[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <54DB91C6.6070400@intel.com>
Date: Wed, 11 Feb 2015 19:30:46 +0200
From: Mathias Nyman <mathias.nyman@...el.com>
To: Gregory CLEMENT <gregory.clement@...e-electrons.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
linux-usb@...r.kernel.org, linux-kernel@...r.kernel.org
CC: Thomas Petazzoni <thomas.petazzoni@...e-electrons.com>,
Ezequiel Garcia <ezequiel.garcia@...e-electrons.com>,
Maxime Ripard <maxime.ripard@...e-electrons.com>,
Boris BREZILLON <boris.brezillon@...e-electrons.com>,
Lior Amsalem <alior@...vell.com>,
Tawfik Bayouk <tawfik@...vell.com>,
Nadav Haklai <nadavh@...vell.com>,
Shimmer Huang <shimmerh@...vell.com>,
Guang Shen <gshen@...vell.com>, stable@...r.kernel.org
Subject: Re: [PATCH] xhci: Fix the lack of support for the Handle Port Configure
Error
On 06.02.2015 17:20, Gregory CLEMENT wrote:
> From: Shimmer Huang <shimmerh@...vell.com>
>
> 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@...e-electrons.com: ported from 3.10 and added more
> explanations(from Shimmer) in the commit log]
>
> Signed-off-by: Guang Shen <gshen@...vell.com>
> Signed-off-by: Shimmer Huang <shimmerh@...vell.com>
> Signed-off-by: Nadav Haklai <nadavh@...vell.com>
> Reviewed-by: Yehuda Yitschak <yehuday@...vell.com>
> Signed-off-by: Gregory CLEMENT <gregory.clement@...e-electrons.com>
> Cc: <stable@...r.kernel.org>
> ---
> 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@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists