mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 08:19:28 +00:00
bf69bad38c
Add support to wait on multiple futexes. This is the interface
implemented by this syscall:
futex_waitv(struct futex_waitv *waiters, unsigned int nr_futexes,
unsigned int flags, struct timespec *timeout, clockid_t clockid)
struct futex_waitv {
__u64 val;
__u64 uaddr;
__u32 flags;
__u32 __reserved;
};
Given an array of struct futex_waitv, wait on each uaddr. The thread
wakes if a futex_wake() is performed at any uaddr. The syscall returns
immediately if any waiter has *uaddr != val. *timeout is an optional
absolute timeout value for the operation. This syscall supports only
64bit sized timeout structs. The flags argument of the syscall should be
empty, but it can be used for future extensions. Flags for shared
futexes, sizes, etc. should be used on the individual flags of each
waiter.
__reserved is used for explicit padding and should be 0, but it might be
used for future extensions. If the userspace uses 32-bit pointers, it
should make sure to explicitly cast it when assigning to waitv::uaddr.
Returns the array index of one of the woken futexes. There’s no given
information of how many were woken, or any particular attribute of it
(if it’s the first woken, if it is of the smaller index...).
Signed-off-by: André Almeida <andrealmeid@collabora.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210923171111.300673-17-andrealmeid@collabora.com
180 lines
5.6 KiB
C
180 lines
5.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
|
#ifndef _UAPI_LINUX_FUTEX_H
|
|
#define _UAPI_LINUX_FUTEX_H
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/types.h>
|
|
|
|
/* Second argument to futex syscall */
|
|
|
|
|
|
#define FUTEX_WAIT 0
|
|
#define FUTEX_WAKE 1
|
|
#define FUTEX_FD 2
|
|
#define FUTEX_REQUEUE 3
|
|
#define FUTEX_CMP_REQUEUE 4
|
|
#define FUTEX_WAKE_OP 5
|
|
#define FUTEX_LOCK_PI 6
|
|
#define FUTEX_UNLOCK_PI 7
|
|
#define FUTEX_TRYLOCK_PI 8
|
|
#define FUTEX_WAIT_BITSET 9
|
|
#define FUTEX_WAKE_BITSET 10
|
|
#define FUTEX_WAIT_REQUEUE_PI 11
|
|
#define FUTEX_CMP_REQUEUE_PI 12
|
|
#define FUTEX_LOCK_PI2 13
|
|
|
|
#define FUTEX_PRIVATE_FLAG 128
|
|
#define FUTEX_CLOCK_REALTIME 256
|
|
#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
|
|
|
|
#define FUTEX_WAIT_PRIVATE (FUTEX_WAIT | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_WAKE_PRIVATE (FUTEX_WAKE | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_REQUEUE_PRIVATE (FUTEX_REQUEUE | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_CMP_REQUEUE_PRIVATE (FUTEX_CMP_REQUEUE | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_WAKE_OP_PRIVATE (FUTEX_WAKE_OP | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_LOCK_PI_PRIVATE (FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_LOCK_PI2_PRIVATE (FUTEX_LOCK_PI2 | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_UNLOCK_PI_PRIVATE (FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITSET | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_WAKE_BITSET_PRIVATE (FUTEX_WAKE_BITSET | FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_WAIT_REQUEUE_PI_PRIVATE (FUTEX_WAIT_REQUEUE_PI | \
|
|
FUTEX_PRIVATE_FLAG)
|
|
#define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | \
|
|
FUTEX_PRIVATE_FLAG)
|
|
|
|
/*
|
|
* Flags to specify the bit length of the futex word for futex2 syscalls.
|
|
* Currently, only 32 is supported.
|
|
*/
|
|
#define FUTEX_32 2
|
|
|
|
/*
|
|
* Max numbers of elements in a futex_waitv array
|
|
*/
|
|
#define FUTEX_WAITV_MAX 128
|
|
|
|
/**
|
|
* struct futex_waitv - A waiter for vectorized wait
|
|
* @val: Expected value at uaddr
|
|
* @uaddr: User address to wait on
|
|
* @flags: Flags for this waiter
|
|
* @__reserved: Reserved member to preserve data alignment. Should be 0.
|
|
*/
|
|
struct futex_waitv {
|
|
__u64 val;
|
|
__u64 uaddr;
|
|
__u32 flags;
|
|
__u32 __reserved;
|
|
};
|
|
|
|
/*
|
|
* Support for robust futexes: the kernel cleans up held futexes at
|
|
* thread exit time.
|
|
*/
|
|
|
|
/*
|
|
* Per-lock list entry - embedded in user-space locks, somewhere close
|
|
* to the futex field. (Note: user-space uses a double-linked list to
|
|
* achieve O(1) list add and remove, but the kernel only needs to know
|
|
* about the forward link)
|
|
*
|
|
* NOTE: this structure is part of the syscall ABI, and must not be
|
|
* changed.
|
|
*/
|
|
struct robust_list {
|
|
struct robust_list __user *next;
|
|
};
|
|
|
|
/*
|
|
* Per-thread list head:
|
|
*
|
|
* NOTE: this structure is part of the syscall ABI, and must only be
|
|
* changed if the change is first communicated with the glibc folks.
|
|
* (When an incompatible change is done, we'll increase the structure
|
|
* size, which glibc will detect)
|
|
*/
|
|
struct robust_list_head {
|
|
/*
|
|
* The head of the list. Points back to itself if empty:
|
|
*/
|
|
struct robust_list list;
|
|
|
|
/*
|
|
* This relative offset is set by user-space, it gives the kernel
|
|
* the relative position of the futex field to examine. This way
|
|
* we keep userspace flexible, to freely shape its data-structure,
|
|
* without hardcoding any particular offset into the kernel:
|
|
*/
|
|
long futex_offset;
|
|
|
|
/*
|
|
* The death of the thread may race with userspace setting
|
|
* up a lock's links. So to handle this race, userspace first
|
|
* sets this field to the address of the to-be-taken lock,
|
|
* then does the lock acquire, and then adds itself to the
|
|
* list, and then clears this field. Hence the kernel will
|
|
* always have full knowledge of all locks that the thread
|
|
* _might_ have taken. We check the owner TID in any case,
|
|
* so only truly owned locks will be handled.
|
|
*/
|
|
struct robust_list __user *list_op_pending;
|
|
};
|
|
|
|
/*
|
|
* Are there any waiters for this robust futex:
|
|
*/
|
|
#define FUTEX_WAITERS 0x80000000
|
|
|
|
/*
|
|
* The kernel signals via this bit that a thread holding a futex
|
|
* has exited without unlocking the futex. The kernel also does
|
|
* a FUTEX_WAKE on such futexes, after setting the bit, to wake
|
|
* up any possible waiters:
|
|
*/
|
|
#define FUTEX_OWNER_DIED 0x40000000
|
|
|
|
/*
|
|
* The rest of the robust-futex field is for the TID:
|
|
*/
|
|
#define FUTEX_TID_MASK 0x3fffffff
|
|
|
|
/*
|
|
* This limit protects against a deliberately circular list.
|
|
* (Not worth introducing an rlimit for it)
|
|
*/
|
|
#define ROBUST_LIST_LIMIT 2048
|
|
|
|
/*
|
|
* bitset with all bits set for the FUTEX_xxx_BITSET OPs to request a
|
|
* match of any bit.
|
|
*/
|
|
#define FUTEX_BITSET_MATCH_ANY 0xffffffff
|
|
|
|
|
|
#define FUTEX_OP_SET 0 /* *(int *)UADDR2 = OPARG; */
|
|
#define FUTEX_OP_ADD 1 /* *(int *)UADDR2 += OPARG; */
|
|
#define FUTEX_OP_OR 2 /* *(int *)UADDR2 |= OPARG; */
|
|
#define FUTEX_OP_ANDN 3 /* *(int *)UADDR2 &= ~OPARG; */
|
|
#define FUTEX_OP_XOR 4 /* *(int *)UADDR2 ^= OPARG; */
|
|
|
|
#define FUTEX_OP_OPARG_SHIFT 8 /* Use (1 << OPARG) instead of OPARG. */
|
|
|
|
#define FUTEX_OP_CMP_EQ 0 /* if (oldval == CMPARG) wake */
|
|
#define FUTEX_OP_CMP_NE 1 /* if (oldval != CMPARG) wake */
|
|
#define FUTEX_OP_CMP_LT 2 /* if (oldval < CMPARG) wake */
|
|
#define FUTEX_OP_CMP_LE 3 /* if (oldval <= CMPARG) wake */
|
|
#define FUTEX_OP_CMP_GT 4 /* if (oldval > CMPARG) wake */
|
|
#define FUTEX_OP_CMP_GE 5 /* if (oldval >= CMPARG) wake */
|
|
|
|
/* FUTEX_WAKE_OP will perform atomically
|
|
int oldval = *(int *)UADDR2;
|
|
*(int *)UADDR2 = oldval OP OPARG;
|
|
if (oldval CMP CMPARG)
|
|
wake UADDR2; */
|
|
|
|
#define FUTEX_OP(op, oparg, cmp, cmparg) \
|
|
(((op & 0xf) << 28) | ((cmp & 0xf) << 24) \
|
|
| ((oparg & 0xfff) << 12) | (cmparg & 0xfff))
|
|
|
|
#endif /* _UAPI_LINUX_FUTEX_H */
|