1 files changed, 275 insertions, 188 deletions

diff --git a/mm/page_io.c b/mm/page_io.c
index 76965be1d40e..2af34dd8fa4d 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -25,28 +25,10 @@
 #include <linux/psi.h>
 #include <linux/uio.h>
 #include <linux/sched/task.h>
-#include <asm/pgtable.h>
+#include <linux/delayacct.h>
+#include "swap.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) {
-		struct block_device *bdev;
-
-		bio->bi_iter.bi_sector = map_swap_page(page, &bdev);
-		bio_set_dev(bio, bdev);
-		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
-		bio->bi_end_io = end_io;
-
-		bio_add_page(bio, page, PAGE_SIZE * hpage_nr_pages(page), 0);
-	}
-	return bio;
-}
-
-void end_swap_bio_write(struct bio *bio)
+static void end_swap_bio_write(struct bio *bio)
 {
 	struct page *page = bio_first_page_all(bio);
 
@@ -58,66 +40,18 @@ void end_swap_bio_write(struct bio *bio)
 		 * 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);
-		pr_alert("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);
+		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);
 		ClearPageReclaim(page);
 	}
 	end_page_writeback(page);
 	bio_put(bio);
 }
 
-static void swap_slot_free_notify(struct page *page)
-{
-	struct swap_info_struct *sis;
-	struct gendisk *disk;
-	swp_entry_t entry;
-
-	/*
-	 * 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 (unlikely(!PageSwapCache(page)))
-		return;
-
-	sis = page_swap_info(page);
-	if (!(sis->flags & SWP_BLKDEV))
-		return;
-
-	/*
-	 * 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.
-	 */
-	disk = sis->bdev->bd_disk;
-	entry.val = page_private(page);
-	if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) {
-		unsigned long offset;
-
-		offset = swp_offset(entry);
-
-		SetPageDirty(page);
-		disk->fops->swap_slot_free_notify(sis->bdev,
-				offset);
-	}
-}
-
 static void end_swap_bio_read(struct bio *bio)
 {
 	struct page *page = bio_first_page_all(bio);
@@ -126,14 +60,13 @@ static void end_swap_bio_read(struct bio *bio)
 	if (bio->bi_status) {
 		SetPageError(page);
 		ClearPageUptodate(page);
-		pr_alert("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);
+		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);
 		goto out;
 	}
 
 	SetPageUptodate(page);
-	swap_slot_free_notify(page);
 out:
 	unlock_page(page);
 	WRITE_ONCE(bio->bi_private, NULL);
@@ -247,129 +180,295 @@ bad_bmap:
  */
 int swap_writepage(struct page *page, struct writeback_control *wbc)
 {
+	struct folio *folio = page_folio(page);
 	int ret = 0;
 
-	if (try_to_free_swap(page)) {
-		unlock_page(page);
+	if (folio_free_swap(folio)) {
+		folio_unlock(folio);
 		goto out;
 	}
-	if (frontswap_store(page) == 0) {
-		set_page_writeback(page);
-		unlock_page(page);
-		end_page_writeback(page);
+	/*
+	 * Arch code may have to preserve more data than just the page
+	 * contents, e.g. memory tags.
+	 */
+	ret = arch_prepare_to_swap(&folio->page);
+	if (ret) {
+		folio_mark_dirty(folio);
+		folio_unlock(folio);
+		goto out;
+	}
+	if (frontswap_store(&folio->page) == 0) {
+		folio_start_writeback(folio);
+		folio_unlock(folio);
+		folio_end_writeback(folio);
 		goto out;
 	}
-	ret = __swap_writepage(page, wbc, end_swap_bio_write);
+	ret = __swap_writepage(&folio->page, wbc);
 out:
 	return ret;
 }
 
-static sector_t swap_page_sector(struct page *page)
-{
-	return (sector_t)__page_file_index(page) << (PAGE_SHIFT - 9);
-}
-
 static inline void count_swpout_vm_event(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (unlikely(PageTransHuge(page)))
 		count_vm_event(THP_SWPOUT);
 #endif
-	count_vm_events(PSWPOUT, hpage_nr_pages(page));
+	count_vm_events(PSWPOUT, thp_nr_pages(page));
 }
 
-int __swap_writepage(struct page *page, struct writeback_control *wbc,
-		bio_end_io_t end_write_func)
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
 {
-	struct bio *bio;
-	int ret;
-	struct swap_info_struct *sis = page_swap_info(page);
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *memcg;
 
-	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
-	if (sis->flags & SWP_FS) {
-		struct kiocb kiocb;
-		struct file *swap_file = sis->swap_file;
-		struct address_space *mapping = swap_file->f_mapping;
-		struct bio_vec bv = {
-			.bv_page = page,
-			.bv_len  = PAGE_SIZE,
-			.bv_offset = 0
-		};
-		struct iov_iter from;
-
-		iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE);
-		init_sync_kiocb(&kiocb, swap_file);
-		kiocb.ki_pos = page_file_offset(page);
-
-		set_page_writeback(page);
-		unlock_page(page);
-		ret = mapping->a_ops->direct_IO(&kiocb, &from);
-		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.
-			 */
+	memcg = page_memcg(page);
+	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, page)		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 but do not flag PageError like
+		 * the normal direct-to-bio case as it could
+		 * be temporary.
+		 */
+		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);
-			pr_err_ratelimited("Write error on dio swapfile (%llu)\n",
-					   page_file_offset(page));
 		}
-		end_page_writeback(page);
-		return ret;
+	} else {
+		for (p = 0; p < sio->pages; p++)
+			count_swpout_vm_event(sio->bvec[p].bv_page);
 	}
 
+	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 = NULL;
+	struct swap_info_struct *sis = page_swap_info(page);
+	struct file *swap_file = sis->swap_file;
+	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->len != 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 = pos;
+		sio->pages = 0;
+		sio->len = 0;
+	}
+	sio->bvec[sio->pages].bv_page = page;
+	sio->bvec[sio->pages].bv_len = thp_size(page);
+	sio->bvec[sio->pages].bv_offset = 0;
+	sio->len += thp_size(page);
+	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)
+{
+	struct bio *bio;
+	int ret;
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+	/*
+	 * ->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))
+		return swap_writepage_fs(page, wbc);
+
 	ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
 	if (!ret) {
 		count_swpout_vm_event(page);
 		return 0;
 	}
 
-	ret = 0;
-	bio = get_swap_bio(GFP_NOIO, page, end_write_func);
-	if (bio == NULL) {
-		set_page_dirty(page);
-		unlock_page(page);
-		ret = -ENOMEM;
-		goto out;
-	}
-	bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
+	bio = bio_alloc(sis->bdev, 1,
+			REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc),
+			GFP_NOIO);
+	bio->bi_iter.bi_sector = swap_page_sector(page);
+	bio->bi_end_io = end_swap_bio_write;
+	bio_add_page(bio, page, thp_size(page), 0);
+
 	bio_associate_blkg_from_page(bio, page);
 	count_swpout_vm_event(page);
 	set_page_writeback(page);
 	unlock_page(page);
 	submit_bio(bio);
-out:
-	return ret;
+
+	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, sio->len);
+	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	if (ret != -EIOCBQUEUED)
+		sio_write_complete(&sio->iocb, ret);
 }
 
-int swap_readpage(struct page *page, bool synchronous)
+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 page *page = sio->bvec[p].bv_page;
+
+			SetPageUptodate(page);
+			unlock_page(page);
+		}
+		count_vm_events(PSWPIN, sio->pages);
+	} else {
+		for (p = 0; p < sio->pages; p++) {
+			struct page *page = sio->bvec[p].bv_page;
+
+			SetPageError(page);
+			ClearPageUptodate(page);
+			unlock_page(page);
+		}
+		pr_alert_ratelimited("Read-error on swap-device\n");
+	}
+	mempool_free(sio, sio_pool);
+}
+
+static void swap_readpage_fs(struct page *page,
+			     struct swap_iocb **plug)
+{
+	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_iocb *sio = NULL;
+	loff_t pos = page_file_offset(page);
+
+	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;
+		}
+	}
+	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;
+	}
+	sio->bvec[sio->pages].bv_page = page;
+	sio->bvec[sio->pages].bv_len = thp_size(page);
+	sio->bvec[sio->pages].bv_offset = 0;
+	sio->len += thp_size(page);
+	sio->pages += 1;
+	if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) {
+		swap_read_unplug(sio);
+		sio = NULL;
+	}
+	if (plug)
+		*plug = sio;
+}
+
+int swap_readpage(struct page *page, bool synchronous,
+		  struct swap_iocb **plug)
 {
 	struct bio *bio;
 	int ret = 0;
 	struct swap_info_struct *sis = page_swap_info(page);
-	blk_qc_t qc;
-	struct gendisk *disk;
+	bool workingset = PageWorkingset(page);
 	unsigned long pflags;
+	bool in_thrashing;
 
 	VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageUptodate(page), page);
 
 	/*
-	 * Count submission time as memory stall. When the device is congested,
-	 * or the submitting cgroup IO-throttled, submission can be a
-	 * significant part of overall IO time.
+	 * 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.
 	 */
-	psi_memstall_enter(&pflags);
+	if (workingset) {
+		delayacct_thrashing_start(&in_thrashing);
+		psi_memstall_enter(&pflags);
+	}
+	delayacct_swapin_start();
 
 	if (frontswap_load(page) == 0) {
 		SetPageUptodate(page);
@@ -377,74 +476,62 @@ int swap_readpage(struct page *page, bool synchronous)
 		goto out;
 	}
 
-	if (sis->flags & SWP_FS) {
-		struct file *swap_file = sis->swap_file;
-		struct address_space *mapping = swap_file->f_mapping;
-
-		ret = mapping->a_ops->readpage(swap_file, page);
-		if (!ret)
-			count_vm_event(PSWPIN);
+	if (data_race(sis->flags & SWP_FS_OPS)) {
+		swap_readpage_fs(page, plug);
 		goto out;
 	}
 
-	ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
-	if (!ret) {
-		if (trylock_page(page)) {
-			swap_slot_free_notify(page);
-			unlock_page(page);
+	if (sis->flags & SWP_SYNCHRONOUS_IO) {
+		ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
+		if (!ret) {
+			count_vm_event(PSWPIN);
+			goto out;
 		}
-
-		count_vm_event(PSWPIN);
-		goto out;
 	}
 
 	ret = 0;
-	bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
-	if (bio == NULL) {
-		unlock_page(page);
-		ret = -ENOMEM;
-		goto out;
-	}
-	disk = bio->bi_disk;
+	bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL);
+	bio->bi_iter.bi_sector = swap_page_sector(page);
+	bio->bi_end_io = end_swap_bio_read;
+	bio_add_page(bio, page, thp_size(page), 0);
 	/*
 	 * Keep this task valid during swap readpage because the oom killer may
 	 * attempt to access it in the page fault retry time check.
 	 */
-	bio_set_op_attrs(bio, REQ_OP_READ, 0);
 	if (synchronous) {
-		bio->bi_opf |= REQ_HIPRI;
 		get_task_struct(current);
 		bio->bi_private = current;
 	}
 	count_vm_event(PSWPIN);
 	bio_get(bio);
-	qc = submit_bio(bio);
+	submit_bio(bio);
 	while (synchronous) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		if (!READ_ONCE(bio->bi_private))
 			break;
 
-		if (!blk_poll(disk->queue, qc, true))
-			io_schedule();
+		blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
 	bio_put(bio);
 
 out:
-	psi_memstall_leave(&pflags);
+	if (workingset) {
+		delayacct_thrashing_end(&in_thrashing);
+		psi_memstall_leave(&pflags);
+	}
+	delayacct_swapin_end();
 	return ret;
 }
 
-int swap_set_page_dirty(struct page *page)
+void __swap_read_unplug(struct swap_iocb *sio)
 {
-	struct swap_info_struct *sis = page_swap_info(page);
-
-	if (sis->flags & SWP_FS) {
-		struct address_space *mapping = sis->swap_file->f_mapping;
+	struct iov_iter from;
+	struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
+	int ret;
 
-		VM_BUG_ON_PAGE(!PageSwapCache(page), page);
-		return mapping->a_ops->set_page_dirty(page);
-	} else {
-		return __set_page_dirty_no_writeback(page);
-	}
+	iov_iter_bvec(&from, READ, sio->bvec, sio->pages, sio->len);
+	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	if (ret != -EIOCBQUEUED)
+		sio_read_complete(&sio->iocb, ret);
 }