// SPDX-License-Identifier: GPL-2.0-or-later #include <linux/plist.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/freezer.h> #include "futex.h" /* * READ this before attempting to hack on futexes! * * Basic futex operation and ordering guarantees * ============================================= * * The waiter reads the futex value in user space and calls * futex_wait(). This function computes the hash bucket and acquires * the hash bucket lock. After that it reads the futex user space value * again and verifies that the data has not changed. If it has not changed * it enqueues itself into the hash bucket, releases the hash bucket lock * and schedules. * * The waker side modifies the user space value of the futex and calls * futex_wake(). This function computes the hash bucket and acquires the * hash bucket lock. Then it looks for waiters on that futex in the hash * bucket and wakes them. * * In futex wake up scenarios where no tasks are blocked on a futex, taking * the hb spinlock can be avoided and simply return. In order for this * optimization to work, ordering guarantees must exist so that the waiter * being added to the list is acknowledged when the list is concurrently being * checked by the waker, avoiding scenarios like the following: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * uval = *futex; * *futex = newval; * sys_futex(WAKE, futex); * futex_wake(futex); * if (queue_empty()) * return; * if (uval == val) * lock(hash_bucket(futex)); * queue(); * unlock(hash_bucket(futex)); * schedule(); * * This would cause the waiter on CPU 0 to wait forever because it * missed the transition of the user space value from val to newval * and the waker did not find the waiter in the hash bucket queue. * * The correct serialization ensures that a waiter either observes * the changed user space value before blocking or is woken by a * concurrent waker: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * * waiters++; (a) * smp_mb(); (A) <-- paired with -. * | * lock(hash_bucket(futex)); | * | * uval = *futex; | * | *futex = newval; * | sys_futex(WAKE, futex); * | futex_wake(futex); * | * `--------> smp_mb(); (B) * if (uval == val) * queue(); * unlock(hash_bucket(futex)); * schedule(); if (waiters) * lock(hash_bucket(futex)); * else wake_waiters(futex); * waiters--; (b) unlock(hash_bucket(futex)); * * Where (A) orders the waiters increment and the futex value read through * atomic operations (see futex_hb_waiters_inc) and where (B) orders the write * to futex and the waiters read (see futex_hb_waiters_pending()). * * This yields the following case (where X:=waiters, Y:=futex): * * X = Y = 0 * * w[X]=1 w[Y]=1 * MB MB * r[Y]=y r[X]=x * * Which guarantees that x==0 && y==0 is impossible; which translates back into * the guarantee that we cannot both miss the futex variable change and the * enqueue. * * Note that a new waiter is accounted for in (a) even when it is possible that * the wait call can return error, in which case we backtrack from it in (b). * Refer to the comment in futex_q_lock(). * * Similarly, in order to account for waiters being requeued on another * address we always increment the waiters for the destination bucket before * acquiring the lock. It then decrements them again after releasing it - * the code that actually moves the futex(es) between hash buckets (requeue_futex) * will do the additional required waiter count housekeeping. This is done for * double_lock_hb() and double_unlock_hb(), respectively. */ bool __futex_wake_mark(struct futex_q *q) { … } /* * The hash bucket lock must be held when this is called. * Afterwards, the futex_q must not be accessed. Callers * must ensure to later call wake_up_q() for the actual * wakeups to occur. */ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) { … } /* * Wake up waiters matching bitset queued on this futex (uaddr). */ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) { … } static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) { … } /* * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { … } static long futex_wait_restart(struct restart_block *restart); /** * futex_wait_queue() - futex_queue() and wait for wakeup, timeout, or signal * @hb: the futex hash bucket, must be locked by the caller * @q: the futex_q to queue up on * @timeout: the prepared hrtimer_sleeper, or null for no timeout */ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, struct hrtimer_sleeper *timeout) { … } /** * futex_unqueue_multiple - Remove various futexes from their hash bucket * @v: The list of futexes to unqueue * @count: Number of futexes in the list * * Helper to unqueue a list of futexes. This can't fail. * * Return: * - >=0 - Index of the last futex that was awoken; * - -1 - No futex was awoken */ int futex_unqueue_multiple(struct futex_vector *v, int count) { … } /** * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes * @vs: The futex list to wait on * @count: The size of the list * @woken: Index of the last woken futex, if any. Used to notify the * caller that it can return this index to userspace (return parameter) * * Prepare multiple futexes in a single step and enqueue them. This may fail if * the futex list is invalid or if any futex was already awoken. On success the * task is ready to interruptible sleep. * * Return: * - 1 - One of the futexes was woken by another thread * - 0 - Success * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL */ int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) { … } /** * futex_sleep_multiple - Check sleeping conditions and sleep * @vs: List of futexes to wait for * @count: Length of vs * @to: Timeout * * Sleep if and only if the timeout hasn't expired and no futex on the list has * been woken up. */ static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { … } /** * futex_wait_multiple - Prepare to wait on and enqueue several futexes * @vs: The list of futexes to wait on * @count: The number of objects * @to: Timeout before giving up and returning to userspace * * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function * sleeps on a group of futexes and returns on the first futex that is * wake, or after the timeout has elapsed. * * Return: * - >=0 - Hint to the futex that was awoken * - <0 - On error */ int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { … } /** * futex_wait_setup() - Prepare to wait on a futex * @uaddr: the futex userspace address * @val: the expected value * @flags: futex flags (FLAGS_SHARED, etc.) * @q: the associated futex_q * @hb: storage for hash_bucket pointer to be returned to caller * * Setup the futex_q and locate the hash_bucket. Get the futex value and * compare it with the expected value. Handle atomic faults internally. * Return with the hb lock held on success, and unlocked on failure. * * Return: * - 0 - uaddr contains val and hb has been locked; * - <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked */ int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, struct futex_hash_bucket **hb) { … } int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset) { … } int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset) { … } static long futex_wait_restart(struct restart_block *restart) { … }
Codebase Browser
linux