diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index f5801b0ba9e9..92c16dfb8ca6 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -219,6 +219,19 @@ do { \ (typeof(*ptr))VAL; \ }) +#define SMP_TIMEOUT_POLL_COUNT 1 + +/* Re-declared here to avoid include dependency. */ +extern bool arch_timer_evtstrm_available(void); + +#define cpu_poll_relax(ptr, val) \ +do { \ + if (arch_timer_evtstrm_available()) \ + __cmpwait_relaxed(ptr, val); \ + else \ + cpu_relax(); \ +} while (0) + #include #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/rqspinlock.h b/arch/arm64/include/asm/rqspinlock.h index 9ea0a74e5892..a385603436e9 100644 --- a/arch/arm64/include/asm/rqspinlock.h +++ b/arch/arm64/include/asm/rqspinlock.h @@ -3,91 +3,6 @@ #define _ASM_RQSPINLOCK_H #include - -/* - * Hardcode res_smp_cond_load_acquire implementations for arm64 to a custom - * version based on [0]. In rqspinlock code, our conditional expression involves - * checking the value _and_ additionally a timeout. However, on arm64, the - * WFE-based implementation may never spin again if no stores occur to the - * locked byte in the lock word. As such, we may be stuck forever if - * event-stream based unblocking is not available on the platform for WFE spin - * loops (arch_timer_evtstrm_available). - * - * Once support for smp_cond_load_acquire_timewait [0] lands, we can drop this - * copy-paste. - * - * While we rely on the implementation to amortize the cost of sampling - * cond_expr for us, it will not happen when event stream support is - * unavailable, time_expr check is amortized. This is not the common case, and - * it would be difficult to fit our logic in the time_expr_ns >= time_limit_ns - * comparison, hence just let it be. In case of event-stream, the loop is woken - * up at microsecond granularity. - * - * [0]: https://lore.kernel.org/lkml/20250203214911.898276-1-ankur.a.arora@oracle.com - */ - -#ifndef smp_cond_load_acquire_timewait - -#define smp_cond_time_check_count 200 - -#define __smp_cond_load_relaxed_spinwait(ptr, cond_expr, time_expr_ns, \ - time_limit_ns) ({ \ - typeof(ptr) __PTR = (ptr); \ - __unqual_scalar_typeof(*ptr) VAL; \ - unsigned int __count = 0; \ - for (;;) { \ - VAL = READ_ONCE(*__PTR); \ - if (cond_expr) \ - break; \ - cpu_relax(); \ - if (__count++ < smp_cond_time_check_count) \ - continue; \ - if ((time_expr_ns) >= (time_limit_ns)) \ - break; \ - __count = 0; \ - } \ - (typeof(*ptr))VAL; \ -}) - -#define __smp_cond_load_acquire_timewait(ptr, cond_expr, \ - time_expr_ns, time_limit_ns) \ -({ \ - typeof(ptr) __PTR = (ptr); \ - __unqual_scalar_typeof(*ptr) VAL; \ - for (;;) { \ - VAL = smp_load_acquire(__PTR); \ - if (cond_expr) \ - break; \ - __cmpwait_relaxed(__PTR, VAL); \ - if ((time_expr_ns) >= (time_limit_ns)) \ - break; \ - } \ - (typeof(*ptr))VAL; \ -}) - -#define smp_cond_load_acquire_timewait(ptr, cond_expr, \ - time_expr_ns, time_limit_ns) \ -({ \ - __unqual_scalar_typeof(*ptr) _val; \ - int __wfe = arch_timer_evtstrm_available(); \ - \ - if (likely(__wfe)) { \ - _val = __smp_cond_load_acquire_timewait(ptr, cond_expr, \ - time_expr_ns, \ - time_limit_ns); \ - } else { \ - _val = __smp_cond_load_relaxed_spinwait(ptr, cond_expr, \ - time_expr_ns, \ - time_limit_ns); \ - smp_acquire__after_ctrl_dep(); \ - } \ - (typeof(*ptr))_val; \ -}) - -#endif - -#define res_smp_cond_load_acquire(v, c) smp_cond_load_acquire_timewait(v, c, 0, 1) - #include #endif /* _ASM_RQSPINLOCK_H */ diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 9b6d90a72601..dc7f4b424fec 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -8,35 +8,22 @@ #include #include -#define POLL_IDLE_RELAX_COUNT 200 - static int __cpuidle poll_idle(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { - u64 time_start; - - time_start = local_clock_noinstr(); + u64 time_end; + u32 flags = 0; dev->poll_time_limit = false; + time_end = local_clock_noinstr() + cpuidle_poll_time(drv, dev); + raw_local_irq_enable(); if (!current_set_polling_and_test()) { - unsigned int loop_count = 0; - u64 limit; - - limit = cpuidle_poll_time(drv, dev); - - while (!need_resched()) { - cpu_relax(); - if (loop_count++ < POLL_IDLE_RELAX_COUNT) - continue; - - loop_count = 0; - if (local_clock_noinstr() - time_start > limit) { - dev->poll_time_limit = true; - break; - } - } + flags = smp_cond_load_relaxed_timeout(¤t_thread_info()->flags, + (VAL & _TIF_NEED_RESCHED), + (local_clock_noinstr() >= time_end)); + dev->poll_time_limit = !(flags & _TIF_NEED_RESCHED); } raw_local_irq_disable(); diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index d4f581c1e21d..9a218f558c5c 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -273,6 +273,69 @@ do { \ }) #endif +#ifndef SMP_TIMEOUT_POLL_COUNT +#define SMP_TIMEOUT_POLL_COUNT 200 +#endif + +#ifndef cpu_poll_relax +#define cpu_poll_relax(ptr, val) cpu_relax() +#endif + +/** + * smp_cond_load_relaxed_timeout() - (Spin) wait for cond with no ordering + * guarantees until a timeout expires. + * @ptr: pointer to the variable to wait on + * @cond: boolean expression to wait for + * @time_check_expr: expression to decide when to bail out + * + * Equivalent to using READ_ONCE() on the condition variable. + */ +#ifndef smp_cond_load_relaxed_timeout +#define smp_cond_load_relaxed_timeout(ptr, cond_expr, time_check_expr) \ +({ \ + typeof(ptr) __PTR = (ptr); \ + __unqual_scalar_typeof(*ptr) VAL; \ + u32 __n = 0, __spin = SMP_TIMEOUT_POLL_COUNT; \ + \ + for (;;) { \ + VAL = READ_ONCE(*__PTR); \ + if (cond_expr) \ + break; \ + cpu_poll_relax(__PTR, VAL); \ + if (++__n < __spin) \ + continue; \ + if (time_check_expr) { \ + VAL = READ_ONCE(*__PTR); \ + break; \ + } \ + __n = 0; \ + } \ + (typeof(*ptr))VAL; \ +}) +#endif + +/** + * smp_cond_load_acquire_timeout() - (Spin) wait for cond with ACQUIRE ordering + * until a timeout expires. + * + * Arguments: same as smp_cond_load_relaxed_timeout(). + * + * Equivalent to using smp_cond_load_acquire() on the condition variable with + * a timeout. + */ +#ifndef smp_cond_load_acquire_timeout +#define smp_cond_load_acquire_timeout(ptr, cond_expr, time_check_expr) \ +({ \ + __unqual_scalar_typeof(*ptr) _val; \ + _val = smp_cond_load_relaxed_timeout(ptr, cond_expr, \ + time_check_expr); \ + \ + /* Depends on the control dependency of the wait above. */ \ + smp_acquire__after_ctrl_dep(); \ + (typeof(*ptr))_val; \ +}) +#endif + /* * pmem_wmb() ensures that all stores for which the modification * are written to persistent storage by preceding instructions have diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 8dd57c3a99e9..49f8100ad8af 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -31,6 +31,16 @@ #define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) #define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) +#define atomic_cond_read_acquire_timeout(v, c, t) \ + smp_cond_load_acquire_timeout(&(v)->counter, (c), (t)) +#define atomic_cond_read_relaxed_timeout(v, c, t) \ + smp_cond_load_relaxed_timeout(&(v)->counter, (c), (t)) + +#define atomic64_cond_read_acquire_timeout(v, c, t) \ + smp_cond_load_acquire_timeout(&(v)->counter, (c), (t)) +#define atomic64_cond_read_relaxed_timeout(v, c, t) \ + smp_cond_load_relaxed_timeout(&(v)->counter, (c), (t)) + /* * The idea here is to build acquire/release variants by adding explicit * barriers on top of the relaxed variant. In the case where the relaxed diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c index 21be48108e96..c90cb66f3b45 100644 --- a/kernel/bpf/rqspinlock.c +++ b/kernel/bpf/rqspinlock.c @@ -238,20 +238,14 @@ static noinline int check_timeout(rqspinlock_t *lock, u32 mask, } /* - * Do not amortize with spins when res_smp_cond_load_acquire is defined, - * as the macro does internal amortization for us. + * Amortize timeout check for busy-wait loops. */ -#ifndef res_smp_cond_load_acquire #define RES_CHECK_TIMEOUT(ts, ret, mask) \ ({ \ if (!(ts).spin++) \ (ret) = check_timeout((lock), (mask), &(ts)); \ (ret); \ }) -#else -#define RES_CHECK_TIMEOUT(ts, ret, mask) \ - ({ (ret) = check_timeout((lock), (mask), &(ts)); }) -#endif /* * Initialize the 'spin' member. @@ -265,6 +259,16 @@ static noinline int check_timeout(rqspinlock_t *lock, u32 mask, */ #define RES_RESET_TIMEOUT(ts, _duration) ({ (ts).timeout_end = 0; (ts).duration = _duration; }) +/* + * Limit how often check_timeout() is invoked while spin-waiting in + * smp_cond_load_acquire_timeout() or atomic_cond_read_acquire_timeout(). + * (ARM64, typically uses a waited implementation so we exclude that.) + */ +#ifndef CONFIG_ARM64 +#undef SMP_TIMEOUT_POLL_COUNT +#define SMP_TIMEOUT_POLL_COUNT (16*1024) +#endif + /* * Provide a test-and-set fallback for cases when queued spin lock support is * absent from the architecture. @@ -310,12 +314,6 @@ EXPORT_SYMBOL_GPL(resilient_tas_spin_lock); */ static DEFINE_PER_CPU_ALIGNED(struct qnode, rqnodes[_Q_MAX_NODES]); -#ifndef res_smp_cond_load_acquire -#define res_smp_cond_load_acquire(v, c) smp_cond_load_acquire(v, c) -#endif - -#define res_atomic_cond_read_acquire(v, c) res_smp_cond_load_acquire(&(v)->counter, (c)) - /** * resilient_queued_spin_lock_slowpath - acquire the queued spinlock * @lock: Pointer to queued spinlock structure @@ -415,7 +413,8 @@ int __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val) */ if (val & _Q_LOCKED_MASK) { RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT); - res_smp_cond_load_acquire(&lock->locked, !VAL || RES_CHECK_TIMEOUT(ts, ret, _Q_LOCKED_MASK)); + smp_cond_load_acquire_timeout(&lock->locked, !VAL, + (ret = check_timeout(lock, _Q_LOCKED_MASK, &ts))); } if (ret) { @@ -569,9 +568,8 @@ int __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val) * us. */ RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT * 2); - val = res_atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK) || - RES_CHECK_TIMEOUT(ts, ret, _Q_LOCKED_PENDING_MASK)); - + val = atomic_cond_read_acquire_timeout(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK), + (ret = check_timeout(lock, _Q_LOCKED_PENDING_MASK, &ts))); waitq_timeout: if (ret) { /*