From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.linuxfoundation.org ([140.211.169.12]:40528 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752200AbbJWRmK (ORCPT ); Fri, 23 Oct 2015 13:42:10 -0400 Subject: Patch "svcrdma: handle rdma read with a non-zero initial page offset" has been added to the 4.2-stable tree To: swise@opengridcomputing.com, bfields@redhat.com, chuck.lever@oracle.com, gregkh@linuxfoundation.org Cc: , From: Date: Fri, 23 Oct 2015 10:42:09 -0700 Message-ID: <1445622129188106@kroah.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ANSI_X3.4-1968 Content-Transfer-Encoding: 8bit Sender: stable-owner@vger.kernel.org List-ID: This is a note to let you know that I've just added the patch titled svcrdma: handle rdma read with a non-zero initial page offset to the 4.2-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: svcrdma-handle-rdma-read-with-a-non-zero-initial-page-offset.patch and it can be found in the queue-4.2 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let know about it. >>From c91aed9896946721bb30705ea2904edb3725dd61 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Mon, 28 Sep 2015 16:46:06 -0500 Subject: svcrdma: handle rdma read with a non-zero initial page offset From: Steve Wise commit c91aed9896946721bb30705ea2904edb3725dd61 upstream. The server rdma_read_chunk_lcl() and rdma_read_chunk_frmr() functions were not taking into account the initial page_offset when determining the rdma read length. This resulted in a read who's starting address and length exceeded the base/bounds of the frmr. The server gets an async error from the rdma device and kills the connection, and the client then reconnects and resends. This repeats indefinitely, and the application hangs. Most work loads don't tickle this bug apparently, but one test hit it every time: building the linux kernel on a 16 core node with 'make -j 16 O=/mnt/0' where /mnt/0 is a ramdisk mounted via NFSRDMA. This bug seems to only be tripped with devices having small fastreg page list depths. I didn't see it with mlx4, for instance. Fixes: 0bf4828983df ('svcrdma: refactor marshalling logic') Signed-off-by: Steve Wise Tested-by: Chuck Lever Signed-off-by: J. Bruce Fields Signed-off-by: Greg Kroah-Hartman --- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -146,7 +146,8 @@ int rdma_read_chunk_lcl(struct svcxprt_r ctxt->read_hdr = head; pages_needed = min_t(int, pages_needed, rdma_read_max_sge(xprt, pages_needed)); - read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); + read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset, + rs_length); for (pno = 0; pno < pages_needed; pno++) { int len = min_t(int, rs_length, PAGE_SIZE - pg_off); @@ -245,7 +246,8 @@ int rdma_read_chunk_frmr(struct svcxprt_ ctxt->direction = DMA_FROM_DEVICE; ctxt->frmr = frmr; pages_needed = min_t(int, pages_needed, xprt->sc_frmr_pg_list_len); - read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); + read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset, + rs_length); frmr->kva = page_address(rqstp->rq_arg.pages[pg_no]); frmr->direction = DMA_FROM_DEVICE; Patches currently in stable-queue which might be from swise@opengridcomputing.com are queue-4.2/svcrdma-handle-rdma-read-with-a-non-zero-initial-page-offset.patch