Patchwork [3.5.y.z,extended,stable] Patch "usb: core: don't try to reset_device() a port that got just" has been added to staging queue

login
register
mail settings
Submitter Luis Henriques
Date Aug. 13, 2013, 1:59 p.m.
Message ID <1376402395-18775-1-git-send-email-luis.henriques@canonical.com>
Download mbox | patch
Permalink /patch/266810/
State New
Headers show

Comments

Luis Henriques - Aug. 13, 2013, 1:59 p.m.
This is a note to let you know that I have just added a patch titled

    usb: core: don't try to reset_device() a port that got just

to the linux-3.5.y-queue branch of the 3.5.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.5.y-queue

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.5.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Luis

------

From bdd0ccb77ce150945754b1de5cc1583fcb7a1394 Mon Sep 17 00:00:00 2001
From: Julius Werner <jwerner@chromium.org>
Date: Tue, 30 Jul 2013 19:51:20 -0700
Subject: [PATCH] usb: core: don't try to reset_device() a port that got just
 disconnected

commit 481f2d4f89f87a0baa26147f323380e31cfa7c44 upstream.

The USB hub driver's event handler contains a check to catch SuperSpeed
devices that transitioned into the SS.Inactive state and tries to fix
them with a reset. It decides whether to do a plain hub port reset or
call the usb_reset_device() function based on whether there was a device
attached to the port.

However, there are device/hub combinations (found with a JetFlash
Transcend mass storage stick (8564:1000) on the root hub of an Intel
LynxPoint PCH) which can transition to the SS.Inactive state on
disconnect (and stay there long enough for the host to notice). In this
case, above-mentioned reset check will call usb_reset_device() on the
stale device data structure. The kernel will send pointless LPM control
messages to the no longer connected device address and can even cause
several 5 second khubd stalls on some (buggy?) host controllers, before
finally accepting the device's fate amongst a flurry of error messages.

This patch makes the choice of reset dependent on the port status that
has just been read from the hub in addition to the existence of an
in-kernel data structure for the device, and only proceeds with the more
extensive reset if both are valid.

Signed-off-by: Julius Werner <jwerner@chromium.org>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
---
 drivers/usb/core/hub.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

--
1.8.3.2

Patch

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index d5515c0..8deaeb5 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4552,7 +4552,8 @@  static void hub_events(void)
 					hub->hdev->children[i - 1];

 				dev_dbg(hub_dev, "warm reset port %d\n", i);
-				if (!udev) {
+				if (!udev || !(portstatus &
+						USB_PORT_STAT_CONNECTION)) {
 					status = hub_port_reset(hub, i,
 							NULL, HUB_BH_RESET_TIME,
 							true);
@@ -4562,8 +4563,8 @@  static void hub_events(void)
 					usb_lock_device(udev);
 					status = usb_reset_device(udev);
 					usb_unlock_device(udev);
+					connect_change = 0;
 				}
-				connect_change = 0;
 			}

 			if (connect_change)