mm: set up vma iterator for vma_iter_prealloc() calls

Set the correct limits for vma_iter_prealloc() calls so that the maple
tree can be smarter about how many nodes are needed.

Link: https://lkml.kernel.org/r/20230724183157.3939892-11-Liam.Howlett@oracle.comSigned-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Peng Zhang <zhangpeng.00@bytedance.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

fs/exec.c

@@ -701,6 +701,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 	if (vma != vma_next(&vmi))
 		return -EFAULT;
 
+	vma_iter_prev_range(&vmi);
 	/*
 	 * cover the whole range: [new_start, old_end)
 	 */

mm/internal.h

@@ -1052,23 +1052,21 @@ static inline void vma_iter_config(struct vma_iterator *vmi,
 /*
  * VMA Iterator functions shared between nommu and mmap
  */
-static inline int vma_iter_prealloc(struct vma_iterator *vmi)
+static inline int vma_iter_prealloc(struct vma_iterator *vmi,
+		struct vm_area_struct *vma)
 {
-	return mas_preallocate(&vmi->mas, NULL, GFP_KERNEL);
+	return mas_preallocate(&vmi->mas, vma, GFP_KERNEL);
 }
 
-static inline void vma_iter_clear(struct vma_iterator *vmi,
-				  unsigned long start, unsigned long end)
+static inline void vma_iter_clear(struct vma_iterator *vmi)
 {
-	mas_set_range(&vmi->mas, start, end - 1);
 	mas_store_prealloc(&vmi->mas, NULL);
 }
 
 static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
 			unsigned long start, unsigned long end, gfp_t gfp)
 {
-	vmi->mas.index = start;
-	vmi->mas.last = end - 1;
+	__mas_set_range(&vmi->mas, start, end - 1);
 	mas_store_gfp(&vmi->mas, NULL, gfp);
 	if (unlikely(mas_is_err(&vmi->mas)))
 		return -ENOMEM;
@@ -1105,8 +1103,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
 		vma_iter_invalidate(vmi);
 
-	vmi->mas.index = vma->vm_start;
-	vmi->mas.last = vma->vm_end - 1;
+	__mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
 	mas_store_prealloc(&vmi->mas, vma);
 }
 
@@ -1117,8 +1114,7 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
 	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
 		vma_iter_invalidate(vmi);
 
-	vmi->mas.index = vma->vm_start;
-	vmi->mas.last = vma->vm_end - 1;
+	__mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
 	mas_store_gfp(&vmi->mas, vma, gfp);
 	if (unlikely(mas_is_err(&vmi->mas)))
 		return -ENOMEM;

mm/mmap.c

@@ -397,7 +397,8 @@ static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma)
 	VMA_ITERATOR(vmi, mm, 0);
 	struct address_space *mapping = NULL;
 
-	if (vma_iter_prealloc(&vmi))
+	vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
+	if (vma_iter_prealloc(&vmi, vma))
 		return -ENOMEM;
 
 	vma_iter_store(&vmi, vma);
@@ -649,19 +650,16 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	/* Only handles expanding */
 	VM_WARN_ON(vma->vm_start < start || vma->vm_end > end);
 
-	if (vma_iter_prealloc(vmi))
+	/* Note: vma iterator must be pointing to 'start' */
+	vma_iter_config(vmi, start, end);
+	if (vma_iter_prealloc(vmi, vma))
 		goto nomem;
 
 	vma_prepare(&vp);
 	vma_adjust_trans_huge(vma, start, end, 0);
-	/* VMA iterator points to previous, so set to start if necessary */
-	if (vma_iter_addr(vmi) != start)
-		vma_iter_set(vmi, start);
-
 	vma->vm_start = start;
 	vma->vm_end = end;
 	vma->vm_pgoff = pgoff;
-	/* Note: mas must be pointing to the expanding VMA */
 	vma_iter_store(vmi, vma);
 
 	vma_complete(&vp, vmi, vma->vm_mm);
@@ -687,19 +685,19 @@ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 	WARN_ON((vma->vm_start != start) && (vma->vm_end != end));
 
-	if (vma_iter_prealloc(vmi))
+	if (vma->vm_start < start)
+		vma_iter_config(vmi, vma->vm_start, start);
+	else
+		vma_iter_config(vmi, end, vma->vm_end);
+
+	if (vma_iter_prealloc(vmi, NULL))
 		return -ENOMEM;
 
 	init_vma_prep(&vp, vma);
 	vma_prepare(&vp);
 	vma_adjust_trans_huge(vma, start, end, 0);
 
-	if (vma->vm_start < start)
-		vma_iter_clear(vmi, vma->vm_start, start);
-
-	if (vma->vm_end > end)
-		vma_iter_clear(vmi, end, vma->vm_end);
-
+	vma_iter_clear(vmi);
 	vma->vm_start = start;
 	vma->vm_end = end;
 	vma->vm_pgoff = pgoff;
@@ -973,7 +971,17 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
 	if (err)
 		return NULL;
 
-	if (vma_iter_prealloc(vmi))
+	if (vma_start < vma->vm_start || vma_end > vma->vm_end)
+		vma_expanded = true;
+
+	if (vma_expanded) {
+		vma_iter_config(vmi, vma_start, vma_end);
+	} else {
+		vma_iter_config(vmi, adjust->vm_start + adj_start,
+				adjust->vm_end);
+	}
+
+	if (vma_iter_prealloc(vmi, vma))
 		return NULL;
 
 	init_multi_vma_prep(&vp, vma, adjust, remove, remove2);
@@ -982,8 +990,6 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
 
 	vma_prepare(&vp);
 	vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start);
-	if (vma_start < vma->vm_start || vma_end > vma->vm_end)
-		vma_expanded = true;
 
 	vma->vm_start = vma_start;
 	vma->vm_end = vma_end;
@@ -1923,7 +1929,7 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 	struct vm_area_struct *next;
 	unsigned long gap_addr;
 	int error = 0;
-	MA_STATE(mas, &mm->mm_mt, 0, 0);
+	MA_STATE(mas, &mm->mm_mt, vma->vm_start, address);
 
 	if (!(vma->vm_flags & VM_GROWSUP))
 		return -EFAULT;
@@ -1948,6 +1954,10 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		/* Check that both stack segments have the same anon_vma? */
 	}
 
+	if (next)
+		mas_prev_range(&mas, address);
+
+	__mas_set_range(&mas, vma->vm_start, address - 1);
 	if (mas_preallocate(&mas, vma, GFP_KERNEL))
 		return -ENOMEM;
 
@@ -1993,7 +2003,6 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				anon_vma_interval_tree_pre_update_vma(vma);
 				vma->vm_end = address;
 				/* Overwrite old entry in mtree. */
-				mas_set_range(&mas, vma->vm_start, address - 1);
 				mas_store_prealloc(&mas, vma);
 				anon_vma_interval_tree_post_update_vma(vma);
 				spin_unlock(&mm->page_table_lock);
@@ -2038,6 +2047,10 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address)
 			return -ENOMEM;
 	}
 
+	if (prev)
+		mas_next_range(&mas, vma->vm_start);
+
+	__mas_set_range(&mas, address, vma->vm_end - 1);
 	if (mas_preallocate(&mas, vma, GFP_KERNEL))
 		return -ENOMEM;
 
@@ -2084,7 +2097,6 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address)
 				vma->vm_start = address;
 				vma->vm_pgoff -= grow;
 				/* Overwrite old entry in mtree. */
-				mas_set_range(&mas, address, vma->vm_end - 1);
 				mas_store_prealloc(&mas, vma);
 				anon_vma_interval_tree_post_update_vma(vma);
 				spin_unlock(&mm->page_table_lock);
@@ -2325,10 +2337,6 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	if (!new)
 		return -ENOMEM;
 
-	err = -ENOMEM;
-	if (vma_iter_prealloc(vmi))
-		goto out_free_vma;
-
 	if (new_below) {
 		new->vm_end = addr;
 	} else {
@@ -2336,6 +2344,11 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
 	}
 
+	err = -ENOMEM;
+	vma_iter_config(vmi, new->vm_start, new->vm_end);
+	if (vma_iter_prealloc(vmi, new))
+		goto out_free_vma;
+
 	err = vma_dup_policy(vma, new);
 	if (err)
 		goto out_free_vmi;
@@ -2693,7 +2706,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		vma_iter_next_range(&vmi);
 	}
 
-
 	/* Actually expand, if possible */
 	if (vma &&
 	    !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) {
@@ -2790,7 +2802,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		goto close_and_free_vma;
 
 	error = -ENOMEM;
-	if (vma_iter_prealloc(&vmi))
+	if (vma_iter_prealloc(&vmi, vma))
 		goto close_and_free_vma;
 
 	/* Lock the VMA since it is modified after insertion into VMA tree */
@@ -3053,7 +3065,8 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	if (vma && vma->vm_end == addr && !vma_policy(vma) &&
 	    can_vma_merge_after(vma, flags, NULL, NULL,
 				addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) {
-		if (vma_iter_prealloc(vmi))
+		vma_iter_config(vmi, vma->vm_start, addr + len);
+		if (vma_iter_prealloc(vmi, vma))
 			goto unacct_fail;
 
 		init_vma_prep(&vp, vma);
@@ -3068,6 +3081,8 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		goto out;
 	}
 
+	if (vma)
+		vma_iter_next_range(vmi);
 	/* create a vma struct for an anonymous mapping */
 	vma = vm_area_alloc(mm);
 	if (!vma)

mm/nommu.c

@@ -583,7 +583,8 @@ static int delete_vma_from_mm(struct vm_area_struct *vma)
 {
 	VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_start);
 
-	if (vma_iter_prealloc(&vmi)) {
+	vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
+	if (vma_iter_prealloc(&vmi, vma)) {
 		pr_warn("Allocation of vma tree for process %d failed\n",
 		       current->pid);
 		return -ENOMEM;
@@ -591,7 +592,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma)
 	cleanup_vma_from_mm(vma);
 
 	/* remove from the MM's tree and list */
-	vma_iter_clear(&vmi, vma->vm_start, vma->vm_end);
+	vma_iter_clear(&vmi);
 	return 0;
 }
 /*
@@ -1054,9 +1055,6 @@ unsigned long do_mmap(struct file *file,
 	if (!vma)
 		goto error_getting_vma;
 
-	if (vma_iter_prealloc(&vmi))
-		goto error_vma_iter_prealloc;
-
 	region->vm_usage = 1;
 	region->vm_flags = vm_flags;
 	region->vm_pgoff = pgoff;
@@ -1198,6 +1196,10 @@ unsigned long do_mmap(struct file *file,
 
 share:
 	BUG_ON(!vma->vm_region);
+	vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
+	if (vma_iter_prealloc(&vmi, vma))
+		goto error_just_free;
+
 	setup_vma_to_mm(vma, current->mm);
 	current->mm->map_count++;
 	/* add the VMA to the tree */
@@ -1244,14 +1246,6 @@ unsigned long do_mmap(struct file *file,
 			len, current->pid);
 	show_mem();
 	return -ENOMEM;
-
-error_vma_iter_prealloc:
-	kmem_cache_free(vm_region_jar, region);
-	vm_area_free(vma);
-	pr_warn("Allocation of vma tree for process %d failed\n", current->pid);
-	show_mem();
-	return -ENOMEM;
-
 }
 
 unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
@@ -1336,12 +1330,6 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	if (!new)
 		goto err_vma_dup;
 
-	if (vma_iter_prealloc(vmi)) {
-		pr_warn("Allocation of vma tree for process %d failed\n",
-			current->pid);
-		goto err_vmi_preallocate;
-	}
-
 	/* most fields are the same, copy all, and then fixup */
 	*region = *vma->vm_region;
 	new->vm_region = region;
@@ -1355,6 +1343,13 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		region->vm_pgoff = new->vm_pgoff += npages;
 	}
 
+	vma_iter_config(vmi, new->vm_start, new->vm_end);
+	if (vma_iter_prealloc(vmi, vma)) {
+		pr_warn("Allocation of vma tree for process %d failed\n",
+			current->pid);
+		goto err_vmi_preallocate;
+	}
+
 	if (new->vm_ops && new->vm_ops->open)
 		new->vm_ops->open(new);