1 files changed, 327 insertions, 292 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e53c8541f5b2..dcf701b05cc1 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -4,8 +4,8 @@
 #include <linux/backing-dev.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/swap.h>
 #include <linux/pagemap.h>
-#include <linux/writeback.h>	/* generic_writepages */
 #include <linux/slab.h>
 #include <linux/pagevec.h>
 #include <linux/task_io_accounting_ops.h>
@@ -63,7 +63,7 @@
 	 (CONGESTION_ON_THRESH(congestion_kb) >> 2))
 
 static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
-					struct folio *folio, void **_fsdata);
+					struct folio **foliop, void **_fsdata);
 
 static inline struct ceph_snap_context *page_snap_context(struct page *page)
 {
@@ -76,18 +76,17 @@ static inline struct ceph_snap_context *page_snap_context(struct page *page)
  * Dirty a page.  Optimistically adjust accounting, on the assumption
  * that we won't race with invalidate.  If we do, readjust.
  */
-static int ceph_set_page_dirty(struct page *page)
+static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 {
-	struct address_space *mapping = page->mapping;
 	struct inode *inode;
 	struct ceph_inode_info *ci;
 	struct ceph_snap_context *snapc;
 
-	if (PageDirty(page)) {
-		dout("%p set_page_dirty %p idx %lu -- already dirty\n",
-		     mapping->host, page, page->index);
-		BUG_ON(!PagePrivate(page));
-		return 0;
+	if (folio_test_dirty(folio)) {
+		dout("%p dirty_folio %p idx %lu -- already dirty\n",
+		     mapping->host, folio, folio->index);
+		VM_BUG_ON_FOLIO(!folio_test_private(folio), folio);
+		return false;
 	}
 
 	inode = mapping->host;
@@ -111,75 +110,81 @@ static int ceph_set_page_dirty(struct page *page)
 	if (ci->i_wrbuffer_ref == 0)
 		ihold(inode);
 	++ci->i_wrbuffer_ref;
-	dout("%p set_page_dirty %p idx %lu head %d/%d -> %d/%d "
+	dout("%p dirty_folio %p idx %lu head %d/%d -> %d/%d "
 	     "snapc %p seq %lld (%d snaps)\n",
-	     mapping->host, page, page->index,
+	     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);
 	spin_unlock(&ci->i_ceph_lock);
 
 	/*
-	 * Reference snap context in page->private.  Also set
-	 * PagePrivate so that we get invalidatepage callback.
+	 * Reference snap context in folio->private.  Also set
+	 * PagePrivate so that we get invalidate_folio callback.
 	 */
-	BUG_ON(PagePrivate(page));
-	attach_page_private(page, snapc);
+	VM_WARN_ON_FOLIO(folio->private, folio);
+	folio_attach_private(folio, snapc);
 
-	return __set_page_dirty_nobuffers(page);
+	return ceph_fscache_dirty_folio(mapping, folio);
 }
 
 /*
- * If we are truncating the full page (i.e. offset == 0), adjust the
- * dirty page counters appropriately.  Only called if there is private
- * data on the page.
+ * If we are truncating the full folio (i.e. offset == 0), adjust the
+ * dirty folio counters appropriately.  Only called if there is private
+ * data on the folio.
  */
-static void ceph_invalidatepage(struct page *page, unsigned int offset,
-				unsigned int length)
+static void ceph_invalidate_folio(struct folio *folio, size_t offset,
+				size_t length)
 {
 	struct inode *inode;
 	struct ceph_inode_info *ci;
 	struct ceph_snap_context *snapc;
 
-	wait_on_page_fscache(page);
-
-	inode = page->mapping->host;
+	inode = folio->mapping->host;
 	ci = ceph_inode(inode);
 
-	if (offset != 0 || length != thp_size(page)) {
-		dout("%p invalidatepage %p idx %lu partial dirty page %u~%u\n",
-		     inode, page, page->index, offset, length);
+	if (offset != 0 || length != folio_size(folio)) {
+		dout("%p invalidate_folio idx %lu partial dirty page %zu~%zu\n",
+		     inode, folio->index, offset, length);
 		return;
 	}
 
-	WARN_ON(!PageLocked(page));
-	if (!PagePrivate(page))
-		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);
 
-	dout("%p invalidatepage %p idx %lu full dirty page\n",
-	     inode, page, page->index);
+		snapc = folio_detach_private(folio);
+		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
+		ceph_put_snap_context(snapc);
+	}
 
-	snapc = detach_page_private(page);
-	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
-	ceph_put_snap_context(snapc);
+	folio_wait_fscache(folio);
 }
 
-static int ceph_releasepage(struct page *page, gfp_t gfp)
+static bool ceph_release_folio(struct folio *folio, gfp_t gfp)
 {
-	dout("%p releasepage %p idx %lu (%sdirty)\n", page->mapping->host,
-	     page, page->index, PageDirty(page) ? "" : "not ");
+	struct inode *inode = folio->mapping->host;
 
-	if (PageFsCache(page)) {
-		if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS))
-			return 0;
-		wait_on_page_fscache(page);
+	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);
 	}
-	return !PagePrivate(page);
+	ceph_fscache_note_page_release(inode);
+	return true;
 }
 
-static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq)
+static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
 {
-	struct inode *inode = rreq->mapping->host;
+	struct inode *inode = rreq->inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_layout *lo = &ci->i_layout;
 	u32 blockoff;
@@ -194,9 +199,9 @@ static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq)
 	rreq->len = roundup(rreq->len, lo->stripe_unit);
 }
 
-static bool ceph_netfs_clamp_length(struct netfs_read_subrequest *subreq)
+static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
 {
-	struct inode *inode = subreq->rreq->mapping->host;
+	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;
@@ -213,7 +218,7 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 {
 	struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
-	struct netfs_read_subrequest *subreq = req->r_priv;
+	struct netfs_io_subrequest *subreq = req->r_priv;
 	int num_pages;
 	int err = req->r_result;
 
@@ -232,17 +237,72 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	if (err >= 0 && err < subreq->len)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 
-	netfs_subreq_terminated(subreq, err, true);
+	netfs_subreq_terminated(subreq, err, false);
 
 	num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
 	ceph_put_page_vector(osd_data->pages, num_pages, false);
 	iput(req->r_inode);
 }
 
-static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
+static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 {
-	struct netfs_read_request *rreq = subreq->rreq;
-	struct inode *inode = rreq->mapping->host;
+	struct netfs_io_request *rreq = subreq->rreq;
+	struct inode *inode = rreq->inode;
+	struct ceph_mds_reply_info_parsed *rinfo;
+	struct ceph_mds_reply_info_in *iinfo;
+	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);
+	__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
+
+	if (subreq->start >= inode->i_size)
+		goto out;
+
+	/* We need to fetch the inline data. */
+	mode = ceph_try_to_choose_auth_mds(inode, CEPH_STAT_CAP_INLINE_DATA);
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, mode);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto out;
+	}
+	req->r_ino1 = ci->i_vino;
+	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INLINE_DATA);
+	req->r_num_caps = 2;
+
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	if (err < 0)
+		goto out;
+
+	rinfo = &req->r_reply_info;
+	iinfo = &rinfo->targeti;
+	if (iinfo->inline_version == CEPH_INLINE_NONE) {
+		/* The data got uninlined */
+		ceph_mdsc_put_request(req);
+		return false;
+	}
+
+	len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len);
+	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
+	err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter);
+	if (err == 0)
+		err = -EFAULT;
+
+	ceph_mdsc_put_request(req);
+out:
+	netfs_subreq_terminated(subreq, err, false);
+	return true;
+}
+
+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;
@@ -253,6 +313,9 @@ static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
 	int err = 0;
 	u64 len = subreq->len;
 
+	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,
@@ -265,7 +328,7 @@ static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
 
 	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
 	iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
-	err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off);
+	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;
@@ -274,6 +337,7 @@ static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
 	/* 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);
 	req->r_callback = finish_netfs_read;
@@ -281,9 +345,7 @@ static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
 	req->r_inode = inode;
 	ihold(inode);
 
-	err = ceph_osdc_start_request(req->r_osdc, req, false);
-	if (err)
-		iput(inode);
+	ceph_osdc_start_request(req->r_osdc, req);
 out:
 	ceph_osdc_put_request(req);
 	if (err)
@@ -291,92 +353,95 @@ out:
 	dout("%s: result %d\n", __func__, err);
 }
 
-static void ceph_init_rreq(struct netfs_read_request *rreq, struct file *file)
+static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 {
+	struct inode *inode = rreq->inode;
+	int got = 0, want = CEPH_CAP_FILE_CACHE;
+	int ret = 0;
+
+	if (rreq->origin != NETFS_READAHEAD)
+		return 0;
+
+	if (file) {
+		struct ceph_rw_context *rw_ctx;
+		struct ceph_file_info *fi = file->private_data;
+
+		rw_ctx = ceph_find_rw_context(fi);
+		if (rw_ctx)
+			return 0;
+	}
+
+	/*
+	 * readahead callers do not necessarily hold Fcb caps
+	 * (e.g. fadvise, madvise).
+	 */
+	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;
+	}
+
+	if (!(got & want)) {
+		dout("start_read %p, no cache cap\n", inode);
+		return -EACCES;
+	}
+	if (ret == 0)
+		return -EACCES;
+
+	rreq->netfs_priv = (void *)(uintptr_t)got;
+	return 0;
 }
 
-static void ceph_readahead_cleanup(struct address_space *mapping, void *priv)
+static void ceph_netfs_free_request(struct netfs_io_request *rreq)
 {
-	struct inode *inode = mapping->host;
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	int got = (uintptr_t)priv;
+	struct ceph_inode_info *ci = ceph_inode(rreq->inode);
+	int got = (uintptr_t)rreq->netfs_priv;
 
 	if (got)
 		ceph_put_cap_refs(ci, got);
 }
 
-static const struct netfs_read_request_ops ceph_netfs_read_ops = {
-	.init_rreq		= ceph_init_rreq,
-	.is_cache_enabled	= ceph_is_cache_enabled,
+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,
-	.issue_op		= ceph_netfs_issue_op,
+	.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,
-	.cleanup		= ceph_readahead_cleanup,
 };
 
-/* read a single page, without unlocking it. */
-static int ceph_readpage(struct file *file, struct page *subpage)
+#ifdef CONFIG_CEPH_FSCACHE
+static void ceph_set_page_fscache(struct page *page)
 {
-	struct folio *folio = page_folio(subpage);
-	struct inode *inode = file_inode(file);
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_vino vino = ceph_vino(inode);
-	size_t len = folio_size(folio);
-	u64 off = folio_file_pos(folio);
-
-	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		/*
-		 * Uptodate inline data should have been added
-		 * into page cache while getting Fcr caps.
-		 */
-		if (off == 0) {
-			folio_unlock(folio);
-			return -EINVAL;
-		}
-		zero_user_segment(&folio->page, 0, folio_size(folio));
-		folio_mark_uptodate(folio);
-		folio_unlock(folio);
-		return 0;
-	}
-
-	dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n",
-	     vino.ino, vino.snap, file, off, len, folio, folio_index(folio));
-
-	return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL);
+	set_page_fscache(page);
 }
 
-static void ceph_readahead(struct readahead_control *ractl)
+static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
 {
-	struct inode *inode = file_inode(ractl->file);
-	struct ceph_file_info *fi = ractl->file->private_data;
-	struct ceph_rw_context *rw_ctx;
-	int got = 0;
-	int ret = 0;
+	struct inode *inode = priv;
 
-	if (ceph_inode(inode)->i_inline_version != CEPH_INLINE_NONE)
-		return;
+	if (IS_ERR_VALUE(error) && error != -ENOBUFS)
+		ceph_fscache_invalidate(inode, false);
+}
 
-	rw_ctx = ceph_find_rw_context(fi);
-	if (!rw_ctx) {
-		/*
-		 * readahead callers do not necessarily hold Fcb caps
-		 * (e.g. fadvise, madvise).
-		 */
-		int want = CEPH_CAP_FILE_CACHE;
+static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct fscache_cookie *cookie = ceph_fscache_cookie(ci);
 
-		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);
-		else if (!(got & want))
-			dout("start_read %p, no cache cap\n", inode);
+	fscache_write_to_cache(cookie, inode->i_mapping, off, len, i_size_read(inode),
+			       ceph_fscache_write_terminated, inode, caching);
+}
+#else
+static inline void ceph_set_page_fscache(struct page *page)
+{
+}
 
-		if (ret <= 0)
-			return;
-	}
-	netfs_readahead(ractl, &ceph_netfs_read_ops, (void *)(uintptr_t)got);
+static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
+{
 }
+#endif /* CONFIG_CEPH_FSCACHE */
 
 struct ceph_writeback_ctl
 {
@@ -483,6 +548,7 @@ static u64 get_writepages_data_length(struct inode *inode,
  */
 static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 {
+	struct folio *folio = page_folio(page);
 	struct inode *inode = page->mapping->host;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
@@ -493,6 +559,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	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);
 
 	dout("writepage %p idx %lu\n", page, page->index);
 
@@ -516,8 +583,9 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
 	/* is this a partial page at end of file? */
 	if (page_off >= ceph_wbc.i_size) {
-		dout("%p page eof %llu\n", page, ceph_wbc.i_size);
-		page->mapping->a_ops->invalidatepage(page, 0, thp_size(page));
+		dout("folio at %lu beyond eof %llu\n", folio->index,
+				ceph_wbc.i_size);
+		folio_invalidate(folio, 0, folio_size(folio));
 		return 0;
 	}
 
@@ -529,28 +597,30 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
 	if (atomic_long_inc_return(&fsc->writeback_count) >
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
-		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+		fsc->write_congested = true;
 
-	set_page_writeback(page);
 	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);
 	if (IS_ERR(req)) {
 		redirty_page_for_writepage(wbc, page);
-		end_page_writeback(page);
 		return PTR_ERR(req);
 	}
 
+	set_page_writeback(page);
+	if (caching)
+		ceph_set_page_fscache(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);
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(osdc, req, true);
-	if (!err)
-		err = ceph_osdc_wait_request(osdc, req);
+	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);
@@ -588,7 +658,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
 	if (atomic_long_dec_return(&fsc->writeback_count) <
 	    CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
-		clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+		fsc->write_congested = false;
 
 	return err;
 }
@@ -599,6 +669,13 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
 	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
@@ -652,8 +729,11 @@ 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)
+		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);
 			break;
+		}
 
 		osd_data = osd_req_op_extent_osd_data(req, i);
 		BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
@@ -669,8 +749,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 			if (atomic_long_dec_return(&fsc->writeback_count) <
 			     CONGESTION_OFF_THRESH(
 					fsc->mount_options->congestion_kb))
-				clear_bdi_congested(inode_to_bdi(inode),
-						    BLK_RW_ASYNC);
+				fsc->write_congested = false;
 
 			ceph_put_snap_context(detach_page_private(page));
 			end_page_writeback(page);
@@ -720,6 +799,11 @@ static int ceph_writepages_start(struct address_space *mapping,
 	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" :
@@ -828,14 +912,16 @@ get_more_pages:
 				continue;
 			}
 			if (page_offset(page) >= ceph_wbc.i_size) {
-				dout("%p page eof %llu\n",
-				     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 ||
-				    page_offset(page) >= i_size_read(inode)) &&
-				    clear_page_dirty_for_io(page))
-					mapping->a_ops->invalidatepage(page,
-								0, thp_size(page));
-				unlock_page(page);
+				    folio_pos(folio) >= i_size_read(inode)) &&
+				    folio_clear_dirty_for_io(folio))
+					folio_invalidate(folio, 0,
+							folio_size(folio));
+				folio_unlock(folio);
 				continue;
 			}
 			if (strip_unit_end && (page->index > strip_unit_end)) {
@@ -843,7 +929,7 @@ get_more_pages:
 				unlock_page(page);
 				break;
 			}
-			if (PageWriteback(page)) {
+			if (PageWriteback(page) || PageFsCache(page)) {
 				if (wbc->sync_mode == WB_SYNC_NONE) {
 					dout("%p under writeback\n", page);
 					unlock_page(page);
@@ -851,6 +937,7 @@ get_more_pages:
 				}
 				dout("waiting on writeback %p\n", page);
 				wait_on_page_writeback(page);
+				wait_on_page_fscache(page);
 			}
 
 			if (!clear_page_dirty_for_io(page)) {
@@ -914,11 +1001,8 @@ get_more_pages:
 
 			if (atomic_long_inc_return(&fsc->writeback_count) >
 			    CONGESTION_ON_THRESH(
-				    fsc->mount_options->congestion_kb)) {
-				set_bdi_congested(inode_to_bdi(inode),
-						  BLK_RW_ASYNC);
-			}
-
+				    fsc->mount_options->congestion_kb))
+				fsc->write_congested = true;
 
 			pages[locked_pages++] = page;
 			pvec.pages[i] = NULL;
@@ -983,9 +1067,19 @@ new_request:
 		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",
@@ -996,14 +1090,17 @@ new_request:
 				osd_req_op_extent_update(req, op_idx, len);
 
 				len = 0;
-				offset = cur_offset; 
+				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);
 		}
+		ceph_fscache_write_to_cache(inode, offset, len, caching);
 
 		if (ceph_wbc.size_stable) {
 			len = min(len, ceph_wbc.i_size - offset);
@@ -1051,8 +1148,7 @@ new_request:
 		}
 
 		req->r_mtime = inode->i_mtime;
-		rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
-		BUG_ON(rc);
+		ceph_osdc_start_request(&fsc->client->osdc, req);
 		req = NULL;
 
 		wbc->nr_to_write -= i;
@@ -1188,18 +1284,19 @@ ceph_find_incompatible(struct page *page)
 }
 
 static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
-					struct folio *folio, void **_fsdata)
+					struct folio **foliop, void **_fsdata)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_snap_context *snapc;
 
-	snapc = ceph_find_incompatible(folio_page(folio, 0));
+	snapc = ceph_find_incompatible(folio_page(*foliop, 0));
 	if (snapc) {
 		int r;
 
-		folio_unlock(folio);
-		folio_put(folio);
+		folio_unlock(*foliop);
+		folio_put(*foliop);
+		*foliop = NULL;
 		if (IS_ERR(snapc))
 			return PTR_ERR(snapc);
 
@@ -1217,59 +1314,22 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
  * clean, or already dirty within the same snap context.
  */
 static int ceph_write_begin(struct file *file, struct address_space *mapping,
-			    loff_t pos, unsigned len, unsigned aop_flags,
+			    loff_t pos, unsigned len,
 			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct folio *folio = NULL;
-	pgoff_t index = pos >> PAGE_SHIFT;
 	int r;
 
-	/*
-	 * Uninlining should have already been done and everything updated, EXCEPT
-	 * for inline_version sent to the MDS.
-	 */
-	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
-		if (aop_flags & AOP_FLAG_NOFS)
-			fgp_flags |= FGP_NOFS;
-		folio = __filemap_get_folio(mapping, index, fgp_flags,
-					    mapping_gfp_mask(mapping));
-		if (!folio)
-			return -ENOMEM;
+	r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
+	if (r < 0)
+		return r;
 
-		/*
-		 * The inline_version on a new inode is set to 1. If that's the
-		 * case, then the folio is brand new and isn't yet Uptodate.
-		 */
-		r = 0;
-		if (index == 0 && ci->i_inline_version != 1) {
-			if (!folio_test_uptodate(folio)) {
-				WARN_ONCE(1, "ceph: write_begin called on still-inlined inode (inline_version %llu)!\n",
-					  ci->i_inline_version);
-				r = -EINVAL;
-			}
-			goto out;
-		}
-		zero_user_segment(&folio->page, 0, folio_size(folio));
-		folio_mark_uptodate(folio);
-		goto out;
-	}
-
-	r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL,
-			      &ceph_netfs_read_ops, NULL);
-out:
-	if (r == 0)
-		folio_wait_fscache(folio);
-	if (r < 0) {
-		if (folio)
-			folio_put(folio);
-	} else {
-		WARN_ON_ONCE(!folio_test_locked(folio));
-		*pagep = &folio->page;
-	}
-	return r;
+	folio_wait_fscache(folio);
+	WARN_ON_ONCE(!folio_test_locked(folio));
+	*pagep = &folio->page;
+	return 0;
 }
 
 /*
@@ -1313,15 +1373,15 @@ out:
 }
 
 const struct address_space_operations ceph_aops = {
-	.readpage = ceph_readpage,
-	.readahead = ceph_readahead,
+	.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,
-	.set_page_dirty = ceph_set_page_dirty,
-	.invalidatepage = ceph_invalidatepage,
-	.releasepage = ceph_releasepage,
+	.dirty_folio = ceph_dirty_folio,
+	.invalidate_folio = ceph_invalidate_folio,
+	.release_folio = ceph_release_folio,
 	.direct_IO = noop_direct_IO,
 };
 
@@ -1372,7 +1432,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 	     inode, off, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
-	    ci->i_inline_version == CEPH_INLINE_NONE) {
+	    !ceph_has_inline_data(ci)) {
 		CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
 		ceph_add_rw_context(fi, &rw_ctx);
 		ret = filemap_fault(vmf);
@@ -1455,19 +1515,6 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 	ceph_block_sigs(&oldset);
 
-	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		struct page *locked_page = NULL;
-		if (off == 0) {
-			lock_page(page);
-			locked_page = page;
-		}
-		err = ceph_uninline_data(vma->vm_file, locked_page);
-		if (locked_page)
-			unlock_page(locked_page);
-		if (err < 0)
-			goto out_free;
-	}
-
 	if (off + thp_size(page) <= size)
 		len = thp_size(page);
 	else
@@ -1524,11 +1571,9 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 		ceph_put_snap_context(snapc);
 	} while (err == 0);
 
-	if (ret == VM_FAULT_LOCKED ||
-	    ci->i_inline_version != CEPH_INLINE_NONE) {
+	if (ret == VM_FAULT_LOCKED) {
 		int dirty;
 		spin_lock(&ci->i_ceph_lock);
-		ci->i_inline_version = CEPH_INLINE_NONE;
 		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
 					       &prealloc_cf);
 		spin_unlock(&ci->i_ceph_lock);
@@ -1592,16 +1637,18 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 	}
 }
 
-int ceph_uninline_data(struct file *filp, struct page *locked_page)
+int ceph_uninline_data(struct file *file)
 {
-	struct inode *inode = file_inode(filp);
+	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_osd_request *req;
-	struct page *page = NULL;
-	u64 len, inline_version;
+	struct ceph_osd_request *req = NULL;
+	struct ceph_cap_flush *prealloc_cf;
+	struct folio *folio = NULL;
+	u64 inline_version = CEPH_INLINE_NONE;
+	struct page *pages[1];
 	int err = 0;
-	bool from_pagecache = false;
+	u64 len;
 
 	spin_lock(&ci->i_ceph_lock);
 	inline_version = ci->i_inline_version;
@@ -1610,64 +1657,43 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 	dout("uninline_data %p %llx.%llx inline_version %llu\n",
 	     inode, ceph_vinop(inode), inline_version);
 
-	if (inline_version == 1 || /* initial version, no data */
-	    inline_version == CEPH_INLINE_NONE)
-		goto out;
+	if (inline_version == CEPH_INLINE_NONE)
+		return 0;
 
-	if (locked_page) {
-		page = locked_page;
-		WARN_ON(!PageUptodate(page));
-	} else if (ceph_caps_issued(ci) &
-		   (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) {
-		page = find_get_page(inode->i_mapping, 0);
-		if (page) {
-			if (PageUptodate(page)) {
-				from_pagecache = true;
-				lock_page(page);
-			} else {
-				put_page(page);
-				page = NULL;
-			}
-		}
-	}
+	prealloc_cf = ceph_alloc_cap_flush();
+	if (!prealloc_cf)
+		return -ENOMEM;
 
-	if (page) {
-		len = i_size_read(inode);
-		if (len > PAGE_SIZE)
-			len = PAGE_SIZE;
-	} else {
-		page = __page_cache_alloc(GFP_NOFS);
-		if (!page) {
-			err = -ENOMEM;
-			goto out;
-		}
-		err = __ceph_do_getattr(inode, page,
-					CEPH_STAT_CAP_INLINE_DATA, true);
-		if (err < 0) {
-			/* no inline data */
-			if (err == -ENODATA)
-				err = 0;
-			goto out;
-		}
-		len = err;
+	if (inline_version == 1) /* initial version, no data */
+		goto out_uninline;
+
+	folio = read_mapping_folio(inode->i_mapping, 0, file);
+	if (IS_ERR(folio)) {
+		err = PTR_ERR(folio);
+		goto out;
 	}
 
+	folio_lock(folio);
+
+	len = i_size_read(inode);
+	if (len > folio_size(folio))
+		len = folio_size(folio);
+
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), 0, &len, 0, 1,
 				    CEPH_OSD_OP_CREATE, CEPH_OSD_FLAG_WRITE,
 				    NULL, 0, 0, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
-		goto out;
+		goto out_unlock;
 	}
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+	ceph_osdc_start_request(&fsc->client->osdc, req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, req);
 	ceph_osdc_put_request(req);
 	if (err < 0)
-		goto out;
+		goto out_unlock;
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), 0, &len, 1, 3,
@@ -1676,10 +1702,11 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 				    ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
-		goto out;
+		goto out_unlock;
 	}
 
-	osd_req_op_extent_osd_data_pages(req, 1, &page, len, 0, false, false);
+	pages[0] = folio_page(folio, 0);
+	osd_req_op_extent_osd_data_pages(req, 1, pages, len, 0, false, false);
 
 	{
 		__le64 xattr_buf = cpu_to_le64(inline_version);
@@ -1689,7 +1716,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 					    CEPH_OSD_CMPXATTR_OP_GT,
 					    CEPH_OSD_CMPXATTR_MODE_U64);
 		if (err)
-			goto out_put;
+			goto out_put_req;
 	}
 
 	{
@@ -1700,30 +1727,41 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 					    "inline_version",
 					    xattr_buf, xattr_len, 0, 0);
 		if (err)
-			goto out_put;
+			goto out_put_req;
 	}
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+	ceph_osdc_start_request(&fsc->client->osdc, req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
 
-out_put:
+out_uninline:
+	if (!err) {
+		int dirty;
+
+		/* Set to CAP_INLINE_NONE and dirty the caps */
+		down_read(&fsc->mdsc->snap_rwsem);
+		spin_lock(&ci->i_ceph_lock);
+		ci->i_inline_version = CEPH_INLINE_NONE;
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR, &prealloc_cf);
+		spin_unlock(&ci->i_ceph_lock);
+		up_read(&fsc->mdsc->snap_rwsem);
+		if (dirty)
+			__mark_inode_dirty(inode, dirty);
+	}
+out_put_req:
 	ceph_osdc_put_request(req);
 	if (err == -ECANCELED)
 		err = 0;
-out:
-	if (page && page != locked_page) {
-		if (from_pagecache) {
-			unlock_page(page);
-			put_page(page);
-		} else
-			__free_pages(page, 0);
+out_unlock:
+	if (folio) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
-
+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);
 	return err;
@@ -1738,9 +1776,8 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = file->f_mapping;
 
-	if (!mapping->a_ops->readpage)
+	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
-	file_accessed(file);
 	vma->vm_ops = &ceph_vmops;
 	return 0;
 }
@@ -1753,7 +1790,7 @@ 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->vfs_inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->netfs.inode);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_osd_request *rd_req = NULL, *wr_req = NULL;
 	struct rb_node **p, *parent;
@@ -1866,15 +1903,13 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 
 	osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE,
 				     0, false, true);
-	err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
+	ceph_osdc_start_request(&fsc->client->osdc, rd_req);
 
-	wr_req->r_mtime = ci->vfs_inode.i_mtime;
-	err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
+	wr_req->r_mtime = ci->netfs.inode.i_mtime;
+	ceph_osdc_start_request(&fsc->client->osdc, wr_req);
 
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
-	if (!err2)
-		err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
+	err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
 
 	if (err >= 0 || err == -ENOENT)
 		have |= POOL_READ;