From owner-svn-src-all@FreeBSD.ORG Fri Nov 20 14:41:37 2009 Return-Path: Delivered-To: svn-src-all@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D08D61065670; Fri, 20 Nov 2009 14:41:37 +0000 (UTC) (envelope-from jhb@freebsd.org) Received: from cyrus.watson.org (cyrus.watson.org [65.122.17.42]) by mx1.freebsd.org (Postfix) with ESMTP id 8D33D8FC15; Fri, 20 Nov 2009 14:41:37 +0000 (UTC) Received: from bigwig.baldwin.cx (66.111.2.69.static.nyinternet.net [66.111.2.69]) by cyrus.watson.org (Postfix) with ESMTPSA id 2942E46B03; Fri, 20 Nov 2009 09:41:37 -0500 (EST) Received: from jhbbsd.hudson-trading.com (unknown [209.249.190.9]) by bigwig.baldwin.cx (Postfix) with ESMTPA id 768678A01B; Fri, 20 Nov 2009 09:41:36 -0500 (EST) From: John Baldwin To: Jung-uk Kim Date: Fri, 20 Nov 2009 07:43:26 -0500 User-Agent: KMail/1.9.7 References: <200911182340.nAINeJ3W087652@svn.freebsd.org> <200911191649.37198.jhb@freebsd.org> <200911191731.04075.jkim@FreeBSD.org> In-Reply-To: <200911191731.04075.jkim@FreeBSD.org> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200911200743.27239.jhb@freebsd.org> X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.0.1 (bigwig.baldwin.cx); Fri, 20 Nov 2009 09:41:36 -0500 (EST) X-Virus-Scanned: clamav-milter 0.95.1 at bigwig.baldwin.cx X-Virus-Status: Clean X-Spam-Status: No, score=-2.5 required=4.2 tests=AWL,BAYES_00,RDNS_NONE autolearn=no version=3.2.5 X-Spam-Checker-Version: SpamAssassin 3.2.5 (2008-06-10) on bigwig.baldwin.cx Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org, Robert Watson Subject: Re: svn commit: r199498 - in head/sys: amd64/amd64 i386/i386 net X-BeenThere: svn-src-all@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: "SVN commit messages for the entire src tree \(except for " user" and " projects" \)" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 20 Nov 2009 14:41:37 -0000 On Thursday 19 November 2009 5:31:00 pm Jung-uk Kim wrote: > On Thursday 19 November 2009 04:49 pm, John Baldwin wrote: > > On Thursday 19 November 2009 11:15:01 am Jung-uk Kim wrote: > > > On Thursday 19 November 2009 03:26 am, Robert Watson wrote: > > > > On Wed, 18 Nov 2009, Jung-uk Kim wrote: > > > > > - Change internal function bpf_jit_compile() to return > > > > > allocated size of the generated binary and remove page size > > > > > limitation for userland. - Use contigmalloc(9)/contigfree(9) > > > > > instead of malloc(9)/free(9) to make sure the generated > > > > > binary aligns properly and make it physically contiguous. > > > > > > > > Is physical contiguity actually required here -- I would have > > > > thought virtual contiguity and alignment would be sufficient, > > > > in which case the normal trick is to allocate using malloc the > > > > size + min-align + 1 and then fudge the pointer forward until > > > > it's properly aligned. > > > > > > I don't believe it is strictly necessary but I assumed it might > > > have performance benefit for very big BPF programs although I > > > have not measured it. Also, contigmalloc(9)/contigfree(9) is too > > > obvious to ignore for this purpose. :-) > > > > Why would it have a performance benefit to have the pages be > > physically contiguous? contigmalloc() is expensive and should > > really only be used if you truly need contiguous memory. If you > > can get by with malloc(), just use malloc(). > > Remember are allocating memory for a function pointer here. If we > want to take care of alignment, then "fudging the pointer forward" > trick is not going to be easy unless I embed real offset in the > structure and pass it around with the pointer. I don't mind doing it > but it seemed unnecessary to me. Besides, it is very unlikely to see > a lot of parallel BPF filter allocations in real world. Actually, > that is a big assumption for BPF JIT compiler by itself because > filter compilation is expensive. Also, if contigmalloc() fails, > bpf(4) simply falls back to good old bpf_filter(). So, I don't see > anything wrong with this. Why does a function pointer matter? Fudging the pointer forward will always work as virtual addresses always have the same sub-page alignment as physical addresses, so doing something like: foo *realp; void *p; align = 16; p = malloc(size + (align -1)); realp = (foo *)(roundup2((uintptr_t)p, align)); Will always work to give a 16-byte aligned pointer. However, the in-kernel malloc() already gives you aligned memory anyway. Are you seeing any panics or buggy behavior when using malloc()? -- John Baldwin