[PATCH v6 1/2] mm: store zero pages to be swapped out in a bitmap

[Usama Arif]

Approximately 10-20% of pages to be swapped out are zero pages [1].
Rather than reading/writing these pages to flash resulting
in increased I/O and flash wear, a bitmap can be used to mark these
pages as zero at write time, and the pages can be filled at
read time if the bit corresponding to the page is set.
With this patch, NVMe writes in Meta server fleet decreased
by almost 10% with conventional swap setup (zswap disabled).

[1] https://lore.kernel.org/all/20171018104832epcms5p1b2232e2236258de3d03d1344dde9fce0@epcms5p1/

Signed-off-by: Usama Arif <usamaarif642@xxxxxxxxx>
Reviewed-by: Chengming Zhou <chengming.zhou@xxxxxxxxx>
Reviewed-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Reviewed-by: Nhat Pham <nphamcs@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Shakeel Butt <shakeel.butt@xxxxxxxxx>
Cc: Usama Arif <usamaarif642@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
 include/linux/swap.h |   1 +
 mm/page_io.c         | 113 ++++++++++++++++++++++++++++++++++++++++++-
 mm/swapfile.c        |  15 ++++++
 3 files changed, 128 insertions(+), 1 deletion(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3df75d62a835..ed03d421febd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -299,6 +299,7 @@ struct swap_info_struct {
 	signed char	type;		/* strange name for an index */
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
+	unsigned long *zeromap;		/* vmalloc'ed bitmap to track zero pages */
 	struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
 	struct swap_cluster_list free_clusters; /* free clusters list */
 	unsigned int lowest_bit;	/* index of first free in swap_map */
diff --git a/mm/page_io.c b/mm/page_io.c
index 6c1c1828bb88..480b8f221d90 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -172,6 +172,88 @@ int generic_swapfile_activate(struct swap_info_struct *sis,
 	goto out;
 }
 
+static bool is_folio_page_zero_filled(struct folio *folio, int i)
+{
+	unsigned long *data;
+	unsigned int pos, last_pos = PAGE_SIZE / sizeof(*data) - 1;
+	bool ret = false;
+
+	data = kmap_local_folio(folio, i * PAGE_SIZE);
+	if (data[last_pos])
+		goto out;
+	for (pos = 0; pos < PAGE_SIZE / sizeof(*data); pos++) {
+		if (data[pos])
+			goto out;
+	}
+	ret = true;
+out:
+	kunmap_local(data);
+	return ret;
+}
+
+static bool is_folio_zero_filled(struct folio *folio)
+{
+	unsigned int i;
+
+	for (i = 0; i < folio_nr_pages(folio); i++) {
+		if (!is_folio_page_zero_filled(folio, i))
+			return false;
+	}
+	return true;
+}
+
+static void folio_zero_fill(struct folio *folio)
+{
+	unsigned int i;
+
+	for (i = 0; i < folio_nr_pages(folio); i++)
+		clear_highpage(folio_page(folio, i));
+}
+
+static void swap_zeromap_folio_set(struct folio *folio)
+{
+	struct swap_info_struct *sis = swp_swap_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));
+		set_bit(swp_offset(entry), sis->zeromap);
+	}
+}
+
+static void swap_zeromap_folio_clear(struct folio *folio)
+{
+	struct swap_info_struct *sis = swp_swap_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);
+	}
+}
+
+/*
+ * Return the index of the first subpage which is not zero-filled
+ * according to swap_info_struct->zeromap.
+ * If all pages are zero-filled according to zeromap, it will return
+ * folio_nr_pages(folio).
+ */
+static unsigned int swap_zeromap_folio_test(struct folio *folio)
+{
+	struct swap_info_struct *sis = swp_swap_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));
+		if (!test_bit(swp_offset(entry), sis->zeromap))
+			return i;
+	}
+	return i;
+}
+
 /*
  * We may have stale swap cache pages in memory: notice
  * them here and get rid of the unnecessary final write.
@@ -195,6 +277,13 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		folio_unlock(folio);
 		return ret;
 	}
+
+	if (is_folio_zero_filled(folio)) {
+		swap_zeromap_folio_set(folio);
+		folio_unlock(folio);
+		return 0;
+	}
+	swap_zeromap_folio_clear(folio);
 	if (zswap_store(folio)) {
 		folio_unlock(folio);
 		return 0;
@@ -424,6 +513,26 @@ static void sio_read_complete(struct kiocb *iocb, long ret)
 	mempool_free(sio, sio_pool);
 }
 
+static bool swap_read_folio_zeromap(struct folio *folio)
+{
+	unsigned int idx = swap_zeromap_folio_test(folio);
+
+	if (idx == 0)
+		return false;
+
+	/*
+	 * 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(idx < folio_nr_pages(folio)))
+		return true;
+
+	folio_zero_fill(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 = swp_swap_info(folio->swap);
@@ -514,7 +623,9 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
 	}
 	delayacct_swapin_start();
 
-	if (zswap_load(folio)) {
+	if (swap_read_folio_zeromap(folio)) {
+		folio_unlock(folio);
+	} else if (zswap_load(folio)) {
 		folio_unlock(folio);
 	} else if (data_race(sis->flags & SWP_FS_OPS)) {
 		swap_read_folio_fs(folio, plug);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 9c6d8e557c0f..2263f71baa31 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -747,6 +747,14 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 	unsigned long begin = offset;
 	unsigned long end = offset + nr_entries - 1;
 	void (*swap_slot_free_notify)(struct block_device *, unsigned long);
+	unsigned int i;
+
+	/*
+	 * Use atomic clear_bit operations only on zeromap instead of non-atomic
+	 * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes.
+	 */
+	for (i = 0; i < nr_entries; i++)
+		clear_bit(offset + i, si->zeromap);
 
 	if (offset < si->lowest_bit)
 		si->lowest_bit = offset;
@@ -2635,6 +2643,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	free_percpu(p->cluster_next_cpu);
 	p->cluster_next_cpu = NULL;
 	vfree(swap_map);
+	kvfree(p->zeromap);
 	kvfree(cluster_info);
 	/* Destroy swap account information */
 	swap_cgroup_swapoff(p->type);
@@ -3161,6 +3170,12 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
+	p->zeromap = kvzalloc(DIV_ROUND_UP(maxpages, 8), GFP_KERNEL);
+	if (!p->zeromap) {
+		error = -ENOMEM;
+		goto bad_swap_unlock_inode;
+	}
+
 	if (p->bdev && bdev_stable_writes(p->bdev))
 		p->flags |= SWP_STABLE_WRITES;
 
-- 
2.43.0