Skip to contentSkip to conversation

mm-lock-vma-explicitly-before-doing-vm_flags_reset-and-vm_flags_reset_once.patch removed from -mm tree

merged mm-stable Andrew Morton 1 participant 1 message Aug 21, 2023

lore
Share & tools
lore

Andrew Morton

author tree notice Applied
#0 lore raw

The quilt patch titled
Subject: mm: lock vma explicitly before doing vm_flags_reset and vm_flags_reset_once
has been removed from the -mm tree. Its filename was
mm-lock-vma-explicitly-before-doing-vm_flags_reset-and-vm_flags_reset_once.patch

This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

------------------------------------------------------
From: Suren Baghdasaryan <[email protected]>
Subject: mm: lock vma explicitly before doing vm_flags_reset and vm_flags_reset_once
Date: Fri, 4 Aug 2023 08:27:22 -0700

Implicit vma locking inside vm_flags_reset() and vm_flags_reset_once() is not obvious and makes it hard to understand where vma locking is happening. Also in some cases (like in dup_userfaultfd()) vma should be locked earlier than vma_flags modification. To make locking more visible, change these functions to assert that the vma write lock is taken and explicitly lock the vma beforehand. Fix userfaultfd functions which should lock the vma earlier.

---

 arch/powerpc/kvm/book3s_hv_uvmem.c |    1 +
 fs/userfaultfd.c                   |    6 ++++++
 include/linux/mm.h                 |   10 +++++++---
 mm/madvise.c                       |    5 ++---
 mm/mlock.c                         |    3 ++-
 mm/mprotect.c                      |    1 +
 6 files changed, 19 insertions(+), 7 deletions(-)
arch/powerpc/kvm/book3s_hv_uvmem.c renamed from arch/powerpc/kvm/book3s_hv_uvmem.c~mm-lock-vma-explicitly-before-doing-vm_flags_reset-and-vm_flags_reset_once +1 -0
@@ -410,6 +410,7 @@ static int kvmppc_memslot_page_merge(str
 			ret = H_STATE;
 			break;
 		}
+		vma_start_write(vma);
 		/* Copy vm_flags to avoid partial modifications in ksm_madvise */
 		vm_flags = vma->vm_flags;
 		ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
fs/userfaultfd.c renamed from fs/userfaultfd.c~mm-lock-vma-explicitly-before-doing-vm_flags_reset-and-vm_flags_reset_once +6 -0
@@ -667,6 +667,7 @@ static void userfaultfd_event_wait_compl
 		mmap_write_lock(mm);
 		for_each_vma(vmi, vma) {
 			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
+				vma_start_write(vma);
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 				userfaultfd_set_vm_flags(vma,
 							 vma->vm_flags & ~__VM_UFFD_FLAGS);
@@ -702,6 +703,7 @@ int dup_userfaultfd(struct vm_area_struc
 
 	octx = vma->vm_userfaultfd_ctx.ctx;
 	if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
+		vma_start_write(vma);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 		userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
 		return 0;
@@ -783,6 +785,7 @@ void mremap_userfaultfd_prep(struct vm_a
 		atomic_inc(&ctx->mmap_changing);
 	} else {
 		/* Drop uffd context if remap feature not enabled */
+		vma_start_write(vma);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 		userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
 	}
@@ -940,6 +943,7 @@ static int userfaultfd_release(struct in
 			prev = vma;
 		}
 
+		vma_start_write(vma);
 		userfaultfd_set_vm_flags(vma, new_flags);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
@@ -1511,6 +1515,7 @@ static int userfaultfd_register(struct u
 		 * the next vma was merged into the current one and
 		 * the current one has not been updated yet.
 		 */
+		vma_start_write(vma);
 		userfaultfd_set_vm_flags(vma, new_flags);
 		vma->vm_userfaultfd_ctx.ctx = ctx;
 
@@ -1694,6 +1699,7 @@ static int userfaultfd_unregister(struct
 		 * the next vma was merged into the current one and
 		 * the current one has not been updated yet.
 		 */
+		vma_start_write(vma);
 		userfaultfd_set_vm_flags(vma, new_flags);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 
include/linux/mm.h renamed from include/linux/mm.h~mm-lock-vma-explicitly-before-doing-vm_flags_reset-and-vm_flags_reset_once +7 -3
@@ -774,18 +774,22 @@ static inline void vm_flags_init(struct
 	ACCESS_PRIVATE(vma, __vm_flags) = flags;
 }
 
-/* Use when VMA is part of the VMA tree and modifications need coordination */
+/*
+ * Use when VMA is part of the VMA tree and modifications need coordination
+ * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and
+ * it should be locked explicitly beforehand.
+ */
 static inline void vm_flags_reset(struct vm_area_struct *vma,
 				  vm_flags_t flags)
 {
-	vma_start_write(vma);
+	vma_assert_write_locked(vma);
 	vm_flags_init(vma, flags);
 }
 
 static inline void vm_flags_reset_once(struct vm_area_struct *vma,
 				       vm_flags_t flags)
 {
-	vma_start_write(vma);
+	vma_assert_write_locked(vma);
 	WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags);
 }
 
mm/madvise.c renamed from mm/madvise.c~mm-lock-vma-explicitly-before-doing-vm_flags_reset-and-vm_flags_reset_once +2 -3
@@ -173,9 +173,8 @@ static int madvise_update_vma(struct vm_
 	}
 
 success:
-	/*
-	 * vm_flags is protected by the mmap_lock held in write mode.
-	 */
+	/* vm_flags is protected by the mmap_lock held in write mode. */
+	vma_start_write(vma);
 	vm_flags_reset(vma, new_flags);
 	if (!vma->vm_file || vma_is_anon_shmem(vma)) {
 		error = replace_anon_vma_name(vma, anon_name);
mm/mlock.c renamed from mm/mlock.c~mm-lock-vma-explicitly-before-doing-vm_flags_reset-and-vm_flags_reset_once +2 -1
@@ -386,6 +386,7 @@ static void mlock_vma_pages_range(struct
 	 */
 	if (newflags & VM_LOCKED)
 		newflags |= VM_IO;
+	vma_start_write(vma);
 	vm_flags_reset_once(vma, newflags);
 
 	lru_add_drain();
@@ -460,9 +461,9 @@ success:
 	 * It's okay if try_to_unmap_one unmaps a page just after we
 	 * set VM_LOCKED, populate_vma_page_range will bring it back.
 	 */
-
 	if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) {
 		/* No work to do, and mlocking twice would be wrong */
+		vma_start_write(vma);
 		vm_flags_reset(vma, newflags);
 	} else {
 		mlock_vma_pages_range(vma, start, end, newflags);
mm/mprotect.c renamed from mm/mprotect.c~mm-lock-vma-explicitly-before-doing-vm_flags_reset-and-vm_flags_reset_once +1 -0
@@ -656,6 +656,7 @@ success:
 	 * vm_flags and vm_page_prot are protected by the mmap_lock
 	 * held in write mode.
 	 */
+	vma_start_write(vma);
 	vm_flags_reset(vma, newflags);
 	if (vma_wants_manual_pte_write_upgrade(vma))
 		mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE;

_

Patches currently in -mm which might be from [email protected] are

swap-remove-remnants-of-polling-from-read_swap_cache_async.patch mm-add-missing-vm_fault_result_trace-name-for-vm_fault_completed.patch mm-drop-per-vma-lock-when-returning-vm_fault_retry-or-vm_fault_completed.patch mm-change-folio_lock_or_retry-to-use-vm_fault-directly.patch mm-handle-swap-page-faults-under-per-vma-lock.patch mm-handle-userfaults-under-vma-lock.patch mm-handle-userfaults-under-vma-lock-fix.patch