As pointed out by Arnd Bergmann, in include/linux/usb/ehci_def.h, struct
ehci_caps is defined with __attribute__((packed)) for no good reason,
and this triggers undefined behaviour when using ARM's readl() on
pointers to elements of this structure:

http://lkml.kernel.org/r/201102021700.20683.arnd@arndb.de

The same problem exists with the other two structures in ehci_def.h too,
so remove the __attribute__((packed)) from all of them.

Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: NRabin Vincent <rabin@rab.in>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The reset value of the uSOF cycle period is incorrect.  Set it to
60,000 bits.  Without this, several commercial USB flash memory
devices and hubs fail to work properly.
Signed-off-by: NDavid Daney <ddaney@caviumnetworks.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Additional PHY tuning is needed to obtain compliant 'eye' diagram
electrical characteristics.
Signed-off-by: NDavid Daney <ddaney@caviumnetworks.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The UCTL clock initialization will cause the ehci and ohci blocks to
become inoperable if the clocks are reinitialized.

Check to see if the clocks have already been initialized.

Also use a mutex to protect the clock initialization code so that
there can be no attempt to use the clocks before they are fully
configured.
Signed-off-by: NDavid Daney <ddaney@caviumnetworks.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Merge branch 'for-usb-next' of git+ssh://master.kernel.org/pub/scm/linux/kernel/git/sarah/xhci into usb-next

* 'for-usb-next' of git+ssh://master.kernel.org/pub/scm/linux/kernel/git/sarah/xhci:
  xhci 1.0: Set transfer burst last packet count field.
  xhci 1.0: Set transfer burst count field.
  xhci 1.0: Update TD size field format.
  xhci 1.0: Only interrupt on short packet for IN EPs.
  xhci: Remove sparse warning about cmd_status.
  usbcore: warm reset USB3 port in SS.Inactive state
  usbcore: Refine USB3.0 device suspend and resume
  xHCI: report USB3.0 portstatus comply with USB3.0 specification
  xHCI: Set link state support
  xHCI: Clear link state change support
  xHCI: warm reset support
  usb/ch9: use proper endianess for wBytesPerInterval
  xhci: Remove recursive call to xhci_handle_event
  xhci: Add an assertion to check for virt_dev=0 bug.
  xhci: Add rmb() between reading event validity & event data access.
  xhci: Make xHCI driver endian-safe

This patch replaces the code that handles qtds. Intead of directly allocating
chip mem and chip slot, enqueue the transfer in a list of queue heads. Use
a centralized function enqueue_qtds() to prioritize and enqueue transfers.

This removes all of the interrupt context BUG() calls when out of chip
mem or transfer slots. It also makes it possible to efficiently use the
dual-port mem on the chip for double-buffered transfers, which improve
transfer times to/from/between usb sticks by about 40 % on my HW.

With this patch it should also be possible to handle qtd scheduling outside
of the interrupt handler, for significantly improved kernel latency. I have
not implemented this since there are some locking issues which I haven't
had time to look at.
Signed-off-by: NArvid Brodin <arvid.brodin@enea.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This fixes a bug in my previous (2.6.38) patch series which caused
urb->status value to be wrong after unlink (broke usbtest 11, 12).
Signed-off-by: NArvid Brodin <arvid.brodin@enea.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Since we always set the OR flag for each transfer, we can just as well set all
these bits to 1 at init and be done with it. Also, HcBufferStatus can be set
at init as per the ISP1761 datasheet page 47 with no loss of performance.
Signed-off-by: NArvid Brodin <arvid.brodin@enea.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This collects urb enqueue code that was spread out all over the place
into a couple of more readable functions.
Signed-off-by: NArvid Brodin <arvid.brodin@enea.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This removes the "qh is 0" printout. qh == NULL if the urb has
been unlinked, so this condition is normal.
Signed-off-by: NArvid Brodin <arvid.brodin@enea.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NAnton Tikhomirov <av.tikhomirov@samsung.com>
Cc: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

When File Storage gadget receives SET CONFIGURATION request it tries
to cancel all pending transfers. If some request is in progress,
gadget waits for its completion. This commit allows gadget to dequeue
invalid requests in progress left after reset.
Signed-off-by: NAnton Tikhomirov <av.tikhomirov@samsung.com>
Reviewed-by: Kyoungil Kim<ki0351.kim@samsung.com>
Cc: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The following should be done for requests after endpoint stall
condition is cleared:
1) 'in progress' request (if any) should be completed since
   Tx FIFO was flushed;
2) next request from queue (if any) should be started.

This commit does that.

Additionally set/clear stall condition code is fixed.
Signed-off-by: NAnton Tikhomirov <av.tikhomirov@samsung.com>
Reviewed-by: Kyoungil Kim<ki0351.kim@samsung.com>
Cc: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

UDC driver does not need to generate reply to host if request is
delivered to gadget. This is gadget's responsibility. This commit
fixes that.
Signed-off-by: NAnton Tikhomirov <av.tikhomirov@samsung.com>
Reviewed-by: Kyoungil Kim<ki0351.kim@samsung.com>
Cc: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This commit does the following:
1) clears all pending interrupts before unmasking;
2) clears interrupts as soon as possible to avoid missing
   next coming that may occur during handling;
3) removes ineffective interrupt cleaning code.
Signed-off-by: NAnton Tikhomirov <av.tikhomirov@samsung.com>
Reviewed-by: Kyoungil Kim<ki0351.kim@samsung.com>
Cc: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This patch fixes code responsible for core reset.
Signed-off-by: NAnton Tikhomirov <av.tikhomirov@samsung.com>
Reviewed-by: Kyoungil Kim<ki0351.kim@samsung.com>
Cc: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NAnatolij Gustschin <agust@denx.de>
Cc: Li Yang <leoli@freescale.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Slightly reworked and cleaned up driver from Freescale LTIB
for MPC5121E. The driver has been ported to the current kernel,
proc interface "/proc/driver/fsl_usb2_otg" has been replaced by
sysfs interface.
Signed-off-by: NLi Yang <leoli@freescale.com>
Signed-off-by: NAnatolij Gustschin <agust@denx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Extend the FSL UDC driver to support MPC5121E DR USB Controller
operation in device mode. Add MPC5121E specific init/uninit
at probe and remove and isolate system interface register accesses
when running on MPC5121E SoC, as these registers are not available
on this platform. This patch relies on previous patch for supporting
big endian registers and descriptors access in the FSL UDC driver.
Additionally support endpoint FIFO status operation by providing
appropriate callback in endpoint ops structure.

Also flush cache for the req buffer used for GetStatus reply.
Without this, the correct reply to an endpoint GetStatus
is written to 'req', but doesn't make it out to the USB bus
since the buffer hasn't been flushed. This would cause the
USBCV Halt Endpoint test to fail (according to changelog in
Freescale LTIB driver code).
Signed-off-by: NAnatolij Gustschin <agust@denx.de>
Cc: Li Yang <leoli@freescale.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

On some SoCs, the USB controller registers and descriptors can be big
or little endian, depending on the version of the chip. In order to be
able to run the same kernel binary on different versions of an SoC, the
BE/LE decision must be made at run time. Provide appropriate register
and descriptor accessors which are configurable at run time using the
configuration flags from fsl_usb2_platform_data data structure.

This is in preparation for adding support for MPC5121E DR USB2 Controller
to the FSL UDC driver.
Signed-off-by: NAnatolij Gustschin <agust@denx.de>
Cc: Li Yang <leoli@freescale.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

When only FSL USB gadget driver is selected in the kernel
configuration the MPH DR OF driver for creation of FSL
USB platform devices from device tree won't be built.
As a result no USB platform devices for MPH DR USB controller
will be created at run time and no probing will be done in
the fsl_udc_core driver.

Add an entry to the Makefile to build the MPH DR OF
platform driver if CONFIG_USB_FSL_MPH_DR_OF is defined.
Signed-off-by: NAnatolij Gustschin <agust@denx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NAnatolij Gustschin <agust@denx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The xHCI 1.0 specification defines a new isochronous TRB field, called
transfer burst last packet count (TBLPC).  This field defines the number
of packets in the last "burst" of packets in a TD.  Only SuperSpeed
endpoints can handle more than one burst, so this is set to the number for
packets in a TD for all non-SuperSpeed devices (minus one, since the field
is zero based).

This patch should have no effect on host controllers that don't advertise
the xHCI 1.0 (0x100) version number in their hci_version field.
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

The xHCI 1.0 specification adds a new field to the fourth dword in an
isochronous TRB: the transfer burst count (TBC).  This field is only
non-zero for SuperSpeed devices.  Each SS endpoint sets the bMaxBurst
field in the SuperSpeed endpoint companion descriptor, which indicates how
many max-packet-sized "bursts" it can handle in one service interval.  The
device driver may choose to burst less max packet sized chunks each
service interval (which is defined by one TD).  The xHCI driver indicates
to the host controller how many bursts it needs to schedule through the
transfer burst count field.

This patch will only effect xHCI hosts that advertise 1.0 support (0x100)
in the HCI version field of their capabilities register.
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

The xHCI 1.0 specification changes the format of the TD size field in
Normal and Isochronous TRBs.  The field in control TRBs is still set to
reserved zero.  Instead of representing the number of bytes left to
transfer in the TD (including the current TRB's buffer), it now represents
the number of packets left to transfer (*not* including this TRB).

See section 4.11.2.4 of the xHCI 1.0 specification for details.  The math
is basically copied straight from there.

Create a new function, xhci_v1_0_td_remainder(), that should be called for
all xHCI 1.0 host controllers.  The field location and maximum value is
still the same, so reuse the old function, xhci_td_remainder(), to handle
the bit shifting.
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

It doesn't make sense to set the interrupt on short packet (TRB_ISP) flag
for TRBs queued to endpoints that only receive packets from the host
controller (i.e. OUT endpoints).  Packets can only be short when they are
sent from a USB device.  Plus, the xHCI 1.0 specification forbids setting
the flag for anything but IN endpoints.

While we're at it, remove some of my snide remarks about the inefficiency
of event data TRBs.
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

Sparse complains about the arguments to xhci_evaluate_context_result() and
xhci_configure_endpoint_result():

  CHECK   drivers/usb/host/xhci.c
drivers/usb/host/xhci.c:1647:53: warning: incorrect type in argument 3 (different signedness)
drivers/usb/host/xhci.c:1647:53:    expected int *cmd_status
drivers/usb/host/xhci.c:1647:53:    got unsigned int [usertype] *[assigned] cmd_status
drivers/usb/host/xhci.c:1648:50: warning: incorrect type in argument 3 (different signedness)
drivers/usb/host/xhci.c:1648:50:    expected int *cmd_status
drivers/usb/host/xhci.c:1648:50:    got unsigned int [usertype] *[assigned] cmd_status

The command status is taken from the command completion event TRB, and
will always be a positive number.  Change the signature of
xhci_evaluate_context_result() and xhci_configure_endpoint_result() to
take a u32 for cmd_status.
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

Some USB3.0 devices go to SS.Inactive state when hot plug to USB3 ports.
Warm reset the port to transition it to U0 state.

This patch fixes the issue that Kingston USB3.0 flash drive can not be
recognized when hot plug to USB3 port.
Signed-off-by: NAndiry Xu <andiry.xu@amd.com>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

In the past, we use USB2.0 request to suspend and resume a USB3.0 device.
Actually, USB3.0 hub does not support Set/Clear PORT_SUSPEND request,
instead, it uses Set PORT_LINK_STATE request. This patch makes USB3.0 device
suspend/resume comply with USB3.0 specification.

This patch fixes the issue that USB3.0 device can not be suspended when
connected to a USB3.0 external hub.
Signed-off-by: NAndiry Xu <andiry.xu@amd.com>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

USB3.0 specification has different wPortStatus and wPortChange definitions
from USB2.0 specification. Since USB3 root hub and USB2 root hub are split
now and USB3 hub only has USB3 protocol ports, we should modify the
portstatus and portchange report of USB3 ports to comply with USB3.0
specification.
Signed-off-by: NAndiry Xu <andiry.xu@amd.com>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

This patch adds support for Set Port Feature(PORT_LINK_STATE) request.

The most significant byte (bits 15..8) of the wIndex field specifies
the U state the host software wants to put the link connected to the
port into. This request is only valid when the PORT_ENABLE bit is set
and the PORT_LINK_STATE should not be above value '5' (Rx.Detect).

This request will be later used to replace the set/clear suspend USB3
protocol ports in hub driver.
Signed-off-by: NAndiry Xu <andiry.xu@amd.com>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

This patch adds support for Clear Port Feature(C_PORT_LINK_STATE)
request from usbcore.
Signed-off-by: NAndiry Xu <andiry.xu@amd.com>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

This patch adds warm reset support to xhci hub control.
It handles Set Port Feature(BH_PORT_RESET) and Clear Port Feature
(C_BH_PORT_RESET) request from usbcore.
Note warm reset is called BH reset some places in USB3.0 specification.
Signed-off-by: NAndiry Xu <andiry.xu@amd.com>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

while going through Tatyana's changes for the gadget framework I noticed
that this type is not defined as __le16.
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

Make the caller loop while there are events to handle, instead.
Signed-off-by: NMatt Evans <matt@ozlabs.org>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

During a "plug-unplug" stress test on an NEC xHCI card, a null pointer
dereference was observed.  xhci_address_device() dereferenced a null
virt_dev (possibly an erroneous udev->slot_id?); this patch adds a WARN_ON &
message to aid debug if it can be recreated.
Signed-off-by: NMatt Evans <matt@ozlabs.org>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

On weakly-ordered systems, the reading of an event's content must occur
after reading the event's validity.
Signed-off-by: NMatt Evans <matt@ozlabs.org>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

This patch changes the struct members defining access to xHCI device-visible
memory to use __le32/__le64 where appropriate, and then adds swaps where
required.  Checked with sparse that all accesses are correct.

MMIO accesses use readl/writel so already are performed LE, but prototypes
now reflect this with __le*.

There were a couple of (debug) instances of DMA pointers being truncated to
32bits which have been fixed too.
Signed-off-by: NMatt Evans <matt@ozlabs.org>
Signed-off-by: NSarah Sharp <sarah.a.sharp@linux.intel.com>

Provide common otg_state_string() and use
it in drivers.
Signed-off-by: NAnatolij Gustschin <agust@denx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

dummy_hcd + g_zero:

|./testusb -a -s 1024 -v 1024 -t 10
| usbtest 2-1:3.0: subtest 14 error, status 0

with patch:
  ./testusb -a -t 10
|unknown speed   /proc/bus/usb/001/002
| dummy_udc dummy_udc: disabled ep-a
| dummy_udc dummy_udc: disabled ep-b
| dummy_udc dummy_udc: enabled ep-a (ep1in-bulk) maxpacket 1024
| dummy_udc dummy_udc: enabled ep-b (ep2out-bulk) maxpacket 1024
| zero gadget: source/sink enabled
| usbtest 1-1:3.0: TEST 10:  queue 32 control calls, 1000 times
| dummy_hcd dummy_hcd: timer fired with no URBs pending?
|/proc/bus/usb/001/002 test 10,    0.022370 secs
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>