From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by dpdk.org (Postfix) with ESMTP id 818575A24 for ; Mon, 2 Mar 2015 11:32:44 +0100 (CET) Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by fmsmga103.fm.intel.com with ESMTP; 02 Mar 2015 02:27:38 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.09,674,1418112000"; d="scan'208";a="461256000" Received: from bricha3-mobl3.ger.corp.intel.com ([10.243.20.27]) by FMSMGA003.fm.intel.com with SMTP; 02 Mar 2015 02:26:19 -0800 Received: by (sSMTP sendmail emulation); Mon, 02 Mar 2015 10:32:24 +0025 Date: Mon, 2 Mar 2015 10:32:24 +0000 From: Bruce Richardson To: zhihong.wang@intel.com Message-ID: <20150302103224.GC8520@bricha3-MOBL3> References: <1425287030-18225-1-git-send-email-zhihong.wang@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1425287030-18225-1-git-send-email-zhihong.wang@intel.com> Organization: Intel Shannon Ltd. User-Agent: Mutt/1.5.23 (2014-03-12) Cc: dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH] A fix to work around strict-aliasing rules breaking X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 02 Mar 2015 10:32:45 -0000 On Mon, Mar 02, 2015 at 05:03:50PM +0800, zhihong.wang@intel.com wrote: > Fixed strict-aliasing rules breaking errors for some GCC version. > This looks messy. Also, I believe the definition of memcpy should include the "restrict" keyword to indicate that source and dest can't overlap. Might that help fix the issue? /Bruce > Signed-off-by: Zhihong Wang > --- > .../common/include/arch/x86/rte_memcpy.h | 44 ++++++++++++---------- > 1 file changed, 24 insertions(+), 20 deletions(-) > > diff --git a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h > index 69a5c6f..f412099 100644 > --- a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h > +++ b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h > @@ -195,6 +195,8 @@ rte_mov256blocks(uint8_t *dst, const uint8_t *src, size_t n) > static inline void * > rte_memcpy(void *dst, const void *src, size_t n) > { > + uintptr_t dstu = (uintptr_t)dst; > + uintptr_t srcu = (uintptr_t)src; > void *ret = dst; > int dstofss; > int bits; > @@ -204,22 +206,22 @@ rte_memcpy(void *dst, const void *src, size_t n) > */ > if (n < 16) { > if (n & 0x01) { > - *(uint8_t *)dst = *(const uint8_t *)src; > - src = (const uint8_t *)src + 1; > - dst = (uint8_t *)dst + 1; > + *(uint8_t *)dstu = *(const uint8_t *)srcu; > + srcu = (uintptr_t)((const uint8_t *)srcu + 1); > + dstu = (uintptr_t)((uint8_t *)dstu + 1); > } > if (n & 0x02) { > - *(uint16_t *)dst = *(const uint16_t *)src; > - src = (const uint16_t *)src + 1; > - dst = (uint16_t *)dst + 1; > + *(uint16_t *)dstu = *(const uint16_t *)srcu; > + srcu = (uintptr_t)((const uint16_t *)srcu + 1); > + dstu = (uintptr_t)((uint16_t *)dstu + 1); > } > if (n & 0x04) { > - *(uint32_t *)dst = *(const uint32_t *)src; > - src = (const uint32_t *)src + 1; > - dst = (uint32_t *)dst + 1; > + *(uint32_t *)dstu = *(const uint32_t *)srcu; > + srcu = (uintptr_t)((const uint32_t *)srcu + 1); > + dstu = (uintptr_t)((uint32_t *)dstu + 1); > } > if (n & 0x08) { > - *(uint64_t *)dst = *(const uint64_t *)src; > + *(uint64_t *)dstu = *(const uint64_t *)srcu; > } > return ret; > } > @@ -458,6 +460,8 @@ static inline void * > rte_memcpy(void *dst, const void *src, size_t n) > { > __m128i xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, xmm8; > + uintptr_t dstu = (uintptr_t)dst; > + uintptr_t srcu = (uintptr_t)src; > void *ret = dst; > int dstofss; > int srcofs; > @@ -467,22 +471,22 @@ rte_memcpy(void *dst, const void *src, size_t n) > */ > if (n < 16) { > if (n & 0x01) { > - *(uint8_t *)dst = *(const uint8_t *)src; > - src = (const uint8_t *)src + 1; > - dst = (uint8_t *)dst + 1; > + *(uint8_t *)dstu = *(const uint8_t *)srcu; > + srcu = (uintptr_t)((const uint8_t *)srcu + 1); > + dstu = (uintptr_t)((uint8_t *)dstu + 1); > } > if (n & 0x02) { > - *(uint16_t *)dst = *(const uint16_t *)src; > - src = (const uint16_t *)src + 1; > - dst = (uint16_t *)dst + 1; > + *(uint16_t *)dstu = *(const uint16_t *)srcu; > + srcu = (uintptr_t)((const uint16_t *)srcu + 1); > + dstu = (uintptr_t)((uint16_t *)dstu + 1); > } > if (n & 0x04) { > - *(uint32_t *)dst = *(const uint32_t *)src; > - src = (const uint32_t *)src + 1; > - dst = (uint32_t *)dst + 1; > + *(uint32_t *)dstu = *(const uint32_t *)srcu; > + srcu = (uintptr_t)((const uint32_t *)srcu + 1); > + dstu = (uintptr_t)((uint32_t *)dstu + 1); > } > if (n & 0x08) { > - *(uint64_t *)dst = *(const uint64_t *)src; > + *(uint64_t *)dstu = *(const uint64_t *)srcu; > } > return ret; > } > -- > 1.9.3 >