netfs: Use new folio_queue data type and iterator instead of xarray iter

Make the netfs write-side routines use the new folio_queue struct to hold a
rolling buffer of folios, with the issuer adding folios at the tail and the
collector removing them from the head as they're processed instead of using
an xarray.

This will allow a subsequent patch to simplify the write collector.

The primary mark (as tested by folioq_is_marked()) is used to note if the
corresponding folio needs putting.

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/netfs/internal.h

···
 
 #include <linux/slab.h>
 #include <linux/seq_file.h>
+#include <linux/folio_queue.h>
 #include <linux/netfs.h>
 #include <linux/fscache.h>
 #include <linux/fscache-cache.h>
···
 /*
  * misc.c
  */
+int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio,
+			      bool needs_put);
+struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq);
+void netfs_clear_buffer(struct netfs_io_request *rreq);
 
 /*
  * objects.c
···
 extern atomic_t netfs_n_wh_write_failed;
 extern atomic_t netfs_n_wb_lock_skip;
 extern atomic_t netfs_n_wb_lock_wait;
+extern atomic_t netfs_n_folioq;
 
 int netfs_stats_show(struct seq_file *m, void *v);
 
···
 						loff_t start,
 						enum netfs_io_origin origin);
 void netfs_reissue_write(struct netfs_io_stream *stream,
-			 struct netfs_io_subrequest *subreq);
+			 struct netfs_io_subrequest *subreq,
+			 struct iov_iter *source);
 int netfs_advance_write(struct netfs_io_request *wreq,
 			struct netfs_io_stream *stream,
 			loff_t start, size_t len, bool to_eof);

fs/netfs/misc.c

···
 #include <linux/swap.h>
 #include "internal.h"
 
+/*
+ * Append a folio to the rolling queue.
+ */
+int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio,
+			      bool needs_put)
+{
+	struct folio_queue *tail = rreq->buffer_tail;
+	unsigned int slot, order = folio_order(folio);
+
+	if (WARN_ON_ONCE(!rreq->buffer && tail) ||
+	    WARN_ON_ONCE(rreq->buffer && !tail))
+		return -EIO;
+
+	if (!tail || folioq_full(tail)) {
+		tail = kmalloc(sizeof(*tail), GFP_NOFS);
+		if (!tail)
+			return -ENOMEM;
+		netfs_stat(&netfs_n_folioq);
+		folioq_init(tail);
+		tail->prev = rreq->buffer_tail;
+		if (tail->prev)
+			tail->prev->next = tail;
+		rreq->buffer_tail = tail;
+		if (!rreq->buffer) {
+			rreq->buffer = tail;
+			iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0);
+		}
+		rreq->buffer_tail_slot = 0;
+	}
+
+	rreq->io_iter.count += PAGE_SIZE << order;
+
+	slot = folioq_append(tail, folio);
+	/* Store the counter after setting the slot. */
+	smp_store_release(&rreq->buffer_tail_slot, slot);
+	return 0;
+}
+
+/*
+ * Delete the head of a rolling queue.
+ */
+struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq)
+{
+	struct folio_queue *head = wreq->buffer, *next = head->next;
+
+	if (next)
+		next->prev = NULL;
+	netfs_stat_d(&netfs_n_folioq);
+	kfree(head);
+	wreq->buffer = next;
+	return next;
+}
+
+/*
+ * Clear out a rolling queue.
+ */
+void netfs_clear_buffer(struct netfs_io_request *rreq)
+{
+	struct folio_queue *p;
+
+	while ((p = rreq->buffer)) {
+		rreq->buffer = p->next;
+		for (int slot = 0; slot < folioq_nr_slots(p); slot++) {
+			struct folio *folio = folioq_folio(p, slot);
+			if (!folio)
+				continue;
+			if (folioq_is_marked(p, slot)) {
+				trace_netfs_folio(folio, netfs_folio_trace_put);
+				folio_put(folio);
+			}
+		}
+		netfs_stat_d(&netfs_n_folioq);
+		kfree(p);
+	}
+}
+
 /**
  * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback
  * @mapping: The mapping the folio belongs to.

fs/netfs/objects.c

···
 		}
 		kvfree(rreq->direct_bv);
 	}
+	netfs_clear_buffer(rreq);
 
 	if (atomic_dec_and_test(&ictx->io_count))
 		wake_up_var(&ictx->io_count);

fs/netfs/stats.c

···
 atomic_t netfs_n_wh_write_failed;
 atomic_t netfs_n_wb_lock_skip;
 atomic_t netfs_n_wb_lock_wait;
+atomic_t netfs_n_folioq;
 
 int netfs_stats_show(struct seq_file *m, void *v)
 {
···
 		   atomic_read(&netfs_n_wh_write),
 		   atomic_read(&netfs_n_wh_write_done),
 		   atomic_read(&netfs_n_wh_write_failed));
-	seq_printf(m, "Objs   : rr=%u sr=%u wsc=%u\n",
+	seq_printf(m, "Objs   : rr=%u sr=%u foq=%u wsc=%u\n",
 		   atomic_read(&netfs_n_rh_rreq),
 		   atomic_read(&netfs_n_rh_sreq),
+		   atomic_read(&netfs_n_folioq),
 		   atomic_read(&netfs_n_wh_wstream_conflict));
 	seq_printf(m, "WbLock : skip=%u wait=%u\n",
 		   atomic_read(&netfs_n_wb_lock_skip),

fs/netfs/write_collect.c

···
 }
 
 /*
- * Get hold of a folio we have under writeback.  We don't want to get the
- * refcount on it.
- */
-static struct folio *netfs_writeback_lookup_folio(struct netfs_io_request *wreq, loff_t pos)
-{
-	XA_STATE(xas, &wreq->mapping->i_pages, pos / PAGE_SIZE);
-	struct folio *folio;
-
-	rcu_read_lock();
-
-	for (;;) {
-		xas_reset(&xas);
-		folio = xas_load(&xas);
-		if (xas_retry(&xas, folio))
-			continue;
-
-		if (!folio || xa_is_value(folio))
-			kdebug("R=%08x: folio %lx (%llx) not present",
-			       wreq->debug_id, xas.xa_index, pos / PAGE_SIZE);
-		BUG_ON(!folio || xa_is_value(folio));
-
-		if (folio == xas_reload(&xas))
-			break;
-	}
-
-	rcu_read_unlock();
-
-	if (WARN_ONCE(!folio_test_writeback(folio),
-		      "R=%08x: folio %lx is not under writeback\n",
-		      wreq->debug_id, folio->index)) {
-		trace_netfs_folio(folio, netfs_folio_trace_not_under_wback);
-	}
-	return folio;
-}
-
-/*
  * Unlock any folios we've finished with.
  */
 static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq,
 					  unsigned long long collected_to,
 					  unsigned int *notes)
 {
+	struct folio_queue *folioq = wreq->buffer;
+	unsigned int slot = wreq->buffer_head_slot;
+
+	if (slot >= folioq_nr_slots(folioq)) {
+		folioq = netfs_delete_buffer_head(wreq);
+		slot = 0;
+	}
+
 	for (;;) {
 		struct folio *folio;
 		struct netfs_folio *finfo;
 		unsigned long long fpos, fend;
 		size_t fsize, flen;
 
-		folio = netfs_writeback_lookup_folio(wreq, wreq->cleaned_to);
+		folio = folioq_folio(folioq, slot);
+		if (WARN_ONCE(!folio_test_writeback(folio),
+			      "R=%08x: folio %lx is not under writeback\n",
+			      wreq->debug_id, folio->index))
+			trace_netfs_folio(folio, netfs_folio_trace_not_under_wback);
 
 		fpos = folio_pos(folio);
 		fsize = folio_size(folio);
···
 		wreq->cleaned_to = fpos + fsize;
 		*notes |= MADE_PROGRESS;
 
+		/* Clean up the head folioq.  If we clear an entire folioq, then
+		 * we can get rid of it provided it's not also the tail folioq
+		 * being filled by the issuer.
+		 */
+		folioq_clear(folioq, slot);
+		slot++;
+		if (slot >= folioq_nr_slots(folioq)) {
+			if (READ_ONCE(wreq->buffer_tail) == folioq)
+				break;
+			folioq = netfs_delete_buffer_head(wreq);
+			slot = 0;
+		}
+
 		if (fpos + fsize >= collected_to)
 			break;
 	}
+
+	wreq->buffer = folioq;
+	wreq->buffer_head_slot = slot;
 }
 
 /*
···
 			if (test_bit(NETFS_SREQ_FAILED, &subreq->flags))
 				break;
 			if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) {
+				struct iov_iter source = subreq->io_iter;
+
+				iov_iter_revert(&source, subreq->len - source.count);
 				__set_bit(NETFS_SREQ_RETRYING, &subreq->flags);
 				netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
-				netfs_reissue_write(stream, subreq);
+				netfs_reissue_write(stream, subreq, &source);
 			}
 		}
 		return;
···
 
 	do {
 		struct netfs_io_subrequest *subreq = NULL, *from, *to, *tmp;
+		struct iov_iter source;
 		unsigned long long start, len;
 		size_t part;
 		bool boundary = false;
···
 			len += to->len;
 		}
 
+		/* Determine the set of buffers we're going to use.  Each
+		 * subreq gets a subset of a single overall contiguous buffer.
+		 */
+		source = from->io_iter;
+		iov_iter_revert(&source, subreq->len - source.count);
+		iov_iter_advance(&source, from->transferred);
+		source.count = len;
+
 		/* Work through the sublist. */
 		subreq = from;
 		list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) {
···
 				boundary = true;
 
 			netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
-			netfs_reissue_write(stream, subreq);
+			netfs_reissue_write(stream, subreq, &source);
 			if (subreq == to)
 				break;
 		}
···
 				boundary = false;
 			}
 
-			netfs_reissue_write(stream, subreq);
+			netfs_reissue_write(stream, subreq, &source);
 			if (!len)
 				break;
 

fs/netfs/write_issue.c

···
  * netfs_write_subrequest_terminated() when complete.
  */
 static void netfs_do_issue_write(struct netfs_io_stream *stream,
-				 struct netfs_io_subrequest *subreq)
+				 struct netfs_io_subrequest *subreq,
+				 struct iov_iter *source)
 {
 	struct netfs_io_request *wreq = subreq->rreq;
+	size_t size = subreq->len - subreq->transferred;
 
 	_enter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len);
 
···
 		return netfs_write_subrequest_terminated(subreq, subreq->error, false);
 
 	// TODO: Use encrypted buffer
-	if (test_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags)) {
-		subreq->io_iter = wreq->io_iter;
-		iov_iter_advance(&subreq->io_iter,
-				 subreq->start + subreq->transferred - wreq->start);
-		iov_iter_truncate(&subreq->io_iter,
-				 subreq->len - subreq->transferred);
-	} else {
-		iov_iter_xarray(&subreq->io_iter, ITER_SOURCE, &wreq->mapping->i_pages,
-				subreq->start + subreq->transferred,
-				subreq->len   - subreq->transferred);
-	}
+	subreq->io_iter = *source;
+	iov_iter_advance(source, size);
+	iov_iter_truncate(&subreq->io_iter, size);
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 	stream->issue_write(subreq);
 }
 
 void netfs_reissue_write(struct netfs_io_stream *stream,
-			 struct netfs_io_subrequest *subreq)
+			 struct netfs_io_subrequest *subreq,
+			 struct iov_iter *source)
 {
 	__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-	netfs_do_issue_write(stream, subreq);
+	netfs_do_issue_write(stream, subreq, source);
 }
 
 static void netfs_issue_write(struct netfs_io_request *wreq,
···
 
 	if (subreq->start + subreq->len > wreq->start + wreq->submitted)
 		WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start);
-	netfs_do_issue_write(stream, subreq);
+	netfs_do_issue_write(stream, subreq, &wreq->io_iter);
 }
 
 /*
···
 	} else {
 		trace_netfs_folio(folio, netfs_folio_trace_store_plus);
 	}
+
+	/* Attach the folio to the rolling buffer. */
+	netfs_buffer_append_folio(wreq, folio, false);
 
 	/* Move the submission point forward to allow for write-streaming data
 	 * not starting at the front of the page.  We don't do write-streaming

include/linux/netfs.h

···
 	folio_set_private_2(folio);
 }
 
-/* Marks used on xarray-based buffers */
-#define NETFS_BUF_PUT_MARK	XA_MARK_0	/* - Page needs putting  */
-#define NETFS_BUF_PAGECACHE_MARK XA_MARK_1	/* - Page needs wb/dirty flag wrangling */
-
 enum netfs_io_source {
 	NETFS_SOURCE_UNKNOWN,
 	NETFS_FILL_WITH_ZEROES,
···
 	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 folio_queue	*buffer;	/* Head of I/O buffer */
+	struct folio_queue	*buffer_tail;	/* Tail of I/O buffer */
 	struct iov_iter		iter;		/* Unencrypted-side iterator */
 	struct iov_iter		io_iter;	/* I/O (Encrypted-side) iterator */
 	void			*netfs_priv;	/* Private data for the netfs */
···
 	short			error;		/* 0 or error that occurred */
 	enum netfs_io_origin	origin;		/* Origin of the request */
 	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
+	u8			buffer_head_slot; /* First slot in ->buffer */
+	u8			buffer_tail_slot; /* Next slot in ->buffer_tail */
 	unsigned long long	i_size;		/* Size of the file */
 	unsigned long long	start;		/* Start position */
 	atomic64_t		issued_to;	/* Write issuer folio cursor */

include/trace/events/netfs.h

···
 	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
 	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
 	EM(netfs_folio_trace_not_under_wback,	"!wback")	\
+	EM(netfs_folio_trace_put,		"put")		\
 	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
 	EM(netfs_folio_trace_redirtied,		"redirtied")	\
 	EM(netfs_folio_trace_store,		"store")	\