netfs: Change the read result collector to only use one work item

Change the way netfslib collects read results to do all the collection for
a particular read request using a single work item that walks along the
subrequest queue as subrequests make progress or complete, unlocking folios
progressively rather than doing the unlock in parallel as parallel requests
come in.

The code is remodelled to be more like the write-side code, though only
using a single stream.  This makes it more directly comparable and thus
easier to duplicate fixes between the two sides.

This has a number of advantages:

 (1) It's simpler.  There doesn't need to be a complex donation mechanism
     to handle mismatches between the size and alignment of subrequests and
     folios.  The collector unlocks folios as the subrequests covering each
     complete.

 (2) It should cause less scheduler overhead as there's a single work item
     in play unlocking pages in parallel when a read gets split up into a
     lot of subrequests instead of one per subrequest.

     Whilst the parallellism is nice in theory, in practice, the vast
     majority of loads are sequential reads of the whole file, so
     committing a bunch of threads to unlocking folios out of order doesn't
     help in those cases.

 (3) It should make it easier to implement content decryption.  A folio
     cannot be decrypted until all the requests that contribute to it have
     completed - and, again, most loads are sequential and so, most of the
     time, we want to begin decryption sequentially (though it's great if
     the decryption can happen in parallel).

There is a disadvantage in that we're losing the ability to decrypt and
unlock things on an as-things-arrive basis which may affect some
applications.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20241216204124.3752367-28-dhowells@redhat.com
cc: Jeff Layton <jlayton@kernel.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 6 insertions, 10 deletions

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 27e62f7d2940..071d05d81d38 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -181,9 +181,6 @@ struct netfs_io_subrequest {
 	unsigned long long	start;		/* Where to start the I/O */
 	size_t			len;		/* Size of the I/O */
 	size_t			transferred;	/* Amount of data transferred */
-	size_t			consumed;	/* Amount of read data consumed */
-	size_t			prev_donated;	/* Amount of data donated from previous subreq */
-	size_t			next_donated;	/* Amount of data donated from next subreq */
 	refcount_t		ref;
 	short			error;		/* 0 or error that occurred */
 	unsigned short		debug_index;	/* Index in list (for debugging output) */
@@ -191,9 +188,6 @@ struct netfs_io_subrequest {
 	u8			retry_count;	/* The number of retries (0 on initial pass) */
 	enum netfs_io_source	source;		/* Where to read from/write to */
 	unsigned char		stream_nr;	/* I/O stream this belongs to */
-	unsigned char		curr_folioq_slot; /* Folio currently being read */
-	unsigned char		curr_folio_order; /* Order of folio */
-	struct folio_queue	*curr_folioq;	/* Queue segment in which current folio resides */
 	unsigned long		flags;
 #define NETFS_SREQ_COPY_TO_CACHE	0	/* Set if should copy the data to the cache */
 #define NETFS_SREQ_CLEAR_TAIL		1	/* Set if the rest of the read should be cleared */
@@ -236,15 +230,16 @@ struct netfs_io_request {
 	struct address_space	*mapping;	/* The mapping being accessed */
 	struct kiocb		*iocb;		/* AIO completion vector */
 	struct netfs_cache_resources cache_resources;
+	struct netfs_io_request	*copy_to_cache;	/* Request to write just-read data to the cache */
 	struct readahead_control *ractl;	/* Readahead descriptor */
 	struct list_head	proc_link;	/* Link in netfs_iorequests */
-	struct list_head	subrequests;	/* Contributory I/O operations */
 	struct netfs_io_stream	io_streams[2];	/* Streams of parallel I/O operations */
 #define NR_IO_STREAMS 2 //wreq->nr_io_streams
 	struct netfs_group	*group;		/* Writeback group being written back */
 	struct rolling_buffer	buffer;		/* Unencrypted buffer */
 #define NETFS_ROLLBUF_PUT_MARK		ROLLBUF_MARK_1
 #define NETFS_ROLLBUF_PAGECACHE_MARK	ROLLBUF_MARK_2
+	wait_queue_head_t	waitq;		/* Processor waiter */
 	void			*netfs_priv;	/* Private data for the netfs */
 	void			*netfs_priv2;	/* Private data for the netfs */
 	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
@@ -255,7 +250,6 @@ struct netfs_io_request {
 	atomic_t		subreq_counter;	/* Next subreq->debug_index */
 	unsigned int		nr_group_rel;	/* Number of refs to release on ->group */
 	spinlock_t		lock;		/* Lock for queuing subreqs */
-	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	unsigned long long	submitted;	/* Amount submitted for I/O so far */
 	unsigned long long	len;		/* Length of the request */
 	size_t			transferred;	/* Amount to be indicated as transferred */
@@ -267,14 +261,17 @@ struct netfs_io_request {
 	atomic64_t		issued_to;	/* Write issuer folio cursor */
 	unsigned long long	collected_to;	/* Point we've collected to */
 	unsigned long long	cleaned_to;	/* Position we've cleaned folios to */
+	unsigned long long	abandon_to;	/* Position to abandon folios to */
 	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
-	size_t			prev_donated;	/* Fallback for subreq->prev_donated */
+	unsigned char		front_folio_order; /* Order (size) of front folio */
 	refcount_t		ref;
 	unsigned long		flags;
+#define NETFS_RREQ_OFFLOAD_COLLECTION	0	/* Offload collection to workqueue */
 #define NETFS_RREQ_NO_UNLOCK_FOLIO	2	/* Don't unlock no_unlock_folio on completion */
 #define NETFS_RREQ_DONT_UNLOCK_FOLIOS	3	/* Don't unlock the folios on completion */
 #define NETFS_RREQ_FAILED		4	/* The request failed */
 #define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
+#define NETFS_RREQ_FOLIO_COPY_TO_CACHE	6	/* Copy current folio to cache from read */
 #define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
 #define NETFS_RREQ_NONBLOCK		9	/* Don't block if possible (O_NONBLOCK) */
 #define NETFS_RREQ_BLOCKED		10	/* We blocked */
@@ -439,7 +436,6 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 /* (Sub)request management API. */
 void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq);
 void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq);
-void netfs_read_subreq_termination_worker(struct work_struct *work);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
 void netfs_put_subrequest(struct netfs_io_subrequest *subreq,