From patchwork Tue Oct 8 09:55:24 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ruifeng Wang X-Patchwork-Id: 60695 Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id D13FF1BFE4; Tue, 8 Oct 2019 11:55:47 +0200 (CEST) Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by dpdk.org (Postfix) with ESMTP id DACC037AF; Tue, 8 Oct 2019 11:55:45 +0200 (CEST) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 52E931570; Tue, 8 Oct 2019 02:55:45 -0700 (PDT) Received: from net-arm-c2400-02.shanghai.arm.com (net-arm-c2400-02.shanghai.arm.com [10.169.40.42]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 27D263F6C4; Tue, 8 Oct 2019 02:55:42 -0700 (PDT) From: Ruifeng Wang To: david.hunt@intel.com Cc: dev@dpdk.org, hkalra@marvell.com, gavin.hu@arm.com, honnappa.nagarahalli@arm.com, nd@arm.com, Ruifeng Wang , stable@dpdk.org Date: Tue, 8 Oct 2019 17:55:24 +0800 Message-Id: <20191008095524.1585-1-ruifeng.wang@arm.com> X-Mailer: git-send-email 2.17.1 Subject: [dpdk-dev] [PATCH] lib/distributor: fix deadlock issue for aarch64 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Distributor and worker threads rely on data structs in cache line for synchronization. The shared data structs were not protected. This caused deadlock issue on weaker memory ordering platforms as aarch64. Fix this issue by adding memory barriers to ensure synchronization among cores. Bugzilla ID: 342 Fixes: 775003ad2f96 ("distributor: add new burst-capable library") Cc: stable@dpdk.org Signed-off-by: Ruifeng Wang Reviewed-by: Gavin Hu Acked-by: David Hunt --- lib/librte_distributor/rte_distributor.c | 28 ++++++++++------ lib/librte_distributor/rte_distributor_v20.c | 34 +++++++++++++------- 2 files changed, 41 insertions(+), 21 deletions(-) diff --git a/lib/librte_distributor/rte_distributor.c b/lib/librte_distributor/rte_distributor.c index 21eb1fb0a..7bf96e224 100644 --- a/lib/librte_distributor/rte_distributor.c +++ b/lib/librte_distributor/rte_distributor.c @@ -50,7 +50,8 @@ rte_distributor_request_pkt_v1705(struct rte_distributor *d, retptr64 = &(buf->retptr64[0]); /* Spin while handshake bits are set (scheduler clears it) */ - while (unlikely(*retptr64 & RTE_DISTRIB_GET_BUF)) { + while (unlikely(__atomic_load_n(retptr64, __ATOMIC_ACQUIRE) + & RTE_DISTRIB_GET_BUF)) { rte_pause(); uint64_t t = rte_rdtsc()+100; @@ -76,7 +77,8 @@ rte_distributor_request_pkt_v1705(struct rte_distributor *d, * Finally, set the GET_BUF to signal to distributor that cache * line is ready for processing */ - *retptr64 |= RTE_DISTRIB_GET_BUF; + __atomic_store_n(retptr64, *retptr64 | RTE_DISTRIB_GET_BUF, + __ATOMIC_RELEASE); } BIND_DEFAULT_SYMBOL(rte_distributor_request_pkt, _v1705, 17.05); MAP_STATIC_SYMBOL(void rte_distributor_request_pkt(struct rte_distributor *d, @@ -99,7 +101,8 @@ rte_distributor_poll_pkt_v1705(struct rte_distributor *d, } /* If bit is set, return */ - if (buf->bufptr64[0] & RTE_DISTRIB_GET_BUF) + if (__atomic_load_n(&(buf->bufptr64[0]), __ATOMIC_ACQUIRE) + & RTE_DISTRIB_GET_BUF) return -1; /* since bufptr64 is signed, this should be an arithmetic shift */ @@ -116,6 +119,8 @@ rte_distributor_poll_pkt_v1705(struct rte_distributor *d, * on the next cacheline while we're working. */ buf->bufptr64[0] |= RTE_DISTRIB_GET_BUF; + __atomic_store_n(&(buf->bufptr64[0]), + buf->bufptr64[0] | RTE_DISTRIB_GET_BUF, __ATOMIC_RELEASE); return count; } @@ -183,7 +188,8 @@ rte_distributor_return_pkt_v1705(struct rte_distributor *d, RTE_DISTRIB_FLAG_BITS) | RTE_DISTRIB_RETURN_BUF; /* set the GET_BUF but even if we got no returns */ - buf->retptr64[0] |= RTE_DISTRIB_GET_BUF; + __atomic_store_n(&(buf->retptr64[0]), + buf->retptr64[0] | RTE_DISTRIB_GET_BUF, __ATOMIC_RELEASE); return 0; } @@ -273,7 +279,8 @@ handle_returns(struct rte_distributor *d, unsigned int wkr) unsigned int count = 0; unsigned int i; - if (buf->retptr64[0] & RTE_DISTRIB_GET_BUF) { + if (__atomic_load_n(&(buf->retptr64[0]), __ATOMIC_ACQUIRE) + & RTE_DISTRIB_GET_BUF) { for (i = 0; i < RTE_DIST_BURST_SIZE; i++) { if (buf->retptr64[i] & RTE_DISTRIB_RETURN_BUF) { oldbuf = ((uintptr_t)(buf->retptr64[i] >> @@ -287,7 +294,7 @@ handle_returns(struct rte_distributor *d, unsigned int wkr) d->returns.start = ret_start; d->returns.count = ret_count; /* Clear for the worker to populate with more returns */ - buf->retptr64[0] = 0; + __atomic_store_n(&(buf->retptr64[0]), 0, __ATOMIC_RELEASE); } return count; } @@ -307,7 +314,8 @@ release(struct rte_distributor *d, unsigned int wkr) struct rte_distributor_buffer *buf = &(d->bufs[wkr]); unsigned int i; - while (!(d->bufs[wkr].bufptr64[0] & RTE_DISTRIB_GET_BUF)) + while (!(__atomic_load_n(&(d->bufs[wkr].bufptr64[0]), __ATOMIC_ACQUIRE) + & RTE_DISTRIB_GET_BUF)) rte_pause(); handle_returns(d, wkr); @@ -328,7 +336,8 @@ release(struct rte_distributor *d, unsigned int wkr) d->backlog[wkr].count = 0; /* Clear the GET bit */ - buf->bufptr64[0] &= ~RTE_DISTRIB_GET_BUF; + __atomic_store_n(&(buf->bufptr64[0]), + buf->bufptr64[0] & ~RTE_DISTRIB_GET_BUF, __ATOMIC_RELEASE); return buf->count; } @@ -574,7 +583,8 @@ rte_distributor_clear_returns_v1705(struct rte_distributor *d) /* throw away returns, so workers can exit */ for (wkr = 0; wkr < d->num_workers; wkr++) - d->bufs[wkr].retptr64[0] = 0; + __atomic_store_n(&(d->bufs[wkr].retptr64[0]), 0, + __ATOMIC_RELEASE); } BIND_DEFAULT_SYMBOL(rte_distributor_clear_returns, _v1705, 17.05); MAP_STATIC_SYMBOL(void rte_distributor_clear_returns(struct rte_distributor *d), diff --git a/lib/librte_distributor/rte_distributor_v20.c b/lib/librte_distributor/rte_distributor_v20.c index cdc0969a8..3a5810c6d 100644 --- a/lib/librte_distributor/rte_distributor_v20.c +++ b/lib/librte_distributor/rte_distributor_v20.c @@ -34,9 +34,10 @@ rte_distributor_request_pkt_v20(struct rte_distributor_v20 *d, union rte_distributor_buffer_v20 *buf = &d->bufs[worker_id]; int64_t req = (((int64_t)(uintptr_t)oldpkt) << RTE_DISTRIB_FLAG_BITS) | RTE_DISTRIB_GET_BUF; - while (unlikely(buf->bufptr64 & RTE_DISTRIB_FLAGS_MASK)) + while (unlikely(__atomic_load_n(&(buf->bufptr64), __ATOMIC_ACQUIRE) + & RTE_DISTRIB_FLAGS_MASK)) rte_pause(); - buf->bufptr64 = req; + __atomic_store_n(&(buf->bufptr64), req, __ATOMIC_RELEASE); } VERSION_SYMBOL(rte_distributor_request_pkt, _v20, 2.0); @@ -45,7 +46,8 @@ rte_distributor_poll_pkt_v20(struct rte_distributor_v20 *d, unsigned worker_id) { union rte_distributor_buffer_v20 *buf = &d->bufs[worker_id]; - if (buf->bufptr64 & RTE_DISTRIB_GET_BUF) + if (__atomic_load_n(&(buf->bufptr64), __ATOMIC_ACQUIRE) + & RTE_DISTRIB_GET_BUF) return NULL; /* since bufptr64 is signed, this should be an arithmetic shift */ @@ -73,7 +75,7 @@ rte_distributor_return_pkt_v20(struct rte_distributor_v20 *d, union rte_distributor_buffer_v20 *buf = &d->bufs[worker_id]; uint64_t req = (((int64_t)(uintptr_t)oldpkt) << RTE_DISTRIB_FLAG_BITS) | RTE_DISTRIB_RETURN_BUF; - buf->bufptr64 = req; + __atomic_store_n(&(buf->bufptr64), req, __ATOMIC_RELEASE); return 0; } VERSION_SYMBOL(rte_distributor_return_pkt, _v20, 2.0); @@ -117,7 +119,7 @@ handle_worker_shutdown(struct rte_distributor_v20 *d, unsigned int wkr) { d->in_flight_tags[wkr] = 0; d->in_flight_bitmask &= ~(1UL << wkr); - d->bufs[wkr].bufptr64 = 0; + __atomic_store_n(&(d->bufs[wkr].bufptr64), 0, __ATOMIC_RELEASE); if (unlikely(d->backlog[wkr].count != 0)) { /* On return of a packet, we need to move the * queued packets for this core elsewhere. @@ -165,13 +167,17 @@ process_returns(struct rte_distributor_v20 *d) const int64_t data = d->bufs[wkr].bufptr64; uintptr_t oldbuf = 0; - if (data & RTE_DISTRIB_GET_BUF) { + if (__atomic_load_n(&data, __ATOMIC_ACQUIRE) + & RTE_DISTRIB_GET_BUF) { flushed++; if (d->backlog[wkr].count) - d->bufs[wkr].bufptr64 = - backlog_pop(&d->backlog[wkr]); + __atomic_store_n(&(d->bufs[wkr].bufptr64), + backlog_pop(&d->backlog[wkr]), + __ATOMIC_RELEASE); else { - d->bufs[wkr].bufptr64 = RTE_DISTRIB_GET_BUF; + __atomic_store_n(&(d->bufs[wkr].bufptr64), + RTE_DISTRIB_GET_BUF, + __ATOMIC_RELEASE); d->in_flight_tags[wkr] = 0; d->in_flight_bitmask &= ~(1UL << wkr); } @@ -251,7 +257,8 @@ rte_distributor_process_v20(struct rte_distributor_v20 *d, } } - if ((data & RTE_DISTRIB_GET_BUF) && + if ((__atomic_load_n(&data, __ATOMIC_ACQUIRE) + & RTE_DISTRIB_GET_BUF) && (d->backlog[wkr].count || next_mb)) { if (d->backlog[wkr].count) @@ -280,13 +287,16 @@ rte_distributor_process_v20(struct rte_distributor_v20 *d, * if they are ready */ for (wkr = 0; wkr < d->num_workers; wkr++) if (d->backlog[wkr].count && - (d->bufs[wkr].bufptr64 & RTE_DISTRIB_GET_BUF)) { + (__atomic_load_n(&(d->bufs[wkr].bufptr64), + __ATOMIC_ACQUIRE) & RTE_DISTRIB_GET_BUF)) { int64_t oldbuf = d->bufs[wkr].bufptr64 >> RTE_DISTRIB_FLAG_BITS; store_return(oldbuf, d, &ret_start, &ret_count); - d->bufs[wkr].bufptr64 = backlog_pop(&d->backlog[wkr]); + __atomic_store_n(&(d->bufs[wkr].bufptr64), + backlog_pop(&d->backlog[wkr]), + __ATOMIC_RELEASE); } d->returns.start = ret_start;