Return-path: Received: from crystal.sipsolutions.net ([195.210.38.204]:56810 "EHLO sipsolutions.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752920AbYCTOfM (ORCPT ); Thu, 20 Mar 2008 10:35:12 -0400 Subject: [PATCH/RFC] introduce ARCH_CAN_UNALIGNED_ACCESS Kconfig symbol From: Johannes Berg To: Daniel Drake Cc: Linux Kernel list , linux-wireless , netdev Content-Type: text/plain Date: Thu, 20 Mar 2008 15:34:55 +0100 Message-Id: <1206023695.16475.137.camel@johannes.berg> (sfid-20080320_143518_554842_D4F1086B) Mime-Version: 1.0 Sender: linux-wireless-owner@vger.kernel.org List-ID: In many cases, especially in networking, it can be beneficial to know at compile time whether the architecture can do unaligned accesses. This patch introduces a new Kconfig symbol ARCH_CAN_UNALIGNED_ACCESS for that purpose and adds it to the powerpc and x86 architectures. Also add some documentation about alignment and networking, and especially one intended use of this symbol. Signed-off-by: Johannes Berg --- Users will be added later, especially wireless networking can benefit. Documentation/unaligned-memory-access.txt | 32 +++++++++++++++++++++++++++--- arch/powerpc/Kconfig | 3 ++ arch/x86/Kconfig | 3 ++ 3 files changed, 35 insertions(+), 3 deletions(-) --- everything.orig/Documentation/unaligned-memory-access.txt 2008-03-20 15:19:06.000000000 +0100 +++ everything/Documentation/unaligned-memory-access.txt 2008-03-20 15:29:13.000000000 +0100 @@ -218,9 +218,35 @@ If use of such macros is not convenient, where the source or destination (or both) are of type u8* or unsigned char*. Due to the byte-wise nature of this operation, unaligned accesses are avoided. + +Alignment vs. Networking +======================== + +On architectures that require aligned loads, networking requires that the IP +header is aligned on a four-byte boundary to optimise the IP stack. For +regular ethernet hardware, the constant NET_IP_ALIGN is used, on most +architectures this constant has the value 2 because the normal ethernet +header is 14 bytes long, so in order to get proper alignment one needs to +DMA to an address that is can be expressed as 4*n + 2. One notable exception +here is powerpc which defines NET_IP_ALIGN to 0 because DMA to unaligned +addresses can be very expensive and dwarf the cost of unaligned loads. + +For some ethernet hardware that cannot DMA to unaligned addresses like +4*n+2 or non-ethernet hardware, this can be a problem, and it is then +required to copy the incoming frame into an aligned buffer. Because this is +unnecessary on architectures that can do unaligned accesses, the code can be +made depend on CONFIG_ARCH_CAN_UNALIGNED_ACCESS like so: + +#ifdef CONFIG_ARCH_CAN_UNALIGNED_ACCESS + skb = copy skb +#else + skb = original skb +#endif + -- -Author: Daniel Drake +Authors: Daniel Drake , + Johannes Berg With help from: Alan Cox, Avuton Olrich, Heikki Orsila, Jan Engelhardt, -Johannes Berg, Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, -Uli Kunitz, Vadim Lobanov +Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, Uli Kunitz, +Vadim Lobanov --- everything.orig/arch/powerpc/Kconfig 2008-03-20 15:17:50.000000000 +0100 +++ everything/arch/powerpc/Kconfig 2008-03-20 15:19:00.000000000 +0100 @@ -84,6 +84,9 @@ config GENERIC_FIND_NEXT_BIT config ARCH_NO_VIRT_TO_BUS def_bool PPC64 +config ARCH_CAN_UNALIGNED_ACCESS + def_bool y + config PPC bool default y --- everything.orig/arch/x86/Kconfig 2008-03-20 15:29:31.000000000 +0100 +++ everything/arch/x86/Kconfig 2008-03-20 15:29:49.000000000 +0100 @@ -144,6 +144,9 @@ config AUDIT_ARCH config ARCH_SUPPORTS_AOUT def_bool y +config ARCH_CAN_UNALIGNED_ACCESS + def_bool y + # Use the generic interrupt handling code in kernel/irq/: config GENERIC_HARDIRQS bool