Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Content-Type: text/plain;
        charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 12.1 \(3445.101.1\))
Subject: Re: [PATCH v2] xhci: workaround CSS timeout on AMD SNPS 3.0 xHC
From:   Kai Heng Feng <kai.heng.feng@canonical.com>
In-Reply-To: <1542860548-3109-1-git-send-email-Sandeep.Singh@amd.com>
Date:   Fri, 23 Nov 2018 17:29:26 +0800
Cc:     "mathias.nyman@intel.com" <mathias.nyman@intel.com>,
        "gregkh@linuxfoundation.org" <gregkh@linuxfoundation.org>,
        "linux-usb@vger.kernel.org" <linux-usb@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "S-k, Shyam-sundar" <Shyam-sundar.S-k@amd.com>,
        "Shah, Nehal-bakulchandra" <Nehal-bakulchandra.Shah@amd.com>
Content-Transfer-Encoding: 8BIT
Message-Id: <31DD822A-AB20-4CE2-A5C9-878299011F62@canonical.com>
References: <1542860548-3109-1-git-send-email-Sandeep.Singh@amd.com>
To:     "Singh, Sandeep" <Sandeep.Singh@amd.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Hi Sandeep,

> On Nov 22, 2018, at 12:23 PM, Singh, Sandeep <Sandeep.Singh@amd.com> wrote:
> 
> From: Sandeep Singh <sandeep.singh@amd.com>
> 
> Occasionally AMD SNPS 3.0 xHC does not respond to
> CSS when set, also it does not flag anything on SRE and HCE
> to point the internal xHC errors on USBSTS register. This stalls
> the entire system wide suspend and there is no point in stalling
> just because of xHC CSS is not responding.
> 
> To work around this problem, if the xHC does not flag
> anything on SRE and HCE, we can skip the CSS
> timeout and allow the system to continue the suspend. Once the
> system resume happens we can internally reset the controller
> using XHCI_RESET_ON_RESUME quirk
> 
> Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
> Signed-off-by: Sandeep Singh <Sandeep.Singh@amd.com>
> cc: Nehal Shah <Nehal-bakulchandra.Shah@amd.com>
> ---
> Changes since v1:
> 
> -> New Variable based decision making when SNPS issue happens hence 
>   quirk interdependency removed.
> -> Removed STS conditional check in suspend function.
> 
> drivers/usb/host/xhci-pci.c |  4 ++++
> drivers/usb/host/xhci.c     | 26 ++++++++++++++++++++++----
> drivers/usb/host/xhci.h     |  3 +++
> 3 files changed, 29 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
> index 01c5705..72493c4 100644
> --- a/drivers/usb/host/xhci-pci.c
> +++ b/drivers/usb/host/xhci-pci.c
> @@ -139,6 +139,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
> 		 pdev->device == 0x43bb))
> 		xhci->quirks |= XHCI_SUSPEND_DELAY;
> 
> +	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
> +	    (pdev->device == 0x15e0 || pdev->device == 0x15e1))
> +		xhci->quirks |= XHCI_SNPS_BROKEN_SUSPEND;
> +
> 	if (pdev->vendor == PCI_VENDOR_ID_AMD)
> 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
> 
> diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
> index 0420eef..808677d 100644
> --- a/drivers/usb/host/xhci.c
> +++ b/drivers/usb/host/xhci.c
> @@ -970,6 +970,7 @@ int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup)
> 	unsigned int		delay = XHCI_MAX_HALT_USEC;
> 	struct usb_hcd		*hcd = xhci_to_hcd(xhci);
> 	u32			command;
> +	u32			res;
> 
> 	if (!hcd->state)
> 		return 0;
> @@ -1023,11 +1024,28 @@ int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup)
> 	command = readl(&xhci->op_regs->command);
> 	command |= CMD_CSS;
> 	writel(command, &xhci->op_regs->command);
> +	xhci->broken_suspend = 0;
> 	if (xhci_handshake(&xhci->op_regs->status,
> 				STS_SAVE, 0, 10 * 1000)) {
> -		xhci_warn(xhci, "WARN: xHC save state timeout\n");
> -		spin_unlock_irq(&xhci->lock);
> -		return -ETIMEDOUT;
> +	/*
> +	 * AMD SNPS xHC 3.0 occasionally does not clear the
> +	 * SSS bit of USBSTS and when driver tries to poll
> +	 * to see if the xHC clears BIT(8) which never happens
> +	 * and driver assumes that controller is not responding
> +	 * and times out. To workaround this, its good to check
> +	 * if SRE and HCE bits are not set (as per xhci
> +	 * Section 5.4.2) and bypass the timeout.
> +	 */
> +		res = readl(&xhci->op_regs->status);
> +		if ((xhci->quirks & XHCI_SNPS_BROKEN_SUSPEND) &&
> +		    (((res & STS_SRE) == 0) &&
> +				((res & STS_HCE) == 0))) {
> +			xhci->broken_suspend = 1;
> +		} else {
> +			xhci_warn(xhci, "WARN: xHC save state timeout\n");
> +			spin_unlock_irq(&xhci->lock);
> +			return -ETIMEDOUT;
> +		}
> 	}
> 	spin_unlock_irq(&xhci->lock);
> 
> @@ -1080,7 +1098,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
> 	set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags);
> 
> 	spin_lock_irq(&xhci->lock);
> -	if (xhci->quirks & XHCI_RESET_ON_RESUME)
> +	if ((xhci->quirks & XHCI_RESET_ON_RESUME) || xhci->broken_suspend)
> 		hibernated = true;
> 
> 	if (!hibernated) {
> diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
> index bf0b369..d5d19b2 100644
> --- a/drivers/usb/host/xhci.h
> +++ b/drivers/usb/host/xhci.h
> @@ -1849,6 +1849,7 @@ struct xhci_hcd {
> #define XHCI_INTEL_USB_ROLE_SW	BIT_ULL(31)
> #define XHCI_ZERO_64B_REGS	BIT_ULL(32)
> #define XHCI_DEFAULT_PM_RUNTIME_ALLOW	BIT_ULL(33)
> +#define XHCI_SNPS_BROKEN_SUSPEND    BIT_ULL(34)

This bit is already in use by a another patch, so please update its value.

Kai-Heng

> 
> 	unsigned int		num_active_eps;
> 	unsigned int		limit_active_eps;
> @@ -1878,6 +1879,8 @@ struct xhci_hcd {
> 	void			*dbc;
> 	/* platform-specific data -- must come last */
> 	unsigned long		priv[0] __aligned(sizeof(s64));
> +	/* Broken Suspend flag for SNPS Suspend resume issue */
> +	u8			broken_suspend;
> };
> 
> /* Platform specific overrides to generic XHCI hc_driver ops */
> -- 
> 2.7.4
>