Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

1 files changed, 121 insertions, 101 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index d600404580b2..8f1000bc35df 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -182,7 +182,8 @@ static int check_brk_limits(unsigned long addr, unsigned long len)
 	if (IS_ERR_VALUE(mapped_addr))
 		return mapped_addr;
 
-	return mlock_future_check(current->mm, current->mm->def_flags, len);
+	return mlock_future_ok(current->mm, current->mm->def_flags, len)
+		? 0 : -EAGAIN;
 }
 static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma,
 		unsigned long addr, unsigned long request, unsigned long flags);
@@ -300,61 +301,40 @@ out:
 }
 
 #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
-extern void mt_validate(struct maple_tree *mt);
-extern void mt_dump(const struct maple_tree *mt);
-
-/* Validate the maple tree */
-static void validate_mm_mt(struct mm_struct *mm)
-{
-	struct maple_tree *mt = &mm->mm_mt;
-	struct vm_area_struct *vma_mt;
-
-	MA_STATE(mas, mt, 0, 0);
-
-	mt_validate(&mm->mm_mt);
-	mas_for_each(&mas, vma_mt, ULONG_MAX) {
-		if ((vma_mt->vm_start != mas.index) ||
-		    (vma_mt->vm_end - 1 != mas.last)) {
-			pr_emerg("issue in %s\n", current->comm);
-			dump_stack();
-			dump_vma(vma_mt);
-			pr_emerg("mt piv: %p %lu - %lu\n", vma_mt,
-				 mas.index, mas.last);
-			pr_emerg("mt vma: %p %lu - %lu\n", vma_mt,
-				 vma_mt->vm_start, vma_mt->vm_end);
-
-			mt_dump(mas.tree);
-			if (vma_mt->vm_end != mas.last + 1) {
-				pr_err("vma: %p vma_mt %lu-%lu\tmt %lu-%lu\n",
-						mm, vma_mt->vm_start, vma_mt->vm_end,
-						mas.index, mas.last);
-				mt_dump(mas.tree);
-			}
-			VM_BUG_ON_MM(vma_mt->vm_end != mas.last + 1, mm);
-			if (vma_mt->vm_start != mas.index) {
-				pr_err("vma: %p vma_mt %p %lu - %lu doesn't match\n",
-						mm, vma_mt, vma_mt->vm_start, vma_mt->vm_end);
-				mt_dump(mas.tree);
-			}
-			VM_BUG_ON_MM(vma_mt->vm_start != mas.index, mm);
-		}
-	}
-}
-
 static void validate_mm(struct mm_struct *mm)
 {
 	int bug = 0;
 	int i = 0;
 	struct vm_area_struct *vma;
-	MA_STATE(mas, &mm->mm_mt, 0, 0);
-
-	validate_mm_mt(mm);
+	VMA_ITERATOR(vmi, mm, 0);
 
-	mas_for_each(&mas, vma, ULONG_MAX) {
+	mt_validate(&mm->mm_mt);
+	for_each_vma(vmi, vma) {
 #ifdef CONFIG_DEBUG_VM_RB
 		struct anon_vma *anon_vma = vma->anon_vma;
 		struct anon_vma_chain *avc;
+#endif
+		unsigned long vmi_start, vmi_end;
+		bool warn = 0;
+
+		vmi_start = vma_iter_addr(&vmi);
+		vmi_end = vma_iter_end(&vmi);
+		if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm))
+			warn = 1;
+
+		if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm))
+			warn = 1;
 
+		if (warn) {
+			pr_emerg("issue in %s\n", current->comm);
+			dump_stack();
+			dump_vma(vma);
+			pr_emerg("tree range: %px start %lx end %lx\n", vma,
+				 vmi_start, vmi_end - 1);
+			vma_iter_dump_tree(&vmi);
+		}
+
+#ifdef CONFIG_DEBUG_VM_RB
 		if (anon_vma) {
 			anon_vma_lock_read(anon_vma);
 			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
@@ -365,14 +345,13 @@ static void validate_mm(struct mm_struct *mm)
 		i++;
 	}
 	if (i != mm->map_count) {
-		pr_emerg("map_count %d mas_for_each %d\n", mm->map_count, i);
+		pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i);
 		bug = 1;
 	}
 	VM_BUG_ON_MM(bug, mm);
 }
 
 #else /* !CONFIG_DEBUG_VM_MAPLE_TREE */
-#define validate_mm_mt(root) do { } while (0)
 #define validate_mm(mm) do { } while (0)
 #endif /* CONFIG_DEBUG_VM_MAPLE_TREE */
 
@@ -1167,21 +1146,21 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
 	return hint;
 }
 
-int mlock_future_check(struct mm_struct *mm, unsigned long flags,
-		       unsigned long len)
+bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
+			unsigned long bytes)
 {
-	unsigned long locked, lock_limit;
+	unsigned long locked_pages, limit_pages;
 
-	/*  mlock MCL_FUTURE? */
-	if (flags & VM_LOCKED) {
-		locked = len >> PAGE_SHIFT;
-		locked += mm->locked_vm;
-		lock_limit = rlimit(RLIMIT_MEMLOCK);
-		lock_limit >>= PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			return -EAGAIN;
-	}
-	return 0;
+	if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
+		return true;
+
+	locked_pages = bytes >> PAGE_SHIFT;
+	locked_pages += mm->locked_vm;
+
+	limit_pages = rlimit(RLIMIT_MEMLOCK);
+	limit_pages >>= PAGE_SHIFT;
+
+	return locked_pages <= limit_pages;
 }
 
 static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
@@ -1293,7 +1272,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 		if (!can_do_mlock())
 			return -EPERM;
 
-	if (mlock_future_check(mm, vm_flags, len))
+	if (!mlock_future_ok(mm, vm_flags, len))
 		return -EAGAIN;
 
 	if (file) {
@@ -1475,6 +1454,48 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 }
 #endif /* __ARCH_WANT_SYS_OLD_MMAP */
 
+static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops)
+{
+	return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite);
+}
+
+static bool vma_is_shared_writable(struct vm_area_struct *vma)
+{
+	return (vma->vm_flags & (VM_WRITE | VM_SHARED)) ==
+		(VM_WRITE | VM_SHARED);
+}
+
+static bool vma_fs_can_writeback(struct vm_area_struct *vma)
+{
+	/* No managed pages to writeback. */
+	if (vma->vm_flags & VM_PFNMAP)
+		return false;
+
+	return vma->vm_file && vma->vm_file->f_mapping &&
+		mapping_can_writeback(vma->vm_file->f_mapping);
+}
+
+/*
+ * Does this VMA require the underlying folios to have their dirty state
+ * tracked?
+ */
+bool vma_needs_dirty_tracking(struct vm_area_struct *vma)
+{
+	/* Only shared, writable VMAs require dirty tracking. */
+	if (!vma_is_shared_writable(vma))
+		return false;
+
+	/* Does the filesystem need to be notified? */
+	if (vm_ops_needs_writenotify(vma->vm_ops))
+		return true;
+
+	/*
+	 * Even if the filesystem doesn't indicate a need for writenotify, if it
+	 * can writeback, dirty tracking is still required.
+	 */
+	return vma_fs_can_writeback(vma);
+}
+
 /*
  * Some shared mappings will want the pages marked read-only
  * to track write events. If so, we'll downgrade vm_page_prot
@@ -1483,21 +1504,18 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
  */
 int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 {
-	vm_flags_t vm_flags = vma->vm_flags;
-	const struct vm_operations_struct *vm_ops = vma->vm_ops;
-
 	/* If it was private or non-writable, the write bit is already clear */
-	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
+	if (!vma_is_shared_writable(vma))
 		return 0;
 
 	/* The backer wishes to know when pages are first written to? */
-	if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite))
+	if (vm_ops_needs_writenotify(vma->vm_ops))
 		return 1;
 
 	/* The open routine did something to the protections that pgprot_modify
 	 * won't preserve? */
 	if (pgprot_val(vm_page_prot) !=
-	    pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags)))
+	    pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags)))
 		return 0;
 
 	/*
@@ -1511,13 +1529,8 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 	if (userfaultfd_wp(vma))
 		return 1;
 
-	/* Specialty mapping? */
-	if (vm_flags & VM_PFNMAP)
-		return 0;
-
 	/* Can the mapping track the dirty pages? */
-	return vma->vm_file && vma->vm_file->f_mapping &&
-		mapping_can_writeback(vma->vm_file->f_mapping);
+	return vma_fs_can_writeback(vma);
 }
 
 /*
@@ -1911,7 +1924,7 @@ static int acct_stack_growth(struct vm_area_struct *vma,
 		return -ENOMEM;
 
 	/* mlock limit tests */
-	if (mlock_future_check(mm, vma->vm_flags, grow << PAGE_SHIFT))
+	if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT))
 		return -ENOMEM;
 
 	/* Check to ensure the stack will not grow into a hugetlb-only region */
@@ -2234,7 +2247,7 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	struct vm_area_struct *new;
 	int err;
 
-	validate_mm_mt(vma->vm_mm);
+	validate_mm(vma->vm_mm);
 
 	WARN_ON(vma->vm_start >= addr);
 	WARN_ON(vma->vm_end <= addr);
@@ -2292,7 +2305,7 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	/* Success. */
 	if (new_below)
 		vma_next(vmi);
-	validate_mm_mt(vma->vm_mm);
+	validate_mm(vma->vm_mm);
 	return 0;
 
 out_free_mpol:
@@ -2301,7 +2314,7 @@ out_free_vmi:
 	vma_iter_free(vmi);
 out_free_vma:
 	vm_area_free(new);
-	validate_mm_mt(vma->vm_mm);
+	validate_mm(vma->vm_mm);
 	return err;
 }
 
@@ -2394,28 +2407,32 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 			locked_vm += vma_pages(next);
 
 		count++;
+		if (unlikely(uf)) {
+			/*
+			 * If userfaultfd_unmap_prep returns an error the vmas
+			 * will remain split, but userland will get a
+			 * highly unexpected error anyway. This is no
+			 * different than the case where the first of the two
+			 * __split_vma fails, but we don't undo the first
+			 * split, despite we could. This is unlikely enough
+			 * failure that it's not worth optimizing it for.
+			 */
+			error = userfaultfd_unmap_prep(next, start, end, uf);
+
+			if (error)
+				goto userfaultfd_error;
+		}
 #ifdef CONFIG_DEBUG_VM_MAPLE_TREE
 		BUG_ON(next->vm_start < start);
 		BUG_ON(next->vm_start > end);
 #endif
 	}
 
-	next = vma_next(vmi);
-	if (unlikely(uf)) {
-		/*
-		 * If userfaultfd_unmap_prep returns an error the vmas
-		 * will remain split, but userland will get a
-		 * highly unexpected error anyway. This is no
-		 * different than the case where the first of the two
-		 * __split_vma fails, but we don't undo the first
-		 * split, despite we could. This is unlikely enough
-		 * failure that it's not worth optimizing it for.
-		 */
-		error = userfaultfd_unmap_prep(mm, start, end, uf);
+	if (vma_iter_end(vmi) > end)
+		next = vma_iter_load(vmi);
 
-		if (error)
-			goto userfaultfd_error;
-	}
+	if (!next)
+		next = vma_next(vmi);
 
 #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
 	/* Make sure no VMAs are about to be lost. */
@@ -2620,6 +2637,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	}
 
 cannot_expand:
+	if (prev)
+		vma_iter_next_range(&vmi);
+
 	/*
 	 * Determine the object being mapped and call the appropriate
 	 * specific mapper. the address has already been validated, but
@@ -2933,7 +2953,7 @@ int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 	arch_unmap(mm, start, end);
 	ret = do_vmi_align_munmap(vmi, vma, mm, start, end, uf, downgrade);
-	validate_mm_mt(mm);
+	validate_mm(mm);
 	return ret;
 }
 
@@ -2955,7 +2975,7 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	struct mm_struct *mm = current->mm;
 	struct vma_prepare vp;
 
-	validate_mm_mt(mm);
+	validate_mm(mm);
 	/*
 	 * Check against address space limits by the changed size
 	 * Note: This happens *after* clearing old mappings in some code paths.
@@ -3196,7 +3216,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	bool faulted_in_anon_vma = true;
 	VMA_ITERATOR(vmi, mm, addr);
 
-	validate_mm_mt(mm);
+	validate_mm(mm);
 	/*
 	 * If anonymous vma has not yet been faulted, update new pgoff
 	 * to match new location, to increase its chance of merging.
@@ -3255,7 +3275,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 			goto out_vma_link;
 		*need_rmap_locks = false;
 	}
-	validate_mm_mt(mm);
+	validate_mm(mm);
 	return new_vma;
 
 out_vma_link:
@@ -3271,7 +3291,7 @@ out_free_mempol:
 out_free_vma:
 	vm_area_free(new_vma);
 out:
-	validate_mm_mt(mm);
+	validate_mm(mm);
 	return NULL;
 }
 
@@ -3408,7 +3428,7 @@ static struct vm_area_struct *__install_special_mapping(
 	int ret;
 	struct vm_area_struct *vma;
 
-	validate_mm_mt(mm);
+	validate_mm(mm);
 	vma = vm_area_alloc(mm);
 	if (unlikely(vma == NULL))
 		return ERR_PTR(-ENOMEM);
@@ -3431,12 +3451,12 @@ static struct vm_area_struct *__install_special_mapping(
 
 	perf_event_mmap(vma);
 
-	validate_mm_mt(mm);
+	validate_mm(mm);
 	return vma;
 
 out:
 	vm_area_free(vma);
-	validate_mm_mt(mm);
+	validate_mm(mm);
 	return ERR_PTR(ret);
 }