cachefiles, netfs: Fix write to partial block at EOF

Because it uses DIO writes, cachefiles is unable to make a write to the
backing file if that write is not aligned to and sized according to the
backing file's DIO block alignment. This makes it tricky to handle a write
to the cache where the EOF on the network file is not correctly aligned.

To get around this, netfslib attempts to tell the driver it is calling how
much more data there is available beyond the EOF that it can use to pad the
write (netfslib preclears the part of the folio above the EOF). However,
it tries to tell the cache what the maximum length is, but doesn't
calculate this correctly; and, in any case, cachefiles actually ignores the
value and just skips the block.

Fix this by:

(1) Change the value passed to indicate the amount of extra data that can
be added to the operation (now ->submit_extendable_to). This is much
simpler to calculate as it's just the end of the folio minus the top
of the data within the folio - rather than having to account for data
spread over multiple folios.

(2) Make cachefiles add some of this data if the subrequest it is given
ends at the network file's i_size if the extra data is sufficient to
pad out to a whole block.

Signed-off-by: David Howells <[e-mail]>
cc: Jeff Layton <[e-mail]>
cc: [e-mail]
cc: [e-mail]
Link: https://lore.kernel.org/r/[e-mail]/ # v2
Signed-off-by: Christian Brauner <[e-mail]>

fs/cachefiles/io.c

···
 	struct netfs_cache_resources *cres = &wreq->cache_resources;
 	struct cachefiles_object *object = cachefiles_cres_object(cres);
 	struct cachefiles_cache *cache = object->volume->cache;
+	struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
 	const struct cred *saved_cred;
 	size_t off, pre, post, len = subreq->len;
 	loff_t start = subreq->start;
···
 	if (off) {
 		pre = CACHEFILES_DIO_BLOCK_SIZE - off;
 		if (pre >= len) {
+			fscache_count_dio_misfit();
 			netfs_write_subrequest_terminated(subreq, len, false);
 			return;
 		}
···
 	}
 
 	/* We also need to end on the cache granularity boundary */
+	if (start + len == wreq->i_size) {
+		size_t part = len % CACHEFILES_DIO_BLOCK_SIZE;
+		size_t need = CACHEFILES_DIO_BLOCK_SIZE - part;
+
+		if (part && stream->submit_extendable_to >= need) {
+			len += need;
+			subreq->len += need;
+			subreq->io_iter.count += need;
+		}
+	}
+
 	post = len & (CACHEFILES_DIO_BLOCK_SIZE - 1);
 	if (post) {
 		len -= post;
 		if (len == 0) {
+			fscache_count_dio_misfit();
 			netfs_write_subrequest_terminated(subreq, post, false);
 			return;
 		}

fs/netfs/read_pgpriv2.c

···
 	if (netfs_buffer_append_folio(wreq, folio, false) < 0)
 		return -ENOMEM;
 
-	cache->submit_max_len = fsize;
+	cache->submit_extendable_to = fsize;
 	cache->submit_off = 0;
 	cache->submit_len = flen;
 
···
 		wreq->io_iter.iov_offset = cache->submit_off;
 
 		atomic64_set(&wreq->issued_to, fpos + cache->submit_off);
+		cache->submit_extendable_to = fsize - cache->submit_off;
 		part = netfs_advance_write(wreq, cache, fpos + cache->submit_off,
 					   cache->submit_len, to_eof);
 		cache->submit_off += part;
-		cache->submit_max_len -= part;
 		if (part > cache->submit_len)
 			cache->submit_len = 0;
 		else

fs/netfs/write_issue.c

···
 	_debug("part %zx/%zx %zx/%zx", subreq->len, stream->sreq_max_len, part, len);
 	subreq->len += part;
 	subreq->nr_segs++;
+	stream->submit_extendable_to -= part;
 
 	if (subreq->len >= stream->sreq_max_len ||
 	    subreq->nr_segs >= stream->sreq_max_segs ||
···
 	 */
 	for (int s = 0; s < NR_IO_STREAMS; s++) {
 		stream = &wreq->io_streams[s];
-		stream->submit_max_len = fsize;
 		stream->submit_off = foff;
 		stream->submit_len = flen;
 		if ((stream->source == NETFS_WRITE_TO_CACHE && streamw) ||
···
 		     fgroup == NETFS_FOLIO_COPY_TO_CACHE)) {
 			stream->submit_off = UINT_MAX;
 			stream->submit_len = 0;
-			stream->submit_max_len = 0;
 		}
 	}
 
···
 		wreq->io_iter.iov_offset = stream->submit_off;
 
 		atomic64_set(&wreq->issued_to, fpos + stream->submit_off);
+		stream->submit_extendable_to = fsize - stream->submit_off;
 		part = netfs_advance_write(wreq, stream, fpos + stream->submit_off,
 					   stream->submit_len, to_eof);
 		stream->submit_off += part;
-		stream->submit_max_len -= part;
 		if (part > stream->submit_len)
 			stream->submit_len = 0;
 		else

include/linux/netfs.h

···
 	unsigned int		sreq_max_segs;	/* 0 or max number of segments in an iterator */
 	unsigned int		submit_off;	/* Folio offset we're submitting from */
 	unsigned int		submit_len;	/* Amount of data left to submit */
-	unsigned int		submit_max_len;	/* Amount I/O can be rounded up to */
+	unsigned int		submit_extendable_to; /* Amount I/O can be rounded up to */
 	void (*prepare_write)(struct netfs_io_subrequest *subreq);
 	void (*issue_write)(struct netfs_io_subrequest *subreq);
 	/* Collection tracking */