path: root/tools/testing/vma/vma_internal.h

/* SPDX-License-Identifier: GPL-2.0+ */
/*
 * vma_internal.h
 *
 * Header providing userland wrappers and shims for the functionality provided
 * by mm/vma_internal.h.
 *
 * We make the header guard the same as mm/vma_internal.h, so if this shim
 * header is included, it precludes the inclusion of the kernel one.
 */

#ifndef __MM_VMA_INTERNAL_H
#define __MM_VMA_INTERNAL_H

#define __private
#define __bitwise
#define __randomize_layout

#define CONFIG_MMU
#define CONFIG_PER_VMA_LOCK

#include <stdlib.h>

#include <linux/atomic.h>
#include <linux/list.h>
#include <linux/maple_tree.h>
#include <linux/mm.h>
#include <linux/rbtree.h>
#include <linux/refcount.h>
#include <linux/slab.h>

extern unsigned long stack_guard_gap;
#ifdef CONFIG_MMU
extern unsigned long mmap_min_addr;
extern unsigned long dac_mmap_min_addr;
#else
#define mmap_min_addr		0UL
#define dac_mmap_min_addr	0UL
#endif

#define VM_WARN_ON(_expr) (WARN_ON(_expr))
#define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr))
#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr))
#define VM_BUG_ON(_expr) (BUG_ON(_expr))
#define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr))

#define MMF_HAS_MDWE	28

#define VM_NONE		0x00000000
#define VM_READ		0x00000001
#define VM_WRITE	0x00000002
#define VM_EXEC		0x00000004
#define VM_SHARED	0x00000008
#define VM_MAYREAD	0x00000010
#define VM_MAYWRITE	0x00000020
#define VM_MAYEXEC	0x00000040
#define VM_GROWSDOWN	0x00000100
#define VM_PFNMAP	0x00000400
#define VM_LOCKED	0x00002000
#define VM_IO           0x00004000
#define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
#define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */
#define VM_DONTEXPAND	0x00040000
#define VM_LOCKONFAULT	0x00080000
#define VM_ACCOUNT	0x00100000
#define VM_NORESERVE	0x00200000
#define VM_MIXEDMAP	0x10000000
#define VM_STACK	VM_GROWSDOWN
#define VM_SHADOW_STACK	VM_NONE
#define VM_SOFTDIRTY	0
#define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
#define VM_GROWSUP	VM_NONE

#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)

#ifdef CONFIG_STACK_GROWSUP
#define VM_STACK	VM_GROWSUP
#define VM_STACK_EARLY	VM_GROWSDOWN
#else
#define VM_STACK	VM_GROWSDOWN
#define VM_STACK_EARLY	0
#endif

#define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)
#define TASK_SIZE_LOW		DEFAULT_MAP_WINDOW
#define TASK_SIZE_MAX		DEFAULT_MAP_WINDOW
#define STACK_TOP		TASK_SIZE_LOW
#define STACK_TOP_MAX		TASK_SIZE_MAX

/* This mask represents all the VMA flag bits used by mlock */
#define VM_LOCKED_MASK	(VM_LOCKED | VM_LOCKONFAULT)

#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)

#define VM_DATA_FLAGS_TSK_EXEC	(VM_READ | VM_WRITE | TASK_EXEC | \
				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)

#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC

#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)

#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
#define VM_STACK_FLAGS	(VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)

#define RLIMIT_STACK		3	/* max stack size */
#define RLIMIT_MEMLOCK		8	/* max locked-in-memory address space */

#define CAP_IPC_LOCK         14

#ifdef CONFIG_64BIT
#define VM_SEALED_BIT	42
#define VM_SEALED	BIT(VM_SEALED_BIT)
#else
#define VM_SEALED	VM_NONE
#endif

#define FIRST_USER_ADDRESS	0UL
#define USER_PGTABLES_CEILING	0UL

#define vma_policy(vma) NULL

#define down_write_nest_lock(sem, nest_lock)

#define pgprot_val(x)		((x).pgprot)
#define __pgprot(x)		((pgprot_t) { (x) } )

#define for_each_vma(__vmi, __vma)					\
	while (((__vma) = vma_next(&(__vmi))) != NULL)

/* The MM code likes to work with exclusive end addresses */
#define for_each_vma_range(__vmi, __vma, __end)				\
	while (((__vma) = vma_find(&(__vmi), (__end))) != NULL)

#define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)

#define PHYS_PFN(x)	((unsigned long)((x) >> PAGE_SHIFT))

#define test_and_set_bit(nr, addr) __test_and_set_bit(nr, addr)
#define test_and_clear_bit(nr, addr) __test_and_clear_bit(nr, addr)

#define TASK_SIZE ((1ul << 47)-PAGE_SIZE)

#define AS_MM_ALL_LOCKS 2

/* We hardcode this for now. */
#define sysctl_max_map_count 0x1000000UL

#define pgoff_t unsigned long
typedef unsigned long	pgprotval_t;
typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
typedef unsigned long vm_flags_t;
typedef __bitwise unsigned int vm_fault_t;

/*
 * The shared stubs do not implement this, it amounts to an fprintf(STDERR,...)
 * either way :)
 */
#define pr_warn_once pr_err

#define data_race(expr) expr

#define ASSERT_EXCLUSIVE_WRITER(x)

/**
 * swap - swap values of @a and @b
 * @a: first value
 * @b: second value
 */
#define swap(a, b) \
	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)

struct kref {
	refcount_t refcount;
};

/*
 * Define the task command name length as enum, then it can be visible to
 * BPF programs.
 */
enum {
	TASK_COMM_LEN = 16,
};

/*
 * Flags for bug emulation.
 *
 * These occupy the top three bytes.
 */
enum {
	READ_IMPLIES_EXEC =	0x0400000,
};

struct task_struct {
	char comm[TASK_COMM_LEN];
	pid_t pid;
	struct mm_struct *mm;

	/* Used for emulating ABI behavior of previous Linux versions: */
	unsigned int			personality;
};

struct task_struct *get_current(void);
#define current get_current()

struct anon_vma {
	struct anon_vma *root;
	struct rb_root_cached rb_root;

	/* Test fields. */
	bool was_cloned;
	bool was_unlinked;
};

struct anon_vma_chain {
	struct anon_vma *anon_vma;
	struct list_head same_vma;
};

struct anon_vma_name {
	struct kref kref;
	/* The name needs to be at the end because it is dynamically sized. */
	char name[];
};

struct vma_iterator {
	struct ma_state mas;
};

#define VMA_ITERATOR(name, __mm, __addr)				\
	struct vma_iterator name = {					\
		.mas = {						\
			.tree = &(__mm)->mm_mt,				\
			.index = __addr,				\
			.node = NULL,					\
			.status = ma_start,				\
		},							\
	}

struct address_space {
	struct rb_root_cached	i_mmap;
	unsigned long		flags;
	atomic_t		i_mmap_writable;
};

struct vm_userfaultfd_ctx {};
struct mempolicy {};
struct mmu_gather {};
struct mutex {};
#define DEFINE_MUTEX(mutexname) \
	struct mutex mutexname = {}

#define DECLARE_BITMAP(name, bits) \
	unsigned long name[BITS_TO_LONGS(bits)]

#define NUM_MM_FLAG_BITS (64)
typedef struct {
	__private DECLARE_BITMAP(__mm_flags, NUM_MM_FLAG_BITS);
} mm_flags_t;

struct mm_struct {
	struct maple_tree mm_mt;
	int map_count;			/* number of VMAs */
	unsigned long total_vm;	   /* Total pages mapped */
	unsigned long locked_vm;   /* Pages that have PG_mlocked set */
	unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
	unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
	unsigned long stack_vm;	   /* VM_STACK */

	unsigned long def_flags;

	mm_flags_t flags; /* Must use mm_flags_* helpers to access */
};

struct vm_area_struct;

/*
 * Describes a VMA that is about to be mmap()'ed. Drivers may choose to
 * manipulate mutable fields which will cause those fields to be updated in the
 * resultant VMA.
 *
 * Helper functions are not required for manipulating any field.
 */
struct vm_area_desc {
	/* Immutable state. */
	const struct mm_struct *const mm;
	struct file *const file; /* May vary from vm_file in stacked callers. */
	unsigned long start;
	unsigned long end;

	/* Mutable fields. Populated with initial state. */
	pgoff_t pgoff;
	struct file *vm_file;
	vm_flags_t vm_flags;
	pgprot_t page_prot;

	/* Write-only fields. */
	const struct vm_operations_struct *vm_ops;
	void *private_data;
};

struct file_operations {
	int (*mmap)(struct file *, struct vm_area_struct *);
	int (*mmap_prepare)(struct vm_area_desc *);
};

struct file {
	struct address_space	*f_mapping;
	const struct file_operations	*f_op;
};

#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. */

	union {
		struct {
			/* VMA covers [vm_start; vm_end) addresses within mm */
			unsigned long vm_start;
			unsigned long vm_end;
		};
		freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */
	};

	struct mm_struct *vm_mm;	/* The address space we belong to. */
	pgprot_t vm_page_prot;          /* Access permissions of this VMA. */

	/*
	 * Flags, see mm.h.
	 * To modify use vm_flags_{init|reset|set|clear|mod} functions.
	 */
	union {
		const vm_flags_t vm_flags;
		vm_flags_t __private __vm_flags;
	};

#ifdef CONFIG_PER_VMA_LOCK
	/*
	 * Can only be written (using WRITE_ONCE()) while holding both:
	 *  - mmap_lock (in write mode)
	 *  - vm_refcnt bit at VMA_LOCK_OFFSET is set
	 * Can be read reliably while holding one of:
	 *  - mmap_lock (in read or write mode)
	 *  - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1
	 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
	 * while holding nothing (except RCU to keep the VMA struct allocated).
	 *
	 * This sequence counter is explicitly allowed to overflow; sequence
	 * counter reuse can only lead to occasional unnecessary use of the
	 * slowpath.
	 */
	unsigned int vm_lock_seq;
#endif

	/*
	 * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
	 * list, after a COW of one of the file pages.	A MAP_SHARED vma
	 * can only be in the i_mmap tree.  An anonymous MAP_PRIVATE, stack
	 * or brk vma (with NULL file) can only be in an anon_vma list.
	 */
	struct list_head anon_vma_chain; /* Serialized by mmap_lock &
					  * page_table_lock */
	struct anon_vma *anon_vma;	/* Serialized by page_table_lock */

	/* Function pointers to deal with this struct. */
	const struct vm_operations_struct *vm_ops;

	/* Information about our backing store: */
	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
					   units */
	struct file * vm_file;		/* File we map to (can be NULL). */
	void * vm_private_data;		/* was vm_pte (shared mem) */

#ifdef CONFIG_SWAP
	atomic_long_t swap_readahead_info;
#endif
#ifndef CONFIG_MMU
	struct vm_region *vm_region;	/* NOMMU mapping region */
#endif
#ifdef CONFIG_NUMA
	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
#endif
#ifdef CONFIG_NUMA_BALANCING
	struct vma_numab_state *numab_state;	/* NUMA Balancing state */
#endif
#ifdef CONFIG_PER_VMA_LOCK
	/* Unstable RCU readers are allowed to read this. */
	refcount_t vm_refcnt;
#endif
	/*
	 * For areas with an address space and backing store,
	 * linkage into the address_space->i_mmap interval tree.
	 *
	 */
	struct {
		struct rb_node rb;
		unsigned long rb_subtree_last;
	} shared;
#ifdef CONFIG_ANON_VMA_NAME
	/*
	 * For private and shared anonymous mappings, a pointer to a null
	 * terminated string containing the name given to the vma, or NULL if
	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
	 */
	struct anon_vma_name *anon_name;
#endif
	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
} __randomize_layout;

struct vm_fault {};

struct vm_operations_struct {
	void (*open)(struct vm_area_struct * area);
	/**
	 * @close: Called when the VMA is being removed from the MM.
	 * Context: User context.  May sleep.  Caller holds mmap_lock.
	 */
	void (*close)(struct vm_area_struct * area);
	/* Called any time before splitting to check if it's allowed */
	int (*may_split)(struct vm_area_struct *area, unsigned long addr);
	int (*mremap)(struct vm_area_struct *area);
	/*
	 * Called by mprotect() to make driver-specific permission
	 * checks before mprotect() is finalised.   The VMA must not
	 * be modified.  Returns 0 if mprotect() can proceed.
	 */
	int (*mprotect)(struct vm_area_struct *vma, unsigned long start,
			unsigned long end, unsigned long newflags);
	vm_fault_t (*fault)(struct vm_fault *vmf);
	vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order);
	vm_fault_t (*map_pages)(struct vm_fault *vmf,
			pgoff_t start_pgoff, pgoff_t end_pgoff);
	unsigned long (*pagesize)(struct vm_area_struct * area);

	/* notification that a previous