From: Anatoly Burakov Date: Thu, 14 Jan 2021 14:46:07 +0000 (+0000) Subject: eal: add monitor wakeup function X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=55243435f50b35ec465df8e1af59a140262e8c47;p=dpdk.git eal: add monitor wakeup function Now that we have everything in a C file, we can store the information about our sleep, and have a native mechanism to wake up the sleeping core. This mechanism would however only wake up a core that's sleeping while monitoring - waking up from `rte_power_pause` won't work. Signed-off-by: Anatoly Burakov Acked-by: Konstantin Ananyev --- diff --git a/lib/librte_eal/arm/rte_power_intrinsics.c b/lib/librte_eal/arm/rte_power_intrinsics.c index 8d271dc0c1..e83f04072a 100644 --- a/lib/librte_eal/arm/rte_power_intrinsics.c +++ b/lib/librte_eal/arm/rte_power_intrinsics.c @@ -27,3 +27,14 @@ rte_power_pause(const uint64_t tsc_timestamp) return -ENOTSUP; } + +/** + * This function is not supported on ARM. + */ +int +rte_power_monitor_wakeup(const unsigned int lcore_id) +{ + RTE_SET_USED(lcore_id); + + return -ENOTSUP; +} diff --git a/lib/librte_eal/include/generic/rte_power_intrinsics.h b/lib/librte_eal/include/generic/rte_power_intrinsics.h index 85343bc9eb..6109d28faa 100644 --- a/lib/librte_eal/include/generic/rte_power_intrinsics.h +++ b/lib/librte_eal/include/generic/rte_power_intrinsics.h @@ -62,6 +62,22 @@ __rte_experimental int rte_power_monitor(const struct rte_power_monitor_cond *pmc, const uint64_t tsc_timestamp); +/** + * @warning + * @b EXPERIMENTAL: this API may change without prior notice + * + * Wake up a specific lcore that is in a power optimized state and is monitoring + * an address. + * + * @note This function will *not* wake up a core that is in a power optimized + * state due to calling `rte_power_pause`. + * + * @param lcore_id + * Lcore ID of a sleeping thread. + */ +__rte_experimental +int rte_power_monitor_wakeup(const unsigned int lcore_id); + /** * @warning * @b EXPERIMENTAL: this API may change without prior notice diff --git a/lib/librte_eal/ppc/rte_power_intrinsics.c b/lib/librte_eal/ppc/rte_power_intrinsics.c index f7862ea324..7fc9586da7 100644 --- a/lib/librte_eal/ppc/rte_power_intrinsics.c +++ b/lib/librte_eal/ppc/rte_power_intrinsics.c @@ -27,3 +27,14 @@ rte_power_pause(const uint64_t tsc_timestamp) return -ENOTSUP; } + +/** + * This function is not supported on PPC64. + */ +int +rte_power_monitor_wakeup(const unsigned int lcore_id) +{ + RTE_SET_USED(lcore_id); + + return -ENOTSUP; +} diff --git a/lib/librte_eal/version.map b/lib/librte_eal/version.map index 1fcd1d3bed..fce90a112f 100644 --- a/lib/librte_eal/version.map +++ b/lib/librte_eal/version.map @@ -406,6 +406,7 @@ EXPERIMENTAL { # added in 21.02 rte_power_monitor; + rte_power_monitor_wakeup; rte_power_pause; rte_thread_tls_key_create; rte_thread_tls_key_delete; diff --git a/lib/librte_eal/x86/rte_power_intrinsics.c b/lib/librte_eal/x86/rte_power_intrinsics.c index 29247d8638..af3ae3237c 100644 --- a/lib/librte_eal/x86/rte_power_intrinsics.c +++ b/lib/librte_eal/x86/rte_power_intrinsics.c @@ -2,8 +2,31 @@ * Copyright(c) 2020 Intel Corporation */ +#include +#include +#include + #include "rte_power_intrinsics.h" +/* + * Per-lcore structure holding current status of C0.2 sleeps. + */ +static struct power_wait_status { + rte_spinlock_t lock; + volatile void *monitor_addr; /**< NULL if not currently sleeping */ +} __rte_cache_aligned wait_status[RTE_MAX_LCORE]; + +static inline void +__umwait_wakeup(volatile void *addr) +{ + uint64_t val; + + /* trigger a write but don't change the value */ + val = __atomic_load_n((volatile uint64_t *)addr, __ATOMIC_RELAXED); + __atomic_compare_exchange_n((volatile uint64_t *)addr, &val, val, 0, + __ATOMIC_RELAXED, __ATOMIC_RELAXED); +} + static bool wait_supported; static inline uint64_t @@ -51,17 +74,29 @@ rte_power_monitor(const struct rte_power_monitor_cond *pmc, { const uint32_t tsc_l = (uint32_t)tsc_timestamp; const uint32_t tsc_h = (uint32_t)(tsc_timestamp >> 32); + const unsigned int lcore_id = rte_lcore_id(); + struct power_wait_status *s; /* prevent user from running this instruction if it's not supported */ if (!wait_supported) return -ENOTSUP; + /* prevent non-EAL thread from using this API */ + if (lcore_id >= RTE_MAX_LCORE) + return -EINVAL; + if (pmc == NULL) return -EINVAL; if (__check_val_size(pmc->data_sz) < 0) return -EINVAL; + s = &wait_status[lcore_id]; + + /* update sleep address */ + rte_spinlock_lock(&s->lock); + s->monitor_addr = pmc->addr; + /* * we're using raw byte codes for now as only the newest compiler * versions support this instruction natively. @@ -72,6 +107,10 @@ rte_power_monitor(const struct rte_power_monitor_cond *pmc, : : "D"(pmc->addr)); + /* now that we've put this address into monitor, we can unlock */ + rte_spinlock_unlock(&s->lock); + + /* if we have a comparison mask, we might not need to sleep at all */ if (pmc->mask) { const uint64_t cur_value = __get_umwait_val( pmc->addr, pmc->data_sz); @@ -79,14 +118,21 @@ rte_power_monitor(const struct rte_power_monitor_cond *pmc, /* if the masked value is already matching, abort */ if (masked == pmc->val) - return 0; + goto end; } + /* execute UMWAIT */ asm volatile(".byte 0xf2, 0x0f, 0xae, 0xf7;" : /* ignore rflags */ : "D"(0), /* enter C0.2 */ "a"(tsc_l), "d"(tsc_h)); +end: + /* erase sleep address */ + rte_spinlock_lock(&s->lock); + s->monitor_addr = NULL; + rte_spinlock_unlock(&s->lock); + return 0; } @@ -122,3 +168,48 @@ RTE_INIT(rte_power_intrinsics_init) { if (i.power_monitor && i.power_pause) wait_supported = 1; } + +int +rte_power_monitor_wakeup(const unsigned int lcore_id) +{ + struct power_wait_status *s; + + /* prevent user from running this instruction if it's not supported */ + if (!wait_supported) + return -ENOTSUP; + + /* prevent buffer overrun */ + if (lcore_id >= RTE_MAX_LCORE) + return -EINVAL; + + s = &wait_status[lcore_id]; + + /* + * There is a race condition between sleep, wakeup and locking, but we + * don't need to handle it. + * + * Possible situations: + * + * 1. T1 locks, sets address, unlocks + * 2. T2 locks, triggers wakeup, unlocks + * 3. T1 sleeps + * + * In this case, because T1 has already set the address for monitoring, + * we will wake up immediately even if T2 triggers wakeup before T1 + * goes to sleep. + * + * 1. T1 locks, sets address, unlocks, goes to sleep, and wakes up + * 2. T2 locks, triggers wakeup, and unlocks + * 3. T1 locks, erases address, and unlocks + * + * In this case, since we've already woken up, the "wakeup" was + * unneeded, and since T1 is still waiting on T2 releasing the lock, the + * wakeup address is still valid so it's perfectly safe to write it. + */ + rte_spinlock_lock(&s->lock); + if (s->monitor_addr != NULL) + __umwait_wakeup(s->monitor_addr); + rte_spinlock_unlock(&s->lock); + + return 0; +}