From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga01.intel.com (mga01.intel.com [192.55.52.88]) by dpdk.org (Postfix) with ESMTP id 890CD1B2C9; Thu, 21 Dec 2017 18:32:07 +0100 (CET) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga008.jf.intel.com ([10.7.209.65]) by fmsmga101.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 21 Dec 2017 09:32:06 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.45,436,1508828400"; d="scan'208";a="4660469" Received: from irvmail001.ir.intel.com ([163.33.26.43]) by orsmga008.jf.intel.com with ESMTP; 21 Dec 2017 09:32:05 -0800 Received: from sivswdev01.ir.intel.com (sivswdev01.ir.intel.com [10.237.217.45]) by irvmail001.ir.intel.com (8.14.3/8.13.6/MailSET/Hub) with ESMTP id vBLHW4CV029793; Thu, 21 Dec 2017 17:32:04 GMT Received: from sivswdev01.ir.intel.com (localhost [127.0.0.1]) by sivswdev01.ir.intel.com with ESMTP id vBLHW4aP007686; Thu, 21 Dec 2017 17:32:04 GMT Received: (from aburakov@localhost) by sivswdev01.ir.intel.com with LOCAL id vBLHW4cS007682; Thu, 21 Dec 2017 17:32:04 GMT From: Anatoly Burakov To: dev@dpdk.org Cc: Sergio Gonzalez Monroy , stable@dpdk.org Date: Thu, 21 Dec 2017 17:32:04 +0000 Message-Id: <39635342ba1c29bc96bee904e6b888b058f0a5ca.1513865781.git.anatoly.burakov@intel.com> X-Mailer: git-send-email 1.7.0.7 Subject: [dpdk-dev] [PATCH] eal: protect malloc stats with lock 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: , X-List-Received-Date: Thu, 21 Dec 2017 17:32:08 -0000 When we're gathering statistics, we are traversing the freelist, which may change under our feet in multithreaded scenario. This is verified by occasional segfaults when running malloc autotest on a machine with big amount of cores. This patch protects malloc heap stats call with a lock. It changes its definition in the process due to locking invalidating the const-ness, but this isn't a public API, so that's OK. Cc: stable@dpdk.org Signed-off-by: Anatoly Burakov --- lib/librte_eal/common/malloc_heap.c | 6 +++++- lib/librte_eal/common/malloc_heap.h | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/lib/librte_eal/common/malloc_heap.c b/lib/librte_eal/common/malloc_heap.c index 267a4c6..c731f1c 100644 --- a/lib/librte_eal/common/malloc_heap.c +++ b/lib/librte_eal/common/malloc_heap.c @@ -178,12 +178,14 @@ malloc_heap_alloc(struct malloc_heap *heap, * Function to retrieve data for heap on given socket */ int -malloc_heap_get_stats(const struct malloc_heap *heap, +malloc_heap_get_stats(struct malloc_heap *heap, struct rte_malloc_socket_stats *socket_stats) { size_t idx; struct malloc_elem *elem; + rte_spinlock_lock(&heap->lock); + /* Initialise variables for heap */ socket_stats->free_count = 0; socket_stats->heap_freesz_bytes = 0; @@ -205,6 +207,8 @@ malloc_heap_get_stats(const struct malloc_heap *heap, socket_stats->heap_allocsz_bytes = (socket_stats->heap_totalsz_bytes - socket_stats->heap_freesz_bytes); socket_stats->alloc_count = heap->alloc_count; + + rte_spinlock_unlock(&heap->lock); return 0; } diff --git a/lib/librte_eal/common/malloc_heap.h b/lib/librte_eal/common/malloc_heap.h index 3ccbef0..3b1166f 100644 --- a/lib/librte_eal/common/malloc_heap.h +++ b/lib/librte_eal/common/malloc_heap.h @@ -57,7 +57,7 @@ malloc_heap_alloc(struct malloc_heap *heap, const char *type, size_t size, unsigned flags, size_t align, size_t bound); int -malloc_heap_get_stats(const struct malloc_heap *heap, +malloc_heap_get_stats(struct malloc_heap *heap, struct rte_malloc_socket_stats *socket_stats); int -- 2.7.4