[2/3] xhci: Avoid USB autosuspend when resuming USB2 ports.

[2/3] xhci: Avoid USB autosuspend when resuming USB2 ports.

[Greg Kroah-Hartman]

On Fri, Sep 14, 2018 at 03:33:30PM +0300, Mathias Nyman wrote:
> From: Anshuman Gupta <anshuman.gupta@intel.com>
> 
> When USB bus host controller root hub resumes from autosuspend,
> it immediately tries to enter auto-suspend, but there can be a
> scenario when root hub is resuming its usb2 ports, in that particular
> case USB host controller auto suspend fails since it is busy
> to resuming its usb2 ports.
> 
> This makes multiple failed cycles of auto-suspend until all usb2
> ports of host controller root hub do not resume.
> 
> This patch uses USB core framework usb_hcd_start_port_resume,
> usb_hcd_end_port_resume API's in order to  autoresume/autosuspend
> root hub properly.
> 
> Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>

Not needed in stable?  Does this fix a specific commit?

thanks,

greg k-h

[2/3] xhci: Avoid USB autosuspend when resuming USB2 ports.

[Greg Kroah-Hartman]

On Wed, Sep 19, 2018 at 10:54:45AM +0530, Anshuman Gupta wrote:
> On Mon, Sep 17, 2018 at 11:24:20AM +0300, Mathias Nyman wrote:
> > On 14.09.2018 16:00, Greg KH wrote:
> > > On Fri, Sep 14, 2018 at 03:33:30PM +0300, Mathias Nyman wrote:
> > > > From: Anshuman Gupta <anshuman.gupta@intel.com>
> > > > 
> > > > When USB bus host controller root hub resumes from autosuspend,
> > > > it immediately tries to enter auto-suspend, but there can be a
> > > > scenario when root hub is resuming its usb2 ports, in that particular
> > > > case USB host controller auto suspend fails since it is busy
> > > > to resuming its usb2 ports.
> > > > 
> > > > This makes multiple failed cycles of auto-suspend until all usb2
> > > > ports of host controller root hub do not resume.
> > > > 
> > > > This patch uses USB core framework usb_hcd_start_port_resume,
> > > > usb_hcd_end_port_resume API's in order to  autoresume/autosuspend
> > > > root hub properly.
> > > > 
> > > > Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
> > > > Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
> > > 
> > > Not needed in stable?  Does this fix a specific commit?
> > > 
> > > thanks,
> > > 
> > > greg k-h
> > > 
> > 
> > This improves a bad initial design that prevented autosuspend by
> > returning -EBUSY in xhci_bus_suspend() if a usb2 port was resuming.
> > 
> > Instead increment usage count on the roothub to prevent pm from polling
> > xhci_bus_suspend(). This is also what EHCI does.
> > 
> > I'm not sure If this fixes a actual bug for Anshuman Gupta caused by
> > the -EBUSY polling,(4.19 +stable), or if this is just a improvement in
> > suspend/resume code for xhci (4.20).
> > 
> > Anshuman Gupta, any comments?
> This patch is not fixing any bug. 
> This patch provide improvement in runtime suspend/resume path of xhci.

Great, then it shouldn't go into 4.19-final :)

Mathias, can you redo this patch series and resend?

thanks,

greg k-h

[2/3] xhci: Avoid USB autosuspend when resuming USB2 ports.

[Anshuman Gupta]

On Mon, Sep 17, 2018 at 11:24:20AM +0300, Mathias Nyman wrote:
> On 14.09.2018 16:00, Greg KH wrote:
> > On Fri, Sep 14, 2018 at 03:33:30PM +0300, Mathias Nyman wrote:
> > > From: Anshuman Gupta <anshuman.gupta@intel.com>
> > > 
> > > When USB bus host controller root hub resumes from autosuspend,
> > > it immediately tries to enter auto-suspend, but there can be a
> > > scenario when root hub is resuming its usb2 ports, in that particular
> > > case USB host controller auto suspend fails since it is busy
> > > to resuming its usb2 ports.
> > > 
> > > This makes multiple failed cycles of auto-suspend until all usb2
> > > ports of host controller root hub do not resume.
> > > 
> > > This patch uses USB core framework usb_hcd_start_port_resume,
> > > usb_hcd_end_port_resume API's in order to  autoresume/autosuspend
> > > root hub properly.
> > > 
> > > Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
> > > Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
> > 
> > Not needed in stable?  Does this fix a specific commit?
> > 
> > thanks,
> > 
> > greg k-h
> > 
> 
> This improves a bad initial design that prevented autosuspend by
> returning -EBUSY in xhci_bus_suspend() if a usb2 port was resuming.
> 
> Instead increment usage count on the roothub to prevent pm from polling
> xhci_bus_suspend(). This is also what EHCI does.
> 
> I'm not sure If this fixes a actual bug for Anshuman Gupta caused by
> the -EBUSY polling,(4.19 +stable), or if this is just a improvement in
> suspend/resume code for xhci (4.20).
> 
> Anshuman Gupta, any comments?
This patch is not fixing any bug. 
This patch provide improvement in runtime suspend/resume path of xhci.
> 
> -Mathias

[2/3] xhci: Avoid USB autosuspend when resuming USB2 ports.

[Mathias Nyman]

On 14.09.2018 16:00, Greg KH wrote:
> On Fri, Sep 14, 2018 at 03:33:30PM +0300, Mathias Nyman wrote:
>> From: Anshuman Gupta <anshuman.gupta@intel.com>
>>
>> When USB bus host controller root hub resumes from autosuspend,
>> it immediately tries to enter auto-suspend, but there can be a
>> scenario when root hub is resuming its usb2 ports, in that particular
>> case USB host controller auto suspend fails since it is busy
>> to resuming its usb2 ports.
>>
>> This makes multiple failed cycles of auto-suspend until all usb2
>> ports of host controller root hub do not resume.
>>
>> This patch uses USB core framework usb_hcd_start_port_resume,
>> usb_hcd_end_port_resume API's in order to  autoresume/autosuspend
>> root hub properly.
>>
>> Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
>> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
> 
> Not needed in stable?  Does this fix a specific commit?
> 
> thanks,
> 
> greg k-h
> 

This improves a bad initial design that prevented autosuspend by
returning -EBUSY in xhci_bus_suspend() if a usb2 port was resuming.

Instead increment usage count on the roothub to prevent pm from polling
xhci_bus_suspend(). This is also what EHCI does.

I'm not sure If this fixes a actual bug for Anshuman Gupta caused by
the -EBUSY polling,(4.19 +stable), or if this is just a improvement in
suspend/resume code for xhci (4.20).

Anshuman Gupta, any comments?

-Mathias

[2/3] xhci: Avoid USB autosuspend when resuming USB2 ports.

[Mathias Nyman]

From: Anshuman Gupta <anshuman.gupta@intel.com>

When USB bus host controller root hub resumes from autosuspend,
it immediately tries to enter auto-suspend, but there can be a
scenario when root hub is resuming its usb2 ports, in that particular
case USB host controller auto suspend fails since it is busy
to resuming its usb2 ports.

This makes multiple failed cycles of auto-suspend until all usb2
ports of host controller root hub do not resume.

This patch uses USB core framework usb_hcd_start_port_resume,
usb_hcd_end_port_resume API's in order to  autoresume/autosuspend
root hub properly.

Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
---
 drivers/usb/host/xhci-hub.c  | 5 +++++
 drivers/usb/host/xhci-ring.c | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 7e2a531..12eea73 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -900,6 +900,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 				set_bit(wIndex, &bus_state->resuming_ports);
 				bus_state->resume_done[wIndex] = timeout;
 				mod_timer(&hcd->rh_timer, timeout);
+				usb_hcd_start_port_resume(&hcd->self, wIndex);
 			}
 		/* Has resume been signalled for USB_RESUME_TIME yet? */
 		} else if (time_after_eq(jiffies,
@@ -940,6 +941,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 				clear_bit(wIndex, &bus_state->rexit_ports);
 			}
 
+			usb_hcd_end_port_resume(&hcd->self, wIndex);
 			bus_state->port_c_suspend |= 1 << wIndex;
 			bus_state->suspended_ports &= ~(1 << wIndex);
 		} else {
@@ -962,6 +964,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 	    (raw_port_status & PORT_PLS_MASK) != XDEV_RESUME) {
 		bus_state->resume_done[wIndex] = 0;
 		clear_bit(wIndex, &bus_state->resuming_ports);
+		usb_hcd_end_port_resume(&hcd->self, wIndex);
 	}
 
 
@@ -1337,6 +1340,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 					goto error;
 
 				set_bit(wIndex, &bus_state->resuming_ports);
+				usb_hcd_start_port_resume(&hcd->self, wIndex);
 				xhci_set_link_state(xhci, ports[wIndex],
 						    XDEV_RESUME);
 				spin_unlock_irqrestore(&xhci->lock, flags);
@@ -1345,6 +1349,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 				xhci_set_link_state(xhci, ports[wIndex],
 							XDEV_U0);
 				clear_bit(wIndex, &bus_state->resuming_ports);
+				usb_hcd_end_port_resume(&hcd->self, wIndex);
 			}
 			bus_state->port_c_suspend |= 1 << wIndex;
 
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index f0a99aa..cd46597 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1602,6 +1602,7 @@ static void handle_port_status(struct xhci_hcd *xhci,
 			set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
 			mod_timer(&hcd->rh_timer,
 				  bus_state->resume_done[hcd_portnum]);
+			usb_hcd_start_port_resume(&hcd->self, hcd_portnum);
 			bogus_port_status = true;
 		}
 	}