netfs: Provide readahead and readpage netfs helpers

Add a pair of helper functions:

 (*) netfs_readahead()
 (*) netfs_readpage()

to do the work of handling a readahead or a readpage, where the page(s)
that form part of the request may be split between the local cache, the
server or just require clearing, and may be single pages and transparent
huge pages.  This is all handled within the helper.

Note that while both will read from the cache if there is data present,
only netfs_readahead() will expand the request beyond what it was asked to
do, and only netfs_readahead() will write back to the cache.

netfs_readpage(), on the other hand, is synchronous and only fetches the
page (which might be a THP) it is asked for.

The netfs gives the helper parameters from the VM, the cache cookie it
wants to use (or NULL) and a table of operations (only one of which is
mandatory):

 (*) expand_readahead() [optional]

     Called to allow the netfs to request an expansion of a readahead
     request to meet its own alignment requirements.  This is done by
     changing rreq->start and rreq->len.

 (*) clamp_length() [optional]

     Called to allow the netfs to cut down a subrequest to meet its own
     boundary requirements.  If it does this, the helper will generate
     additional subrequests until the full request is satisfied.

 (*) is_still_valid() [optional]

     Called to find out if the data just read from the cache has been
     invalidated and must be reread from the server.

 (*) issue_op() [required]

     Called to ask the netfs to issue a read to the server.  The subrequest
     describes the read.  The read request holds information about the file
     being accessed.

     The netfs can cache information in rreq->netfs_priv.

     Upon completion, the netfs should set the error, transferred and can
     also set FSCACHE_SREQ_CLEAR_TAIL and then call
     fscache_subreq_terminated().

 (*) done() [optional]

     Called after the pages have been unlocked.  The read request is still
     pinning the file and mapping and may still be pinning pages with
     PG_fscache.  rreq->error indicates any error that has been
     accumulated.

 (*) cleanup() [optional]

     Called when the helper is disposing of a finished read request.  This
     allows the netfs to clear rreq->netfs_priv.

Netfs support is enabled with CONFIG_NETFS_SUPPORT=y.  It will be built
even if CONFIG_FSCACHE=n and in this case much of it should be optimised
away, allowing the filesystem to use it even when caching is disabled.

Changes:
v5:
 - Comment why netfs_readahead() is putting pages[2].
 - Use page_file_mapping() rather than page->mapping[2].
 - Use page_index() rather than page->index[2].
 - Use set_page_fscache()[3] rather then SetPageFsCache() as this takes an
   appropriate ref too[4].

v4:
 - Folded in a kerneldoc comment fix.
 - Folded in a fix for the error handling in the case that ENOMEM occurs.
 - Added flag to netfs_subreq_terminated() to indicate that the caller may
   have been running async and stuff that might sleep needs punting to a
   workqueue (can't use in_softirq()[1]).

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-and-tested-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Dave Wysochanski <dwysocha@redhat.com>
Tested-By: Marc Dionne <marc.dionne@auristor.com>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-mm@kvack.org
cc: linux-cachefs@redhat.com
cc: linux-afs@lists.infradead.org
cc: linux-nfs@vger.kernel.org
cc: linux-cifs@vger.kernel.org
cc: ceph-devel@vger.kernel.org
cc: v9fs-developer@lists.sourceforge.net
cc: linux-fsdevel@vger.kernel.org
Link: https://lore.kernel.org/r/20210216084230.GA23669@lst.de/ [1]
Link: https://lore.kernel.org/r/20210321014202.GF3420@casper.infradead.org/ [2]
Link: https://lore.kernel.org/r/2499407.1616505440@warthog.procyon.org.uk/ [3]
Link: https://lore.kernel.org/r/CAHk-=wh+2gbF7XEjYc=HV9w_2uVzVf7vs60BPz0gFA=+pUm3ww@mail.gmail.com/ [4]
Link: https://lore.kernel.org/r/160588497406.3465195.18003475695899726222.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/161118136849.1232039.8923686136144228724.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/161161032290.2537118.13400578415247339173.stgit@warthog.procyon.org.uk/ # v2
Link: https://lore.kernel.org/r/161340394873.1303470.6237319335883242536.stgit@warthog.procyon.org.uk/ # v3
Link: https://lore.kernel.org/r/161539537375.286939.16642940088716990995.stgit@warthog.procyon.org.uk/ # v4
Link: https://lore.kernel.org/r/161653795430.2770958.4947584573720000554.stgit@warthog.procyon.org.uk/ # v5
Link: https://lore.kernel.org/r/161789076581.6155.6745849361504760209.stgit@warthog.procyon.org.uk/ # v6

1 files changed, 83 insertions, 0 deletions

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 8479d63406f7..59e926e62d2e 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -14,6 +14,8 @@
 #ifndef _LINUX_NETFS_H
 #define _LINUX_NETFS_H
 
+#include <linux/workqueue.h>
+#include <linux/fs.h>
 #include <linux/pagemap.h>
 
 /*
@@ -83,4 +85,85 @@ static inline int wait_on_page_fscache_killable(struct page *page)
 	return wait_on_page_private_2_killable(page);
 }
 
+enum netfs_read_source {
+	NETFS_FILL_WITH_ZEROES,
+	NETFS_DOWNLOAD_FROM_SERVER,
+	NETFS_READ_FROM_CACHE,
+	NETFS_INVALID_READ,
+} __mode(byte);
+
+/*
+ * Descriptor for a single component subrequest.
+ */
+struct netfs_read_subrequest {
+	struct netfs_read_request *rreq;	/* Supervising read request */
+	struct list_head	rreq_link;	/* Link in rreq->subrequests */
+	loff_t			start;		/* Where to start the I/O */
+	size_t			len;		/* Size of the I/O */
+	size_t			transferred;	/* Amount of data transferred */
+	refcount_t		usage;
+	short			error;		/* 0 or error that occurred */
+	unsigned short		debug_index;	/* Index in list (for debugging output) */
+	enum netfs_read_source	source;		/* Where to read from */
+	unsigned long		flags;
+#define NETFS_SREQ_WRITE_TO_CACHE	0	/* Set if should write to cache */
+#define NETFS_SREQ_CLEAR_TAIL		1	/* Set if the rest of the read should be cleared */
+#define NETFS_SREQ_SHORT_READ		2	/* Set if there was a short read from the cache */
+#define NETFS_SREQ_SEEK_DATA_READ	3	/* Set if ->read() should SEEK_DATA first */
+#define NETFS_SREQ_NO_PROGRESS		4	/* Set if we didn't manage to read any data */
+};
+
+/*
+ * Descriptor for a read helper request.  This is used to make multiple I/O
+ * requests on a variety of sources and then stitch the result together.
+ */
+struct netfs_read_request {
+	struct work_struct	work;
+	struct inode		*inode;		/* The file being accessed */
+	struct address_space	*mapping;	/* The mapping being accessed */
+	struct list_head	subrequests;	/* Requests to fetch I/O from disk or net */
+	void			*netfs_priv;	/* Private data for the netfs */
+	unsigned int		debug_id;
+	atomic_t		nr_rd_ops;	/* Number of read ops in progress */
+	size_t			submitted;	/* Amount submitted for I/O so far */
+	size_t			len;		/* Length of the request */
+	short			error;		/* 0 or error that occurred */
+	loff_t			i_size;		/* Size of the file */
+	loff_t			start;		/* Start position */
+	pgoff_t			no_unlock_page;	/* Don't unlock this page after read */
+	refcount_t		usage;
+	unsigned long		flags;
+#define NETFS_RREQ_INCOMPLETE_IO	0	/* Some ioreqs terminated short or with error */
+#define NETFS_RREQ_WRITE_TO_CACHE	1	/* Need to write to the cache */
+#define NETFS_RREQ_NO_UNLOCK_PAGE	2	/* Don't unlock no_unlock_page on completion */
+#define NETFS_RREQ_DONT_UNLOCK_PAGES	3	/* Don't unlock the pages on completion */
+#define NETFS_RREQ_FAILED		4	/* The request failed */
+#define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
+	const struct netfs_read_request_ops *netfs_ops;
+};
+
+/*
+ * Operations the network filesystem can/must provide to the helpers.
+ */
+struct netfs_read_request_ops {
+	void (*init_rreq)(struct netfs_read_request *rreq, struct file *file);
+	void (*expand_readahead)(struct netfs_read_request *rreq);
+	bool (*clamp_length)(struct netfs_read_subrequest *subreq);
+	void (*issue_op)(struct netfs_read_subrequest *subreq);
+	bool (*is_still_valid)(struct netfs_read_request *rreq);
+	void (*done)(struct netfs_read_request *rreq);
+	void (*cleanup)(struct address_space *mapping, void *netfs_priv);
+};
+
+struct readahead_control;
+extern void netfs_readahead(struct readahead_control *,
+			    const struct netfs_read_request_ops *,
+			    void *);
+extern int netfs_readpage(struct file *,
+			  struct page *,
+			  const struct netfs_read_request_ops *,
+			  void *);
+
+extern void netfs_subreq_terminated(struct netfs_read_subrequest *, ssize_t, bool);
+
 #endif /* _LINUX_NETFS_H */