Merge tag 'mm-hotfixes-stable-2024-10-28-21-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "21 hotfixes. 13 are cc:stable. 13 are MM and 8 are non-MM.

  No particular theme here - mainly singletons, a couple of doubletons.
  Please see the changelogs"

* tag 'mm-hotfixes-stable-2024-10-28-21-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (21 commits)
  mm: avoid unconditional one-tick sleep when swapcache_prepare fails
  mseal: update mseal.rst
  mm: split critical region in remap_file_pages() and invoke LSMs in between
  selftests/mm: fix deadlock for fork after pthread_create with atomic_bool
  Revert "selftests/mm: replace atomic_bool with pthread_barrier_t"
  Revert "selftests/mm: fix deadlock for fork after pthread_create on ARM"
  tools: testing: add expand-only mode VMA test
  mm/vma: add expand-only VMA merge mode and optimise do_brk_flags()
  resource,kexec: walk_system_ram_res_rev must retain resource flags
  nilfs2: fix kernel bug due to missing clearing of checked flag
  mm: numa_clear_kernel_node_hotplug: Add NUMA_NO_NODE check for node id
  ocfs2: pass u64 to ocfs2_truncate_inline maybe overflow
  mm: shmem: fix data-race in shmem_getattr()
  mm: mark mas allocation in vms_abort_munmap_vmas as __GFP_NOFAIL
  x86/traps: move kmsan check after instrumentation_begin
  resource: remove dependency on SPARSEMEM from GET_FREE_REGION
  mm/mmap: fix race in mmap_region() with ftruncate()
  mm/page_alloc: let GFP_ATOMIC order-0 allocs access highatomic reserves
  fork: only invoke khugepaged, ksm hooks if no error
  fork: do not invoke uffd on fork if error occurs
  ...

22 files changed, 386 insertions, 252 deletions

diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst
index 4132eec995a3..41102f74c5e2 100644
--- a/Documentation/userspace-api/mseal.rst
+++ b/Documentation/userspace-api/mseal.rst
@@ -23,177 +23,166 @@ applications can additionally seal security critical data at runtime.
 A similar feature already exists in the XNU kernel with the
 VM_FLAGS_PERMANENT flag [1] and on OpenBSD with the mimmutable syscall [2].
 
-User API
-========
-mseal()
------------
-The mseal() syscall has the following signature:
-
-``int mseal(void addr, size_t len, unsigned long flags)``
-
-**addr/len**: virtual memory address range.
-
-The address range set by ``addr``/``len`` must meet:
-   - The start address must be in an allocated VMA.
-   - The start address must be page aligned.
-   - The end address (``addr`` + ``len``) must be in an allocated VMA.
-   - no gap (unallocated memory) between start and end address.
-
-The ``len`` will be paged aligned implicitly by the kernel.
-
-**flags**: reserved for future use.
-
-**return values**:
-
-- ``0``: Success.
-
-- ``-EINVAL``:
-    - Invalid input ``flags``.
-    - The start address (``addr``) is not page aligned.
-    - Address range (``addr`` + ``len``) overflow.
-
-- ``-ENOMEM``:
-    - The start address (``addr``) is not allocated.
-    - The end address (``addr`` + ``len``) is not allocated.
-    - A gap (unallocated memory) between start and end address.
-
-- ``-EPERM``:
-    - sealing is supported only on 64-bit CPUs, 32-bit is not supported.
-
-- For above error cases, users can expect the given memory range is
-  unmodified, i.e. no partial update.
-
-- There might be other internal errors/cases not listed here, e.g.
-  error during merging/splitting VMAs, or the process reaching the max
-  number of supported VMAs. In those cases, partial updates to the given
-  memory range could happen. However, those cases should be rare.
-
-**Blocked operations after sealing**:
-    Unmapping, moving to another location, and shrinking the size,
-    via munmap() and mremap(), can leave an empty space, therefore
-    can be replaced with a VMA with a new set of attributes.
-
-    Moving or expanding a different VMA into the current location,
-    via mremap().
-
-    Modifying a VMA via mmap(MAP_FIXED).
-
-    Size expansion, via mremap(), does not appear to pose any
-    specific risks to sealed VMAs. It is included anyway because
-    the use case is unclear. In any case, users can rely on
-    merging to expand a sealed VMA.
-
-    mprotect() and pkey_mprotect().
-
-    Some destructive madvice() behaviors (e.g. MADV_DONTNEED)
-    for anonymous memory, when users don't have write permission to the
-    memory. Those behaviors can alter region contents by discarding pages,
-    effectively a memset(0) for anonymous memory.
-
-    Kernel will return -EPERM for blocked operations.
-
-    For blocked operations, one can expect the given address is unmodified,
-    i.e. no partial update. Note, this is different from existing mm
-    system call behaviors, where partial updates are made till an error is
-    found and returned to userspace. To give an example:
-
-    Assume following code sequence:
-
-    - ptr = mmap(null, 8192, PROT_NONE);
-    - munmap(ptr + 4096, 4096);
-    - ret1 = mprotect(ptr, 8192, PROT_READ);
-    - mseal(ptr, 4096);
-    - ret2 = mprotect(ptr, 8192, PROT_NONE);
-
-    ret1 will be -ENOMEM, the page from ptr is updated to PROT_READ.
-
-    ret2 will be -EPERM, the page remains to be PROT_READ.
-
-**Note**:
-
-- mseal() only works on 64-bit CPUs, not 32-bit CPU.
-
-- users can call mseal() multiple times, mseal() on an already sealed memory
-  is a no-action (not error).
-
-- munseal() is not supported.
-
-Use cases:
-==========
+SYSCALL
+=======
+mseal syscall signature
+-----------------------
+   ``int mseal(void \* addr, size_t len, unsigned long flags)``
+
+   **addr**/**len**: virtual memory address range.
+      The address range set by **addr**/**len** must meet:
+         - The start address must be in an allocated VMA.
+         - The start address must be page aligned.
+         - The end address (**addr** + **len**) must be in an allocated VMA.
+         - no gap (unallocated memory) between start and end address.
+
+      The ``len`` will be paged aligned implicitly by the kernel.
+
+   **flags**: reserved for future use.
+
+   **Return values**:
+      - **0**: Success.
+      - **-EINVAL**:
+         * Invalid input ``flags``.
+         * The start address (``addr``) is not page aligned.
+         * Address range (``addr`` + ``len``) overflow.
+      - **-ENOMEM**:
+         * The start address (``addr``) is not allocated.
+         * The end address (``addr`` + ``len``) is not allocated.
+         * A gap (unallocated memory) between start and end address.
+      - **-EPERM**:
+         * sealing is supported only on 64-bit CPUs, 32-bit is not supported.
+
+   **Note about error return**:
+      - For above error cases, users can expect the given memory range is
+        unmodified, i.e. no partial update.
+      - There might be other internal errors/cases not listed here, e.g.
+        error during merging/splitting VMAs, or the process reaching the maximum
+        number of supported VMAs. In those cases, partial updates to the given
+        memory range could happen. However, those cases should be rare.
+
+   **Architecture support**:
+      mseal only works on 64-bit CPUs, not 32-bit CPUs.
+
+   **Idempotent**:
+      users can call mseal multiple times. mseal on an already sealed memory
+      is a no-action (not error).
+
+   **no munseal**
+      Once mapping is sealed, it can't be unsealed. The kernel should never
+      have munseal, this is consistent with other sealing feature, e.g.
+      F_SEAL_SEAL for file.
+
+Blocked mm syscall for sealed mapping
+-------------------------------------
+   It might be important to note: **once the mapping is sealed, it will
+   stay in the process's memory until the process terminates**.
+
+   Example::
+
+         *ptr = mmap(0, 4096, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+         rc = mseal(ptr, 4096, 0);
+         /* munmap will fail */
+         rc = munmap(ptr, 4096);
+         assert(rc < 0);
+
+   Blocked mm syscall:
+      - munmap
+      - mmap
+      - mremap
+      - mprotect and pkey_mprotect
+      - some destructive madvise behaviors: MADV_DONTNEED, MADV_FREE,
+        MADV_DONTNEED_LOCKED, MADV_FREE, MADV_DONTFORK, MADV_WIPEONFORK
+
+   The first set of syscalls to block is munmap, mremap, mmap. They can
+   either leave an empty space in the address space, therefore allowing
+   replacement with a new mapping with new set of attributes, or can
+   overwrite the existing mapping with another mapping.
+
+   mprotect and pkey_mprotect are blocked because they changes the
+   protection bits (RWX) of the mapping.
+
+   Certain destructive madvise behaviors, specifically MADV_DONTNEED,
+   MADV_FREE, MADV_DONTNEED_LOCKED, and MADV_WIPEONFORK, can introduce
+   risks when applied to anonymous memory by threads lacking write
+   permissions. Consequently, these operations are prohibited under such
+   conditions. The aforementioned behaviors have the potential to modify
+   region contents by discarding pages, effectively performing a memset(0)
+   operation on the anonymous memory.
+
+   Kernel will return -EPERM for blocked syscalls.
+
+   When blocked syscall return -EPERM due to sealing, the memory regions may
+   or may not be changed, depends on the syscall being blocked:
+
+      - munmap: munmap is atomic. If one of VMAs in the given range is
+        sealed, none of VMAs are updated.
+      - mprotect, pkey_mprotect, madvise: partial update might happen, e.g.
+        when mprotect over multiple VMAs, mprotect might update the beginning
+        VMAs before reaching the sealed VMA and return -EPERM.
+      - mmap and mremap: undefined behavior.
+
+Use cases
+=========
 - glibc:
   The dynamic linker, during loading ELF executables, can apply sealing to
-  non-writable memory segments.
-
-- Chrome browser: protect some security sensitive data-structures.
+  mapping segments.
 
-Notes on which memory to seal:
-==============================
+- Chrome browser: protect some security sensitive data structures.
 
-It might be important to note that sealing changes the lifetime of a mapping,
-i.e. the sealed mapping won’t be unmapped till the process terminates or the
-exec system call is invoked. Applications can apply sealing to any virtual
-memory region from userspace, but it is crucial to thoroughly analyze the
-mapping's lifetime prior to apply the sealing.
+When not to use mseal
+=====================
+Applications can apply sealing to any virtual memory region from userspace,
+but it is *crucial to thoroughly analyze the mapping's lifetime* prior to
+apply the sealing. This is because the sealed mapping *won’t be unmapped*
+until the process terminates or the exec system call is invoked.
 
 For example:
+   - aio/shm
+     aio/shm can call mmap and  munmap on behalf of userspace, e.g.
+     ksys_shmdt() in shm.c. The lifetimes of those mapping are not tied to
+     the lifetime of the process. If those memories are sealed from userspace,
+     then munmap will fail, causing leaks in VMA address space during the
+     lifetime of the process.
+
+   - ptr allocated by malloc (heap)
+     Don't use mseal on the memory ptr return from malloc().
+     malloc() is implemented by allocator, e.g. by glibc. Heap manager might
+     allocate a ptr from brk or mapping created by mmap.
+     If an app calls mseal on a ptr returned from malloc(), this can affect
+     the heap manager's ability to manage the mappings; the outcome is
+     non-deterministic.
+
+     Example::
+
+        ptr = malloc(size);
+        /* don't call mseal on ptr return from malloc. */
+        mseal(ptr, size);
+        /* free will success, allocator can't shrink heap lower than ptr */
+        free(ptr);
+
+mseal doesn't block
+===================
+In a nutshell, mseal blocks certain mm syscall from modifying some of VMA's
+attributes, such as protection bits (RWX). Sealed mappings doesn't mean the
+memory is immutable.
 
-- aio/shm
-
-  aio/shm can call mmap()/munmap() on behalf of userspace, e.g. ksys_shmdt() in
-  shm.c. The lifetime of those mapping are not tied to the lifetime of the
-  process. If those memories are sealed from userspace, then munmap() will fail,
-  causing leaks in VMA address space during the lifetime of the process.
-
-- Brk (heap)
-
-  Currently, userspace applications can seal parts of the heap by calling
-  malloc() and mseal().
-  let's assume following calls from user space:
-
-  - ptr = malloc(size);
-  - mprotect(ptr, size, RO);
-  - mseal(ptr, size);
-  - free(ptr);
-
-  Technically, before mseal() is added, the user can change the protection of
-  the heap by calling mprotect(RO). As long as the user changes the protection
-  back to RW before free(), the memory range can be reused.
-
-  Adding mseal() into the picture, however, the heap is then sealed partially,
-  the user can still free it, but the memory remains to be RO. If the address
-  is re-used by the heap manager for another malloc, the process might crash
-  soon after. Therefore, it is important not to apply sealing to any memory
-  that might get recycled.
-
-  Furthermore, even if the application never calls the free() for the ptr,
-  the heap manager may invoke the brk system call to shrink the size of the
-  heap. In the kernel, the brk-shrink will call munmap(). Consequently,
-  depending on the location of the ptr, the outcome of brk-shrink is
-  nondeterministic.
-
-
-Additional notes:
-=================
 As Jann Horn pointed out in [3], there are still a few ways to write
-to RO memory, which is, in a way, by design. Those cases are not covered
-by mseal(). If applications want to block such cases, sandbox tools (such as
-seccomp, LSM, etc) might be considered.
+to RO memory, which is, in a way, by design. And those could be blocked
+by different security measures.
 
 Those cases are:
 
-- Write to read-only memory through /proc/self/mem interface.
-- Write to read-only memory through ptrace (such as PTRACE_POKETEXT).
-- userfaultfd.
+   - Write to read-only memory through /proc/self/mem interface (FOLL_FORCE).
+   - Write to read-only memory through ptrace (such as PTRACE_POKETEXT).
+   - userfaultfd.
 
 The idea that inspired this patch comes from Stephen Röttger’s work in V8
 CFI [4]. Chrome browser in ChromeOS will be the first user of this API.
 
-Reference:
-==========
-[1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274
-
-[2] https://man.openbsd.org/mimmutable.2
-
-[3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com
-
-[4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc
+Reference
+=========
+- [1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274
+- [2] https://man.openbsd.org/mimmutable.2
+- [3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com
+- [4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d05392db5d0f..2dbadf347b5f 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -261,12 +261,6 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	int ud_type;
 	u32 imm;
 
-	/*
-	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
-	 * is a rare case that uses @regs without passing them to
-	 * irqentry_enter().
-	 */
-	kmsan_unpoison_entry_regs(regs);
 	ud_type = decode_bug(regs->ip, &imm);
 	if (ud_type == BUG_NONE)
 		return handled;
@@ -276,6 +270,12 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 */
 	instrumentation_begin();
 	/*
+	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
+	 * is a rare case that uses @regs without passing them to
+	 * irqentry_enter().
+	 */
+	kmsan_unpoison_entry_regs(regs);
+	/*
 	 * Since we're emulating a CALL with exceptions, restore the interrupt
 	 * state to what it was at the exception site.
 	 */
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 5436eb0424bd..10def4b55995 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -401,6 +401,7 @@ void nilfs_clear_folio_dirty(struct folio *folio)
 
 	folio_clear_uptodate(folio);
 	folio_clear_mappedtodisk(folio);
+	folio_clear_checked(folio);
 
 	head = folio_buffers(folio);
 	if (head) {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 58887456e3c5..06af21982c16 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1787,6 +1787,14 @@ int ocfs2_remove_inode_range(struct inode *inode,
 		return 0;
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		int id_count = ocfs2_max_inline_data_with_xattr(inode->i_sb, di);
+
+		if (byte_start > id_count || byte_start + byte_len > id_count) {
+			ret = -EINVAL;
+			mlog_errno(ret);
+			goto out;
+		}
+
 		ret = ocfs2_truncate_inline(inode, di_bh, byte_start,
 					    byte_start + byte_len, 0);
 		if (ret) {
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 68cdd89c97a3..7c0bd0b55f88 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -692,6 +692,34 @@ void dup_userfaultfd_complete(struct list_head *fcs)
 	}
 }
 
+void dup_userfaultfd_fail(struct list_head *fcs)
+{
+	struct userfaultfd_fork_ctx *fctx, *n;
+
+	/*
+	 * An error has occurred on fork, we will tear memory down, but have
+	 * allocated memory for fctx's and raised reference counts for both the
+	 * original and child contexts (and on the mm for each as a result).
+	 *
+	 * These would ordinarily be taken care of by a user handling the event,
+	 * but we are no longer doing so, so manually clean up here.
+	 *
+	 * mm tear down will take care of cleaning up VMA contexts.
+	 */
+	list_for_each_entry_safe(fctx, n, fcs, list) {
+		struct userfaultfd_ctx *octx = fctx->orig;
+		struct userfaultfd_ctx *ctx = fctx->new;
+
+		atomic_dec(&octx->mmap_changing);
+		VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0);
+		userfaultfd_ctx_put(octx);
+		userfaultfd_ctx_put(ctx);
+
+		list_del(&fctx->list);
+		kfree(fctx);
+	}
+}
+
 void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 			     struct vm_userfaultfd_ctx *vm_ctx)
 {
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 11690dacd986..ec9c05044d4f 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm)
 	return atomic_long_read(&mm->ksm_zero_pages);
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
+	/* Adding mm to ksm is best effort on fork. */
 	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
-		return __ksm_enter(mm);
-
-	return 0;
+		__ksm_enter(mm);
 }
 
 static inline int ksm_execve(struct mm_struct *mm)
@@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm)
 	return 0;
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	return 0;
 }
 
 static inline int ksm_execve(struct mm_struct *mm)
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 9fc6ce15c499..cb40f1a1d081 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 
 extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
 extern void dup_userfaultfd_complete(struct list_head *);
+void dup_userfaultfd_fail(struct list_head *);
 
 extern void mremap_userfaultfd_prep(struct vm_area_struct *,
 				    struct vm_userfaultfd_ctx *);
@@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l)
 {
 }
 
+static inline void dup_userfaultfd_fail(struct list_head *l)
+{
+}
+
 static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 					   struct vm_userfaultfd_ctx *ctx)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 89ceb4a68af2..3bf38d260cb3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -653,11 +653,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	mm->exec_vm = oldmm->exec_vm;
 	mm->stack_vm = oldmm->stack_vm;
 
-	retval = ksm_fork(mm, oldmm);
-	if (retval)
-		goto out;
-	khugepaged_fork(mm, oldmm);
-
 	/* Use __mt_dup() to efficiently build an identical maple tree. */
 	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
 	if (unlikely(retval))
@@ -760,6 +755,8 @@ loop_out:
 	vma_iter_free(&vmi);
 	if (!retval) {
 		mt_set_in_rcu(vmi.mas.tree);
+		ksm_fork(mm, oldmm);
+		khugepaged_fork(mm, oldmm);
 	} else if (mpnt) {
 		/*
 		 * The entire maple tree has already been duplicated. If the
@@ -775,7 +772,10 @@ out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
 	mmap_write_unlock(oldmm);
-	dup_userfaultfd_complete(&uf);
+	if (!retval)
+		dup_userfaultfd_complete(&uf);
+	else
+		dup_userfaultfd_fail(&uf);
 fail_uprobe_end:
 	uprobe_end_dup_mmap();
 	return retval;
diff --git a/kernel/resource.c b/kernel/resource.c
index b730bd28b422..4101016e8b20 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -459,9 +459,7 @@ int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
 			rams_size += 16;
 		}
 
-		rams[i].start = res.start;
-		rams[i++].end = res.end;
-
+		rams[i++] = res;
 		start = res.end + 1;
 	}
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 4c9f5ea13271..33fa51d608dc 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1085,7 +1085,6 @@ config HMM_MIRROR
 	depends on MMU
 
 config GET_FREE_REGION
-	depends on SPARSEMEM
 	bool
 
 config DEVICE_PRIVATE
diff --git a/mm/memory.c b/mm/memory.c
index 3ccee51adfbb..bdf77a3ec47b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4187,6 +4187,8 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq);
+
 /*
  * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
@@ -4199,6 +4201,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct folio *swapcache, *folio = NULL;
+	DECLARE_WAITQUEUE(wait, current);
 	struct page *page;
 	struct swap_info_struct *si = NULL;
 	rmap_t rmap_flags = RMAP_NONE;
@@ -4297,7 +4300,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 					 * Relax a bit to prevent rapid
 					 * repeated page faults.
 					 */
+					add_wait_queue(&swapcache_wq, &wait);
 					schedule_timeout_uninterruptible(1);
+					remove_wait_queue(&swapcache_wq, &wait);
 					goto out_page;
 				}
 				need_clear_cache = true;
@@ -4604,8 +4609,11 @@ unlock:
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
 	/* Clear the swap cache pin for direct swapin after PTL unlock */
-	if (need_clear_cache)
+	if (need_clear_cache) {
 		swapcache_clear(si, entry, nr_pages);
+		if (waitqueue_active(&swapcache_wq))
+			wake_up(&swapcache_wq);
+	}
 	if (si)
 		put_swap_device(si);
 	return ret;
@@ -4620,8 +4628,11 @@ out_release:
 		folio_unlock(swapcache);
 		folio_put(swapcache);
 	}
-	if (need_clear_cache)
+	if (need_clear_cache) {
 		swapcache_clear(si, entry, nr_pages);
+		if (waitqueue_active(&swapcache_wq))
+			wake_up(&swapcache_wq);
+	}
 	if (si)
 		put_swap_device(si);
 	return ret;
diff --git a/mm/mmap.c b/mm/mmap.c
index 9c0fb43064b5..1e0e34cb993f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1418,6 +1418,13 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		vmg.flags = vm_flags;
 	}
 
+	/*
+	 * clear PTEs while the vma is still in the tree so that rmap
+	 * cannot race with the freeing later in the truncate scenario.
+	 * This is also needed for call_mmap(), which is why vm_ops
+	 * close function is called.
+	 */
+	vms_clean_up_area(&vms, &mas_detach);
 	vma = vma_merge_new_range(&vmg);
 	if (vma)
 		goto expanded;
@@ -1439,11 +1446,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 
 	if (file) {
 		vma->vm_file = get_file(file);
-		/*
-		 * call_mmap() may map PTE, so ensure there are no existing PTEs
-		 * and call the vm_ops close function if one exists.
-		 */
-		vms_clean_up_area(&vms, &mas_detach);
 		error = call_mmap(file, vma);
 		if (error)
 			goto unmap_and_free_vma;
@@ -1640,6 +1642,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	unsigned long populate = 0;
 	unsigned long ret = -EINVAL;
 	struct file *file;
+	vm_flags_t vm_flags;
 
 	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
 		     current->comm, current->pid);
@@ -1656,12 +1659,60 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
 		return ret;
 
-	if (mmap_write_lock_killable(mm))
+	if (mmap_read_lock_killable(mm))
+		return -EINTR;
+
+	/*
+	 * Look up VMA under read lock first so we can perform the security
+	 * without holding locks (which can be problematic). We reacquire a
+	 * write lock later and check nothing changed underneath us.
+	 */
+	vma = vma_lookup(mm, start);
+
+	if (!vma || !(vma->vm_flags & VM_SHARED)) {
+		mmap_read_unlock(mm);
+		return -EINVAL;
+	}
+
+	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
+	prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
+	prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
+
+	flags &= MAP_NONBLOCK;
+	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
+	if (vma->vm_flags & VM_LOCKED)
+		flags |= MAP_LOCKED;
+
+	/* Save vm_flags used to calculate prot and flags, and recheck later. */
+	vm_flags = vma->vm_flags;
+	file = get_file(vma->vm_file);
+
+	mmap_read_unlock(mm);
+
+	/* Call outside mmap_lock to be consistent with other callers. */
+	ret = security_mmap_file(file, prot, flags);
+	if (ret) {
+		fput(file);
+		return ret;
+	}
+
+	ret = -EINVAL;
+
+	/* OK security check passed, take write lock + let it rip. */
+	if (mmap_write_lock_killable(mm)) {
+		fput(file);
 		return -EINTR;
+	}
 
 	vma = vma_lookup(mm, start);
 
-	if (!vma || !(vma->vm_flags & VM_SHARED))
+	if (!vma)
+		goto out;
+
+	/* Make sure things didn't change under us. */
+	if (vma->vm_flags != vm_flags)
+		goto out;
+	if (vma->vm_file != file)
 		goto out;
 
 	if (start + size > vma->vm_end) {
@@ -1689,25 +1740,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 			goto out;
 	}
 
-	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
-	prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
-	prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
-
-	flags &= MAP_NONBLOCK;
-	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
-	if (vma->vm_flags & VM_LOCKED)
-		flags |= MAP_LOCKED;
-
-	file = get_file(vma->vm_file);
-	ret = security_mmap_file(vma->vm_file, prot, flags);
-	if (ret)
-		goto out_fput;
 	ret = do_mmap(vma->vm_file, start, size,
 			prot, flags, 0, pgoff, &populate, NULL);
-out_fput:
-	fput(file);
 out:
 	mmap_write_unlock(mm);
+	fput(file);
 	if (populate)
 		mm_populate(ret, populate);
 	if (!IS_ERR_VALUE(ret))
@@ -1754,7 +1791,8 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr));
 
 		vmg.prev = vma;
-		vma_iter_next_range(vmi);
+		/* vmi is positioned at prev, which this mode expects. */
+		vmg.merge_flags = VMG_FLAG_JUST_EXPAND;
 
 		if (vma_merge_new_range(&vmg))
 			goto out;
diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c
index be52b93a9c58..a3877e9bc878 100644
--- a/mm/numa_memblks.c
+++ b/mm/numa_memblks.c
@@ -349,7 +349,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 	for_each_reserved_mem_region(mb_region) {
 		int nid = memblock_get_region_node(mb_region);
 
-		if (nid != MAX_NUMNODES)
+		if (numa_valid_node(nid))
 			node_set(nid, reserved_nodemask);
 	}
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8afab64814dc..94a2ffe28008 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2893,12 +2893,12 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
 			page = __rmqueue(zone, order, migratetype, alloc_flags);
 
 			/*
-			 * If the allocation fails, allow OOM handling access
-			 * to HIGHATOMIC reserves as failing now is worse than
-			 * failing a high-order atomic allocation in the
-			 * future.
+			 * If the allocation fails, allow OOM handling and
+			 * order-0 (atomic) allocs access to HIGHATOMIC
+			 * reserves as failing now is worse than failing a
+			 * high-order atomic allocation in the future.
 			 */
-			if (!page && (alloc_flags & ALLOC_OOM))
+			if (!page && (alloc_flags & (ALLOC_OOM|ALLOC_NON_BLOCK)))
 				page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
 
 			if (!page) {
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 461ea3bbd8d9..5f9f01532e67 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -744,7 +744,8 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 	pud = pudp_get(pudp);
 	if (pud_none(pud))
 		goto not_found;
-	if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pud_leaf(pud)) {
+	if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) &&
+	    (!pud_present(pud) || pud_leaf(pud))) {
 		ptl = pud_lock(vma->vm_mm, pudp);
 		pud = pudp_get(pudp);
 
@@ -753,6 +754,10 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 		fw->pudp = pudp;
 		fw->pud = pud;
 
+		/*
+		 * TODO: FW_MIGRATION support for PUD migration entries
+		 * once there are relevant users.
+		 */
 		if (!pud_present(pud) || pud_devmap(pud) || pud_special(pud)) {
 			spin_unlock(ptl);
 			goto not_found;
@@ -769,12 +774,13 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 	}
 
 pmd_table:
-	VM_WARN_ON_ONCE(pud_leaf(*pudp));
+	VM_WARN_ON_ONCE(!pud_present(pud) || pud_leaf(pud));
 	pmdp = pmd_offset(pudp, addr);
 	pmd = pmdp_get_lockless(pmdp);
 	if (pmd_none(pmd))
 		goto not_found;
-	if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pmd_leaf(pmd)) {
+	if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) &&
+	    (!pmd_present(pmd) || pmd_leaf(pmd))) {
 		ptl = pmd_lock(vma->vm_mm, pmdp);
 		pmd = pmdp_get(pmdp);
 
@@ -786,7 +792,7 @@ pmd_table:
 		if (pmd_none(pmd)) {
 			spin_unlock(ptl);
 			goto not_found;
-		} else if (!pmd_leaf(pmd)) {
+		} else if (pmd_present(pmd) && !pmd_leaf(pmd)) {
 			spin_unlock(ptl);
 			goto pte_table;
 		} else if (pmd_present(pmd)) {
@@ -812,7 +818,7 @@ pmd_table:
 	}
 
 pte_table:
-	VM_WARN_ON_ONCE(pmd_leaf(pmdp_get_lockless(pmdp)));
+	VM_WARN_ON_ONCE(!pmd_present(pmd) || pmd_leaf(pmd));
 	ptep = pte_offset_map_lock(vma->vm_mm, pmdp, addr, &ptl);
 	if (!ptep)
 		goto not_found;
diff --git a/mm/shmem.c b/mm/shmem.c
index c5adb987b23c..4ba1d00fabda 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1166,7 +1166,9 @@ static int shmem_getattr(struct mnt_idmap *idmap,
 	stat->attributes_mask |= (STATX_ATTR_APPEND |
 			STATX_ATTR_IMMUTABLE |
 			STATX_ATTR_NODUMP);
+	inode_lock_shared(inode);
 	generic_fillattr(idmap, request_mask, inode, stat);
+	inode_unlock_shared(inode);
 
 	if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0))
 		stat->blksize = HPAGE_PMD_SIZE;
diff --git a/mm/vma.c b/mm/vma.c
index 4737afcb064c..b21ffec33f8e 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -917,6 +917,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
 	pgoff_t pgoff = vmg->pgoff;
 	pgoff_t pglen = PHYS_PFN(end - start);
 	bool can_merge_left, can_merge_right;
+	bool just_expand = vmg->merge_flags & VMG_FLAG_JUST_EXPAND;
 
 	mmap_assert_write_locked(vmg->mm);
 	VM_WARN_ON(vmg->vma);
@@ -930,7 +931,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
 		return NULL;
 
 	can_merge_left = can_vma_merge_left(vmg);
-	can_merge_right = can_vma_merge_right(vmg, can_merge_left);
+	can_merge_right = !just_expand && can_vma_merge_right(vmg, can_merge_left);
 
 	/* If we can merge with the next VMA, adjust vmg accordingly. */
 	if (can_merge_right) {
@@ -953,7 +954,11 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
 		if (can_merge_right && !can_merge_remove_vma(next))
 			vmg->end = end;
 
-		vma_prev(vmg->vmi); /* Equivalent to going to the previous range */
+		/* In expand-only case we are already positioned at prev. */
+		if (!just_expand) {
+			/* Equivalent to going to the previous range. */
+			vma_prev(vmg->vmi);
+		}
 	}
 
 	/*
@@ -967,12 +972,14 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
 	}
 
 	/* If expansion failed, reset state. Allows us to retry merge later. */
-	vmg->vma = NULL;
-	vmg->start = start;
-	vmg->end = end;
-	vmg->pgoff = pgoff;
-	if (vmg->vma == prev)
-		vma_iter_set(vmg->vmi, start);
+	if (!just_expand) {
+		vmg->vma = NULL;
+		vmg->start = start;
+		vmg->end = end;
+		vmg->pgoff = pgoff;
+		if (vmg->vma == prev)
+			vma_iter_set(vmg->vmi, start);
+	}
 
 	return NULL;
 }
diff --git a/mm/vma.h b/mm/vma.h
index 819f994cf727..55457cb68200 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -59,6 +59,17 @@ enum vma_merge_state {
 	VMA_MERGE_SUCCESS,
 };
 
+enum vma_merge_flags {
+	VMG_FLAG_DEFAULT = 0,
+	/*
+	 * If we can expand, simply do so. We know there is nothing to merge to
+	 * the right. Does not reset state upon failure to merge. The VMA
+	 * iterator is assumed to be positioned at the previous VMA, rather than
+	 * at the gap.
+	 */
+	VMG_FLAG_JUST_EXPAND = 1 << 0,
+};
+
 /* Represents a VMA merge operation. */
 struct vma_merge_struct {
 	struct mm_struct *mm;
@@ -75,6 +86,7 @@ struct vma_merge_struct {
 	struct mempolicy *policy;
 	struct vm_userfaultfd_ctx uffd_ctx;
 	struct anon_vma_name *anon_name;
+	enum vma_merge_flags merge_flags;
 	enum vma_merge_state state;
 };
 
@@ -99,6 +111,7 @@ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma,
 		.flags = flags_,					\
 		.pgoff = pgoff_,					\
 		.state = VMA_MERGE_START,				\
+		.merge_flags = VMG_FLAG_DEFAULT,			\
 	}
 
 #define VMG_VMA_STATE(name, vmi_, prev_, vma_, start_, end_)	\
@@ -118,6 +131,7 @@ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma,
 		.uffd_ctx = vma_->vm_userfaultfd_ctx,		\
 		.anon_name = anon_vma_name(vma_),		\
 		.state = VMA_MERGE_START,			\
+		.merge_flags = VMG_FLAG_DEFAULT,		\
 	}
 
 #ifdef CONFIG_DEBUG_VM_MAPLE_TREE
@@ -241,15 +255,9 @@ static inline void vms_abort_munmap_vmas(struct vma_munmap_struct *vms,
 	 * failure method of leaving a gap where the MAP_FIXED mapping failed.
 	 */
 	mas_set_range(mas, vms->start, vms->end - 1);
-	if (unlikely(mas_store_gfp(mas, NULL, GFP_KERNEL))) {
-		pr_warn_once("%s: (%d) Unable to abort munmap() operation\n",
-			     current->comm, current->pid);
-		/* Leaving vmas detached and in-tree may hamper recovery */
-		reattach_vmas(mas_detach);
-	} else {
-		/* Clean up the insertion of the unfortunate gap */
-		vms_complete_munmap_vmas(vms, mas_detach);
-	}
+	mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL);
+	/* Clean up the insertion of the unfortunate gap */
+	vms_complete_munmap_vmas(vms, mas_detach);
 }
 
 int
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index 852e7281026e..717539eddf98 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -18,7 +18,7 @@ bool test_uffdio_wp = true;
 unsigned long long *count_verify;
 uffd_test_ops_t *uffd_test_ops;
 uffd_test_case_ops_t *uffd_test_case_ops;
-pthread_barrier_t ready_for_fork;
+atomic_bool ready_for_fork;
 
 static int uffd_mem_fd_create(off_t mem_size, bool hugetlb)
 {
@@ -519,8 +519,7 @@ void *uffd_poll_thread(void *arg)
 	pollfd[1].fd = pipefd[cpu*2];
 	pollfd[1].events = POLLIN;
 
-	/* Ready for parent thread to fork */
-	pthread_barrier_wait(&ready_for_fork);
+	ready_for_fork = true;
 
 	for (;;) {
 		ret = poll(pollfd, 2, -1);
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
index 3e6228d8e0dc..a70ae10b5f62 100644
--- a/tools/testing/selftests/mm/uffd-common.h
+++ b/tools/testing/selftests/mm/uffd-common.h
@@ -33,6 +33,7 @@
 #include <inttypes.h>
 #include <stdint.h>
 #include <sys/random.h>
+#include <stdatomic.h>
 
 #include "../kselftest.h"
 #include "vm_util.h"
@@ -104,7 +105,7 @@ extern bool map_shared;
 extern bool test_uffdio_wp;
 extern unsigned long long *count_verify;
 extern volatile bool test_uffdio_copy_eexist;
-extern pthread_barrier_t ready_for_fork;
+extern atomic_bool ready_for_fork;
 
 extern uffd_test_ops_t anon_uffd_test_ops;
 extern uffd_test_ops_t shmem_uffd_test_ops;
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index c8a3b1c7edff..a2e71b1636e7 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -241,8 +241,7 @@ static void *fork_event_consumer(void *data)
 	fork_event_args *args = data;
 	struct uffd_msg msg = { 0 };
 
-	/* Ready for parent thread to fork */
-	pthread_barrier_wait(&ready_for_fork);
+	ready_for_fork = true;
 
 	/* Read until a full msg received */
 	while (uffd_read_msg(args->parent_uffd, &msg));
@@ -311,12 +310,11 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin)
 
 	/* Prepare a thread to resolve EVENT_FORK */
 	if (with_event) {
-		pthread_barrier_init(&ready_for_fork, NULL, 2);
+		ready_for_fork = false;
 		if (pthread_create(&thread, NULL, fork_event_consumer, &args))
 			err("pthread_create()");
-		/* Wait for child thread to start before forking */
-		pthread_barrier_wait(&ready_for_fork);
-		pthread_barrier_destroy(&ready_for_fork);
+		while (!ready_for_fork)
+			; /* Wait for the poll_thread to start executing before forking */
 	}
 
 	child = fork();
@@ -781,7 +779,7 @@ static void uffd_sigbus_test_common(bool wp)
 	char c;
 	struct uffd_args args = { 0 };
 
-	pthread_barrier_init(&ready_for_fork, NULL, 2);
+	ready_for_fork = false;
 
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 
@@ -798,9 +796,8 @@ static void uffd_sigbus_test_common(bool wp)
 	if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
 		err("uffd_poll_thread create");
 
-	/* Wait for child thread to start before forking */
-	pthread_barrier_wait(&ready_for_fork);
-	pthread_barrier_destroy(&ready_for_fork);
+	while (!ready_for_fork)
+		; /* Wait for the poll_thread to start executing before forking */
 
 	pid = fork();
 	if (pid < 0)
@@ -841,7 +838,7 @@ static void uffd_events_test_common(bool wp)
 	char c;
 	struct uffd_args args = { 0 };
 
-	pthread_barrier_init(&ready_for_fork, NULL, 2);
+	ready_for_fork = false;
 
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 	if (uffd_register(uffd, area_dst, nr_pages * page_size,
@@ -852,9 +849,8 @@ static void uffd_events_test_common(bool wp)
 	if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
 		err("uffd_poll_thread create");
 
-	/* Wait for child thread to start before forking */
-	pthread_barrier_wait(&ready_for_fork);
-	pthread_barrier_destroy(&ready_for_fork);
+	while (!ready_for_fork)
+		; /* Wait for the poll_thread to start executing before forking */
 
 	pid = fork();
 	if (pid < 0)
diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c
index c53f220eb6cc..b33b47342d41 100644
--- a/tools/testing/vma/vma.c
+++ b/tools/testing/vma/vma.c
@@ -1522,6 +1522,45 @@ static bool test_copy_vma(void)
 	return true;
 }
 
+static bool test_expand_only_mode(void)
+{
+	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	struct mm_struct mm = {};
+	VMA_ITERATOR(vmi, &mm, 0);
+	struct vm_area_struct *vma_prev, *vma;
+	VMG_STATE(vmg, &mm, &vmi, 0x5000, 0x9000, flags, 5);
+
+	/*
+	 * Place a VMA prior to the one we're expanding so we assert that we do
+	 * not erroneously try to traverse to the previous VMA even though we
+	 * have, through the use of VMG_FLAG_JUST_EXPAND, indicated we do not
+	 * need to do so.
+	 */
+	alloc_and_link_vma(&mm, 0, 0x2000, 0, flags);
+
+	/*
+	 * We will be positioned at the prev VMA, but looking to expand to
+	 * 0x9000.
+	 */
+	vma_iter_set(&vmi, 0x3000);
+	vma_prev = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
+	vmg.prev = vma_prev;
+	vmg.merge_flags = VMG_FLAG_JUST_EXPAND;
+
+	vma = vma_merge_new_range(&vmg);
+	ASSERT_NE(vma, NULL);
+	ASSERT_EQ(vma, vma_prev);
+	ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
+	ASSERT_EQ(vma->vm_start, 0x3000);
+	ASSERT_EQ(vma->vm_end, 0x9000);
+	ASSERT_EQ(vma->vm_pgoff, 3);
+	ASSERT_TRUE(vma_write_started(vma));
+	ASSERT_EQ(vma_iter_addr(&vmi), 0x3000);
+
+	cleanup_mm(&mm, &vmi);
+	return true;
+}
+
 int main(void)
 {
 	int num_tests = 0, num_fail = 0;
@@ -1553,6 +1592,7 @@ int main(void)
 	TEST(vmi_prealloc_fail);
 	TEST(merge_extend);
 	TEST(copy_vma);
+	TEST(expand_only_mode);
 
 #undef TEST