nfs: Implement cache I/O by accessing the cache directly

Move NFS to using fscache DIO API instead of the old upstream I/O API as
that has been removed. This is a stopgap solution as the intention is that
at sometime in the future, the cache will move to using larger blocks and
won't be able to store individual pages in order to deal with the potential
for data corruption due to the backing filesystem being able insert/remove
bridging blocks of zeros into its extent list[1].

NFS then reads and writes cache pages synchronously and one page at a time.

The preferred change would be to use the netfs lib, but the new I/O API can
be used directly. It's just that as the cache now needs to track data for
itself, caching blocks may exceed page size...

This code is somewhat borrowed from my "fallback I/O" patchset[2].

Changes
=======
ver #3:
- Restore lost =n fallback for nfs_fscache_release_page()[2].

Signed-off-by: David Howells <[e-mail]>
Tested-by: Dave Wysochanski <[e-mail]>
Acked-by: Jeff Layton <[e-mail]>
cc: Trond Myklebust <[e-mail]>
cc: Anna Schumaker <[e-mail]>
cc: [e-mail]
cc: [e-mail]
Link: https://lore.kernel.org/r/[e-mail] [1]
Link: https://lore.kernel.org/r/[e-mail]/ [2]
Link: https://lore.kernel.org/r/[e-mail]/ [2]
Link: https://lore.kernel.org/r/[e-mail]/ # v2
Link: https://lore.kernel.org/r/[e-mail]/ # v3
Link: https://lore.kernel.org/r/[e-mail]/ # v4

fs/fscache/io.c

···
 }
 EXPORT_SYMBOL(__fscache_begin_read_operation);
 
+int __fscache_begin_write_operation(struct netfs_cache_resources *cres,
+				    struct fscache_cookie *cookie)
+{
+	return fscache_begin_operation(cres, cookie, FSCACHE_WANT_PARAMS,
+				       fscache_access_io_write);
+}
+EXPORT_SYMBOL(__fscache_begin_write_operation);
+
 /**
  * fscache_set_page_dirty - Mark page dirty and pin a cache object for writeback
  * @page: The page being dirtied

fs/nfs/fscache.c

···
 	}
 }
 
+static inline void fscache_end_operation(struct netfs_cache_resources *cres)
+{
+	const struct netfs_cache_ops *ops = fscache_operation_valid(cres);
+
+	if (ops)
+		ops->end_operation(cres);
+}
+
+/*
+ * Fallback page reading interface.
+ */
+static int fscache_fallback_read_page(struct inode *inode, struct page *page)
+{
+	struct netfs_cache_resources cres;
+	struct fscache_cookie *cookie = nfs_i_fscache(inode);
+	struct iov_iter iter;
+	struct bio_vec bvec[1];
+	int ret;
+
+	memset(&cres, 0, sizeof(cres));
+	bvec[0].bv_page		= page;
+	bvec[0].bv_offset	= 0;
+	bvec[0].bv_len		= PAGE_SIZE;
+	iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE);
+
+	ret = fscache_begin_read_operation(&cres, cookie);
+	if (ret < 0)
+		return ret;
+
+	ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL,
+			   NULL, NULL);
+	fscache_end_operation(&cres);
+	return ret;
+}
+
+/*
+ * Fallback page writing interface.
+ */
+static int fscache_fallback_write_page(struct inode *inode, struct page *page,
+				       bool no_space_allocated_yet)
+{
+	struct netfs_cache_resources cres;
+	struct fscache_cookie *cookie = nfs_i_fscache(inode);
+	struct iov_iter iter;
+	struct bio_vec bvec[1];
+	loff_t start = page_offset(page);
+	size_t len = PAGE_SIZE;
+	int ret;
+
+	memset(&cres, 0, sizeof(cres));
+	bvec[0].bv_page		= page;
+	bvec[0].bv_offset	= 0;
+	bvec[0].bv_len		= PAGE_SIZE;
+	iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE);
+
+	ret = fscache_begin_write_operation(&cres, cookie);
+	if (ret < 0)
+		return ret;
+
+	ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode),
+				      no_space_allocated_yet);
+	if (ret == 0)
+		ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL);
+	fscache_end_operation(&cres);
+	return ret;
+}
+
 /*
  * Retrieve a page from fscache
  */
-int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
-				struct inode *inode, struct page *page)
+int __nfs_readpage_from_fscache(struct inode *inode, struct page *page)
 {
+	int ret;
+
 	dfprintk(FSCACHE,
 		 "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
 		 nfs_i_fscache(inode), page, page->index, page->flags, inode);
 
 	if (PageChecked(page)) {
+		dfprintk(FSCACHE, "NFS:    readpage_from_fscache: PageChecked\n");
 		ClearPageChecked(page);
 		return 1;
 	}
 
-	return -ENOBUFS; // TODO: Use netfslib
+	ret = fscache_fallback_read_page(inode, page);
+	if (ret < 0) {
+		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL);
+		dfprintk(FSCACHE,
+			 "NFS:    readpage_from_fscache failed %d\n", ret);
+		SetPageChecked(page);
+		return ret;
+	}
+
+	/* Read completed synchronously */
+	dfprintk(FSCACHE, "NFS:    readpage_from_fscache: read successful\n");
+	nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK);
+	SetPageUptodate(page);
+	return 0;
 }
 
 /*
- * Retrieve a set of pages from fscache
+ * Store a newly fetched page in fscache.  We can be certain there's no page
+ * stored in the cache as yet otherwise we would've read it from there.
  */
-int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
-				 struct inode *inode,
-				 struct address_space *mapping,
-				 struct list_head *pages,
-				 unsigned *nr_pages)
+void __nfs_readpage_to_fscache(struct inode *inode, struct page *page)
 {
-	dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
-		 nfs_i_fscache(inode), *nr_pages, inode);
+	int ret;
 
-	return -ENOBUFS; // TODO: Use netfslib
-}
-
-/*
- * Store a newly fetched page in fscache
- * - PG_fscache must be set on the page
- */
-void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
-{
 	dfprintk(FSCACHE,
-		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
-		 nfs_i_fscache(inode), page, page->index, page->flags, sync);
+		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx))\n",
+		 nfs_i_fscache(inode), page, page->index, page->flags);
 
-	return; // TODO: Use netfslib
+	ret = fscache_fallback_write_page(inode, page, true);
+
+	dfprintk(FSCACHE,
+		 "NFS:     readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
+		 page, page->index, page->flags, ret);
+
+	if (ret != 0) {
+		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL);
+		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED);
+	} else {
+		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_OK);
+	}
 }

fs/nfs/fscache.h

···
 extern void nfs_fscache_open_file(struct inode *, struct file *);
 extern void nfs_fscache_release_file(struct inode *, struct file *);
 
-extern void __nfs_fscache_invalidate_page(struct page *, struct inode *);
-
-extern int __nfs_readpage_from_fscache(struct nfs_open_context *,
-				       struct inode *, struct page *);
-extern int __nfs_readpages_from_fscache(struct nfs_open_context *,
-					struct inode *, struct address_space *,
-					struct list_head *, unsigned *);
-extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int);
+extern int __nfs_readpage_from_fscache(struct inode *, struct page *);
+extern void __nfs_read_completion_to_fscache(struct nfs_pgio_header *hdr,
+					     unsigned long bytes);
+extern void __nfs_readpage_to_fscache(struct inode *, struct page *);
 
 static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
 {
···
 /*
  * Retrieve a page from an inode data storage object.
  */
-static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
-					    struct inode *inode,
+static inline int nfs_readpage_from_fscache(struct inode *inode,
 					    struct page *page)
 {
 	if (NFS_I(inode)->fscache)
-		return __nfs_readpage_from_fscache(ctx, inode, page);
-	return -ENOBUFS;
-}
-
-/*
- * Retrieve a set of pages from an inode data storage object.
- */
-static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
-					     struct inode *inode,
-					     struct address_space *mapping,
-					     struct list_head *pages,
-					     unsigned *nr_pages)
-{
-	if (NFS_I(inode)->fscache)
-		return __nfs_readpages_from_fscache(ctx, inode, mapping, pages,
-						    nr_pages);
+		return __nfs_readpage_from_fscache(inode, page);
 	return -ENOBUFS;
 }
 
···
  * in the cache.
  */
 static inline void nfs_readpage_to_fscache(struct inode *inode,
-					   struct page *page,
-					   int sync)
+					   struct page *page)
 {
-	if (PageFsCache(page))
-		__nfs_readpage_to_fscache(inode, page, sync);
+	if (NFS_I(inode)->fscache)
+		__nfs_readpage_to_fscache(inode, page);
 }
 
 static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
···
 {
 	return 1; /* True: may release page */
 }
-static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
-					    struct inode *inode,
+static inline int nfs_readpage_from_fscache(struct inode *inode,
 					    struct page *page)
 {
 	return -ENOBUFS;
 }
-static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
-					     struct inode *inode,
-					     struct address_space *mapping,
-					     struct list_head *pages,
-					     unsigned *nr_pages)
-{
-	return -ENOBUFS;
-}
 static inline void nfs_readpage_to_fscache(struct inode *inode,
-					   struct page *page, int sync) {}
+					   struct page *page) {}
 
 
 static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {}

fs/nfs/read.c

···
 		struct address_space *mapping = page_file_mapping(page);
 
 		if (PageUptodate(page))
-			nfs_readpage_to_fscache(inode, page, 0);
+			nfs_readpage_to_fscache(inode, page);
 		else if (!PageError(page) && !PagePrivate(page))
 			generic_error_remove_page(mapping, page);
 		unlock_page(page);
···
 
 	aligned_len = min_t(unsigned int, ALIGN(len, rsize), PAGE_SIZE);
 
+	if (!IS_SYNC(page->mapping->host)) {
+		error = nfs_readpage_from_fscache(page->mapping->host, page);
+		if (error == 0)
+			goto out_unlock;
+	}
+
 	new = nfs_create_request(desc->ctx, page, 0, aligned_len);
 	if (IS_ERR(new))
 		goto out_error;
···
 	return 0;
 out_error:
 	error = PTR_ERR(new);
+out_unlock:
 	unlock_page(page);
 out:
 	return error;
···
 		desc.ctx = get_nfs_open_context(nfs_file_open_context(file));
 
 	xchg(&desc.ctx->error, 0);
-	if (!IS_SYNC(inode)) {
-		ret = nfs_readpage_from_fscache(desc.ctx, inode, page);
-		if (ret == 0)
-			goto out_wait;
-	}
-
 	nfs_pageio_init_read(&desc.pgio, inode, false,
 			     &nfs_async_read_completion_ops);
 
···
 
 	nfs_pageio_complete_read(&desc.pgio);
 	ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0;
-out_wait:
 	if (!ret) {
 		ret = wait_on_page_locked_killable(page);
 		if (!PageUptodate(page) && !ret)
···
 	} else
 		desc.ctx = get_nfs_open_context(nfs_file_open_context(file));
 
-	/* attempt to read as many of the pages as possible from the cache
-	 * - this returns -ENOBUFS immediately if the cookie is negative
-	 */
-	ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping,
-					 pages, &nr_pages);
-	if (ret == 0)
-		goto read_complete; /* all pages were read */
-
 	nfs_pageio_init_read(&desc.pgio, inode, false,
 			     &nfs_async_read_completion_ops);
 
···
 
 	nfs_pageio_complete_read(&desc.pgio);
 
-read_complete:
 	put_nfs_open_context(desc.ctx);
 out:
 	trace_nfs_aop_readahead_done(inode, nr_pages, ret);

fs/nfs/write.c

···
 	if (PagePrivate(page))
 		return -EBUSY;
 
-	if (!nfs_fscache_release_page(page, GFP_KERNEL))
-		return -EBUSY;
+	if (PageFsCache(page)) {
+		if (mode == MIGRATE_ASYNC)
+			return -EBUSY;
+		wait_on_page_fscache(page);
+	}
 
 	return migrate_page(mapping, newpage, page, mode);
 }

include/linux/fscache.h

···
 extern void __fscache_resize_cookie(struct fscache_cookie *, loff_t);
 extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int);
 extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *);
+extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *);
 
 extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *,
 				     loff_t, size_t, loff_t, netfs_io_terminated_t, void *,
···
 	const struct netfs_cache_ops *ops = fscache_operation_valid(cres);
 	return ops->read(cres, start_pos, iter, read_hole,
 			 term_func, term_func_priv);
+}
+
+/**
+ * fscache_begin_write_operation - Begin a write operation for the netfs lib
+ * @cres: The cache resources for the write being performed
+ * @cookie: The cookie representing the cache object
+ *
+ * Begin a write operation on behalf of the netfs helper library.  @cres
+ * indicates the cache resources to which the operation state should be
+ * attached; @cookie indicates the cache object that will be accessed.
+ *
+ * @cres->inval_counter is set from @cookie->inval_counter for comparison at
+ * the end of the operation.  This allows invalidation during the operation to
+ * be detected by the caller.
+ *
+ * Returns:
+ * * 0		- Success
+ * * -ENOBUFS	- No caching available
+ * * Other error code from the cache, such as -ENOMEM.
+ */
+static inline
+int fscache_begin_write_operation(struct netfs_cache_resources *cres,
+				  struct fscache_cookie *cookie)
+{
+	if (fscache_cookie_enabled(cookie))
+		return __fscache_begin_write_operation(cres, cookie);
+	return -ENOBUFS;
 }
 
 /**