Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753981AbbBKR3p (ORCPT ); Wed, 11 Feb 2015 12:29:45 -0500 Received: from mga09.intel.com ([134.134.136.24]:1264 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753925AbbBKR3m (ORCPT ); Wed, 11 Feb 2015 12:29:42 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.09,559,1418112000"; d="scan'208";a="453215614" Message-ID: <54DB91C6.6070400@intel.com> Date: Wed, 11 Feb 2015 19:30:46 +0200 From: Mathias Nyman User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 MIME-Version: 1.0 To: Gregory CLEMENT , Greg Kroah-Hartman , linux-usb@vger.kernel.org, linux-kernel@vger.kernel.org CC: Thomas Petazzoni , Ezequiel Garcia , Maxime Ripard , Boris BREZILLON , Lior Amsalem , Tawfik Bayouk , Nadav Haklai , Shimmer Huang , Guang Shen , stable@vger.kernel.org Subject: Re: [PATCH] xhci: Fix the lack of support for the Handle Port Configure Error References: <1423236046-24229-1-git-send-email-gregory.clement@free-electrons.com> In-Reply-To: <1423236046-24229-1-git-send-email-gregory.clement@free-electrons.com> X-Enigmail-Version: 1.6 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3030 Lines: 84 On 06.02.2015 17:20, Gregory CLEMENT wrote: > From: Shimmer Huang > > Linux xHCI driver does not check the CEC bit in register PORTSC when > handling port status events. If Port Configure Error for root hub port > occurs, CEC bit in PORTSC would be set by xHC and remains 1. This > happends when the root port fails to configure its link partner, > e.g. the port fails to exchange port capabilities information using > Port Capability LMPs. > > Then the Port Status Change Events will be blocked until all status > change bits(CEC is one of the change bits) are cleared('0') (refer to > xHCI spec 4.19.2). Otherwise, the port status change event for this > root port will not be generated anymore, then root port would look > like “dead” for user and can’t be recovered until a Host Controller > Reset(HCRST) > > This patch is to check CEC bit and clear the CEC bit if it's set to 1 > in function handle_port_status(). > > [gregory.clement@free-electrons.com: ported from 3.10 and added more > explanations(from Shimmer) in the commit log] > > Signed-off-by: Guang Shen > Signed-off-by: Shimmer Huang > Signed-off-by: Nadav Haklai > Reviewed-by: Yehuda Yitschak > Signed-off-by: Gregory CLEMENT > Cc: > --- > Hi, > > usually I tried to add a kernel version for the stable team, but for > this patch I don't know since when it makes sens to apply it. > > Gregory > > > drivers/usb/host/xhci-ring.c | 7 +++++++ > 1 file changed, 7 insertions(+) > > diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c > index e692e769c50c..45d8dd7e07f3 100644 > --- a/drivers/usb/host/xhci-ring.c > +++ b/drivers/usb/host/xhci-ring.c > @@ -1541,6 +1541,13 @@ static void handle_port_status(struct xhci_hcd *xhci, > port_id); > > temp = readl(port_array[faked_port_index]); > + > + if (temp & PORT_CEC) { > + xhci_dbg(xhci, "port failed to configure its link partner.\n"); > + xhci_test_and_clear_bit(xhci, port_array, > + faked_port_index, PORT_CEC); > + } > + > if (hcd->state == HC_STATE_SUSPENDED) { > xhci_dbg(xhci, "resume root hub\n"); > usb_hcd_resume_root_hub(hcd); > Nice catch, Looks like we're not handling the Config Error Change (CEC) at all in xhci. I think we instead need to set a Config Error in the return status of the GetPortStatus requests by setting USB_PORT_FEAT_C_PORT_CONFIG_ERROR in xhci_get_port_status(). This should cause a ClearPortFeature request, where we then can clear the bit in xhci_clear_port_change_bit() So going the long way round informing the usb core about the error instead of immediately clearing the bit. -Mathias -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/