Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-12-28 05:41:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

futex: Split out syscalls

Browse Source 
Put the syscalls in their own little file.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: André Almeida <andrealmeid@collabora.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: André Almeida <andrealmeid@collabora.com>
Link: https://lore.kernel.org/r/20210923171111.300673-3-andrealmeid@collabora.com
This commit is contained in:
Peter Zijlstra 2021-09-23 14:10:51 -03:00
parent 77e52ae354
commit af8cc9600b
6 changed files with 460 additions and 425 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
include/linux/syscalls.h
View File

@ -610,7 +610,7 @@ asmlinkage long sys_waitid(int which, pid_t pid,
asmlinkage long sys_set_tid_address(int __user *tidptr);
asmlinkage long sys_unshare(unsigned long unshare_flags);
/* kernel/futex.c */
/* kernel/futex/syscalls.c */
asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
const struct __kernel_timespec __user *utime,
u32 __user *uaddr2, u32 val3);

2
kernel/futex/Makefile
View File

@ -1,3 +1,3 @@
# SPDX-License-Identifier: GPL-2.0
obj-y += core.o
obj-y += core.o syscalls.o

542
kernel/futex/core.c
View File

@ -34,14 +34,12 @@
#include <linux/compat.h>
#include <linux/jhash.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/freezer.h>
#include <linux/memblock.h>
#include <linux/fault-inject.h>
#include <linux/time_namespace.h>
#include <asm/futex.h>
#include <linux/slab.h>
#include "futex.h"
#include "../locking/rtmutex_common.h"
/*
@ -144,27 +142,10 @@
* double_lock_hb() and double_unlock_hb(), respectively.
*/
#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
#define futex_cmpxchg_enabled 1
#else
static int __read_mostly futex_cmpxchg_enabled;
#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
int __read_mostly futex_cmpxchg_enabled;
#endif
/*
* Futex flags used to encode options to functions and preserve them across
* restarts.
*/
#ifdef CONFIG_MMU
# define FLAGS_SHARED 0x01
#else
/*
* NOMMU does not have per process address space. Let the compiler optimize
* code away.
*/
# define FLAGS_SHARED 0x00
#endif
#define FLAGS_CLOCKRT 0x02
#define FLAGS_HAS_TIMEOUT 0x04
/*
* Priority Inheritance state:
@ -329,7 +310,7 @@ static int __init setup_fail_futex(char *str)
}
__setup("fail_futex=", setup_fail_futex);
static bool should_fail_futex(bool fshared)
bool should_fail_futex(bool fshared)
{
if (fail_futex.ignore_private && !fshared)
return false;
@ -358,17 +339,8 @@ late_initcall(fail_futex_debugfs);
#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
#else
static inline bool should_fail_futex(bool fshared)
{
return false;
}
#endif /* CONFIG_FAIL_FUTEX */
#ifdef CONFIG_COMPAT
static void compat_exit_robust_list(struct task_struct *curr);
#endif
/*
* Reflects a new waiter being added to the waitqueue.
*/
@ -1647,8 +1619,7 @@ double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
/*
* Wake up waiters matching bitset queued on this futex (uaddr).
*/
static int
futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
@ -1743,9 +1714,8 @@ 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:
*/
static int
futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
int nr_wake, int nr_wake2, int op)
int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
int nr_wake, int nr_wake2, int op)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
struct futex_hash_bucket *hb1, *hb2;
@ -2124,9 +2094,8 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1,
* - >=0 - on success, the number of tasks requeued or woken;
* - <0 - on error
*/
static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
u32 __user *uaddr2, int nr_wake, int nr_requeue,
u32 *cmpval, int requeue_pi)
int futex_requeue(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
int task_count = 0, ret;
@ -2926,8 +2895,7 @@ retry_private:
return ret;
}
static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
ktime_t *abs_time, u32 bitset)
int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset)
{
struct hrtimer_sleeper timeout, *to;
struct restart_block *restart;
@ -3015,8 +2983,7 @@ static long futex_wait_restart(struct restart_block *restart)
*
* Also serves as futex trylock_pi()'ing, and due semantics.
*/
static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
ktime_t *time, int trylock)
int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock)
{
struct hrtimer_sleeper timeout, *to;
struct task_struct *exiting = NULL;
@ -3186,7 +3153,7 @@ uaddr_faulted:
* This is the in-kernel slowpath: we look up the PI state (if any),
* and do the rt-mutex unlock.
*/
static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
u32 curval, uval, vpid = task_pid_vnr(current);
union futex_key key = FUTEX_KEY_INIT;
@ -3403,9 +3370,9 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
* - 0 - On success;
* - <0 - On error
*/
static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
u32 val, ktime_t *abs_time, u32 bitset,
u32 __user *uaddr2)
int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
u32 val, ktime_t *abs_time, u32 bitset,
u32 __user *uaddr2)
{
struct hrtimer_sleeper timeout, *to;
struct rt_mutex_waiter rt_waiter;
@ -3539,87 +3506,6 @@ out:
return ret;
}
/*
* Support for robust futexes: the kernel cleans up held futexes at
* thread exit time.
*
* Implementation: user-space maintains a per-thread list of locks it
* is holding. Upon do_exit(), the kernel carefully walks this list,
* and marks all locks that are owned by this thread with the
* FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is
* always manipulated with the lock held, so the list is private and
* per-thread. Userspace also maintains a per-thread 'list_op_pending'
* field, to allow the kernel to clean up if the thread dies after
* acquiring the lock, but just before it could have added itself to
* the list. There can only be one such pending lock.
*/
/**
* sys_set_robust_list() - Set the robust-futex list head of a task
* @head: pointer to the list-head
* @len: length of the list-head, as userspace expects
*/
SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
size_t, len)
{
if (!futex_cmpxchg_enabled)
return -ENOSYS;
/*
* The kernel knows only one size for now:
*/
if (unlikely(len != sizeof(*head)))
return -EINVAL;
current->robust_list = head;
return 0;
}
/**
* sys_get_robust_list() - Get the robust-futex list head of a task
* @pid: pid of the process [zero for current task]
* @head_ptr: pointer to a list-head pointer, the kernel fills it in
* @len_ptr: pointer to a length field, the kernel fills in the header size
*/
SYSCALL_DEFINE3(get_robust_list, int, pid,
struct robust_list_head __user * __user *, head_ptr,
size_t __user *, len_ptr)
{
struct robust_list_head __user *head;
unsigned long ret;
struct task_struct *p;
if (!futex_cmpxchg_enabled)
return -ENOSYS;
rcu_read_lock();
ret = -ESRCH;
if (!pid)
p = current;
else {
p = find_task_by_vpid(pid);
if (!p)
goto err_unlock;
}
ret = -EPERM;
if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
head = p->robust_list;
rcu_read_unlock();
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(head, head_ptr);
err_unlock:
rcu_read_unlock();
return ret;
}
/* Constants for the pending_op argument of handle_futex_death */
#define HANDLE_DEATH_PENDING true
#define HANDLE_DEATH_LIST false
@ -3821,6 +3707,110 @@ static void exit_robust_list(struct task_struct *curr)
}
}
#ifdef CONFIG_COMPAT
static void __user *futex_uaddr(struct robust_list __user *entry,
compat_long_t futex_offset)
{
compat_uptr_t base = ptr_to_compat(entry);
void __user *uaddr = compat_ptr(base + futex_offset);
return uaddr;
}
/*
* Fetch a robust-list pointer. Bit 0 signals PI futexes:
*/
static inline int
compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
compat_uptr_t __user *head, unsigned int *pi)
{
if (get_user(*uentry, head))
return -EFAULT;
*entry = compat_ptr((*uentry) & ~1);
*pi = (unsigned int)(*uentry) & 1;
return 0;
}
/*
* Walk curr->robust_list (very carefully, it's a userspace list!)
* and mark any locks found there dead, and notify any waiters.
*
* We silently return on any sign of list-walking problem.
*/
static void compat_exit_robust_list(struct task_struct *curr)
{
struct compat_robust_list_head __user *head = curr->compat_robust_list;
struct robust_list __user *entry, *next_entry, *pending;
unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
unsigned int next_pi;
compat_uptr_t uentry, next_uentry, upending;
compat_long_t futex_offset;
int rc;
if (!futex_cmpxchg_enabled)
return;
/*
* Fetch the list head (which was registered earlier, via
* sys_set_robust_list()):
*/
if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi))
return;
/*
* Fetch the relative futex offset:
*/
if (get_user(futex_offset, &head->futex_offset))
return;
/*
* Fetch any possibly pending lock-add first, and handle it
* if it exists:
*/
if (compat_fetch_robust_entry(&upending, &pending,
&head->list_op_pending, &pip))
return;
next_entry = NULL; /* avoid warning with gcc */
while (entry != (struct robust_list __user *) &head->list) {
/*
* Fetch the next entry in the list before calling
* handle_futex_death:
*/
rc = compat_fetch_robust_entry(&next_uentry, &next_entry,
(compat_uptr_t __user *)&entry->next, &next_pi);
/*
* A pending lock might already be on the list, so
* dont process it twice:
*/
if (entry != pending) {
void __user *uaddr = futex_uaddr(entry, futex_offset);
if (handle_futex_death(uaddr, curr, pi,
HANDLE_DEATH_LIST))
return;
}
if (rc)
return;
uentry = next_uentry;
entry = next_entry;
pi = next_pi;
/*
* Avoid excessively long or circular lists:
*/
if (!--limit)
break;
cond_resched();
}
if (pending) {
void __user *uaddr = futex_uaddr(pending, futex_offset);
handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING);
}
}
#endif
static void futex_cleanup(struct task_struct *tsk)
{
if (unlikely(tsk->robust_list)) {
@ -3929,298 +3919,6 @@ void futex_exit_release(struct task_struct *tsk)
futex_cleanup_end(tsk, FUTEX_STATE_DEAD);
}
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
int cmd = op & FUTEX_CMD_MASK;
unsigned int flags = 0;
if (!(op & FUTEX_PRIVATE_FLAG))
flags |= FLAGS_SHARED;
if (op & FUTEX_CLOCK_REALTIME) {
flags |= FLAGS_CLOCKRT;
if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI &&
cmd != FUTEX_LOCK_PI2)
return -ENOSYS;
}
switch (cmd) {
case FUTEX_LOCK_PI:
case FUTEX_LOCK_PI2:
case FUTEX_UNLOCK_PI:
case FUTEX_TRYLOCK_PI:
case FUTEX_WAIT_REQUEUE_PI:
case FUTEX_CMP_REQUEUE_PI:
if (!futex_cmpxchg_enabled)
return -ENOSYS;
}
switch (cmd) {
case FUTEX_WAIT:
val3 = FUTEX_BITSET_MATCH_ANY;
fallthrough;
case FUTEX_WAIT_BITSET:
return futex_wait(uaddr, flags, val, timeout, val3);
case FUTEX_WAKE:
val3 = FUTEX_BITSET_MATCH_ANY;
fallthrough;
case FUTEX_WAKE_BITSET:
return futex_wake(uaddr, flags, val, val3);
case FUTEX_REQUEUE:
return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0);
case FUTEX_CMP_REQUEUE:
return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0);
case FUTEX_WAKE_OP:
return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
case FUTEX_LOCK_PI:
flags |= FLAGS_CLOCKRT;
fallthrough;
case FUTEX_LOCK_PI2:
return futex_lock_pi(uaddr, flags, timeout, 0);
case FUTEX_UNLOCK_PI:
return futex_unlock_pi(uaddr, flags);
case FUTEX_TRYLOCK_PI:
return futex_lock_pi(uaddr, flags, NULL, 1);
case FUTEX_WAIT_REQUEUE_PI:
val3 = FUTEX_BITSET_MATCH_ANY;
return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
uaddr2);
case FUTEX_CMP_REQUEUE_PI:
return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
}
return -ENOSYS;
}
static __always_inline bool futex_cmd_has_timeout(u32 cmd)
{
switch (cmd) {
case FUTEX_WAIT:
case FUTEX_LOCK_PI:
case FUTEX_LOCK_PI2:
case FUTEX_WAIT_BITSET:
case FUTEX_WAIT_REQUEUE_PI:
return true;
}
return false;
}
static __always_inline int
futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t)
{
if (!timespec64_valid(ts))
return -EINVAL;
*t = timespec64_to_ktime(*ts);
if (cmd == FUTEX_WAIT)
*t = ktime_add_safe(ktime_get(), *t);
else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME))
*t = timens_ktime_to_host(CLOCK_MONOTONIC, *t);
return 0;
}
SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
const struct __kernel_timespec __user *, utime,
u32 __user *, uaddr2, u32, val3)
{
int ret, cmd = op & FUTEX_CMD_MASK;
ktime_t t, *tp = NULL;
struct timespec64 ts;
if (utime && futex_cmd_has_timeout(cmd)) {
if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG))))
return -EFAULT;
if (get_timespec64(&ts, utime))
return -EFAULT;
ret = futex_init_timeout(cmd, op, &ts, &t);
if (ret)
return ret;
tp = &t;
}
return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
}
#ifdef CONFIG_COMPAT
/*
* Fetch a robust-list pointer. Bit 0 signals PI futexes:
*/
static inline int
compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
compat_uptr_t __user *head, unsigned int *pi)
{
if (get_user(*uentry, head))
return -EFAULT;
*entry = compat_ptr((*uentry) & ~1);
*pi = (unsigned int)(*uentry) & 1;
return 0;
}
static void __user *futex_uaddr(struct robust_list __user *entry,
compat_long_t futex_offset)
{
compat_uptr_t base = ptr_to_compat(entry);
void __user *uaddr = compat_ptr(base + futex_offset);
return uaddr;
}
/*
* Walk curr->robust_list (very carefully, it's a userspace list!)
* and mark any locks found there dead, and notify any waiters.
*
* We silently return on any sign of list-walking problem.
*/
static void compat_exit_robust_list(struct task_struct *curr)
{
struct compat_robust_list_head __user *head = curr->compat_robust_list;
struct robust_list __user *entry, *next_entry, *pending;
unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
unsigned int next_pi;
compat_uptr_t uentry, next_uentry, upending;
compat_long_t futex_offset;
int rc;
if (!futex_cmpxchg_enabled)
return;
/*
* Fetch the list head (which was registered earlier, via
* sys_set_robust_list()):
*/
if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi))
return;
/*
* Fetch the relative futex offset:
*/
if (get_user(futex_offset, &head->futex_offset))
return;
/*
* Fetch any possibly pending lock-add first, and handle it
* if it exists:
*/
if (compat_fetch_robust_entry(&upending, &pending,
&head->list_op_pending, &pip))
return;
next_entry = NULL; /* avoid warning with gcc */
while (entry != (struct robust_list __user *) &head->list) {
/*
* Fetch the next entry in the list before calling
* handle_futex_death:
*/
rc = compat_fetch_robust_entry(&next_uentry, &next_entry,
(compat_uptr_t __user *)&entry->next, &next_pi);
/*
* A pending lock might already be on the list, so
* dont process it twice:
*/
if (entry != pending) {
void __user *uaddr = futex_uaddr(entry, futex_offset);
if (handle_futex_death(uaddr, curr, pi,
HANDLE_DEATH_LIST))
return;
}
if (rc)
return;
uentry = next_uentry;
entry = next_entry;
pi = next_pi;
/*
* Avoid excessively long or circular lists:
*/
if (!--limit)
break;
cond_resched();
}
if (pending) {
void __user *uaddr = futex_uaddr(pending, futex_offset);
handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING);
}
}
COMPAT_SYSCALL_DEFINE2(set_robust_list,
struct compat_robust_list_head __user *, head,
compat_size_t, len)
{
if (!futex_cmpxchg_enabled)
return -ENOSYS;
if (unlikely(len != sizeof(*head)))
return -EINVAL;
current->compat_robust_list = head;
return 0;
}
COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
compat_uptr_t __user *, head_ptr,
compat_size_t __user *, len_ptr)
{
struct compat_robust_list_head __user *head;
unsigned long ret;
struct task_struct *p;
if (!futex_cmpxchg_enabled)
return -ENOSYS;
rcu_read_lock();
ret = -ESRCH;
if (!pid)
p = current;
else {
p = find_task_by_vpid(pid);
if (!p)
goto err_unlock;
}
ret = -EPERM;
if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
head = p->compat_robust_list;
rcu_read_unlock();
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(ptr_to_compat(head), head_ptr);
err_unlock:
rcu_read_unlock();
return ret;
}
#endif /* CONFIG_COMPAT */
#ifdef CONFIG_COMPAT_32BIT_TIME
SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
const struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
u32, val3)
{
int ret, cmd = op & FUTEX_CMD_MASK;
ktime_t t, *tp = NULL;
struct timespec64 ts;
if (utime && futex_cmd_has_timeout(cmd)) {
if (get_old_timespec32(&ts, utime))
return -EFAULT;
ret = futex_init_timeout(cmd, op, &ts, &t);
if (ret)
return ret;
tp = &t;
}
return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
}
#endif /* CONFIG_COMPAT_32BIT_TIME */
static void __init futex_detect_cmpxchg(void)
{
#ifndef CONFIG_HAVE_FUTEX_CMPXCHG

58
kernel/futex/futex.h Normal file
View File

@ -0,0 +1,58 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _FUTEX_H
#define _FUTEX_H
#include <asm/futex.h>
/*
* Futex flags used to encode options to functions and preserve them across
* restarts.
*/
#ifdef CONFIG_MMU
# define FLAGS_SHARED 0x01
#else
/*
* NOMMU does not have per process address space. Let the compiler optimize
* code away.
*/
# define FLAGS_SHARED 0x00
#endif
#define FLAGS_CLOCKRT 0x02
#define FLAGS_HAS_TIMEOUT 0x04
#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
#define futex_cmpxchg_enabled 1
#else
extern int __read_mostly futex_cmpxchg_enabled;
#endif
#ifdef CONFIG_FAIL_FUTEX
extern bool should_fail_futex(bool fshared);
#else
static inline bool should_fail_futex(bool fshared)
{
return false;
}
#endif
extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32
val, ktime_t *abs_time, u32 bitset, u32 __user
*uaddr2);
extern int futex_requeue(u32 __user *uaddr1, unsigned int flags,
u32 __user *uaddr2, int nr_wake, int nr_requeue,
u32 *cmpval, int requeue_pi);
extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
ktime_t *abs_time, u32 bitset);
extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset);
extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags,
u32 __user *uaddr2, int nr_wake, int nr_wake2, int op);
extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags);
extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock);
#endif /* _FUTEX_H */

279
kernel/futex/syscalls.c Normal file
View File

@ -0,0 +1,279 @@
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/time_namespace.h>
#include "futex.h"
/*
* Support for robust futexes: the kernel cleans up held futexes at
* thread exit time.
*
* Implementation: user-space maintains a per-thread list of locks it
* is holding. Upon do_exit(), the kernel carefully walks this list,
* and marks all locks that are owned by this thread with the
* FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is
* always manipulated with the lock held, so the list is private and
* per-thread. Userspace also maintains a per-thread 'list_op_pending'
* field, to allow the kernel to clean up if the thread dies after
* acquiring the lock, but just before it could have added itself to
* the list. There can only be one such pending lock.
*/
/**
* sys_set_robust_list() - Set the robust-futex list head of a task
* @head: pointer to the list-head
* @len: length of the list-head, as userspace expects
*/
SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
size_t, len)
{
if (!futex_cmpxchg_enabled)
return -ENOSYS;
/*
* The kernel knows only one size for now:
*/
if (unlikely(len != sizeof(*head)))
return -EINVAL;
current->robust_list = head;
return 0;
}
/**
* sys_get_robust_list() - Get the robust-futex list head of a task
* @pid: pid of the process [zero for current task]
* @head_ptr: pointer to a list-head pointer, the kernel fills it in
* @len_ptr: pointer to a length field, the kernel fills in the header size
*/
SYSCALL_DEFINE3(get_robust_list, int, pid,
struct robust_list_head __user * __user *, head_ptr,
size_t __user *, len_ptr)
{
struct robust_list_head __user *head;
unsigned long ret;
struct task_struct *p;
if (!futex_cmpxchg_enabled)
return -ENOSYS;
rcu_read_lock();
ret = -ESRCH;
if (!pid)
p = current;
else {
p = find_task_by_vpid(pid);
if (!p)
goto err_unlock;
}
ret = -EPERM;
if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
head = p->robust_list;
rcu_read_unlock();
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(head, head_ptr);
err_unlock:
rcu_read_unlock();
return ret;
}
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
int cmd = op & FUTEX_CMD_MASK;
unsigned int flags = 0;
if (!(op & FUTEX_PRIVATE_FLAG))
flags |= FLAGS_SHARED;
if (op & FUTEX_CLOCK_REALTIME) {
flags |= FLAGS_CLOCKRT;
if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI &&
cmd != FUTEX_LOCK_PI2)
return -ENOSYS;
}
switch (cmd) {
case FUTEX_LOCK_PI:
case FUTEX_LOCK_PI2:
case FUTEX_UNLOCK_PI:
case FUTEX_TRYLOCK_PI:
case FUTEX_WAIT_REQUEUE_PI:
case FUTEX_CMP_REQUEUE_PI:
if (!futex_cmpxchg_enabled)
return -ENOSYS;
}
switch (cmd) {
case FUTEX_WAIT:
val3 = FUTEX_BITSET_MATCH_ANY;
fallthrough;
case FUTEX_WAIT_BITSET:
return futex_wait(uaddr, flags, val, timeout, val3);
case FUTEX_WAKE:
val3 = FUTEX_BITSET_MATCH_ANY;
fallthrough;
case FUTEX_WAKE_BITSET:
return futex_wake(uaddr, flags, val, val3);
case FUTEX_REQUEUE:
return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0);
case FUTEX_CMP_REQUEUE:
return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0);
case FUTEX_WAKE_OP:
return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
case FUTEX_LOCK_PI:
flags |= FLAGS_CLOCKRT;
fallthrough;
case FUTEX_LOCK_PI2:
return futex_lock_pi(uaddr, flags, timeout, 0);
case FUTEX_UNLOCK_PI:
return futex_unlock_pi(uaddr, flags);
case FUTEX_TRYLOCK_PI:
return futex_lock_pi(uaddr, flags, NULL, 1);
case FUTEX_WAIT_REQUEUE_PI:
val3 = FUTEX_BITSET_MATCH_ANY;
return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
uaddr2);
case FUTEX_CMP_REQUEUE_PI:
return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
}
return -ENOSYS;
}
static __always_inline bool futex_cmd_has_timeout(u32 cmd)
{
switch (cmd) {
case FUTEX_WAIT:
case FUTEX_LOCK_PI:
case FUTEX_LOCK_PI2:
case FUTEX_WAIT_BITSET:
case FUTEX_WAIT_REQUEUE_PI:
return true;
}
return false;
}
static __always_inline int
futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t)
{
if (!timespec64_valid(ts))
return -EINVAL;
*t = timespec64_to_ktime(*ts);
if (cmd == FUTEX_WAIT)
*t = ktime_add_safe(ktime_get(), *t);
else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME))
*t = timens_ktime_to_host(CLOCK_MONOTONIC, *t);
return 0;
}
SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
const struct __kernel_timespec __user *, utime,
u32 __user *, uaddr2, u32, val3)
{
int ret, cmd = op & FUTEX_CMD_MASK;
ktime_t t, *tp = NULL;
struct timespec64 ts;
if (utime && futex_cmd_has_timeout(cmd)) {
if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG))))
return -EFAULT;
if (get_timespec64(&ts, utime))
return -EFAULT;
ret = futex_init_timeout(cmd, op, &ts, &t);
if (ret)
return ret;
tp = &t;
}
return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(set_robust_list,
struct compat_robust_list_head __user *, head,
compat_size_t, len)
{
if (!futex_cmpxchg_enabled)
return -ENOSYS;
if (unlikely(len != sizeof(*head)))
return -EINVAL;
current->compat_robust_list = head;
return 0;
}
COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
compat_uptr_t __user *, head_ptr,
compat_size_t __user *, len_ptr)
{
struct compat_robust_list_head __user *head;
unsigned long ret;
struct task_struct *p;
if (!futex_cmpxchg_enabled)
return -ENOSYS;
rcu_read_lock();
ret = -ESRCH;
if (!pid)
p = current;
else {
p = find_task_by_vpid(pid);
if (!p)
goto err_unlock;
}
ret = -EPERM;
if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
goto err_unlock;
head = p->compat_robust_list;
rcu_read_unlock();
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(ptr_to_compat(head), head_ptr);
err_unlock:
rcu_read_unlock();
return ret;
}
#endif /* CONFIG_COMPAT */
#ifdef CONFIG_COMPAT_32BIT_TIME
SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
const struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
u32, val3)
{
int ret, cmd = op & FUTEX_CMD_MASK;
ktime_t t, *tp = NULL;
struct timespec64 ts;
if (utime && futex_cmd_has_timeout(cmd)) {
if (get_old_timespec32(&ts, utime))
return -EFAULT;
ret = futex_init_timeout(cmd, op, &ts, &t);
if (ret)
return ret;
tp = &t;
}
return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
}
#endif /* CONFIG_COMPAT_32BIT_TIME */

2
kernel/sys_ni.c
View File

@ -143,7 +143,7 @@ COND_SYSCALL(capset);
/* __ARCH_WANT_SYS_CLONE3 */
COND_SYSCALL(clone3);
/* kernel/futex.c */
/* kernel/futex/syscalls.c */
COND_SYSCALL(futex);
COND_SYSCALL(futex_time32);
COND_SYSCALL(set_robust_list);