From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 80ACC42829; Thu, 23 Mar 2023 23:34:57 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id A32BE42B7E; Thu, 23 Mar 2023 23:34:46 +0100 (CET) Received: from linux.microsoft.com (linux.microsoft.com [13.77.154.182]) by mails.dpdk.org (Postfix) with ESMTP id A17394111C for ; Thu, 23 Mar 2023 23:34:43 +0100 (CET) Received: by linux.microsoft.com (Postfix, from userid 1086) id E6E0320DEE3C; Thu, 23 Mar 2023 15:34:42 -0700 (PDT) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com E6E0320DEE3C DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1679610882; bh=TqXnesmaBxjdKF6DG3ykxoKllgcb0eTh9BOuIYQigRM=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=tAVahbcTl2viIr1gR8RZ9NdovKqW2H8SkGU1gpehK5MLPlrJVgmWNMGrAMM1Ew+bu k4vpDSlw86W164enCSj+a6dxptA1ustV/Rhs4g0HoAXCuZ/y6DLHMGG/Fujorm2erI h7RYEQV9pHddeHB74bw+ecaH4u59wuuDDVwrztMo= From: Tyler Retzlaff To: dev@dpdk.org Cc: Honnappa.Nagarahalli@arm.com, Ruifeng.Wang@arm.com, thomas@monjalon.net, stephen@networkplumber.org, mb@smartsharesystems.com, Tyler Retzlaff Subject: [PATCH v2 2/7] stack: replace rte atomics with GCC builtin atomics Date: Thu, 23 Mar 2023 15:34:36 -0700 Message-Id: <1679610881-25997-3-git-send-email-roretzla@linux.microsoft.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1679610881-25997-1-git-send-email-roretzla@linux.microsoft.com> References: <1679084388-19267-1-git-send-email-roretzla@linux.microsoft.com> <1679610881-25997-1-git-send-email-roretzla@linux.microsoft.com> X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Replace the use of rte_atomic.h types and functions, instead use GCC supplied C++11 memory model builtins. Signed-off-by: Tyler Retzlaff --- lib/stack/rte_stack_lf_generic.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/lib/stack/rte_stack_lf_generic.h b/lib/stack/rte_stack_lf_generic.h index 7fa29ce..ffed2bf 100644 --- a/lib/stack/rte_stack_lf_generic.h +++ b/lib/stack/rte_stack_lf_generic.h @@ -26,8 +26,8 @@ * elements. If the mempool is near-empty to the point that this is a * concern, the user should consider increasing the mempool size. */ - return (unsigned int)rte_atomic64_read((rte_atomic64_t *) - &s->stack_lf.used.len); + // NOTE: review for potential ordering optimization + return __atomic_load_n(&s->stack_lf.used.len, __ATOMIC_SEQ_CST); } static __rte_always_inline void @@ -67,8 +67,8 @@ 1, __ATOMIC_RELEASE, __ATOMIC_RELAXED); } while (success == 0); - - rte_atomic64_add((rte_atomic64_t *)&list->len, num); + // NOTE: review for potential ordering optimization + __atomic_fetch_add(&list->len, num, __ATOMIC_SEQ_CST); } static __rte_always_inline struct rte_stack_lf_elem * @@ -82,14 +82,16 @@ /* Reserve num elements, if available */ while (1) { - uint64_t len = rte_atomic64_read((rte_atomic64_t *)&list->len); + // NOTE: review for potential ordering optimization + uint64_t len = __atomic_load_n(&list->len, __ATOMIC_SEQ_CST); /* Does the list contain enough elements? */ if (unlikely(len < num)) return NULL; - if (rte_atomic64_cmpset((volatile uint64_t *)&list->len, - len, len - num)) + // NOTE: review for potential ordering optimization + if (__atomic_compare_exchange_n(&list->len, &len, len - num, + 0, __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST)) break; } -- 1.8.3.1