From cb8c4312afca1b2dc64107e7e7cea81911055612 Mon Sep 17 00:00:00 2001 From: "peterz@infradead.org" Date: Thu, 21 Sep 2023 12:45:12 +0200 Subject: futex: Add sys_futex_wait() To complement sys_futex_waitv()/wake(), add sys_futex_wait(). This syscall implements what was previously known as FUTEX_WAIT_BITSET except it uses 'unsigned long' for the value and bitmask arguments, takes timespec and clockid_t arguments for the absolute timeout and uses FUTEX2 flags. The 'unsigned long' allows FUTEX2_SIZE_U64 on 64bit platforms. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Acked-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230921105248.164324363@noisy.programming.kicks-ass.net --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 + arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/syscalls.h | 4 + include/uapi/asm-generic/unistd.h | 4 +- kernel/futex/futex.h | 3 + kernel/futex/syscalls.c | 120 +++++++++++++++++++++------- kernel/futex/waitwake.c | 61 ++++++++------ kernel/sys_ni.c | 1 + 24 files changed, 156 insertions(+), 57 deletions(-) diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 3b86519d68e4..c49f12fd264e 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -493,3 +493,4 @@ 561 common cachestat sys_cachestat 562 common fchmodat2 sys_fchmodat2 563 common futex_wake sys_futex_wake +564 common futex_wait sys_futex_wait diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 714abeb1e6fa..a6cf56277327 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -467,3 +467,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 63a8a9c4abc1..f33190f17ebb 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -39,7 +39,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 455 +#define __NR_compat_syscalls 456 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 68974683737b..6e7d37282ba1 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -913,6 +913,8 @@ __SYSCALL(__NR_cachestat, sys_cachestat) __SYSCALL(__NR_fchmodat2, sys_fchmodat2) #define __NR_futex_wake 454 __SYSCALL(__NR_futex_wake, sys_futex_wake) +#define __NR_futex_wait 455 +__SYSCALL(__NR_futex_wait, sys_futex_wait) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index cd50247508e6..4043f0c55170 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -374,3 +374,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 21eb35c693e1..24841674acc5 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -453,3 +453,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 3a4e8513a8e1..f03927ab0220 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -459,3 +459,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 6883ea3b830d..dbb5edfb667b 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -392,3 +392,4 @@ 451 n32 cachestat sys_cachestat 452 n32 fchmodat2 sys_fchmodat2 454 n32 futex_wake sys_futex_wake +455 n32 futex_wait sys_futex_wait diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 48bc0fb4e3dc..faff8dfd2983 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -368,3 +368,4 @@ 451 n64 cachestat sys_cachestat 452 n64 fchmodat2 sys_fchmodat2 454 n64 futex_wake sys_futex_wake +455 n64 futex_wait sys_futex_wait diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index a92625f5bad8..542f75605b3e 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -441,3 +441,4 @@ 451 o32 cachestat sys_cachestat 452 o32 fchmodat2 sys_fchmodat2 454 o32 futex_wake sys_futex_wake +455 o32 futex_wait sys_futex_wait diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 57faa9786ffe..8e50e89551f7 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index e6c6ed6b30ee..ad33a9993a6a 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -540,3 +540,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 754720154dc1..418853fd2a6b 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -456,3 +456,4 @@ 451 common cachestat sys_cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait sys_futex_wait diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 902a997e7ec6..8ef9557d2779 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -456,3 +456,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 8a1f887c8be6..df59a9d5f109 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -499,3 +499,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 9e81323979b0..0f6616822bd5 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -458,3 +458,4 @@ 451 i386 cachestat sys_cachestat 452 i386 fchmodat2 sys_fchmodat2 454 i386 futex_wake sys_futex_wake +455 i386 futex_wait sys_futex_wait diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index d10a6003a7c9..ddf6288823ad 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -376,6 +376,7 @@ 452 common fchmodat2 sys_fchmodat2 453 64 map_shadow_stack sys_map_shadow_stack 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 4e511bfd4b8f..ac278dbce2ee 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -424,3 +424,4 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e174ed86da1d..11f3fdd1ee03 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -552,6 +552,10 @@ asmlinkage long sys_futex_waitv(struct futex_waitv *waiters, asmlinkage long sys_futex_wake(void __user *uaddr, unsigned long mask, int nr, unsigned int flags); +asmlinkage long sys_futex_wait(void __user *uaddr, unsigned long val, unsigned long mask, + unsigned int flags, struct __kernel_timespec __user *timespec, + clockid_t clockid); + asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp, struct __kernel_timespec __user *rmtp); asmlinkage long sys_nanosleep_time32(struct old_timespec32 __user *rqtp, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index f5454e6f4c6f..f6553bd5d213 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -824,9 +824,11 @@ __SYSCALL(__NR_cachestat, sys_cachestat) __SYSCALL(__NR_fchmodat2, sys_fchmodat2) #define __NR_futex_wake 454 __SYSCALL(__NR_futex_wake, sys_futex_wake) +#define __NR_futex_wait 455 +__SYSCALL(__NR_futex_wait, sys_futex_wait) #undef __NR_syscalls -#define __NR_syscalls 455 +#define __NR_syscalls 456 /* * 32 bit systems traditionally used different diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 0e7821a944a2..e74888a7d71d 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -332,6 +332,9 @@ 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, + struct hrtimer_sleeper *to, u32 bitset); + extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 47398926765e..e4c8ec713787 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -221,6 +221,46 @@ static int futex_parse_waitv(struct futex_vector *futexv, return 0; } +static int futex2_setup_timeout(struct __kernel_timespec __user *timeout, + clockid_t clockid, struct hrtimer_sleeper *to) +{ + int flag_clkid = 0, flag_init = 0; + struct timespec64 ts; + ktime_t time; + int ret; + + if (!timeout) + return 0; + + if (clockid == CLOCK_REALTIME) { + flag_clkid = FLAGS_CLOCKRT; + flag_init = FUTEX_CLOCK_REALTIME; + } + + if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) + return -EINVAL; + + if (get_timespec64(&ts, timeout)) + return -EFAULT; + + /* + * Since there's no opcode for futex_waitv, use + * FUTEX_WAIT_BITSET that uses absolute timeout as well + */ + ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); + if (ret) + return ret; + + futex_setup_timer(&time, to, flag_clkid, 0); + return 0; +} + +static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to) +{ + hrtimer_cancel(&to->timer); + destroy_hrtimer_on_stack(&to->timer); +} + /** * sys_futex_waitv - Wait on a list of futexes * @waiters: List of futexes to wait on @@ -250,8 +290,6 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, { struct hrtimer_sleeper to; struct futex_vector *futexv; - struct timespec64 ts; - ktime_t time; int ret; /* This syscall supports no flags for now */ @@ -261,30 +299,8 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) return -EINVAL; - if (timeout) { - int flag_clkid = 0, flag_init = 0; - - if (clockid == CLOCK_REALTIME) { - flag_clkid = FLAGS_CLOCKRT; - flag_init = FUTEX_CLOCK_REALTIME; - } - - if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) - return -EINVAL; - - if (get_timespec64(&ts, timeout)) - return -EFAULT; - - /* - * Since there's no opcode for futex_waitv, use - * FUTEX_WAIT_BITSET that uses absolute timeout as well - */ - ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); - if (ret) - return ret; - - futex_setup_timer(&time, &to, flag_clkid, 0); - } + if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) + return ret; futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); if (!futexv) { @@ -299,10 +315,8 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, kfree(futexv); destroy_timer: - if (timeout) { - hrtimer_cancel(&to.timer); - destroy_hrtimer_on_stack(&to.timer); - } + if (timeout) + futex2_destroy_timeout(&to); return ret; } @@ -336,6 +350,52 @@ SYSCALL_DEFINE4(futex_wake, return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); } +/* + * sys_futex_wait - Wait on a futex + * @uaddr: Address of the futex to wait on + * @val: Value of @uaddr + * @mask: bitmask + * @flags: FUTEX2 flags + * @timeout: Optional absolute timeout + * @clockid: Clock to be used for the timeout, realtime or monotonic + * + * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the + * futex2 familiy of calls. + */ + +SYSCALL_DEFINE6(futex_wait, + void __user *, uaddr, + unsigned long, val, + unsigned long, mask, + unsigned int, flags, + struct __kernel_timespec __user *, timeout, + clockid_t, clockid) +{ + struct hrtimer_sleeper to; + int ret; + + if (flags & ~FUTEX2_VALID_MASK) + return -EINVAL; + + flags = futex2_to_flags(flags); + if (!futex_flags_valid(flags)) + return -EINVAL; + + if (!futex_validate_input(flags, val) || + !futex_validate_input(flags, mask)) + return -EINVAL; + + if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) + return ret; + + ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask); + + if (timeout) + futex2_destroy_timeout(&to); + + return ret; +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index ceb05b876597..b109a0810a2c 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -632,20 +632,18 @@ retry_private: return ret; } -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, + struct hrtimer_sleeper *to, u32 bitset) { - struct hrtimer_sleeper timeout, *to; - struct restart_block *restart; - struct futex_hash_bucket *hb; struct futex_q q = futex_q_init; + struct futex_hash_bucket *hb; int ret; if (!bitset) return -EINVAL; + q.bitset = bitset; - to = futex_setup_timer(abs_time, &timeout, flags, - current->timer_slack_ns); retry: /* * Prepare to wait on uaddr. On success, it holds hb->lock and q @@ -653,18 +651,17 @@ retry: */ ret = futex_wait_setup(uaddr, val, flags, &q, &hb); if (ret) - goto out; + return ret; /* futex_queue and wait for wakeup, timeout, or a signal. */ futex_wait_queue(hb, &q, to); /* If we were woken (and unqueued), we succeeded, whatever. */ - ret = 0; if (!futex_unqueue(&q)) - goto out; - ret = -ETIMEDOUT; + return 0; + if (to && !to->task) - goto out; + return -ETIMEDOUT; /* * We expect signal_pending(current), but we might be the @@ -673,24 +670,38 @@ retry: if (!signal_pending(current)) goto retry; - ret = -ERESTARTSYS; - if (!abs_time) - goto out; + return -ERESTARTSYS; +} - restart = ¤t->restart_block; - restart->futex.uaddr = uaddr; - restart->futex.val = val; - restart->futex.time = *abs_time; - restart->futex.bitset = bitset; - restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; +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; + int ret; + + to = futex_setup_timer(abs_time, &timeout, flags, + current->timer_slack_ns); + + ret = __futex_wait(uaddr, flags, val, to, bitset); + + /* No timeout, nothing to clean up. */ + if (!to) + return ret; + + hrtimer_cancel(&to->timer); + destroy_hrtimer_on_stack(&to->timer); - ret = set_restart_fn(restart, futex_wait_restart); + if (ret == -ERESTARTSYS) { + restart = ¤t->restart_block; + restart->futex.uaddr = uaddr; + restart->futex.val = val; + restart->futex.time = *abs_time; + restart->futex.bitset = bitset; + restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; -out: - if (to) { - hrtimer_cancel(&to->timer); - destroy_hrtimer_on_stack(&to->timer); + return set_restart_fn(restart, futex_wait_restart); } + return ret; } diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 983c0583c627..13df391194e2 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -88,6 +88,7 @@ COND_SYSCALL(get_robust_list); COND_SYSCALL_COMPAT(get_robust_list); COND_SYSCALL(futex_waitv); COND_SYSCALL(futex_wake); +COND_SYSCALL(futex_wait); COND_SYSCALL(kexec_load); COND_SYSCALL_COMPAT(kexec_load); COND_SYSCALL(init_module); -- cgit