linux/drivers/usb, branch v3.17

Merge tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

2014-10-05T17:16:11Z

Pull SCSI fixes from James Bottomley: "This is a set of two small fixes, both to code which went in during the merge window: cxgb4i has a scheduling in atomic bug in its new ipv6 code and uas fails to work properly with the new scsi-mq code" * tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: [SCSI] uas: disable use of blk-mq I/O path [SCSI] cxgb4i: avoid holding mutex in interrupt context

[SCSI] uas: disable use of blk-mq I/O path

2014-10-03T09:27:58Z

The uas driver uses the block layer tag for USB3 stream IDs. With blk-mq we can get larger tag numbers that the queue depth, which breaks this assumption. A fix is under way for 3.18, but sits on top of large changes so can't easily be backported. Set the disable_blk_mq path so that a uas device can't easily crash the system when using blk-mq for SCSI. Signed-off-by: Christoph Hellwig Acked-by: Hans de Goede Signed-off-by: James Bottomley

USB: storage: Add quirks for Entrega/Xircom USB to SCSI converters

2014-09-19T22:01:38Z

This patch adds quirks for Entrega Technologies (later Xircom PortGear) USB- SCSI converters. They use Shuttle Technology EUSB-01/EUSB-S1 chips. The US_FL_SCM_MULT_TARG quirk is needed to allow multiple devices on the SCSI chain to be accessed. Without it only the (single) device with SCSI ID 0 can be used. The standalone converter sold by Entrega had model number U1-SC25. Xircom acquired Entrega and re-branded the product line PortGear. The PortGear USB to SCSI Converter (model PGSCSI) is internally identical to the Entrega product, but later models may use a different USB ID. The Entrega-branded units have USB ID 1645:0007, as does my Xircom PGSCSI, but the Windows and Macintosh drivers also support 085A:0028. Entrega also sold the "Mac USB Dock", which provides two USB ports, a Mac (8-pin mini-DIN) serial port and a SCSI port. It appears to the computer as a four-port hub, USB-serial, and USB-SCSI converters. The USB-SCSI part may have initially used the same ID as the standalone U1-SC25 (1645:0007), but later production used 085A:0026. My Xircom PortGear PGSCSI has bcdDevice=0x0100. Units with bcdDevice=0x0133 probably also exist. This patch adds quirks for 1645:0007, 085A:0026 and 085A:0028. The Windows driver INF file also mentions 085A:0032 "PortStation SCSI Module", but I couldn't find any mention of that actually existing in the wild; perhaps it was cancelled before release? Signed-off-by: Mark Knibbs Cc: stable Signed-off-by: Greg Kroah-Hartman

USB: storage: Add quirk for Ariston Technologies iConnect USB to SCSI adapter

2014-09-19T22:01:38Z

Hi, The Ariston Technologies iConnect 025 and iConnect 050 (also known as e.g. iSCSI-50) are SCSI-USB converters which use Shuttle Technology/SCM Microsystems chips. Only the connectors differ; both have the same USB ID. The US_FL_SCM_MULT_TARG quirk is required to use SCSI devices with ID other than 0. I don't have one of these, but based on the other entries for Shuttle/ SCM-based converters this patch is very likely correct. I used 0x0000 and 0x9999 for bcdDeviceMin and bcdDeviceMax because I'm not sure which bcdDevice value the products use. Signed-off-by: Mark Knibbs Cc: stable Signed-off-by: Greg Kroah-Hartman

USB: storage: Add quirk for Adaptec USBConnect 2000 USB-to-SCSI Adapter

2014-09-19T22:01:38Z

The Adaptec USBConnect 2000 is another SCSI-USB converter which uses Shuttle Technology/SCM Microsystems chips. The US_FL_SCM_MULT_TARG quirk is required to use SCSI devices with ID other than 0. I don't have a USBConnect 2000, but based on the other entries for Shuttle/ SCM-based converters this patch is very likely correct. I used 0x0000 and 0x9999 for bcdDeviceMin and bcdDeviceMax because I'm not sure which bcdDevice value the product uses. Signed-off-by: Mark Knibbs Cc: stable Signed-off-by: Greg Kroah-Hartman

USB: EHCI: unlink QHs even after the controller has stopped

2014-09-19T21:59:17Z

Old code in ehci-hcd tries to expedite disabling endpoints after the controller has stopped, by destroying the endpoint's associated QH without first unlinking the QH. This was necessary back when the driver wasn't so careful about keeping track of the controller's state. But now we are careful about it, and the driver knows that when the controller isn't running, no unlinking delay is needed. Furthermore, skipping the unlink step will trigger a BUG() in qh_destroy() when the preceding QH is released, because the link pointer will be non-NULL. Removing the lines that skip the unlinking step and go directly to QH_STATE_IDLE fixes the problem. Signed-off-by: Alan Stern Reported-by: Joe Lawrence Tested-by: Joe Lawrence CC: Signed-off-by: Greg Kroah-Hartman

Merge tag 'fixes-for-v3.17-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb into usb-linus

2014-09-11T22:08:14Z

Felipe writes: usb: fixes for v3.17-rc4 Some late fixes for dwc3 so we have something more stable on v3.17-final. Most bugs have been there for quite a while and nobody noticed, except for TRB completion when multiple TRBs are started. Patches were tested on AM437x SK and J6 EVM and are passing my tests. Signed-of-by: Felipe Balbi

xhci: fix oops when xhci resumes from hibernate with hw lpm capable devices

2014-09-11T21:23:52Z

Resuming from hibernate (S4) will restart and re-initialize xHC. The device contexts are freed and will be re-allocated later during device reset. Usb core will disable link pm in device resume before device reset, which will try to change the max exit latency, accessing the device contexts before they are re-allocated. There is no need to zero (disable) the max exit latency when disabling hw lpm for a freshly re-initialized xHC. So check that device context exists before doing anything. The max exit latency will be set again after device reset when usb core enables the link pm. Reported-by: Imre Deak Tested-by: Imre Deak Cc: stable Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman

usb: xhci: Fix OOPS in xhci error handling code

2014-09-11T21:23:52Z

The xhci driver will OOPS on resume from S2/S3 if dma_alloc_coherent() is out of memory. This is a result of two things: 1. xhci_mem_cleanup() in xhci-mem.c free's xhci->lpm_command if it's not NULL, but doesn't set it to NULL after the free. 2. xhci_mem_cleanup() is called twice on resume, once for normal restart and once from xhci_mem_init() if dma_alloc_coherent() fails, resulting in a free of xhci->lpm_command that has already been freed. The fix is to set xhci->lpm_command to NULL after freeing it. Signed-off-by: Al Cooper Cc: stable Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman

xhci: Fix null pointer dereference if xhci initialization fails

2014-09-11T21:23:52Z

If xhci initialization fails before the roothub bandwidth domains (xhci->rh_bw[i]) are allocated it will oops when trying to access rh_bw members in xhci_mem_cleanup(). Reported-by: Manuel Reimer Cc: stable Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman