diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 77415ce01a5e..45bd3e475a7a 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1469,6 +1469,14 @@
 			Permit 'security.evm' to be updated regardless of
 			current integrity status.
 
+	early_page_ext [KNL] Enforces page_ext initialization to earlier
+			stages so cover more early boot allocations.
+			Please note that as side effect some optimizations
+			might be disabled to achieve that (e.g. parallelized
+			memory initialization is disabled) so the boot process
+			might take longer, especially on systems with a lot of
+			memory. Available with CONFIG_PAGE_EXTENSION=y.
+
 	failslab=
 	fail_usercopy=
 	fail_page_alloc=
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 10e51ef9c79a..c299a18273ff 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -237,16 +237,6 @@ int pud_huge(pud_t pud)
 	return pud_large(pud);
 }
 
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int flags)
-{
-	if (flags & FOLL_GET)
-		return NULL;
-
-	return pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
-}
-
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
 	if (MACHINE_HAS_EDAT1 && size == PMD_SIZE)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index bc60c9cd3230..9aa0da991cfb 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -869,12 +869,6 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
 	}
 }
 
-/* return true if the memory block is offlined, otherwise, return false */
-bool is_memblock_offlined(struct memory_block *mem)
-{
-	return mem->state == MEM_OFFLINE;
-}
-
 static struct attribute *memory_root_attrs[] = {
 #ifdef CONFIG_ARCH_MEMORY_PROBE
 	&dev_attr_probe.attr,
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 04077a2bb8a2..44de3d125319 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1410,9 +1410,19 @@ compress_again:
 		handle = zs_malloc(zram->mem_pool, comp_len,
 				GFP_NOIO | __GFP_HIGHMEM |
 				__GFP_MOVABLE);
-		if (!IS_ERR((void *)handle))
+		if (IS_ERR((void *)handle))
+			return PTR_ERR((void *)handle);
+
+		if (comp_len != PAGE_SIZE)
 			goto compress_again;
-		return PTR_ERR((void *)handle);
+		/*
+		 * If the page is not compressible, you need to acquire the lock and
+		 * execute the code below. The zcomp_stream_get() call is needed to
+		 * disable the cpu hotplug and grab the zstrm buffer back.
+		 * It is necessary that the dereferencing of the zstrm variable below
+		 * occurs correctly.
+		 */
+		zstrm = zcomp_stream_get(zram->comp);
 	}
 
 	alloced_pages = zs_get_total_pages(zram->mem_pool);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c0a08064b0a7..f1f051ad3147 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -8,6 +8,7 @@
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
+#include <linux/pagevec.h>
 #include <linux/highmem.h>
 #include <linux/kthread.h>
 #include <linux/time.h>
@@ -219,8 +220,7 @@ static noinline void end_compressed_writeback(struct inode *inode,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	unsigned long index = cb->start >> PAGE_SHIFT;
 	unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_SHIFT;
-	struct page *pages[16];
-	unsigned long nr_pages = end_index - index + 1;
+	struct folio_batch fbatch;
 	const int errno = blk_status_to_errno(cb->status);
 	int i;
 	int ret;
@@ -228,24 +228,23 @@ static noinline void end_compressed_writeback(struct inode *inode,
 	if (errno)
 		mapping_set_error(inode->i_mapping, errno);
 
-	while (nr_pages > 0) {
-		ret = find_get_pages_contig(inode->i_mapping, index,
-				     min_t(unsigned long,
-				     nr_pages, ARRAY_SIZE(pages)), pages);
-		if (ret == 0) {
-			nr_pages -= 1;
-			index += 1;
-			continue;
-		}
+	folio_batch_init(&fbatch);
+	while (index <= end_index) {
+		ret = filemap_get_folios(inode->i_mapping, &index, end_index,
+				&fbatch);
+
+		if (ret == 0)
+			return;
+
 		for (i = 0; i < ret; i++) {
+			struct folio *folio = fbatch.folios[i];
+
 			if (errno)
-				SetPageError(pages[i]);
-			btrfs_page_clamp_clear_writeback(fs_info, pages[i],
+				folio_set_error(folio);
+			btrfs_page_clamp_clear_writeback(fs_info, &folio->page,
 							 cb->start, cb->len);
-			put_page(pages[i]);
 		}
-		nr_pages -= ret;
-		index += ret;
+		folio_batch_release(&fbatch);
 	}
 	/* the inode may be gone now */
 }
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 1eae68fbae21..4dcf22e051ff 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -270,9 +270,8 @@ static int __process_pages_contig(struct address_space *mapping,
 	pgoff_t start_index = start >> PAGE_SHIFT;
 	pgoff_t end_index = end >> PAGE_SHIFT;
 	pgoff_t index = start_index;
-	unsigned long nr_pages = end_index - start_index + 1;
 	unsigned long pages_processed = 0;
-	struct page *pages[16];
+	struct folio_batch fbatch;
 	int err = 0;
 	int i;
 
@@ -281,16 +280,17 @@ static int __process_pages_contig(struct address_space *mapping,
 		ASSERT(processed_end && *processed_end == start);
 	}
 
-	if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0)
+	if ((page_ops & PAGE_SET_ERROR) && start_index <= end_index)
 		mapping_set_error(mapping, -EIO);
 
-	while (nr_pages > 0) {
-		int found_pages;
+	folio_batch_init(&fbatch);
+	while (index <= end_index) {
+		int found_folios;
 
-		found_pages = find_get_pages_contig(mapping, index,
-				     min_t(unsigned long,
-				     nr_pages, ARRAY_SIZE(pages)), pages);
-		if (found_pages == 0) {
+		found_folios = filemap_get_folios_contig(mapping, &index,
+				end_index, &fbatch);
+
+		if (found_folios == 0) {
 			/*
 			 * Only if we're going to lock these pages, we can find
 			 * nothing at @index.
@@ -300,23 +300,20 @@ static int __process_pages_contig(struct address_space *mapping,
 			goto out;
 		}
 
-		for (i = 0; i < found_pages; i++) {
+		for (i = 0; i < found_folios; i++) {
 			int process_ret;
-
+			struct folio *folio = fbatch.folios[i];
 			process_ret = process_one_page(fs_info, mapping,
-					pages[i], locked_page, page_ops,
+					&folio->page, locked_page, page_ops,
 					start, end);
 			if (process_ret < 0) {
-				for (; i < found_pages; i++)
-					put_page(pages[i]);
 				err = -EAGAIN;
+				folio_batch_release(&fbatch);
 				goto out;
 			}
-			put_page(pages[i]);
-			pages_processed++;
+			pages_processed += folio_nr_pages(folio);
 		}
-		nr_pages -= found_pages;
-		index += found_pages;
+		folio_batch_release(&fbatch);
 		cond_resched();
 	}
 out:
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 6fc2b77ae5c3..9a176af847d7 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -337,7 +337,7 @@ bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
  *
  * Even with 0 returned, the page still need extra check to make sure
  * it's really the correct page, as the caller is using
- * find_get_pages_contig(), which can race with page invalidating.
+ * filemap_get_folios_contig(), which can race with page invalidating.
  */
 int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info,
 		struct page *page, u64 start, u32 len)
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index f69ec4d2d6eb..350da449db08 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/pagemap.h>
+#include <linux/pagevec.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/sizes.h>
@@ -20,39 +21,40 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
 				       unsigned long flags)
 {
 	int ret;
-	struct page *pages[16];
+	struct folio_batch fbatch;
 	unsigned long index = start >> PAGE_SHIFT;
 	unsigned long end_index = end >> PAGE_SHIFT;
-	unsigned long nr_pages = end_index - index + 1;
 	int i;
 	int count = 0;
 	int loops = 0;
 
-	while (nr_pages > 0) {
-		ret = find_get_pages_contig(inode->i_mapping, index,
-				     min_t(unsigned long, nr_pages,
-				     ARRAY_SIZE(pages)), pages);
+	folio_batch_init(&fbatch);
+
+	while (index <= end_index) {
+		ret = filemap_get_folios_contig(inode->i_mapping, &index,
+				end_index, &fbatch);
 		for (i = 0; i < ret; i++) {
+			struct folio *folio = fbatch.folios[i];
+
 			if (flags & PROCESS_TEST_LOCKED &&
-			    !PageLocked(pages[i]))
+			    !folio_test_locked(folio))
 				count++;
-			if (flags & PROCESS_UNLOCK && PageLocked(pages[i]))
-				unlock_page(pages[i]);
-			put_page(pages[i]);
+			if (flags & PROCESS_UNLOCK && folio_test_locked(folio))
+				folio_unlock(folio);
 			if (flags & PROCESS_RELEASE)
-				put_page(pages[i]);
+				folio_put(folio);
 		}
-		nr_pages -= ret;
-		index += ret;
+		folio_batch_release(&fbatch);
 		cond_resched();
 		loops++;
 		if (loops > 100000) {
 			printk(KERN_ERR
-		"stuck in a loop, start %llu, end %llu, nr_pages %lu, ret %d\n",
-				start, end, nr_pages, ret);
+		"stuck in a loop, start %llu, end %llu, ret %d\n",
+				start, end, ret);
 			break;
 		}
 	}
+
 	return count;
 }
 
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 3267e96c256c..39b7eea2642a 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -480,41 +480,36 @@ unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 					    sector_t start_blk,
 					    sector_t *blkoff)
 {
-	unsigned int i;
+	unsigned int i, nr_folios;
 	pgoff_t index;
-	unsigned int nblocks_in_page;
 	unsigned long length = 0;
-	sector_t b;
-	struct pagevec pvec;
-	struct page *page;
+	struct folio_batch fbatch;
+	struct folio *folio;
 
 	if (inode->i_mapping->nrpages == 0)
 		return 0;
 
 	index = start_blk >> (PAGE_SHIFT - inode->i_blkbits);
-	nblocks_in_page = 1U << (PAGE_SHIFT - inode->i_blkbits);
 
-	pagevec_init(&pvec);
+	folio_batch_init(&fbatch);
 
 repeat:
-	pvec.nr = find_get_pages_contig(inode->i_mapping, index, PAGEVEC_SIZE,
-					pvec.pages);
-	if (pvec.nr == 0)
+	nr_folios = filemap_get_folios_contig(inode->i_mapping, &index, ULONG_MAX,
+			&fbatch);
+	if (nr_folios == 0)
 		return length;
 
-	if (length > 0 && pvec.pages[0]->index > index)
-		goto out;
-
-	b = pvec.pages[0]->index << (PAGE_SHIFT - inode->i_blkbits);
 	i = 0;
 	do {
-		page = pvec.pages[i];
+		folio = fbatch.folios[i];
 
-		lock_page(page);
-		if (page_has_buffers(page)) {
+		folio_lock(folio);
+		if (folio_buffers(folio)) {
 			struct buffer_head *bh, *head;
+			sector_t b;
 
-			bh = head = page_buffers(page);
+			b = folio->index << (PAGE_SHIFT - inode->i_blkbits);
+			bh = head = folio_buffers(folio);
 			do {
 				if (b < start_blk)
 					continue;
@@ -529,21 +524,17 @@ repeat:
 		} else {
 			if (length > 0)
 				goto out_locked;
-
-			b += nblocks_in_page;
 		}
-		unlock_page(page);
+		folio_unlock(folio);
 
-	} while (++i < pagevec_count(&pvec));
+	} while (++i < nr_folios);
 
-	index = page->index + 1;
-	pagevec_release(&pvec);
+	folio_batch_release(&fbatch);
 	cond_resched();
 	goto repeat;
 
 out_locked:
-	unlock_page(page);
-out:
-	pagevec_release(&pvec);
+	folio_unlock(folio);
+	folio_batch_release(&fbatch);
 	return length;
 }
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index ba3525ccc27e..cb240eac5036 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -203,9 +203,9 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
 					    unsigned long addr, unsigned long len,
 					    unsigned long pgoff, unsigned long flags)
 {
-	unsigned long maxpages, lpages, nr, loop, ret;
+	unsigned long maxpages, lpages, nr_folios, loop, ret, nr_pages, pfn;
 	struct inode *inode = file_inode(file);
-	struct page **pages = NULL, **ptr, *page;
+	struct folio_batch fbatch;
 	loff_t isize;
 
 	/* the mapping mustn't extend beyond the EOF */
@@ -221,31 +221,39 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
 		goto out;
 
 	/* gang-find the pages */
-	pages = kcalloc(lpages, sizeof(struct page *), GFP_KERNEL);
-	if (!pages)
-		goto out_free;
-
-	nr = find_get_pages_contig(inode->i_mapping, pgoff, lpages, pages);
-	if (nr != lpages)
-		goto out_free_pages; /* leave if some pages were missing */
+	folio_batch_init(&fbatch);
+	nr_pages = 0;
+repeat:
+	nr_folios = filemap_get_folios_contig(inode->i_mapping, &pgoff,
+			ULONG_MAX, &fbatch);
+	if (!nr_folios) {
+		ret = -ENOSYS;
+		return ret;
+	}
 
+	if (ret == -ENOSYS) {
+		ret = (unsigned long) folio_address(fbatch.folios[0]);
+		pfn = folio_pfn(fbatch.folios[0]);
+	}
 	/* check the pages for physical adjacency */
-	ptr = pages;
-	page = *ptr++;
-	page++;
-	for (loop = lpages; loop > 1; loop--)
-		if (*ptr++ != page++)
-			goto out_free_pages;
+	for (loop = 0; loop < nr_folios; loop++) {
+		if (pfn + nr_pages != folio_pfn(fbatch.folios[loop])) {
+			ret = -ENOSYS;
+			goto out_free; /* leave if not physical adjacent */
+		}
+		nr_pages += folio_nr_pages(fbatch.folios[loop]);
+		if (nr_pages >= lpages)
+			goto out_free; /* successfully found desired pages*/
+	}
 
+	if (nr_pages < lpages) {
+		folio_batch_release(&fbatch);
+		goto repeat; /* loop if pages are missing */
+	}
 	/* okay - all conditions fulfilled */
-	ret = (unsigned long) page_address(pages[0]);
 
-out_free_pages:
-	ptr = pages;
-	for (loop = nr; loop > 0; loop--)
-		put_page(*ptr++);
 out_free:
-	kfree(pages);
+	folio_batch_release(&fbatch);
 out:
 	return ret;
 }
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 567f12323f55..cf115888f3bf 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -354,10 +354,11 @@ struct mem_cgroup {
 };
 
 /*
- * size of first charge trial. "32" comes from vmscan.c's magic value.
- * TODO: maybe necessary to use big numbers in big irons.
+ * size of first charge trial.
+ * TODO: maybe necessary to use big numbers in big irons or dynamic based of the
+ * workload.
  */
-#define MEMCG_CHARGE_BATCH 32U
+#define MEMCG_CHARGE_BATCH 64U
 
 extern struct mem_cgroup *root_mem_cgroup;
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index e0b2209ab71c..51052969dbfe 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -11,7 +11,6 @@ struct page;
 struct zone;
 struct pglist_data;
 struct mem_section;
-struct memory_block;
 struct memory_group;
 struct resource;
 struct vmem_altmap;
@@ -216,6 +215,22 @@ void put_online_mems(void);
 void mem_hotplug_begin(void);
 void mem_hotplug_done(void);
 
+/* See kswapd_is_running() */
+static inline void pgdat_kswapd_lock(pg_data_t *pgdat)
+{
+	mutex_lock(&pgdat->kswapd_lock);
+}
+
+static inline void pgdat_kswapd_unlock(pg_data_t *pgdat)
+{
+	mutex_unlock(&pgdat->kswapd_lock);
+}
+
+static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat)
+{
+	mutex_init(&pgdat->kswapd_lock);
+}
+
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 #define pfn_to_online_page(pfn)			\
 ({						\
@@ -252,6 +267,10 @@ static inline bool movable_node_is_enabled(void)
 {
 	return false;
 }
+
+static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {}
+static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {}
+static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {}
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
 /*
@@ -333,7 +352,6 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 extern void remove_pfn_range_from_zone(struct zone *zone,
 				       unsigned long start_pfn,
 				       unsigned long nr_pages);
-extern bool is_memblock_offlined(struct memory_block *mem);
 extern int sparse_add_section(int nid, unsigned long pfn,
 		unsigned long nr_pages, struct vmem_altmap *altmap,
 		struct dev_pagemap *pgmap);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ebe073cfcf67..fe6c5e04aeaf 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -955,8 +955,10 @@ typedef struct pglist_data {
 	atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */
 	unsigned long nr_reclaim_start;	/* nr pages written while throttled
 					 * when throttling started. */
-	struct task_struct *kswapd;	/* Protected by
-					   mem_hotplug_begin/done() */
+#ifdef CONFIG_MEMORY_HOTPLUG
+	struct mutex kswapd_lock;
+#endif
+	struct task_struct *kswapd;	/* Protected by kswapd_lock */
 	int kswapd_order;
 	enum zone_type kswapd_highest_zoneidx;
 
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 679591301994..78a1c934e416 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -3,15 +3,26 @@
 #define _LINUX_PAGE_COUNTER_H
 
 #include <linux/atomic.h>
+#include <linux/cache.h>
 #include <linux/kernel.h>
 #include <asm/page.h>
 
+#if defined(CONFIG_SMP)
+struct pc_padding {
+	char x[0];
+} ____cacheline_internodealigned_in_smp;
+#define PC_PADDING(name)	struct pc_padding name
+#else
+#define PC_PADDING(name)
+#endif
+
 struct page_counter {
+	/*
+	 * Make sure 'usage' does not share cacheline with any other field. The
+	 * memcg->memory.usage is a hot member of struct mem_cgroup.
+	 */
 	atomic_long_t usage;
-	unsigned long min;
-	unsigned long low;
-	unsigned long high;
-	unsigned long max;
+	PC_PADDING(_pad1_);
 
 	/* effective memory.min and memory.min usage tracking */
 	unsigned long emin;
@@ -23,18 +34,18 @@ struct page_counter {
 	atomic_long_t low_usage;
 	atomic_long_t children_low_usage;
 
-	/* legacy */
 	unsigned long watermark;
 	unsigned long failcnt;
 
-	/*
-	 * 'parent' is placed here to be far from 'usage' to reduce
-	 * cache false sharing, as 'usage' is written mostly while
-	 * parent is frequently read for cgroup's hierarchical
-	 * counting nature.
-	 */
+	/* Keep all the read most fields in a separete cacheline. */
+	PC_PADDING(_pad2_);
+
+	unsigned long min;
+	unsigned long low;
+	unsigned long high;
+	unsigned long max;
 	struct page_counter *parent;
-};
+} ____cacheline_internodealigned_in_smp;
 
 #if BITS_PER_LONG == 32
 #define PAGE_COUNTER_MAX LONG_MAX
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index ed27198cdaf4..22be4582faae 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -36,9 +36,15 @@ struct page_ext {
 	unsigned long flags;
 };
 
+extern bool early_page_ext;
 extern unsigned long page_ext_size;
 extern void pgdat_page_ext_init(struct pglist_data *pgdat);
 
+static inline bool early_page_ext_enabled(void)
+{
+	return early_page_ext;
+}
+
 #ifdef CONFIG_SPARSEMEM
 static inline void page_ext_init_flatmem(void)
 {
@@ -68,6 +74,11 @@ static inline struct page_ext *page_ext_next(struct page_ext *curr)
 #else /* !CONFIG_PAGE_EXTENSION */
 struct page_ext;
 
+static inline bool early_page_ext_enabled(void)
+{
+	return false;
+}
+
 static inline void pgdat_page_ext_init(struct pglist_data *pgdat)
 {
 }
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 201dc7281640..384e12a1a976 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -718,8 +718,8 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index)
 
 unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start,
 		pgoff_t end, struct folio_batch *fbatch);
-unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
-			       unsigned int nr_pages, struct page **pages);
+unsigned filemap_get_folios_contig(struct address_space *mapping,
+		pgoff_t *start, pgoff_t end, struct folio_batch *fbatch);
 unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
 			pgoff_t end, xa_mark_t tag, unsigned int nr_pages,
 			struct page **pages);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 014ee8f0fbaa..d13b4f7cc5be 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1276,8 +1276,7 @@ static inline int pgd_devmap(pgd_t pgd)
 #endif
 
 #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
-	(defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
-	 !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
+	!defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 static inline int pud_trans_huge(pud_t pud)
 {
 	return 0;
@@ -1598,11 +1597,7 @@ typedef unsigned int pgtbl_mod_mask;
 #endif
 
 #ifndef has_transparent_hugepage
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define has_transparent_hugepage() 1
-#else
-#define has_transparent_hugepage() 0
-#endif
+#define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE)
 #endif
 
 /*
diff --git a/init/main.c b/init/main.c
index e827c544b3e3..d97e7b38c34a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -847,6 +847,9 @@ static void __init mm_init(void)
 	pgtable_init();
 	debug_objects_mem_init();
 	vmalloc_init();
+	/* Should be run after vmap initialization */
+	if (early_page_ext_enabled())
+		page_ext_init();
 	/* Should be run before the first non-init thread is created */
 	init_espfix_bsp();
 	/* Should be run after espfix64 is set up. */
@@ -1615,7 +1618,8 @@ static noinline void __init kernel_init_freeable(void)
 	padata_init();
 	page_alloc_init_late();
 	/* Initialize page ext after all struct pages are initialized. */
-	page_ext_init();
+	if (!early_page_ext_enabled())
+		page_ext_init();
 
 	do_basic_setup();
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 3897e924e40f..39a919586949 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -23,7 +23,7 @@ menuconfig SWAP
 	  in your computer.  If unsure say Y.
 
 config ZSWAP
-	bool "Compressed cache for swap pages (EXPERIMENTAL)"
+	bool "Compressed cache for swap pages"
 	depends on SWAP
 	select FRONTSWAP
 	select CRYPTO
@@ -36,12 +36,6 @@ config ZSWAP
 	  in the case where decompressing from RAM is faster than swap device
 	  reads, can also improve workload performance.
 
-	  This is marked experimental because it is a new feature (as of
-	  v3.11) that interacts heavily with memory reclaim.  While these
-	  interactions don't cause any known issues on simple memory setups,
-	  they have not be fully explored on the large set of potential
-	  configurations and workloads that exist.
-
 config ZSWAP_DEFAULT_ON
 	bool "Enable the compressed cache for swap pages by default"
 	depends on ZSWAP
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index de65cb1e5f76..c30419a5e119 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -776,8 +776,6 @@ static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb)
 
 int bdi_init(struct backing_dev_info *bdi)
 {
-	int ret;
-
 	bdi->dev = NULL;
 
 	kref_init(&bdi->refcnt);
@@ -788,9 +786,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&bdi->wb_list);
 	init_waitqueue_head(&bdi->wb_waitq);
 
-	ret = cgwb_bdi_init(bdi);
-
-	return ret;
+	return cgwb_bdi_init(bdi);
 }
 
 struct backing_dev_info *bdi_alloc(int node_id)
diff --git a/mm/compaction.c b/mm/compaction.c
index 10561cb1aaad..13144c46618e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1977,9 +1977,21 @@ static inline bool is_via_compact_memory(int order)
 	return order == -1;
 }
 
+/*
+ * Determine whether kswapd is (or recently was!) running on this node.
+ *
+ * pgdat_kswapd_lock() pins pgdat->kswapd, so a concurrent kswapd_stop() can't
+ * zero it.
+ */
 static bool kswapd_is_running(pg_data_t *pgdat)
 {
-	return pgdat->kswapd && task_is_running(pgdat->kswapd);
+	bool running;
+
+	pgdat_kswapd_lock(pgdat);
+	running = pgdat->kswapd && task_is_running(pgdat->kswapd);
+	pgdat_kswapd_unlock(pgdat);
+
+	return running;
 }
 
 /*
diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
index b1335de200e7..f599838b5f64 100644
--- a/mm/damon/ops-common.c
+++ b/mm/damon/ops-common.c
@@ -88,49 +88,6 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
 #define DAMON_MAX_SUBSCORE	(100)
 #define DAMON_MAX_AGE_IN_LOG	(32)
 
-int damon_pageout_score(struct damon_ctx *c, struct damon_region *r,
-			struct damos *s)
-{
-	unsigned int max_nr_accesses;
-	int freq_subscore;
-	unsigned int age_in_sec;
-	int age_in_log, age_subscore;
-	unsigned int freq_weight = s->quota.weight_nr_accesses;
-	unsigned int age_weight = s->quota.weight_age;
-	int hotness;
-
-	max_nr_accesses = c->aggr_interval / c->sample_interval;
-	freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses;
-
-	age_in_sec = (unsigned long)r->age * c->aggr_interval / 1000000;
-	for (age_in_log = 0; age_in_log < DAMON_MAX_AGE_IN_LOG && age_in_sec;
-			age_in_log++, age_in_sec >>= 1)
-		;
-
-	/* If frequency is 0, higher age means it's colder */
-	if (freq_subscore == 0)
-		age_in_log *= -1;
-
-	/*
-	 * Now age_in_log is in [-DAMON_MAX_AGE_IN_LOG, DAMON_MAX_AGE_IN_LOG].
-	 * Scale it to be in [0, 100] and set it as age subscore.
-	 */
-	age_in_log += DAMON_MAX_AGE_IN_LOG;
-	age_subscore = age_in_log * DAMON_MAX_SUBSCORE /
-		DAMON_MAX_AGE_IN_LOG / 2;
-
-	hotness = (freq_weight * freq_subscore + age_weight * age_subscore);
-	if (freq_weight + age_weight)
-		hotness /= freq_weight + age_weight;
-	/*
-	 * Transform it to fit in [0, DAMOS_MAX_SCORE]
-	 */
-	hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE;
-
-	/* Return coldness of the region */
-	return DAMOS_MAX_SCORE - hotness;
-}
-
 int damon_hot_score(struct damon_ctx *c, struct damon_region *r,
 			struct damos *s)
 {
@@ -172,3 +129,12 @@ int damon_hot_score(struct damon_ctx *c, struct damon_region *r,
 
 	return hotness;
 }
+
+int damon_pageout_score(struct damon_ctx *c, struct damon_region *r,
+			struct damos *s)
+{
+	int hotness = damon_hot_score(c, r, s);
+
+	/* Return coldness of the region */
+	return DAMOS_MAX_SCORE - hotness;
+}
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index dc131c6a5403..6b0d9e6aa677 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -166,8 +166,7 @@ out:
 	return result.accessed;
 }
 
-static void __damon_pa_check_access(struct damon_ctx *ctx,
-				    struct damon_region *r)
+static void __damon_pa_check_access(struct damon_region *r)
 {
 	static unsigned long last_addr;
 	static unsigned long last_page_sz = PAGE_SIZE;
@@ -196,7 +195,7 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
 
 	damon_for_each_target(t, ctx) {
 		damon_for_each_region(r, t) {
-			__damon_pa_check_access(ctx, r);
+			__damon_pa_check_access(r);
 			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
 		}
 	}
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index cc04d467ba23..a8505ad47c60 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -542,16 +542,15 @@ static bool damon_va_young(struct mm_struct *mm, unsigned long addr,
  * mm	'mm_struct' for the given virtual address space
  * r	the region to be checked
  */
-static void __damon_va_check_access(struct damon_ctx *ctx,
-			       struct mm_struct *mm, struct damon_region *r)
+static void __damon_va_check_access(struct mm_struct *mm,
+				struct damon_region *r, bool same_target)
 {
-	static struct mm_struct *last_mm;
 	static unsigned long last_addr;
 	static unsigned long last_page_sz = PAGE_SIZE;
 	static bool last_accessed;
 
 	/* If the region is in the last checked page, reuse the result */
-	if (mm == last_mm && (ALIGN_DOWN(last_addr, last_page_sz) ==
+	if (same_target && (ALIGN_DOWN(last_addr, last_page_sz) ==
 				ALIGN_DOWN(r->sampling_addr, last_page_sz))) {
 		if (last_accessed)
 			r->nr_accesses++;
@@ -562,7 +561,6 @@ static void __damon_va_check_access(struct damon_ctx *ctx,
 	if (last_accessed)
 		r->nr_accesses++;
 
-	last_mm = mm;
 	last_addr = r->sampling_addr;
 }
 
@@ -572,14 +570,17 @@ static unsigned int damon_va_check_accesses(struct damon_ctx *ctx)
 	struct mm_struct *mm;
 	struct damon_region *r;
 	unsigned int max_nr_accesses = 0;
+	bool same_target;
 
 	damon_for_each_target(t, ctx) {
 		mm = damon_get_mm(t);
 		if (!mm)
 			continue;
+		same_target = false;
 		damon_for_each_region(r, t) {
-			__damon_va_check_access(ctx, mm, r);
+			__damon_va_check_access(mm, r, same_target);
 			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
+			same_target = true;
 		}
 		mmput(mm);
 	}
diff --git a/mm/filemap.c b/mm/filemap.c
index c8d7ef70e48c..8cb832af31ff 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2197,30 +2197,31 @@ bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max)
 }
 
 /**
- * find_get_pages_contig - gang contiguous pagecache lookup
+ * filemap_get_folios_contig - Get a batch of contiguous folios
  * @mapping:	The address_space to search
- * @index:	The starting page index
- * @nr_pages:	The maximum number of pages
- * @pages:	Where the resulting pages are placed
+ * @start:	The starting page index
+ * @end:	The final page index (inclusive)
+ * @fbatch:	The batch to fill
  *
- * find_get_pages_contig() works exactly like find_get_pages_range(),
- * except that the returned number of pages are guaranteed to be
- * contiguous.
+ * filemap_get_folios_contig() works exactly like filemap_get_folios(),
+ * except the returned folios are guaranteed to be contiguous. This may
+ * not return all contiguous folios if the batch gets filled up.
  *
- * Return: the number of pages which were found.
+ * Return: The number of folios found.
+ * Also update @start to be positioned for traversal of the next folio.
  */
-unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
-			       unsigned int nr_pages, struct page **pages)
-{
-	XA_STATE(xas, &mapping->i_pages, index);
-	struct folio *folio;
-	unsigned int ret = 0;
 
-	if (unlikely(!nr_pages))
-		return 0;
+unsigned filemap_get_folios_contig(struct address_space *mapping,
+		pgoff_t *start, pgoff_t end, struct folio_batch *fbatch)
+{
+	XA_STATE(xas, &mapping->i_pages, *start);
+	unsigned long nr;
+	struct folio *folio;
 
 	rcu_read_lock();
-	for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) {
+
+	for (folio = xas_load(&xas); folio && xas.xa_index <= end;
+			folio = xas_next(&xas)) {
 		if (xas_retry(&xas, folio))
 			continue;
 		/*
@@ -2228,33 +2229,45 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 		 * No current caller is looking for DAX entries.
 		 */
 		if (xa_is_value(folio))
-			break;
+			goto update_start;
 
 		if (!folio_try_get_rcu(folio))
 			goto retry;
 
 		if (unlikely(folio != xas_reload(&xas)))
-			goto put_page;
+			goto put_folio;
 
-again:
-		pages[ret] = folio_file_page(folio, xas.xa_index);
-		if (++ret == nr_pages)
-			break;
-		if (folio_more_pages(folio, xas.xa_index, ULONG_MAX)) {
-			xas.xa_index++;
-			folio_ref_inc(folio);
-			goto again;
+		if (!folio_batch_add(fbatch, folio)) {
+			nr = folio_nr_pages(folio);
+
+			if (folio_test_hugetlb(folio))
+				nr = 1;
+			*start = folio->index + nr;
+			goto out;
 		}
 		continue;
-put_page:
+put_folio:
 		folio_put(folio);
+
 retry:
 		xas_reset(&xas);
 	}
+
+update_start:
+	nr = folio_batch_count(fbatch);
+
+	if (nr) {
+		folio = fbatch->folios[nr - 1];
+		if (folio_test_hugetlb(folio))
+			*start = folio->index + 1;
+		else
+			*start = folio->index + folio_nr_pages(folio);
+	}
+out:
 	rcu_read_unlock();
-	return ret;
+	return folio_batch_count(fbatch);
 }
-EXPORT_SYMBOL(find_get_pages_contig);
+EXPORT_SYMBOL(filemap_get_folios_contig);
 
 /**
  * find_get_pages_range_tag - Find and return head pages matching @tag.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index fad6d1f2262a..9ae1f98548b1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1940,8 +1940,8 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 	node_states_clear_node(node, &arg);
 	if (arg.status_change_nid >= 0) {
-		kswapd_stop(node);
 		kcompactd_stop(node);
+		kswapd_stop(node);
 	}
 
 	writeback_set_ratelimit();
@@ -1969,11 +1969,10 @@ failed_removal:
 
 static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
 {
-	int ret = !is_memblock_offlined(mem);
 	int *nid = arg;
 
 	*nid = mem->nid;
-	if (unlikely(ret)) {
+	if (unlikely(mem->state != MEM_OFFLINE)) {
 		phys_addr_t beginpa, endpa;
 
 		beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr));
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index dbf6c7a7a7c9..d8efd5a0eb40 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -186,9 +186,16 @@ again:
 		get_page(page);
 
 		/*
-		 * Optimize for the common case where page is only mapped once
-		 * in one process. If we can lock the page, then we can safely
-		 * set up a special migration page table entry now.
+		 * We rely on trylock_page() to avoid deadlock between
+		 * concurrent migrations where each is waiting on the others
+		 * page lock. If we can't immediately lock the page we fail this
+		 * migration as it is only best effort anyway.
+		 *
+		 * If we can lock the page it's safe to set up a migration entry
+		 * now. In the common case where the page is mapped once in a
+		 * single process setting up the migration entry now is an
+		 * optimisation to avoid walking the rmap later with
+		 * try_to_migrate().
 		 */
 		if (trylock_page(page)) {
 			bool anon_exclusive;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ba0b438d57ab..65fba92d6676 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -482,6 +482,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 {
 	static unsigned long prev_end_pfn, nr_initialised;
 
+	if (early_page_ext_enabled())
+		return false;
 	/*
 	 * prev_end_pfn static that contains the end of previous zone
 	 * No need to protect because called very early in boot before smp_init.
@@ -3777,8 +3779,7 @@ struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order,
 /* Lock and remove page from the per-cpu list */
 static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 			struct zone *zone, unsigned int order,
-			gfp_t gfp_flags, int migratetype,
-			unsigned int alloc_flags)
+			int migratetype, unsigned int alloc_flags)
 {
 	struct per_cpu_pages *pcp;
 	struct list_head *list;
@@ -3839,7 +3840,7 @@ struct page *rmqueue(struct zone *preferred_zone,
 		if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA ||
 				migratetype != MIGRATE_MOVABLE) {
 			page = rmqueue_pcplist(preferred_zone, zone, order,
-					gfp_flags, migratetype, alloc_flags);
+					migratetype, alloc_flags);
 			if (likely(page))
 				goto out;
 		}
@@ -7663,6 +7664,7 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
 	int i;
 
 	pgdat_resize_init(pgdat);
+	pgdat_kswapd_lock_init(pgdat);
 
 	pgdat_init_split_queue(pgdat);
 	pgdat_init_kcompactd(pgdat);
diff --git a/mm/page_counter.c b/mm/page_counter.c
index 8a0cc24b60dd..db20d6452b71 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -17,24 +17,23 @@ static void propagate_protected_usage(struct page_counter *c,
 				      unsigned long usage)
 {
 	unsigned long protected, old_protected;
-	unsigned long low, min;
 	long delta;
 
 	if (!c->parent)
 		return;
 
-	min = READ_ONCE(c->min);
-	if (min || atomic_long_read(&c->min_usage)) {
-		protected = min(usage, min);
+	protected = min(usage, READ_ONCE(c->min));
+	old_protected = atomic_long_read(&c->min_usage);
+	if (protected != old_protected) {
 		old_protected = atomic_long_xchg(&c->min_usage, protected);
 		delta = protected - old_protected;
 		if (delta)
 			atomic_long_add(delta, &c->parent->children_min_usage);
 	}
 
-	low = READ_ONCE(c->low);
-	if (low || atomic_long_read(&c->low_usage)) {
-		protected = min(usage, low);
+	protected = min(usage, READ_ONCE(c->low));
+	old_protected = atomic_long_read(&c->low_usage);
+	if (protected != old_protected) {
 		old_protected = atomic_long_xchg(&c->low_usage, protected);
 		delta = protected - old_protected;
 		if (delta)
diff --git a/mm/page_ext.c b/mm/page_ext.c
index b236bdd59fa8..affe80243b6d 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -91,6 +91,14 @@ unsigned long page_ext_size = sizeof(struct page_ext);
 static unsigned long total_usage;
 static struct page_ext *lookup_page_ext(const struct page *page);
 
+bool early_page_ext;
+static int __init setup_early_page_ext(char *str)
+{
+	early_page_ext = true;
+	return 0;
+}
+early_param("early_page_ext", setup_early_page_ext);
+
 static bool __init invoke_need_callbacks(void)
 {
 	int i;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e68c0081e861..a991b909866f 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1300,12 +1300,12 @@ find_vmap_lowest_match(struct rb_root *root, unsigned long size,
 #include <linux/random.h>
 
 static struct vmap_area *
-find_vmap_lowest_linear_match(unsigned long size,
+find_vmap_lowest_linear_match(struct list_head *head, unsigned long size,
 	unsigned long align, unsigned long vstart)
 {
 	struct vmap_area *va;
 
-	list_for_each_entry(va, &free_vmap_area_list, list) {
+	list_for_each_entry(va, head, list) {
 		if (!is_within_this_va(va, size, align, vstart))
 			continue;
 
@@ -1316,7 +1316,8 @@ find_vmap_lowest_linear_match(unsigned long size,
 }
 
 static void
-find_vmap_lowest_match_check(unsigned long size, unsigned long align)
+find_vmap_lowest_match_check(struct rb_root *root, struct list_head *head,
+			     unsigned long size, unsigned long align)
 {
 	struct vmap_area *va_1, *va_2;
 	unsigned long vstart;
@@ -1325,8 +1326,8 @@ find_vmap_lowest_match_check(unsigned long size, unsigned long align)
 	get_random_bytes(&rnd, sizeof(rnd));
 	vstart = VMALLOC_START + rnd;
 
-	va_1 = find_vmap_lowest_match(size, align, vstart, false);
-	va_2 = find_vmap_lowest_linear_match(size, align, vstart);
+	va_1 = find_vmap_lowest_match(root, size, align, vstart, false);
+	va_2 = find_vmap_lowest_linear_match(head, size, align, vstart);
 
 	if (va_1 != va_2)
 		pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n",
@@ -1513,7 +1514,7 @@ __alloc_vmap_area(struct rb_root *root, struct list_head *head,
 		return vend;
 
 #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
-	find_vmap_lowest_match_check(size, align);
+	find_vmap_lowest_match_check(root, head, size, align);
 #endif
 
 	return nva_start_addr;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 380a99e37ef4..0358d87196e9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4651,16 +4651,17 @@ void kswapd_run(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
 
-	if (pgdat->kswapd)
-		return;
-
-	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
-	if (IS_ERR(pgdat->kswapd)) {
-		/* failure at boot is fatal */
-		BUG_ON(system_state < SYSTEM_RUNNING);
-		pr_err("Failed to start kswapd on node %d\n", nid);
-		pgdat->kswapd = NULL;
+	pgdat_kswapd_lock(pgdat);
+	if (!pgdat->kswapd) {
+		pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+		if (IS_ERR(pgdat->kswapd)) {
+			/* failure at boot is fatal */
+			BUG_ON(system_state < SYSTEM_RUNNING);
+			pr_err("Failed to start kswapd on node %d\n", nid);
+			pgdat->kswapd = NULL;
+		}
 	}
+	pgdat_kswapd_unlock(pgdat);
 }
 
 /*
@@ -4669,12 +4670,16 @@ void kswapd_run(int nid)
  */
 void kswapd_stop(int nid)
 {
-	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
+	pg_data_t *pgdat = NODE_DATA(nid);
+	struct task_struct *kswapd;
 
+	pgdat_kswapd_lock(pgdat);
+	kswapd = pgdat->kswapd;
 	if (kswapd) {
 		kthread_stop(kswapd);
-		NODE_DATA(nid)->kswapd = NULL;
+		pgdat->kswapd = NULL;
 	}
+	pgdat_kswapd_unlock(pgdat);
 }
 
 static int __init kswapd_init(void)