mm: store zero pages to be swapped out in a bitmap

Patch series "mm: store zero pages to be swapped out in a bitmap", v8.

As shown in the patch series that introduced the zswap same-filled
optimization [1], 10-20% of the pages stored in zswap are same-filled. 
This is also observed across Meta's server fleet.  By using VM counters in
swap_writepage (not included in this patchseries) it was found that less
than 1% of the same-filled pages to be swapped out are non-zero pages.

For conventional swap setup (without zswap), 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.

When using zswap with swap, this also means that a zswap_entry does not
need to be allocated for zero filled pages resulting in memory savings
which would offset the memory used for the bitmap.

A similar attempt was made earlier in [2] where zswap would only track
zero-filled pages instead of same-filled.  This patchseries adds
zero-filled pages optimization to swap (hence it can be used even if zswap
is disabled) and removes the same-filled code from zswap (as only 1% of
the same-filled pages are non-zero), simplifying code.

[1] https://lore.kernel.org/all/20171018104832epcms5p1b2232e2236258de3d03d1344dde9fce0@epcms5p1/
[2] https://lore.kernel.org/lkml/20240325235018.2028408-1-yosryahmed@google.com/


This patch (of 2):

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/

Link: https://lkml.kernel.org/r/20240823190545.979059-1-usamaarif642@gmail.com
Link: https://lkml.kernel.org/r/20240823190545.979059-2-usamaarif642@gmail.com
Signed-off-by: Usama Arif <usamaarif642@gmail.com>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 33 insertions, 5 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 03dc77457510..8e317c495bfb 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -940,6 +940,14 @@ 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;
@@ -2609,7 +2617,8 @@ static int swap_node(struct swap_info_struct *si)
 
 static void setup_swap_info(struct swap_info_struct *si, int prio,
 			    unsigned char *swap_map,
-			    struct swap_cluster_info *cluster_info)
+			    struct swap_cluster_info *cluster_info,
+			    unsigned long *zeromap)
 {
 	int i;
 
@@ -2634,6 +2643,7 @@ static void setup_swap_info(struct swap_info_struct *si, int prio,
 	}
 	si->swap_map = swap_map;
 	si->cluster_info = cluster_info;
+	si->zeromap = zeromap;
 }
 
 static void _enable_swap_info(struct swap_info_struct *si)
@@ -2662,11 +2672,12 @@ static void _enable_swap_info(struct swap_info_struct *si)
 
 static void enable_swap_info(struct swap_info_struct *si, int prio,
 				unsigned char *swap_map,
-				struct swap_cluster_info *cluster_info)
+				struct swap_cluster_info *cluster_info,
+				unsigned long *zeromap)
 {
 	spin_lock(&swap_lock);
 	spin_lock(&si->lock);
-	setup_swap_info(si, prio, swap_map, cluster_info);
+	setup_swap_info(si, prio, swap_map, cluster_info, zeromap);
 	spin_unlock(&si->lock);
 	spin_unlock(&swap_lock);
 	/*
@@ -2684,7 +2695,7 @@ static void reinsert_swap_info(struct swap_info_struct *si)
 {
 	spin_lock(&swap_lock);
 	spin_lock(&si->lock);
-	setup_swap_info(si, si->prio, si->swap_map, si->cluster_info);
+	setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap);
 	_enable_swap_info(si);
 	spin_unlock(&si->lock);
 	spin_unlock(&swap_lock);
@@ -2709,6 +2720,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 {
 	struct swap_info_struct *p = NULL;
 	unsigned char *swap_map;
+	unsigned long *zeromap;
 	struct swap_cluster_info *cluster_info;
 	struct file *swap_file, *victim;
 	struct address_space *mapping;
@@ -2831,6 +2843,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	p->max = 0;
 	swap_map = p->swap_map;
 	p->swap_map = NULL;
+	zeromap = p->zeromap;
+	p->zeromap = NULL;
 	cluster_info = p->cluster_info;
 	p->cluster_info = NULL;
 	spin_unlock(&p->lock);
@@ -2843,6 +2857,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	free_percpu(p->cluster_next_cpu);
 	p->cluster_next_cpu = NULL;
 	vfree(swap_map);
+	kvfree(zeromap);
 	kvfree(cluster_info);
 	/* Destroy swap account information */
 	swap_cgroup_swapoff(p->type);
@@ -3340,6 +3355,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	sector_t span;
 	unsigned long maxpages;
 	unsigned char *swap_map = NULL;
+	unsigned long *zeromap = NULL;
 	struct swap_cluster_info *cluster_info = NULL;
 	struct page *page = NULL;
 	struct inode *inode = NULL;
@@ -3430,6 +3446,17 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
+	/*
+	 * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might
+	 * be above MAX_PAGE_ORDER incase of a large swap file.
+	 */
+	zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long),
+				    GFP_KERNEL | __GFP_ZERO);
+	if (!zeromap) {
+		error = -ENOMEM;
+		goto bad_swap_unlock_inode;
+	}
+
 	if (si->bdev && bdev_stable_writes(si->bdev))
 		si->flags |= SWP_STABLE_WRITES;
 
@@ -3505,7 +3532,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (swap_flags & SWAP_FLAG_PREFER)
 		prio =
 		  (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
-	enable_swap_info(si, prio, swap_map, cluster_info);
+	enable_swap_info(si, prio, swap_map, cluster_info, zeromap);
 
 	pr_info("Adding %uk swap on %s.  Priority:%d extents:%d across:%lluk %s%s%s%s\n",
 		K(si->pages), name->name, si->prio, nr_extents,
@@ -3540,6 +3567,7 @@ bad_swap:
 	si->flags = 0;
 	spin_unlock(&swap_lock);
 	vfree(swap_map);
+	kvfree(zeromap);
 	kvfree(cluster_info);
 	if (inced_nr_rotate_swap)
 		atomic_dec(&nr_rotate_swap);