From: Jia He Date: Mon, 22 Jan 2018 04:41:28 +0000 (-0800) Subject: ring: introduce C11 memory model barrier option X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=39368ebfc606;p=dpdk.git ring: introduce C11 memory model barrier option This patch is to support C11 memory model barrier in librte_ring. There are 2 barrier implementation options in librte_ring (suggested by Jerin). 1. use rte_smp_rmb 2. use load_acquire/store_release(refer to [1]). The reason why providing 2 options is the performance benchmark difference in different arm machines, refer to [2]. CONFIG_RTE_RING_USE_C11_MEM_MODEL is provided, and by default it is "n" on any architectures and only "y" on arm64 so far. [1] https://github.com/freebsd/freebsd/blob/master/sys/sys/buf_ring.h#L170 [2] http://dpdk.org/ml/archives/dev/2017-October/080861.html Suggested-by: Jerin Jacob Signed-off-by: Jia He Acked-by: Jerin Jacob Acked-by: Olivier Matz Acked-by: Jianbo Liu Acked-by: Hemant Agrawal --- diff --git a/config/common_armv8a_linuxapp b/config/common_armv8a_linuxapp index 790e716263..111c00565e 100644 --- a/config/common_armv8a_linuxapp +++ b/config/common_armv8a_linuxapp @@ -29,6 +29,8 @@ CONFIG_RTE_ARCH_ARM64_MEMCPY=n #CONFIG_RTE_ARM64_MEMCPY_ALIGN_MASK=0xF #CONFIG_RTE_ARM64_MEMCPY_STRICT_ALIGN=n +CONFIG_RTE_RING_USE_C11_MEM_MODEL=y + CONFIG_RTE_LIBRTE_FM10K_PMD=n CONFIG_RTE_LIBRTE_SFC_EFX_PMD=n CONFIG_RTE_LIBRTE_AVP_PMD=n diff --git a/config/common_base b/config/common_base index 170a38939f..c5be864b45 100644 --- a/config/common_base +++ b/config/common_base @@ -611,6 +611,7 @@ CONFIG_RTE_LIBRTE_PMD_DPAA2_EVENTDEV=n # Compile librte_ring # CONFIG_RTE_LIBRTE_RING=y +CONFIG_RTE_RING_USE_C11_MEM_MODEL=n # # Compile librte_mempool diff --git a/lib/librte_ring/Makefile b/lib/librte_ring/Makefile index 281ffb718e..bde8907d6d 100644 --- a/lib/librte_ring/Makefile +++ b/lib/librte_ring/Makefile @@ -18,6 +18,7 @@ SRCS-$(CONFIG_RTE_LIBRTE_RING) := rte_ring.c # install includes SYMLINK-$(CONFIG_RTE_LIBRTE_RING)-include := rte_ring.h \ - rte_ring_generic.h + rte_ring_generic.h \ + rte_ring_c11_mem.h include $(RTE_SDK)/mk/rte.lib.mk diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h index bc3756adce..cbf2f19ed7 100644 --- a/lib/librte_ring/rte_ring.h +++ b/lib/librte_ring/rte_ring.h @@ -357,8 +357,20 @@ void rte_ring_dump(FILE *f, const struct rte_ring *r); } \ } while (0) -/* Move common functions to generic file */ +/* Between load and load. there might be cpu reorder in weak model + * (powerpc/arm). + * There are 2 choices for the users + * 1.use rmb() memory barrier + * 2.use one-direcion load_acquire/store_release barrier,defined by + * CONFIG_RTE_RING_USE_C11_MEM_MODEL=y + * It depends on performance test results. + * By default, move common functions to rte_ring_generic.h + */ +#ifdef RTE_RING_USE_C11_MEM_MODEL +#include "rte_ring_c11_mem.h" +#else #include "rte_ring_generic.h" +#endif /** * @internal Enqueue several objects on the ring diff --git a/lib/librte_ring/rte_ring_c11_mem.h b/lib/librte_ring/rte_ring_c11_mem.h new file mode 100644 index 0000000000..8ccb937f85 --- /dev/null +++ b/lib/librte_ring/rte_ring_c11_mem.h @@ -0,0 +1,218 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2017 HXT-semitech Corporation. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of HXT-semitech Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/* + * Derived from FreeBSD's bufring.h + * + ************************************************************************** + * + * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * 2. The name of Kip Macy nor the names of other + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + * + ***************************************************************************/ + +#ifndef _RTE_RING_C11_MEM_H_ +#define _RTE_RING_C11_MEM_H_ + +static __rte_always_inline void +update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val, + uint32_t single, uint32_t enqueue) +{ + RTE_SET_USED(enqueue); + + /* + * If there are other enqueues/dequeues in progress that preceded us, + * we need to wait for them to complete + */ + if (!single) + while (unlikely(ht->tail != old_val)) + rte_pause(); + + __atomic_store_n(&ht->tail, new_val, __ATOMIC_RELEASE); +} + +/** + * @internal This function updates the producer head for enqueue + * + * @param r + * A pointer to the ring structure + * @param is_sp + * Indicates whether multi-producer path is needed or not + * @param n + * The number of elements we will want to enqueue, i.e. how far should the + * head be moved + * @param behavior + * RTE_RING_QUEUE_FIXED: Enqueue a fixed number of items from a ring + * RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring + * @param old_head + * Returns head value as it was before the move, i.e. where enqueue starts + * @param new_head + * Returns the current/new head value i.e. where enqueue finishes + * @param free_entries + * Returns the amount of free space in the ring BEFORE head was moved + * @return + * Actual number of objects enqueued. + * If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only. + */ +static __rte_always_inline unsigned int +__rte_ring_move_prod_head(struct rte_ring *r, int is_sp, + unsigned int n, enum rte_ring_queue_behavior behavior, + uint32_t *old_head, uint32_t *new_head, + uint32_t *free_entries) +{ + const uint32_t capacity = r->capacity; + unsigned int max = n; + int success; + + do { + /* Reset n to the initial burst count */ + n = max; + + *old_head = __atomic_load_n(&r->prod.head, + __ATOMIC_ACQUIRE); + const uint32_t cons_tail = r->cons.tail; + /* + * The subtraction is done between two unsigned 32bits value + * (the result is always modulo 32 bits even if we have + * *old_head > cons_tail). So 'free_entries' is always between 0 + * and capacity (which is < size). + */ + *free_entries = (capacity + cons_tail - *old_head); + + /* check that we have enough room in ring */ + if (unlikely(n > *free_entries)) + n = (behavior == RTE_RING_QUEUE_FIXED) ? + 0 : *free_entries; + + if (n == 0) + return 0; + + *new_head = *old_head + n; + if (is_sp) + r->prod.head = *new_head, success = 1; + else + success = __atomic_compare_exchange_n(&r->prod.head, + old_head, *new_head, + 0, __ATOMIC_ACQUIRE, + __ATOMIC_RELAXED); + } while (unlikely(success == 0)); + return n; +} + +/** + * @internal This function updates the consumer head for dequeue + * + * @param r + * A pointer to the ring structure + * @param is_sc + * Indicates whether multi-consumer path is needed or not + * @param n + * The number of elements we will want to enqueue, i.e. how far should the + * head be moved + * @param behavior + * RTE_RING_QUEUE_FIXED: Dequeue a fixed number of items from a ring + * RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring + * @param old_head + * Returns head value as it was before the move, i.e. where dequeue starts + * @param new_head + * Returns the current/new head value i.e. where dequeue finishes + * @param entries + * Returns the number of entries in the ring BEFORE head was moved + * @return + * - Actual number of objects dequeued. + * If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only. + */ +static __rte_always_inline unsigned int +__rte_ring_move_cons_head(struct rte_ring *r, int is_sc, + unsigned int n, enum rte_ring_queue_behavior behavior, + uint32_t *old_head, uint32_t *new_head, + uint32_t *entries) +{ + unsigned int max = n; + int success; + + /* move cons.head atomically */ + do { + /* Restore n as it may change every loop */ + n = max; + *old_head = __atomic_load_n(&r->cons.head, + __ATOMIC_ACQUIRE); + const uint32_t prod_tail = r->prod.tail; + /* The subtraction is done between two unsigned 32bits value + * (the result is always modulo 32 bits even if we have + * cons_head > prod_tail). So 'entries' is always between 0 + * and size(ring)-1. + */ + *entries = (prod_tail - *old_head); + + /* Set the actual entries for dequeue */ + if (n > *entries) + n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : *entries; + + if (unlikely(n == 0)) + return 0; + + *new_head = *old_head + n; + if (is_sc) + r->cons.head = *new_head, success = 1; + else + success = __atomic_compare_exchange_n(&r->cons.head, + old_head, *new_head, + 0, __ATOMIC_ACQUIRE, + __ATOMIC_RELAXED); + } while (unlikely(success == 0)); + return n; +} + +#endif /* _RTE_RING_C11_MEM_H_ */