mm: submit multipage write for SWP_FS_OPS swap-space

swap_writepage() is given one page at a time, but may be called repeatedly
in succession.

For block-device swapspace, the blk_plug functionality allows the multiple
pages to be combined together at lower layers.  That cannot be used for
SWP_FS_OPS as blk_plug may not exist - it is only active when
CONFIG_BLOCK=y.  Consequently all swap reads over NFS are single page
reads.

With this patch we pass a pointer-to-pointer via the wbc.  swap_writepage
can store state between calls - much like the pointer passed explicitly to
swap_readpage.  After calling swap_writepage() some number of times, the
state will be passed to swap_write_unplug() which can submit the combined
request.

Link: https://lkml.kernel.org/r/164859778128.29473.5191868522654408537.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/writeback.h

@@ -80,6 +80,13 @@ struct writeback_control {
 
 	unsigned punt_to_cgroup:1;	/* cgrp punting, see __REQ_CGROUP_PUNT */
 
+	/* To enable batching of swap writes to non-block-device backends,
+	 * "plug" can be set point to a 'struct swap_iocb *'.  When all swap
+	 * writes have been submitted, if with swap_iocb is not NULL,
+	 * swap_write_unplug() should be called.
+	 */
+	struct swap_iocb **swap_plug;
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct bdi_writeback *wb;	/* wb this writeback is issued under */
 	struct inode *inode;		/* inode being written out */

mm/page_io.c

@@ -259,8 +259,9 @@ static void sio_write_complete(struct kiocb *iocb, long ret)
 {
 	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
 	struct page *page = sio->bvec[0].bv_page;
+	int p;
 
-	if (ret != PAGE_SIZE) {
+	if (ret != PAGE_SIZE * sio->pages) {
 		/*
 		 * In the case of swap-over-nfs, this can be a
 		 * temporary failure if the system has limited
@@ -271,39 +272,59 @@ static void sio_write_complete(struct kiocb *iocb, long ret)
 		 * the normal direct-to-bio case as it could
 		 * be temporary.
 		 */
-		set_page_dirty(page);
-		ClearPageReclaim(page);
 		pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
 				   ret, page_file_offset(page));
+		for (p = 0; p < sio->pages; p++) {
+			page = sio->bvec[p].bv_page;
+			set_page_dirty(page);
+			ClearPageReclaim(page);
+		}
 	} else
-		count_vm_event(PSWPOUT);
-	end_page_writeback(page);
+		count_vm_events(PSWPOUT, sio->pages);
+
+	for (p = 0; p < sio->pages; p++)
+		end_page_writeback(sio->bvec[p].bv_page);
+
 	mempool_free(sio, sio_pool);
 }
 
 static int swap_writepage_fs(struct page *page, struct writeback_control *wbc)
 {
-	struct swap_iocb *sio;
+	struct swap_iocb *sio = NULL;
 	struct swap_info_struct *sis = page_swap_info(page);
 	struct file *swap_file = sis->swap_file;
-	struct address_space *mapping = swap_file->f_mapping;
-	struct iov_iter from;
-	int ret;
+	loff_t pos = page_file_offset(page);
 
 	set_page_writeback(page);
 	unlock_page(page);
+	if (wbc->swap_plug)
+		sio = *wbc->swap_plug;
+	if (sio) {
+		if (sio->iocb.ki_filp != swap_file ||
+		    sio->iocb.ki_pos + sio->pages * PAGE_SIZE != pos) {
+			swap_write_unplug(sio);
+			sio = NULL;
+		}
+	}
+	if (!sio) {
 		sio = mempool_alloc(sio_pool, GFP_NOIO);
 		init_sync_kiocb(&sio->iocb, swap_file);
 		sio->iocb.ki_complete = sio_write_complete;
-	sio->iocb.ki_pos = page_file_offset(page);
-	sio->bvec[0].bv_page = page;
-	sio->bvec[0].bv_len = PAGE_SIZE;
-	sio->bvec[0].bv_offset = 0;
-	iov_iter_bvec(&from, WRITE, &sio->bvec[0], 1, PAGE_SIZE);
-	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
-	if (ret != -EIOCBQUEUED)
-		sio_write_complete(&sio->iocb, ret);
-	return ret;
+		sio->iocb.ki_pos = pos;
+		sio->pages = 0;
+	}
+	sio->bvec[sio->pages].bv_page = page;
+	sio->bvec[sio->pages].bv_len = PAGE_SIZE;
+	sio->bvec[sio->pages].bv_offset = 0;
+	sio->pages += 1;
+	if (sio->pages == ARRAY_SIZE(sio->bvec) || !wbc->swap_plug) {
+		swap_write_unplug(sio);
+		sio = NULL;
+	}
+	if (wbc->swap_plug)
+		*wbc->swap_plug = sio;
+
+	return 0;
 }
 
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
@@ -344,6 +365,19 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	return 0;
 }
 
+void swap_write_unplug(struct swap_iocb *sio)
+{
+	struct iov_iter from;
+	struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
+	int ret;
+
+	iov_iter_bvec(&from, WRITE, sio->bvec, sio->pages,
+		      PAGE_SIZE * sio->pages);
+	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	if (ret != -EIOCBQUEUED)
+		sio_write_complete(&sio->iocb, ret);
+}
+
 static void sio_read_complete(struct kiocb *iocb, long ret)
 {
 	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);

mm/swap.h

@@ -16,6 +16,7 @@ static inline void swap_read_unplug(struct swap_iocb *plug)
 	if (unlikely(plug))
 		__swap_read_unplug(plug);
 }
+void swap_write_unplug(struct swap_iocb *sio);
 int swap_writepage(struct page *page, struct writeback_control *wbc);
 void end_swap_bio_write(struct bio *bio);
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
@@ -71,6 +72,9 @@ static inline int swap_readpage(struct page *page, bool do_poll,
 {
 	return 0;
 }
+static inline void swap_write_unplug(struct swap_iocb *sio)
+{
+}
 
 static inline struct address_space *swap_address_space(swp_entry_t entry)
 {

mm/vmscan.c

@@ -1156,7 +1156,8 @@ typedef enum {
  * pageout is called by shrink_page_list() for each dirty page.
  * Calls ->writepage().
  */
-static pageout_t pageout(struct folio *folio, struct address_space *mapping)
+static pageout_t pageout(struct folio *folio, struct address_space *mapping,
+			 struct swap_iocb **plug)
 {
 	/*
 	 * If the folio is dirty, only perform writeback if that write
@@ -1201,6 +1202,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping)
 			.range_start = 0,
 			.range_end = LLONG_MAX,
 			.for_reclaim = 1,
+			.swap_plug = plug,
 		};
 
 		folio_set_reclaim(folio);
@@ -1533,6 +1535,7 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 	unsigned int nr_reclaimed = 0;
 	unsigned int pgactivate = 0;
 	bool do_demote_pass;
+	struct swap_iocb *plug = NULL;
 
 	memset(stat, 0, sizeof(*stat));
 	cond_resched();
@@ -1814,7 +1817,7 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 			 * starts and then write it out here.
 			 */
 			try_to_unmap_flush_dirty();
-			switch (pageout(folio, mapping)) {
+			switch (pageout(folio, mapping, &plug)) {
 			case PAGE_KEEP:
 				goto keep_locked;
 			case PAGE_ACTIVATE:
@@ -1968,6 +1971,8 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
 
+	if (plug)
+		swap_write_unplug(plug);
 	return nr_reclaimed;
 }