NFS: Convert buffered read paths to use netfs when fscache is enabled

Convert the NFS buffered read code paths to corresponding netfs APIs,
but only when fscache is configured and enabled.

The netfs API defines struct netfs_request_ops which must be filled
in by the network filesystem.  For NFS, we only need to define 5 of
the functions, the main one being the issue_read() function.
The issue_read() function is called by the netfs layer when a read
cannot be fulfilled locally, and must be sent to the server (either
the cache is not active, or it is active but the data is not available).
Once the read from the server is complete, netfs requires a call to
netfs_subreq_terminated() which conveys either how many bytes were read
successfully, or an error.  Note that issue_read() is called with a
structure, netfs_io_subrequest, which defines the IO requested, and
contains a start and a length (both in bytes), and assumes the underlying
netfs will return a either an error on the whole region, or the number
of bytes successfully read.

The NFS IO path is page based and the main APIs are the pgio APIs defined
in pagelist.c.  For the pgio APIs, there is no way for the caller to
know how many RPCs will be sent and how the pages will be broken up
into underlying RPCs, each of which will have their own completion and
return code.  In contrast, netfs is subrequest based, a single
subrequest may contain multiple pages, and a single subrequest is
initiated with issue_read() and terminated with netfs_subreq_terminated().
Thus, to utilze the netfs APIs, NFS needs some way to accommodate
the netfs API requirement on the single response to the whole
subrequest, while also minimizing disruptive changes to the NFS
pgio layer.

The approach taken with this patch is to allocate a small structure
for each nfs_netfs_issue_read() call, store the final error and number
of bytes successfully transferred in the structure, and update these values
as each RPC completes.  The refcount on the structure is used as a marker
for the last RPC completion, is incremented in nfs_netfs_read_initiate(),
and decremented inside nfs_netfs_read_completion(), when a nfs_pgio_header
contains a valid pointer to the data.  On the final put (which signals
the final outstanding RPC is complete) in nfs_netfs_read_completion(),
call netfs_subreq_terminated() with either the final error value (if
one or more READs complete with an error) or the number of bytes
successfully transferred (if all RPCs complete successfully).  Note
that when all RPCs complete successfully, the number of bytes transferred
is capped to the length of the subrequest.  Capping the transferred length
to the subrequest length prevents "Subreq overread" warnings from netfs.
This is due to the "aligned_len" in nfs_pageio_add_page(), and the
corner case where NFS requests a full page at the end of the file,
even when i_size reflects only a partial page (NFS overread).

Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Tested-by: Daire Byrne <daire@dneg.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

1 files changed, 89 insertions, 33 deletions

diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 38614ed8f951..e1706e736c64 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -34,6 +34,58 @@ struct nfs_fscache_inode_auxdata {
 	u64	change_attr;
 };
 
+struct nfs_netfs_io_data {
+	/*
+	 * NFS may split a netfs_io_subrequest into multiple RPCs, each
+	 * with their own read completion.  In netfs, we can only call
+	 * netfs_subreq_terminated() once for each subrequest.  Use the
+	 * refcount here to double as a marker of the last RPC completion,
+	 * and only call netfs via netfs_subreq_terminated() once.
+	 */
+	refcount_t			refcount;
+	struct netfs_io_subrequest	*sreq;
+
+	/*
+	 * Final disposition of the netfs_io_subrequest, sent in
+	 * netfs_subreq_terminated()
+	 */
+	atomic64_t	transferred;
+	int		error;
+};
+
+static inline void nfs_netfs_get(struct nfs_netfs_io_data *netfs)
+{
+	refcount_inc(&netfs->refcount);
+}
+
+static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs)
+{
+	ssize_t final_len;
+
+	/* Only the last RPC completion should call netfs_subreq_terminated() */
+	if (!refcount_dec_and_test(&netfs->refcount))
+		return;
+
+	/*
+	 * The NFS pageio interface may read a complete page, even when netfs
+	 * only asked for a partial page.  Specifically, this may be seen when
+	 * one thread is truncating a file while another one is reading the last
+	 * page of the file.
+	 * Correct the final length here to be no larger than the netfs subrequest
+	 * length, and thus avoid netfs's "Subreq overread" warning message.
+	 */
+	final_len = min_t(s64, netfs->sreq->len, atomic64_read(&netfs->transferred));
+	netfs_subreq_terminated(netfs->sreq, netfs->error ?: final_len, false);
+	kfree(netfs);
+}
+static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi)
+{
+	netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops);
+}
+extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr);
+extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr);
+extern int nfs_netfs_folio_unlock(struct folio *folio);
+
 /*
  * fscache.c
  */
@@ -44,9 +96,8 @@ extern void nfs_fscache_init_inode(struct inode *);
 extern void nfs_fscache_clear_inode(struct inode *);
 extern void nfs_fscache_open_file(struct inode *, struct file *);
 extern void nfs_fscache_release_file(struct inode *, struct file *);
-
-extern int __nfs_fscache_read_page(struct inode *, struct page *);
-extern void __nfs_fscache_write_page(struct inode *, struct page *);
+extern int nfs_netfs_readahead(struct readahead_control *ractl);
+extern int nfs_netfs_read_folio(struct file *file, struct folio *folio);
 
 static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp)
 {
@@ -54,34 +105,11 @@ static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp)
 		if (current_is_kswapd() || !(gfp & __GFP_FS))
 			return false;
 		folio_wait_fscache(folio);
-		fscache_note_page_release(netfs_i_cookie(&NFS_I(folio->mapping->host)->netfs));
-		nfs_inc_fscache_stats(folio->mapping->host,
-				      NFSIOS_FSCACHE_PAGES_UNCACHED);
 	}
+	fscache_note_page_release(netfs_i_cookie(netfs_inode(folio->mapping->host)));
 	return true;
 }
 
-/*
- * Retrieve a page from an inode data storage object.
- */
-static inline int nfs_fscache_read_page(struct inode *inode, struct page *page)
-{
-	if (netfs_inode(inode)->cache)
-		return __nfs_fscache_read_page(inode, page);
-	return -ENOBUFS;
-}
-
-/*
- * Store a page newly fetched from the server in an inode data storage object
- * in the cache.
- */
-static inline void nfs_fscache_write_page(struct inode *inode,
-					   struct page *page)
-{
-	if (netfs_inode(inode)->cache)
-		__nfs_fscache_write_page(inode, page);
-}
-
 static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
 					      struct inode *inode)
 {
@@ -117,7 +145,28 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server)
 	return "no ";
 }
 
+static inline void nfs_netfs_set_pgio_header(struct nfs_pgio_header *hdr,
+					     struct nfs_pageio_descriptor *desc)
+{
+	hdr->netfs = desc->pg_netfs;
+}
+static inline void nfs_netfs_set_pageio_descriptor(struct nfs_pageio_descriptor *desc,
+						   struct nfs_pgio_header *hdr)
+{
+	desc->pg_netfs = hdr->netfs;
+}
+static inline void nfs_netfs_reset_pageio_descriptor(struct nfs_pageio_descriptor *desc)
+{
+	desc->pg_netfs = NULL;
+}
 #else /* CONFIG_NFS_FSCACHE */
+static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) {}
+static inline void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr) {}
+static inline void nfs_netfs_read_completion(struct nfs_pgio_header *hdr) {}
+static inline int nfs_netfs_folio_unlock(struct folio *folio)
+{
+	return 1;
+}
 static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
 
 static inline void nfs_fscache_init_inode(struct inode *inode) {}
@@ -125,22 +174,29 @@ static inline void nfs_fscache_clear_inode(struct inode *inode) {}
 static inline void nfs_fscache_open_file(struct inode *inode,
 					 struct file *filp) {}
 static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {}
-
-static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp)
+static inline int nfs_netfs_readahead(struct readahead_control *ractl)
 {
-	return true; /* may release folio */
+	return -ENOBUFS;
 }
-static inline int nfs_fscache_read_page(struct inode *inode, struct page *page)
+static inline int nfs_netfs_read_folio(struct file *file, struct folio *folio)
 {
 	return -ENOBUFS;
 }
-static inline void nfs_fscache_write_page(struct inode *inode, struct page *page) {}
+
+static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp)
+{
+	return true; /* may release folio */
+}
 static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {}
 
 static inline const char *nfs_server_fscache_state(struct nfs_server *server)
 {
 	return "no ";
 }
-
+static inline void nfs_netfs_set_pgio_header(struct nfs_pgio_header *hdr,
+					     struct nfs_pageio_descriptor *desc) {}
+static inline void nfs_netfs_set_pageio_descriptor(struct nfs_pageio_descriptor *desc,
+						   struct nfs_pgio_header *hdr) {}
+static inline void nfs_netfs_reset_pageio_descriptor(struct nfs_pageio_descriptor *desc) {}
 #endif /* CONFIG_NFS_FSCACHE */
 #endif /* _NFS_FSCACHE_H */