Return-Path: linux-nfs-owner@vger.kernel.org Received: from aserp1040.oracle.com ([141.146.126.69]:43160 "EHLO aserp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751091AbbAIUVF convert rfc822-to-8bit (ORCPT ); Fri, 9 Jan 2015 15:21:05 -0500 Content-Type: text/plain; charset=windows-1252 Mime-Version: 1.0 (Mac OS X Mail 7.3 \(1878.6\)) Subject: Re: [PATCH v1 09/10] Move read list XDR round-up logic From: Chuck Lever In-Reply-To: <20150109201434.GA30452@fieldses.org> Date: Fri, 9 Jan 2015 15:20:54 -0500 Cc: linux-rdma , Linux NFS Mailing List Message-Id: References: <20150109191910.4901.29548.stgit@klimt.1015granger.net> <20150109192310.4901.62851.stgit@klimt.1015granger.net> <20150109201434.GA30452@fieldses.org> To: "J. Bruce Fields" Sender: linux-nfs-owner@vger.kernel.org List-ID: On Jan 9, 2015, at 3:14 PM, J. Bruce Fields wrote: > On Fri, Jan 09, 2015 at 02:23:11PM -0500, Chuck Lever wrote: >> Simpler approach, and this needs to be done before the tail is >> copied to the end of the read list (pre-requisite for a subsequent >> patch). >> >> Fixes: e560e3b510d2 ("svcrdma: Add zero padding if the client... ") > > Wait, does this actually fix a bug in that previous commit is or it > just cleanup? No change in behavior. > If the latter, the "Fixes:.." line is confusing, just mention it in the > text ("Simpler approach compared to the original attempt in > e560e3b510d2...?). OK. > > --b. > >> Signed-off-by: Chuck Lever >> --- >> >> net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 37 ++++++++----------------------- >> 1 files changed, 9 insertions(+), 28 deletions(-) >> >> diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c >> index 36cf51a..a345cad 100644 >> --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c >> +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c >> @@ -43,7 +43,6 @@ >> #include >> #include >> #include >> -#include >> #include >> #include >> #include >> @@ -434,6 +433,15 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt, >> } >> } >> >> + /* Read list may need XDR round-up (see RFC 5666, s. 3.7) */ >> + if (page_offset & 3) { >> + u32 pad = 4 - (page_offset & 3); >> + >> + head->arg.page_len += pad; >> + head->arg.len += pad; >> + head->arg.buflen += pad; >> + } >> + >> ret = 1; >> head->position = position; >> >> @@ -446,32 +454,6 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt, >> return ret; >> } >> >> -/* >> - * To avoid a separate RDMA READ just for a handful of zero bytes, >> - * RFC 5666 section 3.7 allows the client to omit the XDR zero pad >> - * in chunk lists. >> - */ >> -static void >> -rdma_fix_xdr_pad(struct xdr_buf *buf) >> -{ >> - unsigned int page_len = buf->page_len; >> - unsigned int size = (XDR_QUADLEN(page_len) << 2) - page_len; >> - unsigned int offset, pg_no; >> - char *p; >> - >> - if (size == 0) >> - return; >> - >> - pg_no = page_len >> PAGE_SHIFT; >> - offset = page_len & ~PAGE_MASK; >> - p = page_address(buf->pages[pg_no]); >> - memset(p + offset, 0, size); >> - >> - buf->page_len += size; >> - buf->buflen += size; >> - buf->len += size; >> -} >> - >> static int rdma_read_complete(struct svc_rqst *rqstp, >> struct svc_rdma_op_ctxt *head) >> { >> @@ -499,7 +481,6 @@ static int rdma_read_complete(struct svc_rqst *rqstp, >> } >> >> /* Point rq_arg.pages past header */ >> - rdma_fix_xdr_pad(&head->arg); >> rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count]; >> rqstp->rq_arg.page_len = head->arg.page_len; >> rqstp->rq_arg.page_base = head->arg.page_base; >> >> -- >> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in >> the body of a message to majordomo@vger.kernel.org >> More majordomo info at http://vger.kernel.org/majordomo-info.html > -- > To unsubscribe from this list: send the line "unsubscribe linux-rdma" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html -- Chuck Lever chuck[dot]lever[at]oracle[dot]com