Merge tag 'mm-hotfixes-stable-2022-10-20' of git://git.kernel.org/pub…

…/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morron:
 "Seventeen hotfixes, mainly for MM.

  Five are cc:stable and the remainder address post-6.0 issues"

* tag 'mm-hotfixes-stable-2022-10-20' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  nouveau: fix migrate_to_ram() for faulting page
  mm/huge_memory: do not clobber swp_entry_t during THP split
  hugetlb: fix memory leak associated with vma_lock structure
  mm/page_alloc: reduce potential fragmentation in make_alloc_exact()
  mm: /proc/pid/smaps_rollup: fix maple tree search
  mm,hugetlb: take hugetlb_lock before decrementing h->resv_huge_pages
  mm/mmap: fix MAP_FIXED address return on VMA merge
  mm/mmap.c: __vma_adjust(): suppress uninitialized var warning
  mm/mmap: undo ->mmap() when mas_preallocate() fails
  init: Kconfig: fix spelling mistake "satify" -> "satisfy"
  ocfs2: clear dinode links count in case of error
  ocfs2: fix BUG when iput after ocfs2_mknod fails
  gcov: support GCC 12.1 and newer compilers
  zsmalloc: zs_destroy_pool: add size_class NULL check
  mm/mempolicy: fix mbind_range() arguments to vma_merge()
  mailmap: update email for Qais Yousef
  mailmap: update Dan Carpenter's email address

.mailmap

@@ -104,6 +104,7 @@ Christoph Hellwig <[email protected]>
 Colin Ian King <[email protected]> <[email protected]>
 Corey Minyard <[email protected]>
 Damian Hobson-Garcia <[email protected]>
+Dan Carpenter <[email protected]> <[email protected]>
 Daniel Borkmann <[email protected]> <[email protected]>
 Daniel Borkmann <[email protected]> <[email protected]>
 Daniel Borkmann <[email protected]> <[email protected]>
@@ -353,7 +354,8 @@ Peter Oruba <[email protected]>
 Pratyush Anand <[email protected]> <[email protected]>
 Praveen BP <[email protected]>
 Punit Agrawal <[email protected]> <[email protected]>
-Qais Yousef <[email protected]> <[email protected]>
+Qais Yousef <[email protected]> <[email protected]>
+Qais Yousef <[email protected]> <[email protected]>
 Quentin Monnet <[email protected]> <[email protected]>
 Quentin Perret <[email protected]> <[email protected]>
 Rafael J. Wysocki <[email protected]> <[email protected]>

drivers/gpu/drm/nouveau/nouveau_dmem.c

@@ -176,6 +176,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 		.src		= &src,
 		.dst		= &dst,
 		.pgmap_owner	= drm->dev,
+		.fault_page	= vmf->page,
 		.flags		= MIGRATE_VMA_SELECT_DEVICE_PRIVATE,
 	};
 

fs/ocfs2/namei.c

@@ -232,6 +232,7 @@ static int ocfs2_mknod(struct user_namespace *mnt_userns,
 	handle_t *handle = NULL;
 	struct ocfs2_super *osb;
 	struct ocfs2_dinode *dirfe;
+	struct ocfs2_dinode *fe = NULL;
 	struct buffer_head *new_fe_bh = NULL;
 	struct inode *inode = NULL;
 	struct ocfs2_alloc_context *inode_ac = NULL;
@@ -382,6 +383,7 @@ static int ocfs2_mknod(struct user_namespace *mnt_userns,
 		goto leave;
 	}
 
+	fe = (struct ocfs2_dinode *) new_fe_bh->b_data;
 	if (S_ISDIR(mode)) {
 		status = ocfs2_fill_new_dir(osb, handle, dir, inode,
 					    new_fe_bh, data_ac, meta_ac);
@@ -454,8 +456,11 @@ static int ocfs2_mknod(struct user_namespace *mnt_userns,
 leave:
 	if (status < 0 && did_quota_inode)
 		dquot_free_inode(inode);
-	if (handle)
+	if (handle) {
+		if (status < 0 && fe)
+			ocfs2_set_links_count(fe, 0);
 		ocfs2_commit_trans(osb, handle);
+	}
 
 	ocfs2_inode_unlock(dir, 1);
 	if (did_block_signals)
@@ -632,18 +637,9 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 		return status;
 	}
 
-	status = __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh,
+	return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh,
 				    parent_fe_bh, handle, inode_ac,
 				    fe_blkno, suballoc_loc, suballoc_bit);
-	if (status < 0) {
-		u64 bg_blkno = ocfs2_which_suballoc_group(fe_blkno, suballoc_bit);
-		int tmp = ocfs2_free_suballoc_bits(handle, inode_ac->ac_inode,
-				inode_ac->ac_bh, suballoc_bit, bg_blkno, 1);
-		if (tmp)
-			mlog_errno(tmp);
-	}
-
-	return status;
 }
 
 static int ocfs2_mkdir(struct user_namespace *mnt_userns,
@@ -2028,8 +2024,11 @@ static int ocfs2_symlink(struct user_namespace *mnt_userns,
 					ocfs2_clusters_to_bytes(osb->sb, 1));
 	if (status < 0 && did_quota_inode)
 		dquot_free_inode(inode);
-	if (handle)
+	if (handle) {
+		if (status < 0 && fe)
+			ocfs2_set_links_count(fe, 0);
 		ocfs2_commit_trans(osb, handle);
+	}
 
 	ocfs2_inode_unlock(dir, 1);
 	if (did_block_signals)

fs/proc/task_mmu.c

@@ -902,7 +902,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 		goto out_put_mm;
 
 	hold_task_mempolicy(priv);
-	vma = mas_find(&mas, 0);
+	vma = mas_find(&mas, ULONG_MAX);
 
 	if (unlikely(!vma))
 		goto empty_set;

init/Kconfig

@@ -66,7 +66,7 @@ config RUST_IS_AVAILABLE
 	  This shows whether a suitable Rust toolchain is available (found).
 
 	  Please see Documentation/rust/quick-start.rst for instructions on how
-	  to satify the build requirements of Rust support.
+	  to satisfy the build requirements of Rust support.
 
 	  In particular, the Makefile target 'rustavailable' is useful to check
 	  why the Rust toolchain is not being detected.

kernel/gcov/gcc_4_7.c

@@ -30,6 +30,13 @@
 
 #define GCOV_TAG_FUNCTION_LENGTH	3
 
+/* Since GCC 12.1 sizes are in BYTES and not in WORDS (4B). */
+#if (__GNUC__ >= 12)
+#define GCOV_UNIT_SIZE				4
+#else
+#define GCOV_UNIT_SIZE				1
+#endif
+
 static struct gcov_info *gcov_info_head;
 
 /**
@@ -383,12 +390,18 @@ size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 	pos += store_gcov_u32(buffer, pos, info->version);
 	pos += store_gcov_u32(buffer, pos, info->stamp);
 
+#if (__GNUC__ >= 12)
+	/* Use zero as checksum of the compilation unit. */
+	pos += store_gcov_u32(buffer, pos, 0);
+#endif
+
 	for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
 		fi_ptr = info->functions[fi_idx];
 
 		/* Function record. */
 		pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION);
-		pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH);
+		pos += store_gcov_u32(buffer, pos,
+			GCOV_TAG_FUNCTION_LENGTH * GCOV_UNIT_SIZE);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->ident);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum);
 		pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
@@ -402,7 +415,8 @@ size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 			/* Counter record. */
 			pos += store_gcov_u32(buffer, pos,
 					      GCOV_TAG_FOR_COUNTER(ct_idx));
-			pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2);
+			pos += store_gcov_u32(buffer, pos,
+				ci_ptr->num * 2 * GCOV_UNIT_SIZE);
 
 			for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) {
 				pos += store_gcov_u64(buffer, pos,

mm/huge_memory.c

@@ -2455,7 +2455,16 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			page_tail);
 	page_tail->mapping = head->mapping;
 	page_tail->index = head->index + tail;
-	page_tail->private = 0;
+
+	/*
+	 * page->private should not be set in tail pages with the exception
+	 * of swap cache pages that store the swp_entry_t in tail pages.
+	 * Fix up and warn once if private is unexpectedly set.
+	 */
+	if (!folio_test_swapcache(page_folio(head))) {
+		VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, head);
+		page_tail->private = 0;
+	}
 
 	/* Page flags must be visible before we make the page non-compound. */
 	smp_wmb();

mm/hugetlb.c

@@ -1014,15 +1014,23 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 	/*
 	 * Clear vm_private_data
+	 * - For shared mappings this is a per-vma semaphore that may be
+	 *   allocated in a subsequent call to hugetlb_vm_op_open.
+	 *   Before clearing, make sure pointer is not associated with vma
+	 *   as this will leak the structure.  This is the case when called
+	 *   via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already
+	 *   been called to allocate a new structure.
 	 * - For MAP_PRIVATE mappings, this is the reserve map which does
 	 *   not apply to children.  Faults generated by the children are
 	 *   not guaranteed to succeed, even if read-only.
-	 * - For shared mappings this is a per-vma semaphore that may be
-	 *   allocated in a subsequent call to hugetlb_vm_op_open.
 	 */
-	vma->vm_private_data = (void *)0;
-	if (!(vma->vm_flags & VM_MAYSHARE))
-		return;
+	if (vma->vm_flags & VM_MAYSHARE) {
+		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
+
+		if (vma_lock && vma_lock->vma != vma)
+			vma->vm_private_data = NULL;
+	} else
+		vma->vm_private_data = NULL;
 }
 
 /*
@@ -2924,11 +2932,11 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 		page = alloc_buddy_huge_page_with_mpol(h, vma, addr);
 		if (!page)
 			goto out_uncharge_cgroup;
+		spin_lock_irq(&hugetlb_lock);
 		if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
 			SetHPageRestoreReserve(page);
 			h->resv_huge_pages--;
 		}
-		spin_lock_irq(&hugetlb_lock);
 		list_add(&page->lru, &h->hugepage_activelist);
 		set_page_refcounted(page);
 		/* Fall through */
@@ -4601,6 +4609,7 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 	struct resv_map *resv = vma_resv_map(vma);
 
 	/*
+	 * HPAGE_RESV_OWNER indicates a private mapping.
 	 * This new VMA should share its siblings reservation map if present.
 	 * The VMA will only ever have a valid reservation map pointer where
 	 * it is being copied for another still existing VMA.  As that VMA
@@ -4615,11 +4624,21 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 
 	/*
 	 * vma_lock structure for sharable mappings is vma specific.
-	 * Clear old pointer (if copied via vm_area_dup) and create new.
+	 * Clear old pointer (if copied via vm_area_dup) and allocate
+	 * new structure.  Before clearing, make sure vma_lock is not
+	 * for this vma.
 	 */
 	if (vma->vm_flags & VM_MAYSHARE) {
-		vma->vm_private_data = NULL;
-		hugetlb_vma_lock_alloc(vma);
+		struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
+
+		if (vma_lock) {
+			if (vma_lock->vma != vma) {
+				vma->vm_private_data = NULL;
+				hugetlb_vma_lock_alloc(vma);
+			} else
+				pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__);
+		} else
+			hugetlb_vma_lock_alloc(vma);
 	}
 }
 

mm/mempolicy.c

@@ -787,17 +787,22 @@ static int vma_replace_policy(struct vm_area_struct *vma,
 static int mbind_range(struct mm_struct *mm, unsigned long start,
 		       unsigned long end, struct mempolicy *new_pol)
 {
-	MA_STATE(mas, &mm->mm_mt, start - 1, start - 1);
+	MA_STATE(mas, &mm->mm_mt, start, start);
 	struct vm_area_struct *prev;
 	struct vm_area_struct *vma;
 	int err = 0;
 	pgoff_t pgoff;
 
-	prev = mas_find_rev(&mas, 0);
-	if (prev && (start < prev->vm_end))
-		vma = prev;
-	else
-		vma = mas_next(&mas, end - 1);
+	prev = mas_prev(&mas, 0);
+	if (unlikely(!prev))
+		mas_set(&mas, start);
+
+	vma = mas_find(&mas, end - 1);
+	if (WARN_ON(!vma))
+		return 0;
+
+	if (start > vma->vm_start)
+		prev = vma;
 
 	for (; vma; vma = mas_next(&mas, end - 1)) {
 		unsigned long vmstart = max(start, vma->vm_start);

mm/mmap.c

@@ -618,7 +618,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	struct vm_area_struct *expand)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	struct vm_area_struct *next_next, *next = find_vma(mm, vma->vm_end);
+	struct vm_area_struct *next_next = NULL;	/* uninit var warning */
+	struct vm_area_struct *next = find_vma(mm, vma->vm_end);
 	struct vm_area_struct *orig_vma = vma;
 	struct address_space *mapping = NULL;
 	struct rb_root_cached *root = NULL;
@@ -2625,14 +2626,14 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		if (error)
 			goto unmap_and_free_vma;
 
-		/* Can addr have changed??
-		 *
-		 * Answer: Yes, several device drivers can do it in their
-		 *         f_op->mmap method. -DaveM
+		/*
+		 * Expansion is handled above, merging is handled below.
+		 * Drivers should not alter the address of the VMA.
 		 */
-		WARN_ON_ONCE(addr != vma->vm_start);
-
-		addr = vma->vm_start;
+		if (WARN_ON((addr != vma->vm_start))) {
+			error = -EINVAL;
+			goto close_and_free_vma;
+		}
 		mas_reset(&mas);
 
 		/*
@@ -2654,7 +2655,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 				vm_area_free(vma);
 				vma = merge;
 				/* Update vm_flags to pick up the change. */
-				addr = vma->vm_start;
 				vm_flags = vma->vm_flags;
 				goto unmap_writable;
 			}
@@ -2681,7 +2681,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	if (mas_preallocate(&mas, vma, GFP_KERNEL)) {
 		error = -ENOMEM;
 		if (file)
-			goto unmap_and_free_vma;
+			goto close_and_free_vma;
 		else
 			goto free_vma;
 	}

mm/page_alloc.c

@@ -5784,14 +5784,18 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order,
 		size_t size)
 {
 	if (addr) {
-		unsigned long alloc_end = addr + (PAGE_SIZE << order);
-		unsigned long used = addr + PAGE_ALIGN(size);
-
-		split_page(virt_to_page((void *)addr), order);
-		while (used < alloc_end) {
-			free_page(used);
-			used += PAGE_SIZE;
-		}
+		unsigned long nr = DIV_ROUND_UP(size, PAGE_SIZE);
+		struct page *page = virt_to_page((void *)addr);
+		struct page *last = page + nr;
+
+		split_page_owner(page, 1 << order);
+		split_page_memcg(page, 1 << order);
+		while (page < --last)
+			set_page_refcounted(last);
+
+		last = page + (1UL << order);
+		for (page += nr; page < last; page++)
+			__free_pages_ok(page, 0, FPI_TO_TAIL);
 	}
 	return (void *)addr;
 }

mm/zsmalloc.c

@@ -2311,6 +2311,9 @@ void zs_destroy_pool(struct zs_pool *pool)
 		int fg;
 		struct size_class *class = pool->size_class[i];
 
+		if (!class)
+			continue;
+
 		if (class->index != i)
 			continue;