Merge tag 'mm-hotfixes-stable-2025-03-08-16-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
"33 hotfixes. 24 are cc:stable and the remainder address post-6.13
issues or aren't considered necessary for -stable kernels.

26 are for MM and 7 are for non-MM.

- "mm: memory_failure: unmap poisoned folio during migrate properly"
from Ma Wupeng fixes a couple of two year old bugs involving the
migration of hwpoisoned folios.

- "selftests/damon: three fixes for false results" from SeongJae Park
fixes three one year old bugs in the SAMON selftest code.

The remainder are singletons and doubletons. Please see the individual
changelogs for details"

* tag 'mm-hotfixes-stable-2025-03-08-16-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (33 commits)
mm/page_alloc: fix uninitialized variable
rapidio: add check for rio_add_net() in rio_scan_alloc_net()
rapidio: fix an API misues when rio_add_net() fails
MAINTAINERS: .mailmap: update Sumit Garg's email address
Revert "mm/page_alloc.c: don't show protection in zone's ->lowmem_reserve[] for empty zone"
mm: fix finish_fault() handling for large folios
mm: don't skip arch_sync_kernel_mappings() in error paths
mm: shmem: remove unnecessary warning in shmem_writepage()
userfaultfd: fix PTE unmapping stack-allocated PTE copies
userfaultfd: do not block on locking a large folio with raised refcount
mm: zswap: use ATOMIC_LONG_INIT to initialize zswap_stored_pages
mm: shmem: fix potential data corruption during shmem swapin
mm: fix kernel BUG when userfaultfd_move encounters swapcache
selftests/damon/damon_nr_regions: sort collected regiosn before checking with min/max boundaries
selftests/damon/damon_nr_regions: set ops update for merge results check to 100ms
selftests/damon/damos_quota: make real expectation of quota exceeds
include/linux/log2.h: mark is_power_of_2() with __always_inline
NFS: fix nfs_release_folio() to not deadlock via kcompactd writeback
mm, swap: avoid BUG_ON in relocate_cluster()
mm: swap: use correct step in loop to wait all clusters in wait_for_allocation()
...

.mailmap

···
 Subhash Jadavani <[e-mail]>
 Sudarshan Rajagopalan <[e-mail]> <[e-mail]>
 Sudeep Holla <[e-mail]> Sudeep KarkadaNagesha <[e-mail]>
+Sumit Garg <[e-mail]> <[e-mail]>
 Sumit Semwal <[e-mail]>
 Surabhi Vishnoi <[e-mail]> <[e-mail]>
 Sven Eckelmann <[e-mail]> <[e-mail]>

MAINTAINERS

···
 F:	security/keys/trusted-keys/trusted_dcp.c
 
 KEYS-TRUSTED-TEE
-M:	Sumit Garg <[e-mail]>
+M:	Sumit Garg <[e-mail]>
 L:	[e-mail]
 L:	[e-mail]
 S:	Supported
···
 F:	drivers/tee/optee/
 
 OP-TEE RANDOM NUMBER GENERATOR (RNG) DRIVER
-M:	Sumit Garg <[e-mail]>
+M:	Sumit Garg <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/char/hw_random/optee-rng.c
···
 
 TEE SUBSYSTEM
 M:	Jens Wiklander <[e-mail]>
-R:	Sumit Garg <[e-mail]>
+R:	Sumit Garg <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-class-tee

arch/arm/mm/fault-armv.c

···
 }
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
-		      unsigned long pfn, struct vm_fault *vmf)
+		      unsigned long pfn, bool need_lock)
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
···
 	if (!pte)
 		return 0;
 
-	/*
-	 * If we are using split PTE locks, then we need to take the page
-	 * lock here.  Otherwise we are using shared mm->page_table_lock
-	 * which is already locked, thus cannot take it.
-	 */
-	if (ptl != vmf->ptl) {
+	if (need_lock) {
+		/*
+		 * Use nested version here to indicate that we are already
+		 * holding one similar spinlock.
+		 */
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 		if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
 			pte_unmap_unlock(pte, ptl);
···
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	if (ptl != vmf->ptl)
+	if (need_lock)
 		spin_unlock(ptl);
 	pte_unmap(pte);
 
···
 
 static void
 make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
-	      unsigned long addr, pte_t *ptep, unsigned long pfn,
-	      struct vm_fault *vmf)
+	      unsigned long addr, pte_t *ptep, unsigned long pfn)
 {
+	const unsigned long pmd_start_addr = ALIGN_DOWN(addr, PMD_SIZE);
+	const unsigned long pmd_end_addr = pmd_start_addr + PMD_SIZE;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
···
 	flush_dcache_mmap_lock(mapping);
 	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
 		/*
+		 * If we are using split PTE locks, then we need to take the pte
+		 * lock. Otherwise we are using shared mm->page_table_lock which
+		 * is already locked, thus cannot take it.
+		 */
+		bool need_lock = IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS);
+		unsigned long mpnt_addr;
+
+		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
 		 * that we are fixing up.
···
 		if (!(mpnt->vm_flags & VM_MAYSHARE))
 			continue;
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
-		aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf);
+		mpnt_addr = mpnt->vm_start + offset;
+
+		/* Avoid deadlocks by not grabbing the same PTE lock again. */
+		if (mpnt_addr >= pmd_start_addr && mpnt_addr < pmd_end_addr)
+			need_lock = false;
+		aliases += adjust_pte(mpnt, mpnt_addr, pfn, need_lock);
 	}
 	flush_dcache_mmap_unlock(mapping);
 	if (aliases)
···
 		__flush_dcache_folio(mapping, folio);
 	if (mapping) {
 		if (cache_is_vivt())
-			make_coherent(mapping, vma, addr, ptep, pfn, vmf);
+			make_coherent(mapping, vma, addr, ptep, pfn);
 		else if (vma->vm_flags & VM_EXEC)
 			__flush_icache_all();
 	}

arch/m68k/include/asm/sun3_pgalloc.h

···
 	pgd_t *new_pgd;
 
 	new_pgd = __pgd_alloc(mm, 0);
-	memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
-	memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	if (likely(new_pgd != NULL)) {
+		memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
+		memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	}
 	return new_pgd;
 }
 

drivers/rapidio/devices/rio_mport_cdev.c

···
 		err = rio_add_net(net);
 		if (err) {
 			rmcd_debug(RDEV, "failed to register net, err=%d", err);
-			kfree(net);
+			put_device(&net->dev);
+			mport->net = NULL;
 			goto cleanup;
 		}
 	}

drivers/rapidio/rio-scan.c

···
 		dev_set_name(&net->dev, "rnet_%d", net->id);
 		net->dev.parent = &mport->dev;
 		net->dev.release = rio_scan_release_dev;
-		rio_add_net(net);
+		if (rio_add_net(net)) {
+			put_device(&net->dev);
+			net = NULL;
+		}
 	}
 
 	return net;

fs/nfs/file.c

···
 #include <linux/pagemap.h>
 #include <linux/gfp.h>
 #include <linux/swap.h>
+#include <linux/compaction.h>
 
 #include <linux/uaccess.h>
 #include <linux/filelock.h>
···
 	/* If the private flag is set, then the folio is not freeable */
 	if (folio_test_private(folio)) {
 		if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL ||
-		    current_is_kswapd())
+		    current_is_kswapd() || current_is_kcompactd())
 			return false;
 		if (nfs_wb_folio(folio->mapping->host, folio) < 0)
 			return false;

include/linux/compaction.h

···
 	return 2UL << order;
 }
 
+static inline int current_is_kcompactd(void)
+{
+	return current->flags & PF_KCOMPACTD;
+}
+
 #ifdef CONFIG_COMPACTION
 
 extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);

include/linux/hugetlb.h

···
 
 int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);
+void wait_for_freed_hugetlb_folios(void);
 struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 				unsigned long addr, bool cow_from_owner);
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
···
 		unsigned long end_pfn)
 {
 	return 0;
+}
+
+static inline void wait_for_freed_hugetlb_folios(void)
+{
 }
 
 static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,

include/linux/log2.h

···
  * *not* considered a power of two.
  * Return: true if @n is a power of 2, otherwise false.
  */
-static inline __attribute__((const))
+static __always_inline __attribute__((const))
 bool is_power_of_2(unsigned long n)
 {
 	return (n != 0 && ((n & (n - 1)) == 0));

include/linux/sched.h

···
 #define PF_USED_MATH		0x00002000	/* If unset the fpu must be initialized before use */
 #define PF_USER_WORKER		0x00004000	/* Kernel thread cloned from userspace thread */
 #define PF_NOFREEZE		0x00008000	/* This thread should not be frozen */
-#define PF__HOLE__00010000	0x00010000
+#define PF_KCOMPACTD		0x00010000	/* I am kcompactd */
 #define PF_KSWAPD		0x00020000	/* I am kswapd */
 #define PF_MEMALLOC_NOFS	0x00040000	/* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */
 #define PF_MEMALLOC_NOIO	0x00080000	/* All allocations inherit GFP_NOIO. See memalloc_noio_save() */

lib/Kconfig.debug

···
 	  reallocated, catching possible invalid pointers to the skb.
 
 	  For more information, check
-	  Documentation/dev-tools/fault-injection/fault-injection.rst
+	  Documentation/fault-injection/fault-injection.rst
 
 config FAULT_INJECTION_CONFIGFS
 	bool "Configfs interface for fault-injection capabilities"

mm/compaction.c

···
 	long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
 	long timeout = default_timeout;
 
+	current->flags |= PF_KCOMPACTD;
 	set_freezable();
 
 	pgdat->kcompactd_max_order = 0;
···
 		if (unlikely(pgdat->proactive_compact_trigger))
 			pgdat->proactive_compact_trigger = false;
 	}
+
+	current->flags &= ~PF_KCOMPACTD;
 
 	return 0;
 }

mm/hugetlb.c

···
 	return ret;
 }
 
+void wait_for_freed_hugetlb_folios(void)
+{
+	if (llist_empty(&hpage_freelist))
+		return;
+
+	flush_work(&free_hpage_work);
+}
+
 typedef enum {
 	/*
 	 * For either 0/1: we checked the per-vma resv map, and one resv

mm/internal.h

···
  * mm/memory-failure.c
  */
 #ifdef CONFIG_MEMORY_FAILURE
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu);
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
 void shake_folio(struct folio *folio);
 extern int hwpoison_filter(struct page *p);
 
···
 		struct vm_area_struct *vma);
 
 #else
-static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
 {
+	return -EBUSY;
 }
 #endif
 

mm/kmsan/hooks.c

···
 		size -= to_go;
 	}
 }
+EXPORT_SYMBOL_GPL(kmsan_handle_dma);
 
 void kmsan_handle_dma_sg(struct scatterlist *sg, int nents,
 			 enum dma_data_direction dir)

mm/memory-failure.c

···
 	return ret;
 }
 
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
 {
-	if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
-		struct address_space *mapping;
+	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
+	struct address_space *mapping;
 
+	if (folio_test_swapcache(folio)) {
+		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
+		ttu &= ~TTU_HWPOISON;
+	}
+
+	/*
+	 * Propagate the dirty bit from PTEs to struct page first, because we
+	 * need this to decide if we should kill or just drop the page.
+	 * XXX: the dirty test could be racy: set_page_dirty() may not always
+	 * be called inside page lock (it's recommended but not enforced).
+	 */
+	mapping = folio_mapping(folio);
+	if (!must_kill && !folio_test_dirty(folio) && mapping &&
+	    mapping_can_writeback(mapping)) {
+		if (folio_mkclean(folio)) {
+			folio_set_dirty(folio);
+		} else {
+			ttu &= ~TTU_HWPOISON;
+			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
+				pfn);
+		}
+	}
+
+	if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
 		/*
 		 * For hugetlb folios in shared mappings, try_to_unmap
 		 * could potentially call huge_pmd_unshare.  Because of
···
 		if (!mapping) {
 			pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
 				folio_pfn(folio));
-			return;
+			return -EBUSY;
 		}
 
 		try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
···
 	} else {
 		try_to_unmap(folio, ttu);
 	}
+
+	return folio_mapped(folio) ? -EBUSY : 0;
 }
 
 /*
···
 static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 		unsigned long pfn, int flags)
 {
-	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
-	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	bool unmap_success;
 	int forcekill;
···
 	if (!folio_mapped(folio))
 		return true;
 
-	if (folio_test_swapcache(folio)) {
-		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
-		ttu &= ~TTU_HWPOISON;
-	}
-
-	/*
-	 * Propagate the dirty bit from PTEs to struct page first, because we
-	 * need this to decide if we should kill or just drop the page.
-	 * XXX: the dirty test could be racy: set_page_dirty() may not always
-	 * be called inside page lock (it's recommended but not enforced).
-	 */
-	mapping = folio_mapping(folio);
-	if (!(flags & MF_MUST_KILL) && !folio_test_dirty(folio) && mapping &&
-	    mapping_can_writeback(mapping)) {
-		if (folio_mkclean(folio)) {
-			folio_set_dirty(folio);
-		} else {
-			ttu &= ~TTU_HWPOISON;
-			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
-				pfn);
-		}
-	}
-
 	/*
 	 * First collect all the processes that have the page
 	 * mapped in dirty form.  This has to be done before try_to_unmap,
···
 	 */
 	collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
 
-	unmap_poisoned_folio(folio, ttu);
-
-	unmap_success = !folio_mapped(folio);
+	unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL);
 	if (!unmap_success)
 		pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n",
 		       pfn, folio_mapcount(folio));

mm/memory.c

···
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(*pgd) && !create)
 			continue;
-		if (WARN_ON_ONCE(pgd_leaf(*pgd)))
-			return -EINVAL;
+		if (WARN_ON_ONCE(pgd_leaf(*pgd))) {
+			err = -EINVAL;
+			break;
+		}
 		if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) {
 			if (!create)
 				continue;
···
 	bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) &&
 		      !(vma->vm_flags & VM_SHARED);
 	int type, nr_pages;
-	unsigned long addr = vmf->address;
+	unsigned long addr;
+	bool needs_fallback = false;
+
+fallback:
+	addr = vmf->address;
 
 	/* Did we COW the page? */
 	if (is_cow)
···
 	 * approach also applies to non-anonymous-shmem faults to avoid
 	 * inflating the RSS of the process.
 	 */
-	if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) {
+	if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma)) ||
+	    unlikely(needs_fallback)) {
 		nr_pages = 1;
 	} else if (nr_pages > 1) {
 		pgoff_t idx = folio_page_idx(folio, page);
···
 		ret = VM_FAULT_NOPAGE;
 		goto unlock;
 	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
-		update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages);
-		ret = VM_FAULT_NOPAGE;
-		goto unlock;
+		needs_fallback = true;
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		goto fallback;
 	}
 
 	folio_ref_add(folio, nr_pages - 1);

mm/memory_hotplug.c

···
 		if (folio_test_large(folio))
 			pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1;
 
-		/*
-		 * HWPoison pages have elevated reference counts so the migration would
-		 * fail on them. It also doesn't make any sense to migrate them in the
-		 * first place. Still try to unmap such a page in case it is still mapped
-		 * (keep the unmap as the catch all safety net).
-		 */
-		if (folio_test_hwpoison(folio) ||
-		    (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) {
-			if (WARN_ON(folio_test_lru(folio)))
-				folio_isolate_lru(folio);
-			if (folio_mapped(folio))
-				unmap_poisoned_folio(folio, TTU_IGNORE_MLOCK);
-			continue;
-		}
-
 		if (!folio_try_get(folio))
 			continue;
 
 		if (unlikely(page_folio(page) != folio))
 			goto put_folio;
+
+		if (folio_test_hwpoison(folio) ||
+		    (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) {
+			if (WARN_ON(folio_test_lru(folio)))
+				folio_isolate_lru(folio);
+			if (folio_mapped(folio)) {
+				folio_lock(folio);
+				unmap_poisoned_folio(folio, pfn, false);
+				folio_unlock(folio);
+			}
+
+			goto put_folio;
+		}
 
 		if (!isolate_folio_to_list(folio, &source)) {
 			if (__ratelimit(&migrate_rs)) {

mm/page_alloc.c

···
 restart:
 	compaction_retries = 0;
 	no_progress_loops = 0;
+	compact_result = COMPACT_SKIPPED;
 	compact_priority = DEF_COMPACT_PRIORITY;
 	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist_iter_cookie = zonelist_iter_begin();
···
 
 			for (j = i + 1; j < MAX_NR_ZONES; j++) {
 				struct zone *upper_zone = &pgdat->node_zones[j];
-				bool empty = !zone_managed_pages(upper_zone);
 
 				managed_pages += zone_managed_pages(upper_zone);
 
-				if (clear || empty)
+				if (clear)
 					zone->lowmem_reserve[j] = 0;
 				else
 					zone->lowmem_reserve[j] = managed_pages / ratio;

mm/page_isolation.c

···
 	int ret;
 
 	/*
+	 * Due to the deferred freeing of hugetlb folios, the hugepage folios may
+	 * not immediately release to the buddy system. This can cause PageBuddy()
+	 * to fail in __test_page_isolated_in_pageblock(). To ensure that the
+	 * hugetlb folios are properly released back to the buddy system, we
+	 * invoke the wait_for_freed_hugetlb_folios() function to wait for the
+	 * release to complete.
+	 */
+	wait_for_freed_hugetlb_folios();
+
+	/*
 	 * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free
 	 * pages are not aligned to pageblock_nr_pages.
 	 * Then we just check migratetype first.

mm/shmem.c

···
 	if (WARN_ON_ONCE(!wbc->for_reclaim))
 		goto redirty;
 
-	if (WARN_ON_ONCE((info->flags & VM_LOCKED) || sbinfo->noswap))
+	if ((info->flags & VM_LOCKED) || sbinfo->noswap)
 		goto redirty;
 
 	if (!total_swap_pages)
···
 	struct folio *folio = NULL;
 	bool skip_swapcache = false;
 	swp_entry_t swap;
-	int error, nr_pages;
+	int error, nr_pages, order, split_order;
 
 	VM_BUG_ON(!*foliop || !xa_is_value(*foliop));
 	swap = radix_to_swp_entry(*foliop);
···
 
 	/* Look it up and read it in.. */
 	folio = swap_cache_get_folio(swap, NULL, 0);
+	order = xa_get_order(&mapping->i_pages, index);
 	if (!folio) {
-		int order = xa_get_order(&mapping->i_pages, index);
 		bool fallback_order0 = false;
-		int split_order;
 
 		/* Or update major stats only when swapin succeeds?? */
 		if (fault_type) {
···
 			error = -ENOMEM;
 			goto failed;
 		}
+	} else if (order != folio_order(folio)) {
+		/*
+		 * Swap readahead may swap in order 0 folios into swapcache
+		 * asynchronously, while the shmem mapping can still stores
+		 * large swap entries. In such cases, we should split the
+		 * large swap entry to prevent possible data corruption.
+		 */
+		split_order = shmem_split_large_entry(inode, index, swap, gfp);
+		if (split_order < 0) {
+			error = split_order;
+			goto failed;
+		}
+
+		/*
+		 * If the large swap entry has already been split, it is
+		 * necessary to recalculate the new swap entry based on
+		 * the old order alignment.
+		 */
+		if (split_order > 0) {
+			pgoff_t offset = index - round_down(index, 1 << split_order);
+
+			swap = swp_entry(swp_type(swap), swp_offset(swap) + offset);
+		}
 	}
 
 alloced:
···
 	folio_lock(folio);
 	if ((!skip_swapcache && !folio_test_swapcache(folio)) ||
 	    folio->swap.val != swap.val ||
-	    !shmem_confirm_swap(mapping, index, swap)) {
+	    !shmem_confirm_swap(mapping, index, swap) ||
+	    xa_get_order(&mapping->i_pages, index) != folio_order(folio)) {
 		error = -EEXIST;
 		goto unlock;
 	}

mm/swapfile.c

···
 		return;
 
 	if (!ci->count) {
-		free_cluster(si, ci);
+		if (ci->flags != CLUSTER_FLAG_FREE)
+			free_cluster(si, ci);
 	} else if (ci->count != SWAPFILE_CLUSTER) {
 		if (ci->flags != CLUSTER_FLAG_FRAG)
 			move_cluster(si, ci, &si->frag_clusters[ci->order],
···
 			}
 			offset++;
 		}
+
+		/* in case no swap cache is reclaimed */
+		if (ci->flags == CLUSTER_FLAG_NONE)
+			relocate_cluster(si, ci);
 
 		unlock_cluster(ci);
 		if (to_scan <= 0)
···
 	for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) {
 		ci = lock_cluster(si, offset);
 		unlock_cluster(ci);
-		offset += SWAPFILE_CLUSTER;
 	}
 }
 
···
 	int err, i;
 
 	si = swp_swap_info(entry);
+	if (WARN_ON_ONCE(!si)) {
+		pr_err("%s%08lx\n", Bad_file, entry.val);
+		return -EINVAL;
+	}
 
 	offset = swp_offset(entry);
 	VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);

mm/userfaultfd.c

···
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include "internal.h"
+#include "swap.h"
 
 static __always_inline
 bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
···
 	return err;
 }
 
-static int move_swap_pte(struct mm_struct *mm,
+static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 			 unsigned long dst_addr, unsigned long src_addr,
 			 pte_t *dst_pte, pte_t *src_pte,
 			 pte_t orig_dst_pte, pte_t orig_src_pte,
 			 pmd_t *dst_pmd, pmd_t dst_pmdval,
-			 spinlock_t *dst_ptl, spinlock_t *src_ptl)
+			 spinlock_t *dst_ptl, spinlock_t *src_ptl,
+			 struct folio *src_folio)
 {
-	if (!pte_swp_exclusive(orig_src_pte))
-		return -EBUSY;
-
 	double_pt_lock(dst_ptl, src_ptl);
 
 	if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
 				 dst_pmd, dst_pmdval)) {
 		double_pt_unlock(dst_ptl, src_ptl);
 		return -EAGAIN;
+	}
+
+	/*
+	 * The src_folio resides in the swapcache, requiring an update to its
+	 * index and mapping to align with the dst_vma, where a swap-in may
+	 * occur and hit the swapcache after moving the PTE.
+	 */
+	if (src_folio) {
+		folio_move_anon_rmap(src_folio, dst_vma);
+		src_folio->index = linear_page_index(dst_vma, dst_addr);
 	}
 
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
···
 			  __u64 mode)
 {
 	swp_entry_t entry;
+	struct swap_info_struct *si = NULL;
 	pte_t orig_src_pte, orig_dst_pte;
 	pte_t src_folio_pte;
 	spinlock_t *src_ptl, *dst_ptl;
···
 		 */
 		if (!src_folio) {
 			struct folio *folio;
+			bool locked;
 
 			/*
 			 * Pin the page while holding the lock to be sure the
···
 				goto out;
 			}
 
+			locked = folio_trylock(folio);
+			/*
+			 * We avoid waiting for folio lock with a raised
+			 * refcount for large folios because extra refcounts
+			 * will result in split_folio() failing later and
+			 * retrying.  If multiple tasks are trying to move a
+			 * large folio we can end up livelocking.
+			 */
+			if (!locked && folio_test_large(folio)) {
+				spin_unlock(src_ptl);
+				err = -EAGAIN;
+				goto out;
+			}
+
 			folio_get(folio);
 			src_folio = folio;
 			src_folio_pte = orig_src_pte;
 			spin_unlock(src_ptl);
 
-			if (!folio_trylock(src_folio)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+			if (!locked) {
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				/* now we can block and wait */
 				folio_lock(src_folio);
···
 		/* at this point we have src_folio locked */
 		if (folio_test_large(src_folio)) {
 			/* split_folio() can block */
-			pte_unmap(&orig_src_pte);
-			pte_unmap(&orig_dst_pte);
+			pte_unmap(src_pte);
+			pte_unmap(dst_pte);
 			src_pte = dst_pte = NULL;
 			err = split_folio(src_folio);
 			if (err)
···
 				goto out;
 			}
 			if (!anon_vma_trylock_write(src_anon_vma)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				/* now we can block and wait */
 				anon_vma_lock_write(src_anon_vma);
···
 				       orig_dst_pte, orig_src_pte, dst_pmd,
 				       dst_pmdval, dst_ptl, src_ptl, src_folio);
 	} else {
+		struct folio *folio = NULL;
+
 		entry = pte_to_swp_entry(orig_src_pte);
 		if (non_swap_entry(entry)) {
 			if (is_migration_entry(entry)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				migration_entry_wait(mm, src_pmd, src_addr);
 				err = -EAGAIN;
···
 			goto out;
 		}
 
-		err = move_swap_pte(mm, dst_addr, src_addr, dst_pte, src_pte,
-				    orig_dst_pte, orig_src_pte, dst_pmd,
-				    dst_pmdval, dst_ptl, src_ptl);
+		if (!pte_swp_exclusive(orig_src_pte)) {
+			err = -EBUSY;
+			goto out;
+		}
+
+		si = get_swap_device(entry);
+		if (unlikely(!si)) {
+			err = -EAGAIN;
+			goto out;
+		}
+		/*
+		 * Verify the existence of the swapcache. If present, the folio's
+		 * index and mapping must be updated even when the PTE is a swap
+		 * entry. The anon_vma lock is not taken during this process since
+		 * the folio has already been unmapped, and the swap entry is
+		 * exclusive, preventing rmap walks.
+		 *
+		 * For large folios, return -EBUSY immediately, as split_folio()
+		 * also returns -EBUSY when attempting to split unmapped large
+		 * folios in the swapcache. This issue needs to be resolved
+		 * separately to allow proper handling.
+		 */
+		if (!src_folio)
+			folio = filemap_get_folio(swap_address_space(entry),
+					swap_cache_index(entry));
+		if (!IS_ERR_OR_NULL(folio)) {
+			if (folio_test_large(folio)) {
+				err = -EBUSY;
+				folio_put(folio);
+				goto out;
+			}
+			src_folio = folio;
+			src_folio_pte = orig_src_pte;
+			if (!folio_trylock(src_folio)) {
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
+				src_pte = dst_pte = NULL;
+				put_swap_device(si);
+				si = NULL;
+				/* now we can block and wait */
+				folio_lock(src_folio);
+				goto retry;
+			}
+		}
+		err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte,
+				orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval,
+				dst_ptl, src_ptl, src_folio);
 	}
 
 out:
···
 	if (src_pte)
 		pte_unmap(src_pte);
 	mmu_notifier_invalidate_range_end(&range);
+	if (si)
+		put_swap_device(si);
 
 	return err;
 }

mm/vma.c

···
 static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg)
 {
 	struct vm_area_struct *vma = vmg->vma;
+	unsigned long start = vmg->start;
+	unsigned long end = vmg->end;
 	struct vm_area_struct *merged;
 
 	/* First, try to merge. */
 	merged = vma_merge_existing_range(vmg);
 	if (merged)
 		return merged;
+	if (vmg_nomem(vmg))
+		return ERR_PTR(-ENOMEM);
 
 	/* Split any preceding portion of the VMA. */
-	if (vma->vm_start < vmg->start) {
-		int err = split_vma(vmg->vmi, vma, vmg->start, 1);
+	if (vma->vm_start < start) {
+		int err = split_vma(vmg->vmi, vma, start, 1);
 
 		if (err)
 			return ERR_PTR(err);
 	}
 
 	/* Split any trailing portion of the VMA. */
-	if (vma->vm_end > vmg->end) {
-		int err = split_vma(vmg->vmi, vma, vmg->end, 0);
+	if (vma->vm_end > end) {
+		int err = split_vma(vmg->vmi, vma, end, 0);
 
 		if (err)
 			return ERR_PTR(err);

mm/vmalloc.c

···
 			mask |= PGTBL_PGD_MODIFIED;
 		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
 		if (err)
-			return err;
+			break;
 	} while (pgd++, addr = next, addr != end);
 
 	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
 		arch_sync_kernel_mappings(start, end);
 
-	return 0;
+	return err;
 }
 
 /*

mm/zswap.c

···
 * statistics
 **********************************/
 /* The number of compressed pages currently stored in zswap */
-atomic_long_t zswap_stored_pages = ATOMIC_INIT(0);
+atomic_long_t zswap_stored_pages = ATOMIC_LONG_INIT(0);
 
 /*
  * The statistics below are not protected from concurrent access for

tools/testing/selftests/damon/damon_nr_regions.py

···
 
     test_name = 'nr_regions test with %d/%d/%d real/min/max nr_regions' % (
             real_nr_regions, min_nr_regions, max_nr_regions)
+    collected_nr_regions.sort()
     if (collected_nr_regions[0] < min_nr_regions or
         collected_nr_regions[-1] > max_nr_regions):
         print('fail %s' % test_name)
···
     attrs = kdamonds.kdamonds[0].contexts[0].monitoring_attrs
     attrs.min_nr_regions = 3
     attrs.max_nr_regions = 7
+    attrs.update_us = 100000
     err = kdamonds.kdamonds[0].commit()
     if err is not None:
         proc.terminate()

tools/testing/selftests/damon/damos_quota.py

···
         nr_quota_exceeds = scheme.stats.qt_exceeds
 
     wss_collected.sort()
+    nr_expected_quota_exceeds = 0
     for wss in wss_collected:
         if wss > sz_quota:
             print('quota is not kept: %s > %s' % (wss, sz_quota))
             print('collected samples are as below')
             print('\n'.join(['%d' % wss for wss in wss_collected]))
             exit(1)
+        if wss == sz_quota:
+            nr_expected_quota_exceeds += 1
 
-    if nr_quota_exceeds < len(wss_collected):
-        print('quota is not always exceeded: %d > %d' %
-              (len(wss_collected), nr_quota_exceeds))
+    if nr_quota_exceeds < nr_expected_quota_exceeds:
+        print('quota is exceeded less than expected: %d < %d' %
+              (nr_quota_exceeds, nr_expected_quota_exceeds))
         exit(1)
 
 if __name__ == '__main__':

tools/testing/selftests/damon/damos_quota_goal.py

···
             if last_effective_bytes != 0 else -1.0))
 
         if last_effective_bytes == goal.effective_bytes:
+            # effective quota was already minimum that cannot be more reduced
+            if expect_increase is False and last_effective_bytes == 1:
+                continue
             print('efective bytes not changed: %d' % goal.effective_bytes)
             exit(1)
 

tools/testing/selftests/mm/hugepage-mremap.c

···
 #define _GNU_SOURCE
 #include <stdlib.h>
 #include <stdio.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <sys/mman.h>
 #include <errno.h>
 #include <fcntl.h> /* Definition of O_* constants */

tools/testing/selftests/mm/ksm_functional_tests.c

···
 #include <string.h>
 #include <stdbool.h>
 #include <stdint.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <sys/mman.h>
···
 	munmap(map, size);
 }
 
+#ifdef __NR_userfaultfd
 static void test_unmerge_uffd_wp(void)
 {
 	struct uffdio_writeprotect uffd_writeprotect;
···
 unmap:
 	munmap(map, size);
 }
+#endif
 
 /* Verify that KSM can be enabled / queried with prctl. */
 static void test_prctl(void)
···
 		exit(test_child_ksm());
 	}
 
+#ifdef __NR_userfaultfd
 	tests++;
+#endif
 
 	ksft_print_header();
 	ksft_set_plan(tests);
···
 	test_unmerge();
 	test_unmerge_zero_pages();
 	test_unmerge_discarded();
+#ifdef __NR_userfaultfd
 	test_unmerge_uffd_wp();
+#endif
 
 	test_prot_none();
 

tools/testing/selftests/mm/memfd_secret.c

···
 
 #include <stdlib.h>
 #include <string.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <errno.h>
 #include <stdio.h>
 #include <fcntl.h>
···
 #define fail(fmt, ...) ksft_test_result_fail(fmt, ##__VA_ARGS__)
 #define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__)
 #define skip(fmt, ...) ksft_test_result_skip(fmt, ##__VA_ARGS__)
+
+#ifdef __NR_memfd_secret
 
 #define PATTERN	0x55
 
···
 
 	ksft_finished();
 }
+
+#else /* __NR_memfd_secret */
+
+int main(int argc, char *argv[])
+{
+	printf("skip: skipping memfd_secret test (missing __NR_memfd_secret)\n");
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_memfd_secret */

tools/testing/selftests/mm/mkdirty.c

···
  */
 #include <fcntl.h>
 #include <signal.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <string.h>
 #include <errno.h>
 #include <stdlib.h>
···
 	munmap(mmap_mem, mmap_size);
 }
 
+#ifdef __NR_userfaultfd
 static void test_uffdio_copy(void)
 {
 	struct uffdio_register uffdio_register;
···
 	munmap(dst, pagesize);
 	free(src);
 }
+#endif /* __NR_userfaultfd */
 
 int main(void)
 {
···
 			       thpsize / 1024);
 		tests += 3;
 	}
+#ifdef __NR_userfaultfd
 	tests += 1;
+#endif /* __NR_userfaultfd */
 
 	ksft_print_header();
 	ksft_set_plan(tests);
···
 	if (thpsize)
 		test_pte_mapped_thp();
 	/* Placing a fresh page via userfaultfd may set the PTE dirty. */
+#ifdef __NR_userfaultfd
 	test_uffdio_copy();
+#endif /* __NR_userfaultfd */
 
 	err = ksft_get_fail_cnt();
 	if (err)

tools/testing/selftests/mm/mlock2.h

···
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <asm-generic/unistd.h>
 
 static int mlock2_(void *start, size_t len, int flags)
 {

tools/testing/selftests/mm/protection_keys.c

···
 #include <sys/wait.h>
 #include <sys/stat.h>
 #include <fcntl.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <sys/ptrace.h>
 #include <setjmp.h>
 

tools/testing/selftests/mm/uffd-common.c

···
 
 int uffd_open_sys(unsigned int flags)
 {
+#ifdef __NR_userfaultfd
 	return syscall(__NR_userfaultfd, flags);
+#else
+	return -1;
+#endif
 }
 
 int uffd_open(unsigned int flags)

tools/testing/selftests/mm/uffd-stress.c

···
  * pthread_mutex_lock will also verify the atomicity of the memory
  * transfer (UFFDIO_COPY).
  */
-#include <asm-generic/unistd.h>
+
 #include "uffd-common.h"
 
 uint64_t features;
+#ifdef __NR_userfaultfd
 
 #define BOUNCE_RANDOM		(1<<0)
 #define BOUNCE_RACINGFAULTS	(1<<1)
···
 	       nr_pages, nr_pages_per_cpu);
 	return userfaultfd_stress();
 }
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */

tools/testing/selftests/mm/uffd-unit-tests.c

···
  *  Copyright (C) 2015-2023  Red Hat, Inc.
  */
 
-#include <asm-generic/unistd.h>
 #include "uffd-common.h"
 
 #include "../../../../mm/gup_test.h"
+
+#ifdef __NR_userfaultfd
 
 /* The unit test doesn't need a large or random size, make it 32MB for now */
 #define  UFFD_TEST_MEM_SIZE               (32UL << 20)
···
 	return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS;
 }
 
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("Skipping %s (missing __NR_userfaultfd)\n", __file__);
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */