc.start_index = 0;
+		ceph_wbc.index = 0;
 		goto retry;
 	}
 
-	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-		mapping->writeback_index = index;
+	if (wbc->range_cyclic || (ceph_wbc.range_whole && wbc->nr_to_write > 0))
+		mapping->writeback_index = ceph_wbc.index;
+
+dec_osd_stopping_blocker:
+	ceph_dec_osd_stopping_blocker(fsc->mdsc);
 
 out:
-	ceph_osdc_put_request(req);
-	ceph_put_snap_context(last_snapc);
-	dout("writepages dend - startone, rc = %d\n", rc);
+	ceph_put_snap_context(ceph_wbc.last_snapc);
+	doutc(cl, "%llx.%llx dend - startone, rc = %d\n", ceph_vinop(inode),
+	      rc);
+
 	return rc;
 }
 
-
-
 /*
  * See if a given @snapc is either writeable, or already written.
  */
@@ -1229,53 +1774,56 @@ static int context_is_writeable_or_written(struct inode *inode,
 
 /**
  * ceph_find_incompatible - find an incompatible context and return it
- * @page: page being dirtied
+ * @folio: folio being dirtied
  *
- * We are only allowed to write into/dirty a page if the page is
+ * We are only allowed to write into/dirty a folio if the folio is
  * clean, or already dirty within the same snap context. Returns a
  * conflicting context if there is one, NULL if there isn't, or a
  * negative error code on other errors.
  *
- * Must be called with page lock held.
+ * Must be called with folio lock held.
  */
 static struct ceph_snap_context *
-ceph_find_incompatible(struct page *page)
+ceph_find_incompatible(struct folio *folio)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
 	if (ceph_inode_is_shutdown(inode)) {
-		dout(" page %p %llx:%llx is shutdown\n", page,
-		     ceph_vinop(inode));
+		doutc(cl, " %llx.%llx folio %p is shutdown\n",
+		      ceph_vinop(inode), folio);
 		return ERR_PTR(-ESTALE);
 	}
 
 	for (;;) {
 		struct ceph_snap_context *snapc, *oldest;
 
-		wait_on_page_writeback(page);
+		folio_wait_writeback(folio);
 
-		snapc = page_snap_context(page);
+		snapc = page_snap_context(&folio->page);
 		if (!snapc || snapc == ci->i_head_snapc)
 			break;
 
 		/*
-		 * this page is already dirty in another (older) snap
+		 * this folio is already dirty in another (older) snap
 		 * context!  is it writeable now?
 		 */
 		oldest = get_oldest_context(inode, NULL, NULL);
 		if (snapc->seq > oldest->seq) {
 			/* not writeable -- return it for the caller to deal with */
 			ceph_put_snap_context(oldest);
-			dout(" page %p snapc %p not current or oldest\n", page, snapc);
+			doutc(cl, " %llx.%llx folio %p snapc %p not current or oldest\n",
+			      ceph_vinop(inode), folio, snapc);
 			return ceph_get_snap_context(snapc);
 		}
 		ceph_put_snap_context(oldest);
 
-		/* yay, writeable, do it now (without dropping page lock) */
-		dout(" page %p snapc %p not current, but oldest\n", page, snapc);
-		if (clear_page_dirty_for_io(page)) {
-			int r = writepage_nounlock(page, NULL);
+		/* yay, writeable, do it now (without dropping folio lock) */
+		doutc(cl, " %llx.%llx folio %p snapc %p not current, but oldest\n",
+		      ceph_vinop(inode), folio, snapc);
+		if (folio_clear_dirty_for_io(folio)) {
+			int r = write_folio_nounlock(folio, NULL);
 			if (r < 0)
 				return ERR_PTR(r);
 		}
@@ -1290,7 +1838,7 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_snap_context *snapc;
 
-	snapc = ceph_find_incompatible(folio_page(*foliop, 0));
+	snapc = ceph_find_incompatible(*foliop);
 	if (snapc) {
 		int r;
 
@@ -1313,22 +1861,22 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
  * We are only allowed to write into/dirty the page if the page is
  * clean, or already dirty within the same snap context.
  */
-static int ceph_write_begin(struct file *file, struct address_space *mapping,
+static int ceph_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned len,
-			    struct page **pagep, void **fsdata)
+			    struct folio **foliop, void **fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct folio *folio = NULL;
 	int r;
 
-	r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
+	r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, foliop, NULL);
 	if (r < 0)
 		return r;
 
-	folio_wait_fscache(folio);
-	WARN_ON_ONCE(!folio_test_locked(folio));
-	*pagep = &folio->page;
+	folio_wait_private_2(*foliop); /* [DEPRECATED] */
+	WARN_ON_ONCE(!folio_test_locked(*foliop));
 	return 0;
 }
 
@@ -1336,16 +1884,18 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
  * we don't do anything in here that simple_write_end doesn't do
  * except adjust dirty page accounting
  */
-static int ceph_write_end(struct file *file, struct address_space *mapping,
-			  loff_t pos, unsigned len, unsigned copied,
-			  struct page *subpage, void *fsdata)
+static int ceph_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping, loff_t pos,
+			  unsigned len, unsigned copied,
+			  struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(subpage);
+	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	bool check_cap = false;
 
-	dout("write_end file %p inode %p folio %p %d~%d (%d)\n", file,
-	     inode, folio, (int)pos, (int)copied, (int)len);
+	doutc(cl, "%llx.%llx file %p folio %p %d~%d (%d)\n", ceph_vinop(inode),
+	      file, folio, (int)pos, (int)copied, (int)len);
 
 	if (!folio_test_uptodate(folio)) {
 		/* just return that nothing was copied on a short copy */
@@ -1375,14 +1925,14 @@ out:
 const struct address_space_operations ceph_aops = {
 	.read_folio = netfs_read_folio,
 	.readahead = netfs_readahead,
-	.writepage = ceph_writepage,
 	.writepages = ceph_writepages_start,
 	.write_begin = ceph_write_begin,
 	.write_end = ceph_write_end,
 	.dirty_folio = ceph_dirty_folio,
 	.invalidate_folio = ceph_invalidate_folio,
-	.release_folio = ceph_release_folio,
+	.release_folio = netfs_release_folio,
 	.direct_IO = noop_direct_IO,
+	.migrate_folio = filemap_migrate_folio,
 };
 
 static void ceph_block_sigs(sigset_t *oldset)
@@ -1405,6 +1955,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_file_info *fi = vma->vm_file->private_data;
 	loff_t off = (loff_t)vmf->pgoff << PAGE_SHIFT;
 	int want, got, err;
@@ -1416,8 +1967,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 
 	ceph_block_sigs(&oldset);
 
-	dout("filemap_fault %p %llx.%llx %llu trying to get caps\n",
-	     inode, ceph_vinop(inode), off);
+	doutc(cl, "%llx.%llx %llu trying to get caps\n",
+	      ceph_vinop(inode), off);
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
 		want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
 	else
@@ -1428,8 +1979,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 	if (err < 0)
 		goto out_restore;
 
-	dout("filemap_fault %p %llu got cap refs on %s\n",
-	     inode, off, ceph_cap_string(got));
+	doutc(cl, "%llx.%llx %llu got cap refs on %s\n", ceph_vinop(inode),
+	      off, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
 	    !ceph_has_inline_data(ci)) {
@@ -1437,8 +1988,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		ceph_add_rw_context(fi, &rw_ctx);
 		ret = filemap_fault(vmf);
 		ceph_del_rw_context(fi, &rw_ctx);
-		dout("filemap_fault %p %llu drop cap refs %s ret %x\n",
-		     inode, off, ceph_cap_string(got), ret);
+		doutc(cl, "%llx.%llx %llu drop cap refs %s ret %x\n",
+		      ceph_vinop(inode), off, ceph_cap_string(got), ret);
 	} else
 		err = -EAGAIN;
 
@@ -1479,8 +2030,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
 out_inline:
 		filemap_invalidate_unlock_shared(mapping);
-		dout("filemap_fault %p %llu read inline data ret %x\n",
-		     inode, off, ret);
+		doutc(cl, "%llx.%llx %llu read inline data ret %x\n",
+		      ceph_vinop(inode), off, ret);
 	}
 out_restore:
 	ceph_restore_sigs(&oldset);
@@ -1494,11 +2045,12 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_info *fi = vma->vm_file->private_data;
 	struct ceph_cap_flush *prealloc_cf;
-	struct page *page = vmf->page;
-	loff_t off = page_offset(page);
+	struct folio *folio = page_folio(vmf->page);
+	loff_t off = folio_pos(folio);
 	loff_t size = i_size_read(inode);
 	size_t len;
 	int want, got, err;
@@ -1515,13 +2067,13 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 	ceph_block_sigs(&oldset);
 
-	if (off + thp_size(page) <= size)
-		len = thp_size(page);
+	if (off + folio_size(folio) <= size)
+		len = folio_size(folio);
 	else
-		len = offset_in_thp(page, size);
+		len = offset_in_folio(folio, size);
 
-	dout("page_mkwrite %p %llx.%llx %llu~%zd getting caps i_size %llu\n",
-	     inode, ceph_vinop(inode), off, len, size);
+	doutc(cl, "%llx.%llx %llu~%zd getting caps i_size %llu\n",
+	      ceph_vinop(inode), off, len, size);
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
 		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
 	else
@@ -1532,33 +2084,33 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 	if (err < 0)
 		goto out_free;
 
-	dout("page_mkwrite %p %llu~%zd got cap refs on %s\n",
-	     inode, off, len, ceph_cap_string(got));
+	doutc(cl, "%llx.%llx %llu~%zd got cap refs on %s\n", ceph_vinop(inode),
+	      off, len, ceph_cap_string(got));
 
-	/* Update time before taking page lock */
+	/* Update time before taking folio lock */
 	file_update_time(vma->vm_file);
 	inode_inc_iversion_raw(inode);
 
 	do {
 		struct ceph_snap_context *snapc;
 
-		lock_page(page);
+		folio_lock(folio);
 
-		if (page_mkwrite_check_truncate(page, inode) < 0) {
-			unlock_page(page);
+		if (folio_mkwrite_check_truncate(folio, inode) < 0) {
+			folio_unlock(folio);
 			ret = VM_FAULT_NOPAGE;
 			break;
 		}
 
-		snapc = ceph_find_incompatible(page);
+		snapc = ceph_find_incompatible(folio);
 		if (!snapc) {
-			/* success.  we'll keep the page locked. */
-			set_page_dirty(page);
+			/* success.  we'll keep the folio locked. */
+			folio_mark_dirty(folio);
 			ret = VM_FAULT_LOCKED;
 			break;
 		}
 
-		unlock_page(page);
+		folio_unlock(folio);
 
 		if (IS_ERR(snapc)) {
 			ret = VM_FAULT_SIGBUS;
@@ -1581,8 +2133,8 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 			__mark_inode_dirty(inode, dirty);
 	}
 
-	dout("page_mkwrite %p %llu~%zd dropping cap refs on %s ret %x\n",
-	     inode, off, len, ceph_cap_string(got), ret);
+	doutc(cl, "%llx.%llx %llu~%zd dropping cap refs on %s ret %x\n",
+	      ceph_vinop(inode), off, len, ceph_cap_string(got), ret);
 	ceph_put_cap_refs_async(ci, got);
 out_free:
 	ceph_restore_sigs(&oldset);
@@ -1596,6 +2148,7 @@ out_free:
 void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 			   char	*data, size_t len)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 
@@ -1616,8 +2169,8 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 		}
 	}
 
-	dout("fill_inline_data %p %llx.%llx len %zu locked_page %p\n",
-	     inode, ceph_vinop(inode), len, locked_page);
+	doutc(cl, "%p %llx.%llx len %zu locked_page %p\n", inode,
+	      ceph_vinop(inode), len, locked_page);
 
 	if (len > 0) {
 		void *kaddr = kmap_atomic(page);
@@ -1641,9 +2194,10 @@ int ceph_uninline_data(struct file *file)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_request *req = NULL;
-	struct ceph_cap_flush *prealloc_cf;
+	struct ceph_cap_flush *prealloc_cf = NULL;
 	struct folio *folio = NULL;
 	u64 inline_version = CEPH_INLINE_NONE;
 	struct page *pages[1];
@@ -1654,8 +2208,13 @@ int ceph_uninline_data(struct file *file)
 	inline_version = ci->i_inline_version;
 	spin_unlock(&ci->i_ceph_lock);
 
-	dout("uninline_data %p %llx.%llx inline_version %llu\n",
-	     inode, ceph_vinop(inode), inline_version);
+	doutc(cl, "%llx.%llx inline_version %llu\n", ceph_vinop(inode),
+	      inline_version);
+
+	if (ceph_inode_is_shutdown(inode)) {
+		err = -EIO;
+		goto out;
+	}
 
 	if (inline_version == CEPH_INLINE_NONE)
 		return 0;
@@ -1688,7 +2247,7 @@ int ceph_uninline_data(struct file *file)
 		goto out_unlock;
 	}
 
-	req->r_mtime = inode->i_mtime;
+	req->r_mtime = inode_get_mtime(inode);
 	ceph_osdc_start_request(&fsc->client->osdc, req);
 	err = ceph_osdc_wait_request(&fsc->client->osdc, req);
 	ceph_osdc_put_request(req);
@@ -1730,7 +2289,7 @@ int ceph_uninline_data(struct file *file)
 			goto out_put_req;
 	}
 
-	req->r_mtime = inode->i_mtime;
+	req->r_mtime = inode_get_mtime(inode);
 	ceph_osdc_start_request(&fsc->client->osdc, req);
 	err = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
@@ -1762,8 +2321,8 @@ out_unlock:
 	}
 out:
 	ceph_free_cap_flush(prealloc_cf);
-	dout("uninline_data %p %llx.%llx inline_version %llu = %d\n",
-	     inode, ceph_vinop(inode), inline_version, err);
+	doutc(cl, "%llx.%llx inline_version %llu = %d\n",
+	      ceph_vinop(inode), inline_version, err);
 	return err;
 }
 
@@ -1772,13 +2331,13 @@ static const struct vm_operations_struct ceph_vmops = {
 	.page_mkwrite	= ceph_page_mkwrite,
 };
 
-int ceph_mmap(struct file *file, struct vm_area_struct *vma)
+int ceph_mmap_prepare(struct vm_area_desc *desc)
 {
-	struct address_space *mapping = file->f_mapping;
+	struct address_space *mapping = desc->file->f_mapping;
 
 	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
-	vma->vm_ops = &ceph_vmops;
+	desc->vm_ops = &ceph_vmops;
 	return 0;
 }
 
@@ -1790,8 +2349,9 @@ enum {
 static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 				s64 pool, struct ceph_string *pool_ns)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->netfs.inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(&ci->netfs.inode);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_request *rd_req = NULL, *wr_req = NULL;
 	struct rb_node **p, *parent;
 	struct ceph_pool_perm *perm;
@@ -1826,10 +2386,10 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 		goto out;
 
 	if (pool_ns)
-		dout("__ceph_pool_perm_get pool %lld ns %.*s no perm cached\n",
-		     pool, (int)pool_ns->len, pool_ns->str);
+		doutc(cl, "pool %lld ns %.*s no perm cached\n", pool,
+		      (int)pool_ns->len, pool_ns->str);
 	else
-		dout("__ceph_pool_perm_get pool %lld no perm cached\n", pool);
+		doutc(cl, "pool %lld no perm cached\n", pool);
 
 	down_write(&mdsc->pool_perm_rwsem);
 	p = &mdsc->pool_perm_tree.rb_node;
@@ -1905,7 +2465,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 				     0, false, true);
 	ceph_osdc_start_request(&fsc->client->osdc, rd_req);
 
-	wr_req->r_mtime = ci->netfs.inode.i_mtime;
+	wr_req->r_mtime = inode_get_mtime(&ci->netfs.inode);
 	ceph_osdc_start_request(&fsc->client->osdc, wr_req);
 
 	err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
@@ -1929,7 +2489,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 	}
 
 	pool_ns_len = pool_ns ? pool_ns->len : 0;
-	perm = kmalloc(sizeof(*perm) + pool_ns_len + 1, GFP_NOFS);
+	perm = kmalloc(struct_size(perm, pool_ns, pool_ns_len + 1), GFP_NOFS);
 	if (!perm) {
 		err = -ENOMEM;
 		goto out_unlock;
@@ -1954,15 +2514,16 @@ out:
 	if (!err)
 		err = have;
 	if (pool_ns)
-		dout("__ceph_pool_perm_get pool %lld ns %.*s result = %d\n",
-		     pool, (int)pool_ns->len, pool_ns->str, err);
+		doutc(cl, "pool %lld ns %.*s result = %d\n", pool,
+		      (int)pool_ns->len, pool_ns->str, err);
 	else
-		dout("__ceph_pool_perm_get pool %lld result = %d\n", pool, err);
+		doutc(cl, "pool %lld result = %d\n", pool, err);
 	return err;
 }
 
 int ceph_pool_perm_check(struct inode *inode, int need)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_string *pool_ns;
 	s64 pool;
@@ -1975,13 +2536,13 @@ int ceph_pool_perm_check(struct inode *inode, int need)
 	if (ci->i_vino.snap != CEPH_NOSNAP) {
 		/*
 		 * Pool permission check needs to write to the first object.
-		 * But for snapshot, head of the first object may have alread
+		 * But for snapshot, head of the first object may have already
 		 * been deleted. Skip check to avoid creating orphan object.
 		 */
 		return 0;
 	}
 
-	if (ceph_test_mount_opt(ceph_inode_to_client(inode),
+	if (ceph_test_mount_opt(ceph_inode_to_fs_client(inode),
 				NOPOOLPERM))
 		return 0;
 
@@ -1992,13 +2553,11 @@ int ceph_pool_perm_check(struct inode *inode, int need)
 check:
 	if (flags & CEPH_I_POOL_PERM) {
 		if ((need & CEPH_CAP_FILE_RD) && !(flags & CEPH_I_POOL_RD)) {
-			dout("ceph_pool_perm_check pool %lld no read perm\n",
-			     pool);
+			doutc(cl, "pool %lld no read perm\n", pool);
 			return -EPERM;
 		}
 		if ((need & CEPH_CAP_FILE_WR) && !(flags & CEPH_I_POOL_WR)) {
-			dout("ceph_pool_perm_check pool %lld no write perm\n",
-			     pool);
+			doutc(cl, "pool %lld no write perm\n", pool);
 			return -EPERM;
 		}
 		return 0;