mm: perform VMA allocation, freeing, duplication in mm

Right now these are performed in kernel/fork.c which is odd and a
violation of separation of concerns, as well as preventing us from
integrating this and related logic into userland VMA testing going
forward.

There is a fly in the ointment - nommu - mmap.c is not compiled if
CONFIG_MMU not set, and neither is vma.c.

To square the circle, let's add a new file - vma_init.c.  This will be
compiled for both CONFIG_MMU and nommu builds, and will also form part of
the VMA userland testing.

This allows us to de-duplicate code, while maintaining separation of
concerns and the ability for us to userland test this logic.

Update the VMA userland tests accordingly, additionally adding a
detach_free_vma() helper function to correctly detach VMAs before freeing
them in test code, as this change was triggering the assert for this.

[akpm@linux-foundation.org: remove stray newline, per Liam]
Link: https://lkml.kernel.org/r/f97b3a85a6da0196b28070df331b99e22b263be8.1745853549.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 136 insertions, 35 deletions

diff --git a/tools/testing/vma/Makefile b/tools/testing/vma/Makefile
index 624040fcf193..66f3831a668f 100644
--- a/tools/testing/vma/Makefile
+++ b/tools/testing/vma/Makefile
@@ -9,7 +9,7 @@ include ../shared/shared.mk
 OFILES = $(SHARED_OFILES) vma.o maple-shim.o
 TARGETS = vma
 
-vma.o: vma.c vma_internal.h ../../../mm/vma.c ../../../mm/vma_exec.c ../../../mm/vma.h
+vma.o: vma.c vma_internal.h ../../../mm/vma.c ../../../mm/vma_init.c ../../../mm/vma_exec.c ../../../mm/vma.h
 
 vma:	$(OFILES)
 	$(CC) $(CFLAGS) -o $@ $(OFILES) $(LDLIBS)
diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c
index 5832ae5d797d..2be7597a2ac2 100644
--- a/tools/testing/vma/vma.c
+++ b/tools/testing/vma/vma.c
@@ -28,6 +28,7 @@ unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
  * Directly import the VMA implementation here. Our vma_internal.h wrapper
  * provides userland-equivalent functionality for everything vma.c uses.
  */
+#include "../../../mm/vma_init.c"
 #include "../../../mm/vma_exec.c"
 #include "../../../mm/vma.c"
 
@@ -91,6 +92,12 @@ static int attach_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 	return res;
 }
 
+static void detach_free_vma(struct vm_area_struct *vma)
+{
+	vma_mark_detached(vma);
+	vm_area_free(vma);
+}
+
 /* Helper function to allocate a VMA and link it to the tree. */
 static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
 						 unsigned long start,
@@ -104,7 +111,7 @@ static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
 		return NULL;
 
 	if (attach_vma(mm, vma)) {
-		vm_area_free(vma);
+		detach_free_vma(vma);
 		return NULL;
 	}
 
@@ -249,7 +256,7 @@ static int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi)
 
 	vma_iter_set(vmi, 0);
 	for_each_vma(*vmi, vma) {
-		vm_area_free(vma);
+		detach_free_vma(vma);
 		count++;
 	}
 
@@ -319,7 +326,7 @@ static bool test_simple_merge(void)
 	ASSERT_EQ(vma->vm_pgoff, 0);
 	ASSERT_EQ(vma->vm_flags, flags);
 
-	vm_area_free(vma);
+	detach_free_vma(vma);
 	mtree_destroy(&mm.mm_mt);
 
 	return true;
@@ -361,7 +368,7 @@ static bool test_simple_modify(void)
 	ASSERT_EQ(vma->vm_end, 0x1000);
 	ASSERT_EQ(vma->vm_pgoff, 0);
 
-	vm_area_free(vma);
+	detach_free_vma(vma);
 	vma_iter_clear(&vmi);
 
 	vma = vma_next(&vmi);
@@ -370,7 +377,7 @@ static bool test_simple_modify(void)
 	ASSERT_EQ(vma->vm_end, 0x2000);
 	ASSERT_EQ(vma->vm_pgoff, 1);
 
-	vm_area_free(vma);
+	detach_free_vma(vma);
 	vma_iter_clear(&vmi);
 
 	vma = vma_next(&vmi);
@@ -379,7 +386,7 @@ static bool test_simple_modify(void)
 	ASSERT_EQ(vma->vm_end, 0x3000);
 	ASSERT_EQ(vma->vm_pgoff, 2);
 
-	vm_area_free(vma);
+	detach_free_vma(vma);
 	mtree_destroy(&mm.mm_mt);
 
 	return true;
@@ -407,7 +414,7 @@ static bool test_simple_expand(void)
 	ASSERT_EQ(vma->vm_end, 0x3000);
 	ASSERT_EQ(vma->vm_pgoff, 0);
 
-	vm_area_free(vma);
+	detach_free_vma(vma);
 	mtree_destroy(&mm.mm_mt);
 
 	return true;
@@ -428,7 +435,7 @@ static bool test_simple_shrink(void)
 	ASSERT_EQ(vma->vm_end, 0x1000);
 	ASSERT_EQ(vma->vm_pgoff, 0);
 
-	vm_area_free(vma);
+	detach_free_vma(vma);
 	mtree_destroy(&mm.mm_mt);
 
 	return true;
@@ -619,7 +626,7 @@ static bool test_merge_new(void)
 		ASSERT_EQ(vma->vm_pgoff, 0);
 		ASSERT_EQ(vma->anon_vma, &dummy_anon_vma);
 
-		vm_area_free(vma);
+		detach_free_vma(vma);
 		count++;
 	}
 
@@ -1668,6 +1675,7 @@ int main(void)
 	int num_tests = 0, num_fail = 0;
 
 	maple_tree_init();
+	vma_state_init();
 
 #define TEST(name)							\
 	do {								\
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 32e990313158..198abe66de5a 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -155,6 +155,10 @@ typedef __bitwise unsigned int vm_fault_t;
  */
 #define pr_warn_once pr_err
 
+#define data_race(expr) expr
+
+#define ASSERT_EXCLUSIVE_WRITER(x)
+
 struct kref {
 	refcount_t refcount;
 };
@@ -255,6 +259,8 @@ struct file {
 
 #define VMA_LOCK_OFFSET	0x40000000
 
+typedef struct { unsigned long v; } freeptr_t;
+
 struct vm_area_struct {
 	/* The first cache line has the info for VMA tree walking. */
 
@@ -264,9 +270,7 @@ struct vm_area_struct {
 			unsigned long vm_start;
 			unsigned long vm_end;
 		};
-#ifdef CONFIG_PER_VMA_LOCK
-		struct rcu_head vm_rcu;	/* Used for deferred freeing. */
-#endif
+		freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */
 	};
 
 	struct mm_struct *vm_mm;	/* The address space we belong to. */
@@ -463,6 +467,65 @@ struct pagetable_move_control {
 		.len_in = len_,						\
 	}
 
+struct kmem_cache_args {
+	/**
+	 * @align: The required alignment for the objects.
+	 *
+	 * %0 means no specific alignment is requested.
+	 */
+	unsigned int align;
+	/**
+	 * @useroffset: Usercopy region offset.
+	 *
+	 * %0 is a valid offset, when @usersize is non-%0
+	 */
+	unsigned int useroffset;
+	/**
+	 * @usersize: Usercopy region size.
+	 *
+	 * %0 means no usercopy region is specified.
+	 */
+	unsigned int usersize;
+	/**
+	 * @freeptr_offset: Custom offset for the free pointer
+	 * in &SLAB_TYPESAFE_BY_RCU caches
+	 *
+	 * By default &SLAB_TYPESAFE_BY_RCU caches place the free pointer
+	 * outside of the object. This might cause the object to grow in size.
+	 * Cache creators that have a reason to avoid this can specify a custom
+	 * free pointer offset in their struct where the free pointer will be
+	 * placed.
+	 *
+	 * Note that placing the free pointer inside the object requires the
+	 * caller to ensure that no fields are invalidated that are required to
+	 * guard against object recycling (See &SLAB_TYPESAFE_BY_RCU for
+	 * details).
+	 *
+	 * Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset
+	 * is specified, %use_freeptr_offset must be set %true.
+	 *
+	 * Note that @ctor currently isn't supported with custom free pointers
+	 * as a @ctor requires an external free pointer.
+	 */
+	unsigned int freeptr_offset;
+	/**
+	 * @use_freeptr_offset: Whether a @freeptr_offset is used.
+	 */
+	bool use_freeptr_offset;
+	/**
+	 * @ctor: A constructor for the objects.
+	 *
+	 * The constructor is invoked for each object in a newly allocated slab
+	 * page. It is the cache user's responsibility to free object in the
+	 * same state as after calling the constructor, or deal appropriately
+	 * with any differences between a freshly constructed and a reallocated
+	 * object.
+	 *
+	 * %NULL means no constructor.
+	 */
+	void (*ctor)(void *);
+};
+
 static inline void vma_iter_invalidate(struct vma_iterator *vmi)
 {
 	mas_pause(&vmi->mas);
@@ -547,31 +610,38 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 	vma->vm_lock_seq = UINT_MAX;
 }
 
-static inline struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
-{
-	struct vm_area_struct *vma = calloc(1, sizeof(struct vm_area_struct));
+struct kmem_cache {
+	const char *name;
+	size_t object_size;
+	struct kmem_cache_args *args;
+};
 
-	if (!vma)
-		return NULL;
+static inline struct kmem_cache *__kmem_cache_create(const char *name,
+						     size_t object_size,
+						     struct kmem_cache_args *args)
+{
+	struct kmem_cache *ret = malloc(sizeof(struct kmem_cache));
 
-	vma_init(vma, mm);
+	ret->name = name;
+	ret->object_size = object_size;
+	ret->args = args;
 
-	return vma;
+	return ret;
 }
 
-static inline struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
-{
-	struct vm_area_struct *new = calloc(1, sizeof(struct vm_area_struct));
+#define kmem_cache_create(__name, __object_size, __args, ...)           \
+	__kmem_cache_create((__name), (__object_size), (__args))
 
-	if (!new)
-		return NULL;
+static inline void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
+{
+	(void)gfpflags;
 
-	memcpy(new, orig, sizeof(*new));
-	refcount_set(&new->vm_refcnt, 0);
-	new->vm_lock_seq = UINT_MAX;
-	INIT_LIST_HEAD(&new->anon_vma_chain);
+	return calloc(s->object_size, 1);
+}
 
-	return new;
+static inline void kmem_cache_free(struct kmem_cache *s, void *x)
+{
+	free(x);
 }
 
 /*
@@ -738,11 +808,6 @@ static inline void mpol_put(struct mempolicy *)
 {
 }
 
-static inline void vm_area_free(struct vm_area_struct *vma)
-{
-	free(vma);
-}
-
 static inline void lru_add_drain(void)
 {
 }
@@ -1312,4 +1377,32 @@ static inline void ksm_exit(struct mm_struct *mm)
 	(void)mm;
 }
 
+static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt)
+{
+	(void)vma;
+	(void)reset_refcnt;
+}
+
+static inline void vma_numab_state_init(struct vm_area_struct *vma)
+{
+	(void)vma;
+}
+
+static inline void vma_numab_state_free(struct vm_area_struct *vma)
+{
+	(void)vma;
+}
+
+static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
+				     struct vm_area_struct *new_vma)
+{
+	(void)orig_vma;
+	(void)new_vma;
+}
+
+static inline void free_anon_vma_name(struct vm_area_struct *vma)
+{
+	(void)vma;
+}
+
 #endif	/* __MM_VMA_INTERNAL_H */