Pull mm-hotfixes-stable dependencies into mm-stable.

Merge branch 'mm-hotfixes-stable' into mm-stable

.mailmap

@@ -371,6 +371,7 @@ Rémi Denis-Courmont <rdenis@simphalempin.com>
 Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com>
 Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org>
 Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
+Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org>
 Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
 Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>

Documentation/admin-guide/mm/zswap.rst

@@ -70,9 +70,7 @@ e.g. ``zswap.zpool=zbud``. It can also be changed at runtime using the sysfs
 The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which
 means the compression ratio will always be 2:1 or worse (because of half-full
 zbud pages).  The zsmalloc type zpool has a more complex compressed page
-storage method, and it can achieve greater storage densities.  However,
-zsmalloc does not implement compressed page eviction, so once zswap fills it
-cannot evict the oldest page, it can only reject new pages.
+storage method, and it can achieve greater storage densities.
 
 When a swap page is passed from frontswap to zswap, zswap maintains a mapping
 of the swap entry, a combination of the swap type and swap offset, to the zpool

MAINTAINERS

@@ -6948,7 +6948,7 @@ F:	drivers/gpu/drm/atmel-hlcdc/
 DRM DRIVERS FOR BRIDGE CHIPS
 M:	Andrzej Hajda <andrzej.hajda@intel.com>
 M:	Neil Armstrong <neil.armstrong@linaro.org>
-M:	Robert Foss <robert.foss@linaro.org>
+M:	Robert Foss <rfoss@kernel.org>
 R:	Laurent Pinchart <Laurent.pinchart@ideasonboard.com>
 R:	Jonas Karlman <jonas@kwiboo.se>
 R:	Jernej Skrabec <jernej.skrabec@gmail.com>
@@ -17238,7 +17238,7 @@ F:	Documentation/devicetree/bindings/net/qcom,bam-dmux.yaml
 F:	drivers/net/wwan/qcom_bam_dmux.c
 
 QUALCOMM CAMERA SUBSYSTEM DRIVER
-M:	Robert Foss <robert.foss@linaro.org>
+M:	Robert Foss <rfoss@kernel.org>
 M:	Todor Tomov <todor.too@gmail.com>
 L:	linux-media@vger.kernel.org
 S:	Maintained
@@ -17318,7 +17318,7 @@ F:	drivers/dma/qcom/hidma*
 
 QUALCOMM I2C CCI DRIVER
 M:	Loic Poulain <loic.poulain@linaro.org>
-M:	Robert Foss <robert.foss@linaro.org>
+M:	Robert Foss <rfoss@kernel.org>
 L:	linux-i2c@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained

fs/nilfs2/btree.c

@@ -480,9 +480,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
 	ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh,
 					&submit_ptr);
 	if (ret) {
-		if (ret != -EEXIST)
-			return ret;
-		goto out_check;
+		if (likely(ret == -EEXIST))
+			goto out_check;
+		if (ret == -ENOENT) {
+			/*
+			 * Block address translation failed due to invalid
+			 * value of 'ptr'.  In this case, return internal code
+			 * -EINVAL (broken bmap) to notify bmap layer of fatal
+			 * metadata corruption.
+			 */
+			ret = -EINVAL;
+		}
+		return ret;
 	}
 
 	if (ra) {

fs/userfaultfd.c

@@ -108,6 +108,21 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
 	return ctx->features & UFFD_FEATURE_INITIALIZED;
 }
 
+static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
+				     vm_flags_t flags)
+{
+	const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP;
+
+	vma->vm_flags = flags;
+	/*
+	 * For shared mappings, we want to enable writenotify while
+	 * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply
+	 * recalculate vma->vm_page_prot whenever userfaultfd-wp changes.
+	 */
+	if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed)
+		vma_set_page_prot(vma);
+}
+
 static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
 				     int wake_flags, void *key)
 {
@@ -618,7 +633,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 		for_each_vma(vmi, vma) {
 			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-				vma->vm_flags &= ~__VM_UFFD_FLAGS;
+				userfaultfd_set_vm_flags(vma,
+							 vma->vm_flags & ~__VM_UFFD_FLAGS);
 			}
 		}
 		mmap_write_unlock(mm);
@@ -652,7 +668,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 	octx = vma->vm_userfaultfd_ctx.ctx;
 	if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		vma->vm_flags &= ~__VM_UFFD_FLAGS;
+		userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
 		return 0;
 	}
 
@@ -733,7 +749,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 	} else {
 		/* Drop uffd context if remap feature not enabled */
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		vma->vm_flags &= ~__VM_UFFD_FLAGS;
+		userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
 	}
 }
 
@@ -895,7 +911,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 			prev = vma;
 		}
 
-		vma->vm_flags = new_flags;
+		userfaultfd_set_vm_flags(vma, new_flags);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
 	mmap_write_unlock(mm);
@@ -1463,7 +1479,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		 * the next vma was merged into the current one and
 		 * the current one has not been updated yet.
 		 */
-		vma->vm_flags = new_flags;
+		userfaultfd_set_vm_flags(vma, new_flags);
 		vma->vm_userfaultfd_ctx.ctx = ctx;
 
 		if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
@@ -1651,7 +1667,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		 * the next vma was merged into the current one and
 		 * the current one has not been updated yet.
 		 */
-		vma->vm_flags = new_flags;
+		userfaultfd_set_vm_flags(vma, new_flags);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 
 	skip:

include/linux/mm.h

@@ -1270,10 +1270,10 @@ static inline void folio_put_refs(struct folio *folio, int refs)
 		__folio_put(folio);
 }
 
-/**
- * release_pages - release an array of pages or folios
+/*
+ * union release_pages_arg - an array of pages or folios
  *
- * This just releases a simple array of multiple pages, and
+ * release_pages() releases a simple array of multiple pages, and
  * accepts various different forms of said page array: either
  * a regular old boring array of pages, an array of folios, or
  * an array of encoded page pointers.

include/linux/mm_inline.h

@@ -413,8 +413,7 @@ static inline void free_anon_vma_name(struct vm_area_struct *vma)
 	 * Not using anon_vma_name because it generates a warning if mmap_lock
 	 * is not held, which might be the case here.
 	 */
-	if (!vma->vm_file)
-		anon_vma_name_put(vma->anon_name);
+	anon_vma_name_put(vma->anon_name);
 }
 
 static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,

include/linux/mm_types.h

@@ -581,7 +581,7 @@ struct vm_area_struct {
 	/*
 	 * For private and shared anonymous mappings, a pointer to a null
 	 * terminated string containing the name given to the vma, or NULL if
-	 * unnamed. Serialized by mmap_sem. Use anon_vma_name to access.
+	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
 	 */
 	struct anon_vma_name *anon_name;
 #endif

include/linux/page_ref.h

@@ -301,7 +301,7 @@ static inline bool folio_ref_try_add_rcu(struct folio *folio, int count)
  *
  * You can also use this function if you're holding a lock that prevents
  * pages being frozen & removed; eg the i_pages lock for the page cache
- * or the mmap_sem or page table lock for page tables.  In this case,
+ * or the mmap_lock or page table lock for page tables.  In this case,
  * it will always succeed, and you could have used a plain folio_get(),
  * but it's sometimes more convenient to have a common function called
  * from both locked and RCU-protected contexts.

init/Kconfig

@@ -776,7 +776,7 @@ config PRINTK_SAFE_LOG_BUF_SHIFT
 	depends on PRINTK
 	help
 	  Select the size of an alternate printk per-CPU buffer where messages
-	  printed from usafe contexts are temporary stored. One example would
+	  printed from unsafe contexts are temporary stored. One example would
 	  be NMI messages, another one - printk recursion. The messages are
 	  copied to the main log buffer in a safe context to avoid a deadlock.
 	  The value defines the size as a power of 2.

lib/win_minmax.c

 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * lib/minmax.c: windowed min/max tracker
  *
  * Kathleen Nichols' algorithm for tracking the minimum (or maximum)

mm/hugetlb.c

@@ -94,6 +94,8 @@ static int hugetlb_acct_memory(struct hstate *h, long delta);
 static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
 static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end);
 
 static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
@@ -1181,7 +1183,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 
 /*
  * Reset and decrement one ref on hugepage private reservation.
- * Called with mm->mmap_sem writer semaphore held.
+ * Called with mm->mmap_lock writer semaphore held.
  * This function should be only used by move_vma() and operate on
  * same sized vma. It should never come here with last ref on the
  * reservation.
@@ -4834,6 +4836,25 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
 {
 	if (addr & ~(huge_page_mask(hstate_vma(vma))))
 		return -EINVAL;
+
+	/*
+	 * PMD sharing is only possible for PUD_SIZE-aligned address ranges
+	 * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this
+	 * split, unshare PMDs in the PUD_SIZE interval surrounding addr now.
+	 */
+	if (addr & ~PUD_MASK) {
+		/*
+		 * hugetlb_vm_op_split is called right before we attempt to
+		 * split the VMA. We will need to unshare PMDs in the old and
+		 * new VMAs, so let's unshare before we split.
+		 */
+		unsigned long floor = addr & PUD_MASK;
+		unsigned long ceil = floor + PUD_SIZE;
+
+		if (floor >= vma->vm_start && ceil <= vma->vm_end)
+			hugetlb_unshare_pmds(vma, floor, ceil);
+	}
+
 	return 0;
 }
 
@@ -5030,6 +5051,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 				entry = huge_pte_clear_uffd_wp(entry);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		} else if (unlikely(is_pte_marker(entry))) {
+			/* No swap on hugetlb */
+			WARN_ON_ONCE(
+			    is_swapin_error_entry(pte_to_swp_entry(entry)));
 			/*
 			 * We copy the pte marker only if the dst vma has
 			 * uffd-wp enabled.
@@ -5131,7 +5155,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
 
 	/*
 	 * We don't have to worry about the ordering of src and dst ptlocks
-	 * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock.
+	 * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock.
 	 */
 	if (src_ptl != dst_ptl)
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -6639,8 +6663,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address, psize);
 		if (!ptep) {
-			address |= last_addr_mask;
-			continue;
+			if (!uffd_wp) {
+				address |= last_addr_mask;
+				continue;
+			}
+			/*
+			 * Userfaultfd wr-protect requires pgtable
+			 * pre-allocations to install pte markers.
+			 */
+			ptep = huge_pte_alloc(mm, vma, address, psize);
+			if (!ptep)
+				break;
 		}
 		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, vma, address, ptep)) {
@@ -6658,16 +6691,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 		pte = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
-			spin_unlock(ptl);
-			continue;
-		}
-		if (unlikely(is_hugetlb_entry_migration(pte))) {
+			/* Nothing to do. */
+		} else if (unlikely(is_hugetlb_entry_migration(pte))) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
 			struct page *page = pfn_swap_entry_to_page(entry);
+			pte_t newpte = pte;
 
-			if (!is_readable_migration_entry(entry)) {
-				pte_t newpte;
-
+			if (is_writable_migration_entry(entry)) {
 				if (PageAnon(page))
 					entry = make_readable_exclusive_migration_entry(
 								swp_offset(entry));
@@ -6675,25 +6705,22 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 					entry = make_readable_migration_entry(
 								swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
-				if (uffd_wp)
-					newpte = pte_swp_mkuffd_wp(newpte);
-				else if (uffd_wp_resolve)
-					newpte = pte_swp_clear_uffd_wp(newpte);
-				set_huge_pte_at(mm, address, ptep, newpte);
 				pages++;
 			}
-			spin_unlock(ptl);
-			continue;
-		}
-		if (unlikely(pte_marker_uffd_wp(pte))) {
-			/*
-			 * This is changing a non-present pte into a none pte,
-			 * no need for huge_ptep_modify_prot_start/commit().
-			 */
+
+			if (uffd_wp)
+				newpte = pte_swp_mkuffd_wp(newpte);
+			else if (uffd_wp_resolve)
+				newpte = pte_swp_clear_uffd_wp(newpte);
+			if (!pte_same(pte, newpte))
+				set_huge_pte_at(mm, address, ptep, newpte);
+		} else if (unlikely(is_pte_marker(pte))) {
+			/* No other markers apply for now. */
+			WARN_ON_ONCE(!pte_marker_uffd_wp(pte));
 			if (uffd_wp_resolve)
+				/* Safe to modify directly (non-present->none). */
 				huge_pte_clear(mm, address, ptep, psize);
-		}
-		if (!huge_pte_none(pte)) {
+		} else if (!huge_pte_none(pte)) {
 			pte_t old_pte;
 			unsigned int shift = huge_page_shift(hstate_vma(vma));
 
@@ -7328,26 +7355,21 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re
 	}
 }
 
-/*
- * This function will unconditionally remove all the shared pmd pgtable entries
- * within the specific vma for a hugetlbfs memory range.
- */
-void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+				   unsigned long start,
+				   unsigned long end)
 {
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct mm_struct *mm = vma->vm_mm;
 	struct mmu_notifier_range range;
-	unsigned long address, start, end;
+	unsigned long address;
 	spinlock_t *ptl;
 	pte_t *ptep;
 
 	if (!(vma->vm_flags & VM_MAYSHARE))
 		return;
 
-	start = ALIGN(vma->vm_start, PUD_SIZE);
-	end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
-
 	if (start >= end)
 		return;
 
@@ -7379,6 +7401,16 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
 	mmu_notifier_invalidate_range_end(&range);
 }
 
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+{
+	hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE),
+			ALIGN_DOWN(vma->vm_end, PUD_SIZE));
+}
+
 #ifdef CONFIG_CMA
 static bool cma_reserve_called __initdata;
 

mm/kasan/report.c

@@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(kasan_restore_multi_shot);
  * Whether the KASAN KUnit test suite is currently being executed.
  * Updated in kasan_test.c.
  */
-bool kasan_kunit_executing;
+static bool kasan_kunit_executing;
 
 void kasan_kunit_test_suite_start(void)
 {

mm/khugepaged.c

@@ -1460,14 +1460,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
 		return SCAN_VMA_CHECK;
 
-	/*
-	 * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings
-	 * that got written to. Without this, we'd have to also lock the
-	 * anon_vma if one exists.
-	 */
-	if (vma->anon_vma)
-		return SCAN_VMA_CHECK;
-
 	/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
 	if (userfaultfd_wp(vma))
 		return SCAN_PTE_UFFD_WP;
@@ -1567,8 +1559,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	}
 
 	/* step 4: remove pte entries */
+	/* we make no change to anon, but protect concurrent anon page lookup */
+	if (vma->anon_vma)
+		anon_vma_lock_write(vma->anon_vma);
+
 	collapse_and_free_pmd(mm, vma, haddr, pmd);
 
+	if (vma->anon_vma)
+		anon_vma_unlock_write(vma->anon_vma);
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 
 maybe_install_pmd:
@@ -2649,7 +2647,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 				goto out_nolock;
 			}
 
-			hend = vma->vm_end & HPAGE_PMD_MASK;
+			hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
 		}
 		mmap_assert_locked(mm);
 		memset(cc->node_load, 0, sizeof(cc->node_load));

mm/madvise.c

@@ -130,7 +130,7 @@ static int replace_anon_vma_name(struct vm_area_struct *vma,
 #endif /* CONFIG_ANON_VMA_NAME */
 /*
  * Update the vm_flags on region of a vma, splitting it or merging it as
- * necessary.  Must be called with mmap_sem held for writing;
+ * necessary.  Must be called with mmap_lock held for writing;
  * Caller should ensure anon_name stability by raising its refcount even when
  * anon_name belongs to a valid vma because this function might free that vma.
  */

mm/memory.c

@@ -828,12 +828,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			return -EBUSY;
 		return -ENOENT;
 	} else if (is_pte_marker_entry(entry)) {
-		/*
-		 * We're copying the pgtable should only because dst_vma has
-		 * uffd-wp enabled, do sanity check.
-		 */
-		WARN_ON_ONCE(!userfaultfd_wp(dst_vma));
-		set_pte_at(dst_mm, addr, dst_pte, pte);
+		if (is_swapin_error_entry(entry) || userfaultfd_wp(dst_vma))
+			set_pte_at(dst_mm, addr, dst_pte, pte);
 		return 0;
 	}
 	if (!userfaultfd_wp(dst_vma))
@@ -3629,8 +3625,12 @@ static vm_fault_t pte_marker_clear(struct vm_fault *vmf)
 	/*
 	 * Be careful so that we will only recover a special uffd-wp pte into a
 	 * none pte.  Otherwise it means the pte could have changed, so retry.
+	 *
+	 * This should also cover the case where e.g. the pte changed
+	 * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_SWAPIN_ERROR.
+	 * So is_pte_marker() check is not enough to safely drop the pte.
 	 */
-	if (is_pte_marker(*vmf->pte))
+	if (pte_same(vmf->orig_pte, *vmf->pte))
 		pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return 0;

mm/mmap.c

@@ -1524,6 +1524,10 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 	if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma))
 		return 1;
 
+	/* Do we need write faults for uffd-wp tracking? */
+	if (userfaultfd_wp(vma))
+		return 1;
+
 	/* Specialty mapping? */
 	if (vm_flags & VM_PFNMAP)
 		return 0;
@@ -2290,7 +2294,7 @@ static inline int munmap_sidetree(struct vm_area_struct *vma,
  * @start: The aligned start address to munmap.
  * @end: The aligned end address to munmap.
  * @uf: The userfaultfd list_head
- * @downgrade: Set to true to attempt a write downgrade of the mmap_sem
+ * @downgrade: Set to true to attempt a write downgrade of the mmap_lock
  *
  * If @downgrade is true, check return code for potential release of the lock.
  */
@@ -2465,7 +2469,7 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma,
  * @len: The length of the range to munmap
  * @uf: The userfaultfd list_head
  * @downgrade: set to true if the user wants to attempt to write_downgrade the
- * mmap_sem
+ * mmap_lock
  *
  * This function takes a @mas that is either pointing to the previous VMA or set
  * to MA_START and sets it up to remove the mapping(s).  The @len will be

mm/mprotect.c

@@ -245,7 +245,13 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
 					newpte = pte_swp_mksoft_dirty(newpte);
 				if (pte_swp_uffd_wp(oldpte))
 					newpte = pte_swp_mkuffd_wp(newpte);
-			} else if (pte_marker_entry_uffd_wp(entry)) {
+			} else if (is_pte_marker_entry(entry)) {
+				/*
+				 * Ignore swapin errors unconditionally,
+				 * because any access should sigbus anyway.
+				 */
+				if (is_swapin_error_entry(entry))
+					continue;
 				/*
 				 * If this is uffd-wp pte marker and we'd like
 				 * to unprotect it, drop it; the next page

mm/nommu.c

@@ -559,7 +559,6 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas)
 
 static void setup_vma_to_mm(struct vm_area_struct *vma, struct mm_struct *mm)
 {
-	mm->map_count++;
 	vma->vm_mm = mm;
 
 	/* add the VMA to the mapping */
@@ -587,6 +586,7 @@ static void mas_add_vma_to_mm(struct ma_state *mas, struct mm_struct *mm,
 	BUG_ON(!vma->vm_region);
 
 	setup_vma_to_mm(vma, mm);
+	mm->map_count++;
 
 	/* add the VMA to the tree */
 	vma_mas_store(vma, mas);
@@ -1240,6 +1240,7 @@ unsigned long do_mmap(struct file *file,
 error_just_free:
 	up_write(&nommu_region_sem);
 error:
+	mas_destroy(&mas);
 	if (region->vm_file)
 		fput(region->vm_file);
 	kmem_cache_free(vm_region_jar, region);
@@ -1250,7 +1251,6 @@ unsigned long do_mmap(struct file *file,
 
 sharing_violation:
 	up_write(&nommu_region_sem);
-	mas_destroy(&mas);
 	pr_warn("Attempt to share mismatched mappings\n");
 	ret = -EINVAL;
 	goto error;
@@ -1347,6 +1347,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vma->vm_file)
 		return -ENOMEM;
 
+	mm = vma->vm_mm;
 	if (mm->map_count >= sysctl_max_map_count)
 		return -ENOMEM;
 
@@ -1398,6 +1399,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	mas_set_range(&mas, vma->vm_start, vma->vm_end - 1);
 	mas_store(&mas, vma);
 	vma_mas_store(new, &mas);
+	mm->map_count++;
 	return 0;
 
 err_mas_preallocate:
@@ -1509,7 +1511,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list
 erase_whole_vma:
 	if (delete_vma_from_mm(vma))
 		ret = -ENOMEM;
-	delete_vma(mm, vma);
+	else
+		delete_vma(mm, vma);
 	return ret;
 }
 

mm/shmem.c

@@ -478,12 +478,10 @@ bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode,
 	if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
 	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
 		return false;
-	if (shmem_huge_force)
-		return true;
-	if (shmem_huge == SHMEM_HUGE_FORCE)
-		return true;
 	if (shmem_huge == SHMEM_HUGE_DENY)
 		return false;
+	if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE)
+		return true;
 
 	switch (SHMEM_SB(inode->i_sb)->huge) {
 	case SHMEM_HUGE_ALWAYS:

tools/testing/selftests/proc/proc-empty-vm.c

@@ -25,6 +25,7 @@
 #undef NDEBUG
 #include <assert.h>
 #include <errno.h>
+#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -41,7 +42,7 @@
  * 1: vsyscall VMA is --xp		vsyscall=xonly
  * 2: vsyscall VMA is r-xp		vsyscall=emulate
  */
-static int g_vsyscall;
+static volatile int g_vsyscall;
 static const char *g_proc_pid_maps_vsyscall;
 static const char *g_proc_pid_smaps_vsyscall;
 
@@ -147,11 +148,12 @@ static void vsyscall(void)
 
 		g_vsyscall = 0;
 		/* gettimeofday(NULL, NULL); */
+		uint64_t rax = 0xffffffffff600000;
 		asm volatile (
-			"call %P0"
-			:
-			: "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
-			: "rax", "rcx", "r11"
+			"call *%[rax]"
+			: [rax] "+a" (rax)
+			: "D" (NULL), "S" (NULL)
+			: "rcx", "r11"
 		);
 
 		g_vsyscall = 1;

tools/testing/selftests/proc/proc-pid-vm.c

@@ -257,11 +257,12 @@ static void vsyscall(void)
 
 		g_vsyscall = 0;
 		/* gettimeofday(NULL, NULL); */
+		uint64_t rax = 0xffffffffff600000;
 		asm volatile (
-			"call %P0"
-			:
-			: "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
-			: "rax", "rcx", "r11"
+			"call *%[rax]"
+			: [rax] "+a" (rax)
+			: "D" (NULL), "S" (NULL)
+			: "rcx", "r11"
 		);
 
 		g_vsyscall = 1;