mm: move internal core VMA manipulation functions to own file

This patch introduces vma.c and moves internal core VMA manipulation
functions to this file from mmap.c.

This allows us to isolate VMA functionality in a single place such that we
can create userspace testing code that invokes this functionality in an
environment where we can implement simple unit tests of core
functionality.

This patch ensures that core VMA functionality is explicitly marked as
such by its presence in mm/vma.h.

It also places the header includes required by vma.c in vma_internal.h,
which is simply imported by vma.c.  This makes the VMA functionality
testable, as userland testing code can simply stub out functionality as
required.

Link: https://lkml.kernel.org/r/c77a6aafb4c42aaadb8e7271a853658cbdca2e22.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

8 files changed, 2188 insertions, 2039 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1c0d88446eb8..bd219ac9c026 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1005,21 +1005,6 @@ static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi)
 	return mas_prev(&vmi->mas, 0);
 }
 
-static inline unsigned long vma_iter_addr(struct vma_iterator *vmi)
-{
-	return vmi->mas.index;
-}
-
-static inline unsigned long vma_iter_end(struct vma_iterator *vmi)
-{
-	return vmi->mas.last + 1;
-}
-static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi,
-				      unsigned long count)
-{
-	return mas_expected_entries(&vmi->mas, count);
-}
-
 static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
 			unsigned long start, unsigned long end, gfp_t gfp)
 {
@@ -2534,21 +2519,6 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 #define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
 					    MM_CP_UFFD_WP_RESOLVE)
 
-bool vma_needs_dirty_tracking(struct vm_area_struct *vma);
-bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
-static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma)
-{
-	/*
-	 * We want to check manually if we can change individual PTEs writable
-	 * if we can't do that automatically for all PTEs in a mapping. For
-	 * private mappings, that's always the case when we have write
-	 * permissions as we properly have to handle COW.
-	 */
-	if (vma->vm_flags & VM_SHARED)
-		return vma_wants_writenotify(vma, vma->vm_page_prot);
-	return !!(vma->vm_flags & VM_WRITE);
-
-}
 bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t pte);
 extern long change_protection(struct mmu_gather *tlb,
@@ -3256,12 +3226,7 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node);
 
 /* mmap.c */
 extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
-extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
 extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
-extern void unlink_file_vma(struct vm_area_struct *);
-extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
-	unsigned long addr, unsigned long len, pgoff_t pgoff,
-	bool *need_rmap_locks);
 extern void exit_mmap(struct mm_struct *);
 int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift);
 
diff --git a/mm/Makefile b/mm/Makefile
index b11fefbc13bc..24b918260c7f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -37,7 +37,7 @@ mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= highmem.o memory.o mincore.o \
 			   mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \
 			   msync.o page_vma_mapped.o pagewalk.o \
-			   pgtable-generic.o rmap.o vmalloc.o
+			   pgtable-generic.o rmap.o vmalloc.o vma.o
 
 
 ifdef CONFIG_CROSS_MEMORY_ATTACH
diff --git a/mm/internal.h b/mm/internal.h
index a4d0e98ccb97..1159b04e76a3 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -8,13 +8,18 @@
 #define __MM_INTERNAL_H
 
 #include <linux/fs.h>
+#include <linux/khugepaged.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/tracepoint-defs.h>
 
+/* Internal core VMA manipulation functions. */
+#include "vma.h"
+
 struct folio_batch;
 
 /*
@@ -778,37 +783,6 @@ static inline bool free_area_empty(struct free_area *area, int migratetype)
 	return list_empty(&area->free_list[migratetype]);
 }
 
-/*
- * These three helpers classifies VMAs for virtual memory accounting.
- */
-
-/*
- * Executable code area - executable, not writable, not stack
- */
-static inline bool is_exec_mapping(vm_flags_t flags)
-{
-	return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC;
-}
-
-/*
- * Stack area (including shadow stacks)
- *
- * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
- * do_mmap() forbids all other combinations.
- */
-static inline bool is_stack_mapping(vm_flags_t flags)
-{
-	return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK);
-}
-
-/*
- * Data area - private, writable, not stack
- */
-static inline bool is_data_mapping(vm_flags_t flags)
-{
-	return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
-}
-
 /* mm/util.c */
 struct anon_vma *folio_anon_vma(struct folio *folio);
 
@@ -1237,80 +1211,6 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr,
 void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 	       pmd_t *pmd, bool write);
 
-/*
- * mm/mmap.c
- */
-struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi,
-					struct vm_area_struct *vma,
-					unsigned long delta);
-
-struct vm_area_struct *vma_modify(struct vma_iterator *vmi,
-				  struct vm_area_struct *prev,
-				  struct vm_area_struct *vma,
-				  unsigned long start, unsigned long end,
-				  unsigned long vm_flags,
-				  struct mempolicy *policy,
-				  struct vm_userfaultfd_ctx uffd_ctx,
-				  struct anon_vma_name *anon_name);
-
-/* We are about to modify the VMA's flags. */
-static inline struct vm_area_struct
-*vma_modify_flags(struct vma_iterator *vmi,
-		  struct vm_area_struct *prev,
-		  struct vm_area_struct *vma,
-		  unsigned long start, unsigned long end,
-		  unsigned long new_flags)
-{
-	return vma_modify(vmi, prev, vma, start, end, new_flags,
-			  vma_policy(vma), vma->vm_userfaultfd_ctx,
-			  anon_vma_name(vma));
-}
-
-/* We are about to modify the VMA's flags and/or anon_name. */
-static inline struct vm_area_struct
-*vma_modify_flags_name(struct vma_iterator *vmi,
-		       struct vm_area_struct *prev,
-		       struct vm_area_struct *vma,
-		       unsigned long start,
-		       unsigned long end,
-		       unsigned long new_flags,
-		       struct anon_vma_name *new_name)
-{
-	return vma_modify(vmi, prev, vma, start, end, new_flags,
-			  vma_policy(vma), vma->vm_userfaultfd_ctx, new_name);
-}
-
-/* We are about to modify the VMA's memory policy. */
-static inline struct vm_area_struct
-*vma_modify_policy(struct vma_iterator *vmi,
-		   struct vm_area_struct *prev,
-		   struct vm_area_struct *vma,
-		   unsigned long start, unsigned long end,
-		   struct mempolicy *new_pol)
-{
-	return vma_modify(vmi, prev, vma, start, end, vma->vm_flags,
-			  new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma));
-}
-
-/* We are about to modify the VMA's flags and/or uffd context. */
-static inline struct vm_area_struct
-*vma_modify_flags_uffd(struct vma_iterator *vmi,
-		       struct vm_area_struct *prev,
-		       struct vm_area_struct *vma,
-		       unsigned long start, unsigned long end,
-		       unsigned long new_flags,
-		       struct vm_userfaultfd_ctx new_ctx)
-{
-	return vma_modify(vmi, prev, vma, start, end, new_flags,
-			  vma_policy(vma), new_ctx, anon_vma_name(vma));
-}
-
-int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
-	      unsigned long start, unsigned long end, pgoff_t pgoff,
-	      struct vm_area_struct *next);
-int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
-	       unsigned long start, unsigned long end, pgoff_t pgoff);
-
 enum {
 	/* mark page accessed */
 	FOLL_TOUCH = 1 << 16,
@@ -1437,123 +1337,6 @@ static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte
 	return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte);
 }
 
-static inline void vma_iter_config(struct vma_iterator *vmi,
-		unsigned long index, unsigned long last)
-{
-	__mas_set_range(&vmi->mas, index, last - 1);
-}
-
-static inline void vma_iter_reset(struct vma_iterator *vmi)
-{
-	mas_reset(&vmi->mas);
-}
-
-static inline
-struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min)
-{
-	return mas_prev_range(&vmi->mas, min);
-}
-
-static inline
-struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max)
-{
-	return mas_next_range(&vmi->mas, max);
-}
-
-static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min,
-				       unsigned long max, unsigned long size)
-{
-	return mas_empty_area(&vmi->mas, min, max - 1, size);
-}
-
-static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min,
-					unsigned long max, unsigned long size)
-{
-	return mas_empty_area_rev(&vmi->mas, min, max - 1, size);
-}
-
-/*
- * VMA Iterator functions shared between nommu and mmap
- */
-static inline int vma_iter_prealloc(struct vma_iterator *vmi,
-		struct vm_area_struct *vma)
-{
-	return mas_preallocate(&vmi->mas, vma, GFP_KERNEL);
-}
-
-static inline void vma_iter_clear(struct vma_iterator *vmi)
-{
-	mas_store_prealloc(&vmi->mas, NULL);
-}
-
-static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi)
-{
-	return mas_walk(&vmi->mas);
-}
-
-/* Store a VMA with preallocated memory */
-static inline void vma_iter_store(struct vma_iterator *vmi,
-				  struct vm_area_struct *vma)
-{
-
-#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
-	if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start &&
-			vmi->mas.index > vma->vm_start)) {
-		pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n",
-			vmi->mas.index, vma->vm_start, vma->vm_start,
-			vma->vm_end, vmi->mas.index, vmi->mas.last);
-	}
-	if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start &&
-			vmi->mas.last <  vma->vm_start)) {
-		pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n",
-		       vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end,
-		       vmi->mas.index, vmi->mas.last);
-	}
-#endif
-
-	if (vmi->mas.status != ma_start &&
-	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
-		vma_iter_invalidate(vmi);
-
-	__mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1);
-	mas_store_prealloc(&vmi->mas, vma);
-}
-
-static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
-			struct vm_area_struct *vma, gfp_t gfp)
-{
-	if (vmi->mas.status != ma_start &&
-	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
-		vma_iter_invalidate(vmi);
-
-	__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;
-
-	return 0;
-}
-
-static inline
-struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi)
-{
-	return mas_prev_range(&vmi->mas, 0);
-}
-
-/*
- * VMA lock generalization
- */
-struct vma_prepare {
-	struct vm_area_struct *vma;
-	struct vm_area_struct *adj_next;
-	struct file *file;
-	struct address_space *mapping;
-	struct anon_vma *anon_vma;
-	struct vm_area_struct *insert;
-	struct vm_area_struct *remove;
-	struct vm_area_struct *remove2;
-};
-
 void __meminit __init_single_page(struct page *page, unsigned long pfn,
 				unsigned long zone, int nid);
 
@@ -1642,15 +1425,6 @@ static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry,
 void workingset_update_node(struct xa_node *node);
 extern struct list_lru shadow_nodes;
 
-struct unlink_vma_file_batch {
-	int count;
-	struct vm_area_struct *vmas[8];
-};
-
-void unlink_file_vma_batch_init(struct unlink_vma_file_batch *);
-void unlink_file_vma_batch_add(struct unlink_vma_file_batch *, struct vm_area_struct *);
-void unlink_file_vma_batch_final(struct unlink_vma_file_batch *);
-
 /* mremap.c */
 unsigned long move_page_tables(struct vm_area_struct *vma,
 	unsigned long old_addr, struct vm_area_struct *new_vma,
diff --git a/mm/mmap.c b/mm/mmap.c
index 211148ba2831..4a9c2329b09a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -76,16 +76,6 @@ int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
 static bool ignore_rlimit_data;
 core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
 
-static void unmap_region(struct mm_struct *mm, struct ma_state *mas,
-		struct vm_area_struct *vma, struct vm_area_struct *prev,
-		struct vm_area_struct *next, unsigned long start,
-		unsigned long end, unsigned long tree_end, bool mm_wr_locked);
-
-static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
-{
-	return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
-}
-
 /* Update vma->vm_page_prot to reflect vma->vm_flags. */
 void vma_set_page_prot(struct vm_area_struct *vma)
 {
@@ -102,100 +92,6 @@ void vma_set_page_prot(struct vm_area_struct *vma)
 }
 
 /*
- * Requires inode->i_mapping->i_mmap_rwsem
- */
-static void __remove_shared_vm_struct(struct vm_area_struct *vma,
-				      struct address_space *mapping)
-{
-	if (vma_is_shared_maywrite(vma))
-		mapping_unmap_writable(mapping);
-
-	flush_dcache_mmap_lock(mapping);
-	vma_interval_tree_remove(vma, &mapping->i_mmap);
-	flush_dcache_mmap_unlock(mapping);
-}
-
-/*
- * Unlink a file-based vm structure from its interval tree, to hide
- * vma from rmap and vmtruncate before freeing its page tables.
- */
-void unlink_file_vma(struct vm_area_struct *vma)
-{
-	struct file *file = vma->vm_file;
-
-	if (file) {
-		struct address_space *mapping = file->f_mapping;
-		i_mmap_lock_write(mapping);
-		__remove_shared_vm_struct(vma, mapping);
-		i_mmap_unlock_write(mapping);
-	}
-}
-
-void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb)
-{
-	vb->count = 0;
-}
-
-static void unlink_file_vma_batch_process(struct unlink_vma_file_batch *vb)
-{
-	struct address_space *mapping;
-	int i;
-
-	mapping = vb->vmas[0]->vm_file->f_mapping;
-	i_mmap_lock_write(mapping);
-	for (i = 0; i < vb->count; i++) {
-		VM_WARN_ON_ONCE(vb->vmas[i]->vm_file->f_mapping != mapping);
-		__remove_shared_vm_struct(vb->vmas[i], mapping);
-	}
-	i_mmap_unlock_write(mapping);
-
-	unlink_file_vma_batch_init(vb);
-}
-
-void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb,
-			       struct vm_area_struct *vma)
-{
-	if (vma->vm_file == NULL)
-		return;
-
-	if ((vb->count > 0 && vb->vmas[0]->vm_file != vma->vm_file) ||
-	    vb->count == ARRAY_SIZE(vb->vmas))
-		unlink_file_vma_batch_process(vb);
-
-	vb->vmas[vb->count] = vma;
-	vb->count++;
-}
-
-void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb)
-{
-	if (vb->count > 0)
-		unlink_file_vma_batch_process(vb);
-}
-
-/*
- * Close a vm structure and free it.
- */
-static void remove_vma(struct vm_area_struct *vma, bool unreachable)
-{
-	might_sleep();
-	if (vma->vm_ops && vma->vm_ops->close)
-		vma->vm_ops->close(vma);
-	if (vma->vm_file)
-		fput(vma->vm_file);
-	mpol_put(vma_policy(vma));
-	if (unreachable)
-		__vm_area_free(vma);
-	else
-		vm_area_free(vma);
-}
-
-static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi,
-						    unsigned long min)
-{
-	return mas_prev(&vmi->mas, min);
-}
-
-/*
  * check_brk_limits() - Use platform specific check of range & verify mlock
  * limits.
  * @addr: The address to check
@@ -318,875 +214,6 @@ out:
 	return origbrk;
 }
 
-#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
-static void validate_mm(struct mm_struct *mm)
-{
-	int bug = 0;
-	int i = 0;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	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)
-				anon_vma_interval_tree_verify(avc);
-			anon_vma_unlock_read(anon_vma);
-		}
-#endif
-		i++;
-	}
-	if (i != mm->map_count) {
-		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(mm) do { } while (0)
-#endif /* CONFIG_DEBUG_VM_MAPLE_TREE */
-
-/*
- * vma has some anon_vma assigned, and is already inserted on that
- * anon_vma's interval trees.
- *
- * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the
- * vma must be removed from the anon_vma's interval trees using
- * anon_vma_interval_tree_pre_update_vma().
- *
- * After the update, the vma will be reinserted using
- * anon_vma_interval_tree_post_update_vma().
- *
- * The entire update must be protected by exclusive mmap_lock and by
- * the root anon_vma's mutex.
- */
-static inline void
-anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma)
-{
-	struct anon_vma_chain *avc;
-
-	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
-		anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root);
-}
-
-static inline void
-anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
-{
-	struct anon_vma_chain *avc;
-
-	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
-		anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
-}
-
-static unsigned long count_vma_pages_range(struct mm_struct *mm,
-		unsigned long addr, unsigned long end)
-{
-	VMA_ITERATOR(vmi, mm, addr);
-	struct vm_area_struct *vma;
-	unsigned long nr_pages = 0;
-
-	for_each_vma_range(vmi, vma, end) {
-		unsigned long vm_start = max(addr, vma->vm_start);
-		unsigned long vm_end = min(end, vma->vm_end);
-
-		nr_pages += PHYS_PFN(vm_end - vm_start);
-	}
-
-	return nr_pages;
-}
-
-static void __vma_link_file(struct vm_area_struct *vma,
-			    struct address_space *mapping)
-{
-	if (vma_is_shared_maywrite(vma))
-		mapping_allow_writable(mapping);
-
-	flush_dcache_mmap_lock(mapping);
-	vma_interval_tree_insert(vma, &mapping->i_mmap);
-	flush_dcache_mmap_unlock(mapping);
-}
-
-static void vma_link_file(struct vm_area_struct *vma)
-{
-	struct file *file = vma->vm_file;
-	struct address_space *mapping;
-
-	if (file) {
-		mapping = file->f_mapping;
-		i_mmap_lock_write(mapping);
-		__vma_link_file(vma, mapping);
-		i_mmap_unlock_write(mapping);
-	}
-}
-
-static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma)
-{
-	VMA_ITERATOR(vmi, mm, 0);
-
-	vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
-	if (vma_iter_prealloc(&vmi, vma))
-		return -ENOMEM;
-
-	vma_start_write(vma);
-	vma_iter_store(&vmi, vma);
-	vma_link_file(vma);
-	mm->map_count++;
-	validate_mm(mm);
-	return 0;
-}
-
-/*
- * init_multi_vma_prep() - Initializer for struct vma_prepare
- * @vp: The vma_prepare struct
- * @vma: The vma that will be altered once locked
- * @next: The next vma if it is to be adjusted
- * @remove: The first vma to be removed
- * @remove2: The second vma to be removed
- */
-static inline void init_multi_vma_prep(struct vma_prepare *vp,
-		struct vm_area_struct *vma, struct vm_area_struct *next,
-		struct vm_area_struct *remove, struct vm_area_struct *remove2)
-{
-	memset(vp, 0, sizeof(struct vma_prepare));
-	vp->vma = vma;
-	vp->anon_vma = vma->anon_vma;
-	vp->remove = remove;
-	vp->remove2 = remove2;
-	vp->adj_next = next;
-	if (!vp->anon_vma && next)
-		vp->anon_vma = next->anon_vma;
-
-	vp->file = vma->vm_file;
-	if (vp->file)
-		vp->mapping = vma->vm_file->f_mapping;
-
-}
-
-/*
- * init_vma_prep() - Initializer wrapper for vma_prepare struct
- * @vp: The vma_prepare struct
- * @vma: The vma that will be altered once locked
- */
-static inline void init_vma_prep(struct vma_prepare *vp,
-				 struct vm_area_struct *vma)
-{
-	init_multi_vma_prep(vp, vma, NULL, NULL, NULL);
-}
-
-
-/*
- * vma_prepare() - Helper function for handling locking VMAs prior to altering
- * @vp: The initialized vma_prepare struct
- */
-static inline void vma_prepare(struct vma_prepare *vp)
-{
-	if (vp->file) {
-		uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end);
-
-		if (vp->adj_next)
-			uprobe_munmap(vp->adj_next, vp->adj_next->vm_start,
-				      vp->adj_next->vm_end);
-
-		i_mmap_lock_write(vp->mapping);
-		if (vp->insert && vp->insert->vm_file) {
-			/*
-			 * Put into interval tree now, so instantiated pages
-			 * are visible to arm/parisc __flush_dcache_page
-			 * throughout; but we cannot insert into address
-			 * space until vma start or end is updated.
-			 */
-			__vma_link_file(vp->insert,
-					vp->insert->vm_file->f_mapping);
-		}
-	}
-
-	if (vp->anon_vma) {
-		anon_vma_lock_write(vp->anon_vma);
-		anon_vma_interval_tree_pre_update_vma(vp->vma);
-		if (vp->adj_next)
-			anon_vma_interval_tree_pre_update_vma(vp->adj_next);
-	}
-
-	if (vp->file) {
-		flush_dcache_mmap_lock(vp->mapping);
-		vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap);
-		if (vp->adj_next)
-			vma_interval_tree_remove(vp->adj_next,
-						 &vp->mapping->i_mmap);
-	}
-
-}
-
-/*
- * vma_complete- Helper function for handling the unlocking after altering VMAs,
- * or for inserting a VMA.
- *
- * @vp: The vma_prepare struct
- * @vmi: The vma iterator
- * @mm: The mm_struct
- */
-static inline void vma_complete(struct vma_prepare *vp,
-				struct vma_iterator *vmi, struct mm_struct *mm)
-{
-	if (vp->file) {
-		if (vp->adj_next)
-			vma_interval_tree_insert(vp->adj_next,
-						 &vp->mapping->i_mmap);
-		vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap);
-		flush_dcache_mmap_unlock(vp->mapping);
-	}
-
-	if (vp->remove && vp->file) {
-		__remove_shared_vm_struct(vp->remove, vp->mapping);
-		if (vp->remove2)
-			__remove_shared_vm_struct(vp->remove2, vp->mapping);
-	} else if (vp->insert) {
-		/*
-		 * split_vma has split insert from vma, and needs
-		 * us to insert it before dropping the locks
-		 * (it may either follow vma or precede it).
-		 */
-		vma_iter_store(vmi, vp->insert);
-		mm->map_count++;
-	}
-
-	if (vp->anon_vma) {
-		anon_vma_interval_tree_post_update_vma(vp->vma);
-		if (vp->adj_next)
-			anon_vma_interval_tree_post_update_vma(vp->adj_next);
-		anon_vma_unlock_write(vp->anon_vma);
-	}
-
-	if (vp->file) {
-		i_mmap_unlock_write(vp->mapping);
-		uprobe_mmap(vp->vma);
-
-		if (vp->adj_next)
-			uprobe_mmap(vp->adj_next);
-	}
-
-	if (vp->remove) {
-again:
-		vma_mark_detached(vp->remove, true);
-		if (vp->file) {
-			uprobe_munmap(vp->remove, vp->remove->vm_start,
-				      vp->remove->vm_end);
-			fput(vp->file);
-		}
-		if (vp->remove->anon_vma)
-			anon_vma_merge(vp->vma, vp->remove);
-		mm->map_count--;
-		mpol_put(vma_policy(vp->remove));
-		if (!vp->remove2)
-			WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end);
-		vm_area_free(vp->remove);
-
-		/*
-		 * In mprotect's case 6 (see comments on vma_merge),
-		 * we are removing both mid and next vmas
-		 */
-		if (vp->remove2) {
-			vp->remove = vp->remove2;
-			vp->remove2 = NULL;
-			goto again;
-		}
-	}
-	if (vp->insert && vp->file)
-		uprobe_mmap(vp->insert);
-	validate_mm(mm);
-}
-
-/*
- * dup_anon_vma() - Helper function to duplicate anon_vma
- * @dst: The destination VMA
- * @src: The source VMA
- * @dup: Pointer to the destination VMA when successful.
- *
- * Returns: 0 on success.
- */
-static inline int dup_anon_vma(struct vm_area_struct *dst,
-		struct vm_area_struct *src, struct vm_area_struct **dup)
-{
-	/*
-	 * Easily overlooked: when mprotect shifts the boundary, make sure the
-	 * expanding vma has anon_vma set if the shrinking vma had, to cover any
-	 * anon pages imported.
-	 */
-	if (src->anon_vma && !dst->anon_vma) {
-		int ret;
-
-		vma_assert_write_locked(dst);
-		dst->anon_vma = src->anon_vma;
-		ret = anon_vma_clone(dst, src);
-		if (ret)
-			return ret;
-
-		*dup = dst;
-	}
-
-	return 0;
-}
-
-/*
- * vma_expand - Expand an existing VMA
- *
- * @vmi: The vma iterator
- * @vma: The vma to expand
- * @start: The start of the vma
- * @end: The exclusive end of the vma
- * @pgoff: The page offset of vma
- * @next: The current of next vma.
- *
- * Expand @vma to @start and @end.  Can expand off the start and end.  Will
- * expand over @next if it's different from @vma and @end == @next->vm_end.
- * Checking if the @vma can expand and merge with @next needs to be handled by
- * the caller.
- *
- * Returns: 0 on success
- */
-int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
-	       unsigned long start, unsigned long end, pgoff_t pgoff,
-	       struct vm_area_struct *next)
-{
-	struct vm_area_struct *anon_dup = NULL;
-	bool remove_next = false;
-	struct vma_prepare vp;
-
-	vma_start_write(vma);
-	if (next && (vma != next) && (end == next->vm_end)) {
-		int ret;
-
-		remove_next = true;
-		vma_start_write(next);
-		ret = dup_anon_vma(vma, next, &anon_dup);
-		if (ret)
-			return ret;
-	}
-
-	init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL);
-	/* Not merging but overwriting any part of next is not handled. */
-	VM_WARN_ON(next && !vp.remove &&
-		  next != vma && end > next->vm_start);
-	/* Only handles expanding */
-	VM_WARN_ON(vma->vm_start < start || vma->vm_end > end);
-
-	/* 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_set_range(vma, start, end, pgoff);
-	vma_iter_store(vmi, vma);
-
-	vma_complete(&vp, vmi, vma->vm_mm);
-	return 0;
-
-nomem:
-	if (anon_dup)
-		unlink_anon_vmas(anon_dup);
-	return -ENOMEM;
-}
-
-/*
- * vma_shrink() - Reduce an existing VMAs memory area
- * @vmi: The vma iterator
- * @vma: The VMA to modify
- * @start: The new start
- * @end: The new end
- *
- * Returns: 0 on success, -ENOMEM otherwise
- */
-int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
-	       unsigned long start, unsigned long end, pgoff_t pgoff)
-{
-	struct vma_prepare vp;
-
-	WARN_ON((vma->vm_start != start) && (vma->vm_end != end));
-
-	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;
-
-	vma_start_write(vma);
-
-	init_vma_prep(&vp, vma);
-	vma_prepare(&vp);
-	vma_adjust_trans_huge(vma, start, end, 0);
-
-	vma_iter_clear(vmi);
-	vma_set_range(vma, start, end, pgoff);
-	vma_complete(&vp, vmi, vma->vm_mm);
-	return 0;
-}
-
-/*
- * If the vma has a ->close operation then the driver probably needs to release
- * per-vma resources, so we don't attempt to merge those if the caller indicates
- * the current vma may be removed as part of the merge.
- */
-static inline bool is_mergeable_vma(struct vm_area_struct *vma,
-		struct file *file, unsigned long vm_flags,
-		struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
-		struct anon_vma_name *anon_name, bool may_remove_vma)
-{
-	/*
-	 * VM_SOFTDIRTY should not prevent from VMA merging, if we
-	 * match the flags but dirty bit -- the caller should mark
-	 * merged VMA as dirty. If dirty bit won't be excluded from
-	 * comparison, we increase pressure on the memory system forcing
-	 * the kernel to generate new VMAs when old one could be
-	 * extended instead.
-	 */
-	if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY)
-		return false;
-	if (vma->vm_file != file)
-		return false;
-	if (may_remove_vma && vma->vm_ops && vma->vm_ops->close)
-		return false;
-	if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
-		return false;
-	if (!anon_vma_name_eq(anon_vma_name(vma), anon_name))
-		return false;
-	return true;
-}
-
-static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1,
-		 struct anon_vma *anon_vma2, struct vm_area_struct *vma)
-{
-	/*
-	 * The list_is_singular() test is to avoid merging VMA cloned from
-	 * parents. This can improve scalability caused by anon_vma lock.
-	 */
-	if ((!anon_vma1 || !anon_vma2) && (!vma ||
-		list_is_singular(&vma->anon_vma_chain)))
-		return true;
-	return anon_vma1 == anon_vma2;
-}
-
-/*
- * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
- * in front of (at a lower virtual address and file offset than) the vma.
- *
- * We cannot merge two vmas if they have differently assigned (non-NULL)
- * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
- *
- * We don't check here for the merged mmap wrapping around the end of pagecache
- * indices (16TB on ia32) because do_mmap() does not permit mmap's which
- * wrap, nor mmaps which cover the final page at index -1UL.
- *
- * We assume the vma may be removed as part of the merge.
- */
-static bool
-can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
-		struct anon_vma *anon_vma, struct file *file,
-		pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
-		struct anon_vma_name *anon_name)
-{
-	if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, true) &&
-	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
-		if (vma->vm_pgoff == vm_pgoff)
-			return true;
-	}
-	return false;
-}
-
-/*
- * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
- * beyond (at a higher virtual address and file offset than) the vma.
- *
- * We cannot merge two vmas if they have differently assigned (non-NULL)
- * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
- *
- * We assume that vma is not removed as part of the merge.
- */
-static bool
-can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
-		struct anon_vma *anon_vma, struct file *file,
-		pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfau