1 files changed, 507 insertions, 202 deletions

diff --git a/mm/page_io.c b/mm/page_io.c
index ba05b64e5d8d..3c342db77ce3 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  linux/mm/page_io.c
  *
@@ -17,119 +18,60 @@
 #include <linux/swap.h>
 #include <linux/bio.h>
 #include <linux/swapops.h>
-#include <linux/buffer_head.h>
 #include <linux/writeback.h>
-#include <linux/frontswap.h>
-#include <linux/aio.h>
 #include <linux/blkdev.h>
-#include <asm/pgtable.h>
-
-static struct bio *get_swap_bio(gfp_t gfp_flags,
-				struct page *page, bio_end_io_t end_io)
-{
-	struct bio *bio;
-
-	bio = bio_alloc(gfp_flags, 1);
-	if (bio) {
-		bio->bi_sector = map_swap_page(page, &bio->bi_bdev);
-		bio->bi_sector <<= PAGE_SHIFT - 9;
-		bio->bi_io_vec[0].bv_page = page;
-		bio->bi_io_vec[0].bv_len = PAGE_SIZE;
-		bio->bi_io_vec[0].bv_offset = 0;
-		bio->bi_vcnt = 1;
-		bio->bi_size = PAGE_SIZE;
-		bio->bi_end_io = end_io;
-	}
-	return bio;
-}
-
-void end_swap_bio_write(struct bio *bio, int err)
+#include <linux/psi.h>
+#include <linux/uio.h>
+#include <linux/sched/task.h>
+#include <linux/delayacct.h>
+#include <linux/zswap.h>
+#include "swap.h"
+
+static void __end_swap_bio_write(struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct page *page = bio->bi_io_vec[0].bv_page;
+	struct folio *folio = bio_first_folio_all(bio);
 
-	if (!uptodate) {
-		SetPageError(page);
+	if (bio->bi_status) {
 		/*
 		 * We failed to write the page out to swap-space.
 		 * Re-dirty the page in order to avoid it being reclaimed.
 		 * Also print a dire warning that things will go BAD (tm)
 		 * very quickly.
 		 *
-		 * Also clear PG_reclaim to avoid rotate_reclaimable_page()
+		 * Also clear PG_reclaim to avoid folio_rotate_reclaimable()
 		 */
-		set_page_dirty(page);
-		printk(KERN_ALERT "Write-error on swap-device (%u:%u:%Lu)\n",
-				imajor(bio->bi_bdev->bd_inode),
-				iminor(bio->bi_bdev->bd_inode),
-				(unsigned long long)bio->bi_sector);
-		ClearPageReclaim(page);
+		folio_mark_dirty(folio);
+		pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
+				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
+				     (unsigned long long)bio->bi_iter.bi_sector);
+		folio_clear_reclaim(folio);
 	}
-	end_page_writeback(page);
-	bio_put(bio);
+	folio_end_writeback(folio);
 }
 
-void end_swap_bio_read(struct bio *bio, int err)
+static void end_swap_bio_write(struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct page *page = bio->bi_io_vec[0].bv_page;
-
-	if (!uptodate) {
-		SetPageError(page);
-		ClearPageUptodate(page);
-		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
-				imajor(bio->bi_bdev->bd_inode),
-				iminor(bio->bi_bdev->bd_inode),
-				(unsigned long long)bio->bi_sector);
-		goto out;
-	}
+	__end_swap_bio_write(bio);
+	bio_put(bio);
+}
 
-	SetPageUptodate(page);
+static void __end_swap_bio_read(struct bio *bio)
+{
+	struct folio *folio = bio_first_folio_all(bio);
 
-	/*
-	 * There is no guarantee that the page is in swap cache - the software
-	 * suspend code (at least) uses end_swap_bio_read() against a non-
-	 * swapcache page.  So we must check PG_swapcache before proceeding with
-	 * this optimization.
-	 */
-	if (likely(PageSwapCache(page))) {
-		struct swap_info_struct *sis;
-
-		sis = page_swap_info(page);
-		if (sis->flags & SWP_BLKDEV) {
-			/*
-			 * The swap subsystem performs lazy swap slot freeing,
-			 * expecting that the page will be swapped out again.
-			 * So we can avoid an unnecessary write if the page
-			 * isn't redirtied.
-			 * This is good for real swap storage because we can
-			 * reduce unnecessary I/O and enhance wear-leveling
-			 * if an SSD is used as the as swap device.
-			 * But if in-memory swap device (eg zram) is used,
-			 * this causes a duplicated copy between uncompressed
-			 * data in VM-owned memory and compressed data in
-			 * zram-owned memory.  So let's free zram-owned memory
-			 * and make the VM-owned decompressed page *dirty*,
-			 * so the page should be swapped out somewhere again if
-			 * we again wish to reclaim it.
-			 */
-			struct gendisk *disk = sis->bdev->bd_disk;
-			if (disk->fops->swap_slot_free_notify) {
-				swp_entry_t entry;
-				unsigned long offset;
-
-				entry.val = page_private(page);
-				offset = swp_offset(entry);
-
-				SetPageDirty(page);
-				disk->fops->swap_slot_free_notify(sis->bdev,
-						offset);
-			}
-		}
+	if (bio->bi_status) {
+		pr_alert_ratelimited("Read-error on swap-device (%u:%u:%llu)\n",
+				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
+				     (unsigned long long)bio->bi_iter.bi_sector);
+	} else {
+		folio_mark_uptodate(folio);
 	}
+	folio_unlock(folio);
+}
 
-out:
-	unlock_page(page);
+static void end_swap_bio_read(struct bio *bio)
+{
+	__end_swap_bio_read(bio);
 	bio_put(bio);
 }
 
@@ -153,7 +95,7 @@ int generic_swapfile_activate(struct swap_info_struct *sis,
 	blocks_per_page = PAGE_SIZE >> blkbits;
 
 	/*
-	 * Map all the blocks into the extent list.  This code doesn't try
+	 * Map all the blocks into the extent tree.  This code doesn't try
 	 * to be very smart.
 	 */
 	probe_block = 0;
@@ -164,8 +106,11 @@ int generic_swapfile_activate(struct swap_info_struct *sis,
 		unsigned block_in_page;
 		sector_t first_block;
 
-		first_block = bmap(inode, probe_block);
-		if (first_block == 0)
+		cond_resched();
+
+		first_block = probe_block;
+		ret = bmap(inode, &first_block);
+		if (ret || !first_block)
 			goto bad_bmap;
 
 		/*
@@ -180,9 +125,11 @@ int generic_swapfile_activate(struct swap_info_struct *sis,
 					block_in_page++) {
 			sector_t block;
 
-			block = bmap(inode, probe_block + block_in_page);
-			if (block == 0)
+			block = probe_block + block_in_page;
+			ret = bmap(inode, &block);
+			if (ret || !block)
 				goto bad_bmap;
+
 			if (block != first_block + block_in_page) {
 				/* Discontiguity */
 				probe_block++;
@@ -216,149 +163,507 @@ reprobe:
 		page_no = 1;	/* force Empty message */
 	sis->max = page_no;
 	sis->pages = page_no - 1;
-	sis->highest_bit = page_no - 1;
 out:
 	return ret;
 bad_bmap:
-	printk(KERN_ERR "swapon: swapfile has holes\n");
+	pr_err("swapon: swapfile has holes\n");
 	ret = -EINVAL;
 	goto out;
 }
 
+static bool is_folio_zero_filled(struct folio *folio)
+{
+	unsigned int pos, last_pos;
+	unsigned long *data;
+	unsigned int i;
+
+	last_pos = PAGE_SIZE / sizeof(*data) - 1;
+	for (i = 0; i < folio_nr_pages(folio); i++) {
+		data = kmap_local_folio(folio, i * PAGE_SIZE);
+		/*
+		 * Check last word first, incase the page is zero-filled at
+		 * the start and has non-zero data at the end, which is common
+		 * in real-world workloads.
+		 */
+		if (data[last_pos]) {
+			kunmap_local(data);
+			return false;
+		}
+		for (pos = 0; pos < last_pos; pos++) {
+			if (data[pos]) {
+				kunmap_local(data);
+				return false;
+			}
+		}
+		kunmap_local(data);
+	}
+
+	return true;
+}
+
+static void swap_zeromap_folio_set(struct folio *folio)
+{
+	struct obj_cgroup *objcg = get_obj_cgroup_from_folio(folio);
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+	int nr_pages = folio_nr_pages(folio);
+	swp_entry_t entry;
+	unsigned int i;
+
+	for (i = 0; i < folio_nr_pages(folio); i++) {
+		entry = page_swap_entry(folio_page(folio, i));
+		set_bit(swp_offset(entry), sis->zeromap);
+	}
+
+	count_vm_events(SWPOUT_ZERO, nr_pages);
+	if (objcg) {
+		count_objcg_events(objcg, SWPOUT_ZERO, nr_pages);
+		obj_cgroup_put(objcg);
+	}
+}
+
+static void swap_zeromap_folio_clear(struct folio *folio)
+{
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+	swp_entry_t entry;
+	unsigned int i;
+
+	for (i = 0; i < folio_nr_pages(folio); i++) {
+		entry = page_swap_entry(folio_page(folio, i));
+		clear_bit(swp_offset(entry), sis->zeromap);
+	}
+}
+
 /*
  * We may have stale swap cache pages in memory: notice
  * them here and get rid of the unnecessary final write.
  */
-int swap_writepage(struct page *page, struct writeback_control *wbc)
+int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
 {
 	int ret = 0;
 
-	if (try_to_free_swap(page)) {
-		unlock_page(page);
-		goto out;
+	if (folio_free_swap(folio))
+		goto out_unlock;
+
+	/*
+	 * Arch code may have to preserve more data than just the page
+	 * contents, e.g. memory tags.
+	 */
+	ret = arch_prepare_to_swap(folio);
+	if (ret) {
+		folio_mark_dirty(folio);
+		goto out_unlock;
 	}
-	if (frontswap_store(page) == 0) {
-		set_page_writeback(page);
-		unlock_page(page);
-		end_page_writeback(page);
-		goto out;
+
+	/*
+	 * Use a bitmap (zeromap) to avoid doing IO for zero-filled pages.
+	 * The bits in zeromap are protected by the locked swapcache folio
+	 * and atomic updates are used to protect against read-modify-write
+	 * corruption due to other zero swap entries seeing concurrent updates.
+	 */
+	if (is_folio_zero_filled(folio)) {
+		swap_zeromap_folio_set(folio);
+		goto out_unlock;
 	}
-	ret = __swap_writepage(page, wbc, end_swap_bio_write);
-out:
+
+	/*
+	 * Clear bits this folio occupies in the zeromap to prevent zero data
+	 * being read in from any previous zero writes that occupied the same
+	 * swap entries.
+	 */
+	swap_zeromap_folio_clear(folio);
+
+	if (zswap_store(folio)) {
+		count_mthp_stat(folio_order(folio), MTHP_STAT_ZSWPOUT);
+		goto out_unlock;
+	}
+	if (!mem_cgroup_zswap_writeback_enabled(folio_memcg(folio))) {
+		folio_mark_dirty(folio);
+		return AOP_WRITEPAGE_ACTIVATE;
+	}
+
+	__swap_writepage(folio, swap_plug);
+	return 0;
+out_unlock:
+	folio_unlock(folio);
 	return ret;
 }
 
-int __swap_writepage(struct page *page, struct writeback_control *wbc,
-	void (*end_write_func)(struct bio *, int))
+static inline void count_swpout_vm_event(struct folio *folio)
 {
-	struct bio *bio;
-	int ret = 0, rw = WRITE;
-	struct swap_info_struct *sis = page_swap_info(page);
-
-	if (sis->flags & SWP_FILE) {
-		struct kiocb kiocb;
-		struct file *swap_file = sis->swap_file;
-		struct address_space *mapping = swap_file->f_mapping;
-		struct iovec iov = {
-			.iov_base = kmap(page),
-			.iov_len  = PAGE_SIZE,
-		};
-
-		init_sync_kiocb(&kiocb, swap_file);
-		kiocb.ki_pos = page_file_offset(page);
-		kiocb.ki_left = PAGE_SIZE;
-		kiocb.ki_nbytes = PAGE_SIZE;
-
-		set_page_writeback(page);
-		unlock_page(page);
-		ret = mapping->a_ops->direct_IO(KERNEL_WRITE,
-						&kiocb, &iov,
-						kiocb.ki_pos, 1);
-		kunmap(page);
-		if (ret == PAGE_SIZE) {
-			count_vm_event(PSWPOUT);
-			ret = 0;
-		} else {
-			/*
-			 * In the case of swap-over-nfs, this can be a
-			 * temporary failure if the system has limited
-			 * memory for allocating transmit buffers.
-			 * Mark the page dirty and avoid
-			 * rotate_reclaimable_page but rate-limit the
-			 * messages but do not flag PageError like
-			 * the normal direct-to-bio case as it could
-			 * be temporary.
-			 */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (unlikely(folio_test_pmd_mappable(folio))) {
+		count_memcg_folio_events(folio, THP_SWPOUT, 1);
+		count_vm_event(THP_SWPOUT);
+	}
+#endif
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT);
+	count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio));
+	count_vm_events(PSWPOUT, folio_nr_pages(folio));
+}
+
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+static void bio_associate_blkg_from_page(struct bio *bio, struct folio *folio)
+{
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *memcg;
+
+	memcg = folio_memcg(folio);
+	if (!memcg)
+		return;
+
+	rcu_read_lock();
+	css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys);
+	bio_associate_blkg_from_css(bio, css);
+	rcu_read_unlock();
+}
+#else
+#define bio_associate_blkg_from_page(bio, folio)		do { } while (0)
+#endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
+
+struct swap_iocb {
+	struct kiocb		iocb;
+	struct bio_vec		bvec[SWAP_CLUSTER_MAX];
+	int			pages;
+	int			len;
+};
+static mempool_t *sio_pool;
+
+int sio_pool_init(void)
+{
+	if (!sio_pool) {
+		mempool_t *pool = mempool_create_kmalloc_pool(
+			SWAP_CLUSTER_MAX, sizeof(struct swap_iocb));
+		if (cmpxchg(&sio_pool, NULL, pool))
+			mempool_destroy(pool);
+	}
+	if (!sio_pool)
+		return -ENOMEM;
+	return 0;
+}
+
+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 != sio->len) {
+		/*
+		 * In the case of swap-over-nfs, this can be a
+		 * temporary failure if the system has limited
+		 * memory for allocating transmit buffers.
+		 * Mark the page dirty and avoid
+		 * folio_rotate_reclaimable but rate-limit the
+		 * messages.
+		 */
+		pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
+				   ret, swap_dev_pos(page_swap_entry(page)));
+		for (p = 0; p < sio->pages; p++) {
+			page = sio->bvec[p].bv_page;
 			set_page_dirty(page);
 			ClearPageReclaim(page);
-			pr_err_ratelimited("Write error on dio swapfile (%Lu)\n",
-				page_file_offset(page));
 		}
-		end_page_writeback(page);
-		return ret;
 	}
 
-	bio = get_swap_bio(GFP_NOIO, page, end_write_func);
-	if (bio == NULL) {
-		set_page_dirty(page);
-		unlock_page(page);
-		ret = -ENOMEM;
-		goto out;
+	for (p = 0; p < sio->pages; p++)
+		end_page_writeback(sio->bvec[p].bv_page);
+
+	mempool_free(sio, sio_pool);
+}
+
+static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
+{
+	struct swap_iocb *sio = swap_plug ? *swap_plug : NULL;
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+	struct file *swap_file = sis->swap_file;
+	loff_t pos = swap_dev_pos(folio->swap);
+
+	count_swpout_vm_event(folio);
+	folio_start_writeback(folio);
+	folio_unlock(folio);
+	if (sio) {
+		if (sio->iocb.ki_filp != swap_file ||
+		    sio->iocb.ki_pos + sio->len != pos) {
+			swap_write_unplug(sio);
+			sio = NULL;
+		}
 	}
-	if (wbc->sync_mode == WB_SYNC_ALL)
-		rw |= REQ_SYNC;
-	count_vm_event(PSWPOUT);
-	set_page_writeback(page);
-	unlock_page(page);
-	submit_bio(rw, bio);
-out:
-	return ret;
+	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 = pos;
+		sio->pages = 0;
+		sio->len = 0;
+	}
+	bvec_set_folio(&sio->bvec[sio->pages], folio, folio_size(folio), 0);
+	sio->len += folio_size(folio);
+	sio->pages += 1;
+	if (sio->pages == ARRAY_SIZE(sio->bvec) || !swap_plug) {
+		swap_write_unplug(sio);
+		sio = NULL;
+	}
+	if (swap_plug)
+		*swap_plug = sio;
+}
+
+static void swap_writepage_bdev_sync(struct folio *folio,
+		struct swap_info_struct *sis)
+{
+	struct bio_vec bv;
+	struct bio bio;
+
+	bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_WRITE | REQ_SWAP);
+	bio.bi_iter.bi_sector = swap_folio_sector(folio);
+	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
+
+	bio_associate_blkg_from_page(&bio, folio);
+	count_swpout_vm_event(folio);
+
+	folio_start_writeback(folio);
+	folio_unlock(folio);
+
+	submit_bio_wait(&bio);
+	__end_swap_bio_write(&bio);
 }
 
-int swap_readpage(struct page *page)
+static void swap_writepage_bdev_async(struct folio *folio,
+		struct swap_info_struct *sis)
 {
 	struct bio *bio;
-	int ret = 0;
-	struct swap_info_struct *sis = page_swap_info(page);
-
-	VM_BUG_ON(!PageLocked(page));
-	VM_BUG_ON(PageUptodate(page));
-	if (frontswap_load(page) == 0) {
-		SetPageUptodate(page);
-		unlock_page(page);
-		goto out;
+
+	bio = bio_alloc(sis->bdev, 1, REQ_OP_WRITE | REQ_SWAP, GFP_NOIO);
+	bio->bi_iter.bi_sector = swap_folio_sector(folio);
+	bio->bi_end_io = end_swap_bio_write;
+	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
+
+	bio_associate_blkg_from_page(bio, folio);
+	count_swpout_vm_event(folio);
+	folio_start_writeback(folio);
+	folio_unlock(folio);
+	submit_bio(bio);
+}
+
+void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
+{
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+
+	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
+	/*
+	 * ->flags can be updated non-atomicially (scan_swap_map_slots),
+	 * but that will never affect SWP_FS_OPS, so the data_race
+	 * is safe.
+	 */
+	if (data_race(sis->flags & SWP_FS_OPS))
+		swap_writepage_fs(folio, swap_plug);
+	/*
+	 * ->flags can be updated non-atomicially (scan_swap_map_slots),
+	 * but that will never affect SWP_SYNCHRONOUS_IO, so the data_race
+	 * is safe.
+	 */
+	else if (data_race(sis->flags & SWP_SYNCHRONOUS_IO))
+		swap_writepage_bdev_sync(folio, sis);
+	else
+		swap_writepage_bdev_async(folio, sis);
+}
+
+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, ITER_SOURCE, sio->bvec, sio->pages, sio->len);
+	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);
+	int p;
+
+	if (ret == sio->len) {
+		for (p = 0; p < sio->pages; p++) {
+			struct folio *folio = page_folio(sio->bvec[p].bv_page);
+
+			count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
+			count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
+			folio_mark_uptodate(folio);
+			folio_unlock(folio);
+		}
+		count_vm_events(PSWPIN, sio->pages);
+	} else {
+		for (p = 0; p < sio->pages; p++) {
+			struct folio *folio = page_folio(sio->bvec[p].bv_page);
+
+			folio_unlock(folio);
+		}
+		pr_alert_ratelimited("Read-error on swap-device\n");
 	}
+	mempool_free(sio, sio_pool);
+}
 
-	if (sis->flags & SWP_FILE) {
-		struct file *swap_file = sis->swap_file;
-		struct address_space *mapping = swap_file->f_mapping;
+static bool swap_read_folio_zeromap(struct folio *folio)
+{
+	int nr_pages = folio_nr_pages(folio);
+	struct obj_cgroup *objcg;
+	bool is_zeromap;
 
-		ret = mapping->a_ops->readpage(swap_file, page);
-		if (!ret)
-			count_vm_event(PSWPIN);
-		return ret;
+	/*
+	 * Swapping in a large folio that is partially in the zeromap is not
+	 * currently handled. Return true without marking the folio uptodate so
+	 * that an IO error is emitted (e.g. do_swap_page() will sigbus).
+	 */
+	if (WARN_ON_ONCE(swap_zeromap_batch(folio->swap, nr_pages,
+			&is_zeromap) != nr_pages))
+		return true;
+
+	if (!is_zeromap)
+		return false;
+
+	objcg = get_obj_cgroup_from_folio(folio);
+	count_vm_events(SWPIN_ZERO, nr_pages);
+	if (objcg) {
+		count_objcg_events(objcg, SWPIN_ZERO, nr_pages);
+		obj_cgroup_put(objcg);
 	}
 
-	bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
-	if (bio == NULL) {
-		unlock_page(page);
-		ret = -ENOMEM;
-		goto out;
+	folio_zero_range(folio, 0, folio_size(folio));
+	folio_mark_uptodate(folio);
+	return true;
+}
+
+static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
+{
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+	struct swap_iocb *sio = NULL;
+	loff_t pos = swap_dev_pos(folio->swap);
+
+	if (plug)
+		sio = *plug;
+	if (sio) {
+		if (sio->iocb.ki_filp != sis->swap_file ||
+		    sio->iocb.ki_pos + sio->len != pos) {
+			swap_read_unplug(sio);
+			sio = NULL;
+		}
 	}
-	count_vm_event(PSWPIN);
-	submit_bio(READ, bio);
-out:
-	return ret;
+	if (!sio) {
+		sio = mempool_alloc(sio_pool, GFP_KERNEL);
+		init_sync_kiocb(&sio->iocb, sis->swap_file);
+		sio->iocb.ki_pos = pos;
+		sio->iocb.ki_complete = sio_read_complete;
+		sio->pages = 0;
+		sio->len = 0;
+	}
+	bvec_set_folio(&sio->bvec[sio->pages], folio, folio_size(folio), 0);
+	sio->len += folio_size(folio);
+	sio->pages += 1;
+	if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) {
+		swap_read_unplug(sio);
+		sio = NULL;
+	}
+	if (plug)
+		*plug = sio;
+}
+
+static void swap_read_folio_bdev_sync(struct folio *folio,
+		struct swap_info_struct *sis)
+{
+	struct bio_vec bv;
+	struct bio bio;
+
+	bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ);
+	bio.bi_iter.bi_sector = swap_folio_sector(folio);
+	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
+	/*
+	 * Keep this task valid during swap readpage because the oom killer may
+	 * attempt to access it in the page fault retry time check.
+	 */
+	get_task_struct(current);
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
+	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
+	count_vm_events(PSWPIN, folio_nr_pages(folio));
+	submit_bio_wait(&bio);
+	__end_swap_bio_read(&bio);
+	put_task_struct(current);
+}
+
+static void swap_read_folio_bdev_async(struct folio *folio,
+		struct swap_info_struct *sis)
+{
+	struct bio *bio;
+
+	bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL);
+	bio->bi_iter.bi_sector = swap_folio_sector(folio);
+	bio->bi_end_io = end_swap_bio_read;
+	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
+	count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
+	count_vm_events(PSWPIN, folio_nr_pages(folio));
+	submit_bio(bio);
 }
 
-int swap_set_page_dirty(struct page *page)
+void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
 {
-	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+	bool synchronous = sis->flags & SWP_SYNCHRONOUS_IO;
+	bool workingset = folio_test_workingset(folio);
+	unsigned long pflags;
+	bool in_thrashing;
+
+	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio) && !synchronous, folio);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+	VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio);
+
+	/*
+	 * Count submission time as memory stall and delay. When the device
+	 * is congested, or the submitting cgroup IO-throttled, submission
+	 * can be a significant part of overall IO time.
+	 */
+	if (workingset) {
+		delayacct_thrashing_start(&in_thrashing);
+		psi_memstall_enter(&pflags);
+	}
+	delayacct_swapin_start();
+
+	if (swap_read_folio_zeromap(folio)) {
+		folio_unlock(folio);
+		goto finish;
+	}
 
-	if (sis->flags & SWP_FILE) {
-		struct address_space *mapping = sis->swap_file->f_mapping;
-		return mapping->a_ops->set_page_dirty(page);
+	if (zswap_load(folio) != -ENOENT)
+		goto finish;
+
+	/* We have to read from slower devices. Increase zswap protection. */
+	zswap_folio_swapin(folio);
+
+	if (data_race(sis->flags & SWP_FS_OPS)) {
+		swap_read_folio_fs(folio, plug);
+	} else if (synchronous) {
+		swap_read_folio_bdev_sync(folio, sis);
 	} else {
-		return __set_page_dirty_no_writeback(page);
+		swap_read_folio_bdev_async(folio, sis);
 	}
+
+finish:
+	if (workingset) {
+		delayacct_thrashing_end(&in_thrashing);
+		psi_memstall_leave(&pflags);
+	}
+	delayacct_swapin_end();
+}
+
+void __swap_read_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, ITER_DEST, sio->bvec, sio->pages, sio->len);
+	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	if (ret != -EIOCBQUEUED)
+		sio_read_complete(&sio->iocb, ret);
 }