path: root/kernel/futex/futex.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _FUTEX_H
#define _FUTEX_H

#include <linux/futex.h>
#include <linux/rtmutex.h>
#include <linux/sched/wake_q.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/cleanup.h>

#ifdef CONFIG_PREEMPT_RT
#include <linux/rcuwait.h>
#endif

#include <asm/futex.h>

/*
 * Futex flags used to encode options to functions and preserve them across
 * restarts.
 */
#define FLAGS_SIZE_8		0x0000
#define FLAGS_SIZE_16		0x0001
#define FLAGS_SIZE_32		0x0002
#define FLAGS_SIZE_64		0x0003

#define FLAGS_SIZE_MASK		0x0003

#ifdef CONFIG_MMU
# define FLAGS_SHARED		0x0010
#else
/*
 * NOMMU does not have per process address space. Let the compiler optimize
 * code away.
 */
# define FLAGS_SHARED		0x0000
#endif
#define FLAGS_CLOCKRT		0x0020
#define FLAGS_HAS_TIMEOUT	0x0040
#define FLAGS_NUMA		0x0080
#define FLAGS_STRICT		0x0100
#define FLAGS_MPOL		0x0200

/* FUTEX_ to FLAGS_ */
static inline unsigned int futex_to_flags(unsigned int op)
{
	unsigned int flags = FLAGS_SIZE_32;

	if (!(op & FUTEX_PRIVATE_FLAG))
		flags |= FLAGS_SHARED;

	if (op & FUTEX_CLOCK_REALTIME)
		flags |= FLAGS_CLOCKRT;

	return flags;
}

#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_MPOL | FUTEX2_PRIVATE)

/* FUTEX2_ to FLAGS_ */
static inline unsigned int futex2_to_flags(unsigned int flags2)
{
	unsigned int flags = flags2 & FUTEX2_SIZE_MASK;

	if (!(flags2 & FUTEX2_PRIVATE))
		flags |= FLAGS_SHARED;

	if (flags2 & FUTEX2_NUMA)
		flags |= FLAGS_NUMA;

	if (flags2 & FUTEX2_MPOL)
		flags |= FLAGS_MPOL;

	return flags;
}

static inline unsigned int futex_size(unsigned int flags)
{
	return 1 << (flags & FLAGS_SIZE_MASK);
}

static inline bool futex_flags_valid(unsigned int flags)
{
	/* Only 64bit futexes for 64bit code */
	if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) {
		if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64)
			return false;
	}

	/* Only 32bit futexes are implemented -- for now */
	if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32)
		return false;

	/*
	 * Must be able to represent both FUTEX_NO_NODE and every valid nodeid
	 * in a futex word.
	 */
	if (flags & FLAGS_NUMA) {
		int bits = 8 * futex_size(flags);
		u64 max = ~0ULL;

		max >>= 64 - bits;
		if (nr_node_ids >= max)
			return false;
	}

	return true;
}

static inline bool futex_validate_input(unsigned int flags, u64 val)
{
	int bits = 8 * futex_size(flags);

	if (bits < 64 && (val >> bits))
		return false;

	return true;
}

#ifdef CONFIG_FAIL_FUTEX
extern bool should_fail_futex(bool fshared);
#else
static inline bool should_fail_futex(bool fshared)
{
	return false;
}
#endif

/*
 * Hash buckets are shared by all the futex_keys that hash to the same
 * location.  Each key may have multiple futex_q structures, one for each task
 * waiting on a futex.
 */
struct futex_hash_bucket {
	atomic_t waiters;
	spinlock_t lock;
	struct plist_head chain;
	struct futex_private_hash *priv;
} ____cacheline_aligned_in_smp;

/*
 * Priority Inheritance state:
 */
struct futex_pi_state {
	/*
	 * list of 'owned' pi_state instances - these have to be
	 * cleaned up in do_exit() if the task exits prematurely:
	 */
	struct list_head list;

	/*
	 * The PI object:
	 */
	struct rt_mutex_base pi_mutex;

	struct task_struct *owner;
	refcount_t refcount;

	union futex_key key;
} __randomize_layout;

struct futex_q;
typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q);

/**
 * struct futex_q - The hashed futex queue entry, one per waiting task
 * @list:		priority-sorted list of tasks waiting on this futex
 * @task:		the task waiting on the futex
 * @lock_ptr:		the hash bucket lock
 * @wake:		the wake handler for this queue
 * @wake_data:		data associated with the wake handler
 * @key:		the key the futex is hashed on
 * @pi_state:		optional priority inheritance state
 * @rt_waiter:		rt_waiter storage for use with requeue_pi
 * @requeue_pi_key:	the requeue_pi target futex key
 * @bitset:		bitset for the optional bitmasked wakeup
 * @requeue_state:	State field for futex_requeue_pi()
 * @drop_hb_ref:	Waiter should drop the extra hash bucket reference if true
 * @requeue_wait:	RCU wait for futex_requeue_pi() (RT only)
 *
 * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so
 * we can wake only the relevant ones (hashed queues may be shared).
 *
 * A futex_q has a woken state, just like tasks have TASK_RUNNING.
 * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
 * The order of wakeup is always to make the first condition true, then
 * the second.
 *
 * PI futexes are typically woken before they are removed from the hash list via
 * the rt_mutex code. See futex_unqueue_pi().
 */
struct futex_q {
	struct plist_node list;

	struct task_struct *task;
	spinlock_t *lock_ptr;
	futex_wake_fn *wake;
	void *wake_data;
	union futex_key key;
	struct futex_pi_state *pi_state;
	struct rt_mutex_waiter *rt_waiter;
	union futex_key *requeue_pi_key;
	u32 bitset;
	atomic_t requeue_state;
	bool drop_hb_ref;
#ifdef CONFIG_PREEMPT_RT
	struct rcuwait requeue_wait;
#endif
} __randomize_layout;

extern const struct futex_q futex_q_init;

enum futex_access {
	FUTEX_READ,
	FUTEX_WRITE
};

extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
			 enum futex_access rw);
extern void futex_q_lockptr_lock(struct futex_q *q);
extern struct hrtimer_sleeper *
futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
		  int flags, u64 range_ns);

extern struct futex_hash_bucket *futex_hash(union futex_key *key);
#ifdef CONFIG_FUTEX_PRIVATE_HASH
extern void futex_hash_get(struct futex_hash_bucket *hb);
extern void futex_hash_put(struct futex_hash_bucket *hb);

extern struct futex_private_hash *futex_private_hash(void);
extern void futex_private_hash_put(struct futex_private_hash *fph);

#else /* !CONFIG_FUTEX_PRIVATE_HASH */
static inline void futex_hash_get(struct futex_hash_bucket *hb) { }
static inline void futex_hash_put(struct futex_hash_bucket *hb) { }
static inline struct futex_private_hash *futex_private_hash(void) { return NULL; }
static inline void futex_private_hash_put(struct futex_private_hash *fph) { }
#endif

DEFINE_CLASS(hb, struct futex_hash_bucket *,
	     if (_T) futex_hash_put(_T),
	     futex_hash(key), union futex_key *key);

DEFINE_CLASS(private_hash, struct futex_private_hash *,
	     if (_T) futex_private_hash_put(_T),
	     futex_private_hash(), void);

/**
 * futex_match - Check whether two futex keys are equal
 * @key1:	Pointer to key1
 * @key2:	Pointer to key2
 *
 * Return 1 if two futex_keys are equal, 0 otherwise.
 */
static inline int futex_match(union futex_key *key1, union futex_key *key2)
{
	return (key1 && key2
		&& key1->both.word == key2->both.word
		&& key1->both.ptr == key2->both.ptr
		&& key1->both.offset == key2->both.offset);
}

extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
			    struct futex_q *q, union futex_key *key2,
			    struct task_struct *task);
extern void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout);
extern bool __futex_wake_mark(struct futex_q *q);
extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q);

extern int fault_in_user_writeable(u32 __user *uaddr);
extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key);

static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval)
{
	int ret;

	pagefault_disable();
	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
	pagefault_enable();

	return ret;
}

/* Read from user memory with pagefaults disabled */
static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
{
	guard(pagefault)();
	return get_user_inline(*dest, from);
}

extern void __futex_unqueue(struct futex_q *q);
extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,</