This is based on the last release from PLX:
	http://www.plxtech.com/files/products/net2000/software/selectiontool/RE061204-net2272-linux2.6.18.tgz

I've managed to contact them and they've confirmed that this driver was
wholly written by PLX (Seth Levy).  While they have no problem with it
being merged (and they've already licensed it as GPL), they don't have
any interest in doing so themselves as this is an old part for them.

ADI has long had an add-on card which has this part on it, so we've been
keeping it up-to-date out of tree.  But now that PLX has confirmed the
source of the driver, we can can take the next step of cleaning it up and
getting it merged.

So here we are!  I've done quite a large clean up of the driver and
attempted to address all the common issues.  Hopefully in the process,
I haven't broken anything.  While it seems to still work with the board
that I have access to, it is not a PCI variant.  So I have not tested
any of the PCI logic myself (beyond clean compile).  Perhaps someone who
actually has a card and cares can do so.

I'll try to address further feedback, but don't expect miracles.  I'm
not really familiar with the part itself, just the platform glue.
Signed-off-by: NSeth Levy <seth.levy@plxtech.com>
Signed-off-by: NAsh Aziz <ash.aziz@plxtech.com>
Signed-off-by: NRoy Huang <roy.huang@analog.com>
Signed-off-by: NMichael Hennerich <michael.hennerich@analog.com>
Signed-off-by: NMike Frysinger <vapier@gentoo.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

fusb300_ep0_complete() is an empty function, not called from anywhere,
and causes the following build warning.

fusb300_udc.c:983: warning: fusb300_ep0_complete defined but not used

Remove it.
Signed-off-by: NGuenter Roeck <linux@roeck-us.net>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Commit e66eed65 ("list: remove prefetching from regular list
iterators") removed the include of prefetch.h from list.h, which
uncovered several cases that had apparently relied on that rather
obscure header file dependency.

So this fixes things up a bit, using

   grep -L linux/prefetch.h $(git grep -l '[^a-z_]prefetchw*(' -- '*.[ch]')
   grep -L 'prefetchw*(' $(git grep -l 'linux/prefetch.h' -- '*.[ch]')

to guide us in finding files that either need <linux/prefetch.h>
inclusion, or have it despite not needing it.

There are more of them around (mostly network drivers), but this gets
many core ones.
Reported-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Haavard's e-mail address at Atmel is no longer valid.
Signed-off-by: NJean Delvare <khali@linux-fr.org>
Acked-by: NHavard Skinnemoen <hskinnemoen@gmail.com>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

Commit b826291c, "drivercore/dt: add a match table pointer to struct
device" added an of_match pointer to struct device to cache the
of_match_table entry discovered at driver match time.  This was unsafe
because matching is not an atomic operation with probing a driver.  If
two or more drivers are attempted to be matched to a driver at the
same time, then the cached matching entry pointer could get
overwritten.

This patch reverts the of_match cache pointer and reworks all users to
call of_match_device() directly instead.
Signed-off-by: NGrant Likely <grant.likely@secretlab.ca>

as_out_ep_desc contines to be used during gadget enumeration and thus
should not be marked as __initdata
Signed-off-by: NMartin Jackson <mjackson220.list@gmail.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

composite.c always sets req->length to zero
and expects function driver's setup handlers
to return the amount of bytes to be used
on req->length. If we test against req->length
w_length will always be greater than req->length
thus making us always stall that particular
SEND_ENCAPSULATED_COMMAND request.

Tested against a Windows XP SP3.
Signed-off-by: NFelipe Balbi <balbi@ti.com>
Cc: stable <stable@kernel.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

on 9g20 they are the same as the 9260
Signed-off-by: NJean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Acked-by: NNicolas Ferre <nicolas.ferre@atmel.com>
Cc: stable <stable@kernel.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Return PTR_ERR(hsotg->clk) instead of -EINVAL if clk_get fails
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This patch fixes the checkpatch warnings listed below:

WARNING: braces {} are not necessary for any arm of this statement
WARNING: please, no space before tabs
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This patch fixes the checkpatch error and warning listed below:

ERROR: code indent should use tabs where possible
WARNING: please, no spaces at the start of a line
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

clk_get() returns ERR_PTR() on error, not NULL.
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The Samsung's S3C2416, S3C2443 and S3C2450 includes a USB High-Speed
device controller module. This driver enables support for USB high-speed
gadget functionality for the Samsung S3C24xx SoC's that include this
controller.
Signed-off-by: NThomas Abraham <thomas.ab@samsung.com>
Signed-off-by: NSangbeom Kim <sbkim73@samsung.com>
Signed-off-by: NKukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NAlexander Neumann <alexander@bumpern.de>
Signed-off-by: NHeiko Stuebner <heiko@sntech.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Comparing an unsigned integer with greater than or equal to zero is
always true.  So, it is safe to remove similar checks from
'f_mass_storage.c' and 'file_storage.c'
Signed-off-by: NMaxin B. John <maxin.john@gmail.com>
Acked-by: NMichal Nazarewicz <mina86@mina86.com>
Acked-by: NAlan Stern <stern@rowland.harvard.edu>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Defer the SET_CONFIG and SET_INTERFACE control transfer's data/status
stages till we are ready to process new CBW from the host. This way we
ensure that we don't loose any CBW during MSC compliance tests and cause
lock up.
Signed-off-by: NRoger Quadros <roger.quadros@nokia.com>
Acked-by: NMichal Nazarewicz <mina86@mina86.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Some USB function drivers (e.g. f_mass_storage.c) need to delay or defer the
data/status stages of standard control requests like SET_CONFIGURATION or
SET_INTERFACE till they are done with their bookkeeping and are actually ready
for accepting new commands to their interface.

They can now achieve this functionality by returning USB_GADGET_DELAYED_STATUS
in their setup handlers (e.g. set_alt()). The composite framework will then
defer completion of the control transfer by not completing the data/status stages.

This ensures that the host does not send new packets to the interface till the
function driver is ready to take them.

When the function driver that requested for USB_GADGET_DELAYED_STATUS is done
with its bookkeeping, it should signal the composite framework to continue with
the data/status stages of the control transfer. It can do so by invoking
the new API usb_composite_setup_continue(). This is where the control transfer's
data/status stages are completed and host can initiate new transfers.

The DELAYED_STATUS mechanism is currently only supported if the expected data phase
is 0 bytes (i.e. w_length == 0). Since SET_CONFIGURATION and SET_INTERFACE are the
only cases that will use this mechanism, this is not a limitation.
Signed-off-by: NRoger Quadros <roger.quadros@nokia.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Implement good battery algorithm defined in the battery charging V1.2 spec
for detecting different charging ports.  USB hardware is put into low power
mode when connected to a dedicated charging port.  vbus_draw and set_power
methods are implemented for determining the allowed current from Host in
different states (un-configured/suspend/configured).

The charger block is implemented using vendor specific registers and the
PHY used in MSM8960(28nm PHY) different from older targets like MSM8x60
and MSM7x30(45nm PHY).  The PHY vendor and product id registers are not
implemented in the above chipsets.  Hence PHY type is passed via platform
data.
Signed-off-by: NPavankumar Kondeti <pkondeti@codeaurora.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Though USB controller works without this most of the time, an issue was faced
where USB was configured as printer device and it was dropping first
packet(64 bytes) in full speed mode due to DATA PID mismatch.
The problem gets resolved once unused endpoints are configured as bulk.
As per P1020 RM (Table17-31, bits 19-18, bits 3-2) "When only one endpoint
(RX or TX, but not both) of an endpoint pair is used, the unused endpoint
should be configured as a bulk type endpoint." So according to the RM,
this patch is initializing TX and RX endpoints as bulk type
Signed-off-by: NSuchit Lepcha <Suchit.Lepcha@freescale.com>
Signed-off-by: NRamneek Mehresh <ramneek.mehresh@freescale.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Some of the simulators may cache the ep0 maxpacket size to zero
if the ep0 dQh is not setup before enabling the pullup. Hence
Setup ep0 and initialize the dQh fields once while registering the
gadget(before enabling the pullup).

HSUSB Chipidea link controller spec says ep0 is enabled always
in the HW. Hence disabling and enabling the ep0 as a part of
reset interrupt is unneccesary.
Remove the disable/enable ep0 logic from reset interrupt handling.
Signed-off-by: NAnji jonnala <anjir@codeaurora.org>
Signed-off-by: NPavankumar Kondeti <pkondeti@codeaurora.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The current code queue the control OUT data request to ep0in instead of
ep0out.  Check ep0_dir and use the correct control endpoint.
Signed-off-by: NPavankumar Kondeti <pkondeti@codeaurora.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The OUT endpoints are stored in 0 - hw_ep_max/2 and IN endpoints are
stored from hw_ep_max/2 - hw_ep_max in ci13xxx_ep array.  Retrieve
the IN endpoint correctly while processing endpoint feature requests.
Signed-off-by: NPavankumar Kondeti <pkondeti@codeaurora.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NPavankumar Kondeti <pkondeti@codeaurora.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NPavankumar Kondeti <pkondeti@codeaurora.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NPavankumar Kondeti <pkondeti@codeaurora.org>
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>

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>

This commit fixes an embarrassing bug in the "storage_common:
use kstrto*()" patch which caused fsg_store_ro() to return
zero instead of the length of the consumed buffer.
Signed-off-by: NMichal Nazarewicz <mina86@mina86.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

the_controller is allocated in dummy_hcd_probe() and is NULL if the
allocation failed. The probe function of the udc driver is dereferencing
this pointer and fault.
Alan Stern suggested to abort the dummy_hcd driver probing so the module
is not loaded. The is abort-on-error has been also added to the udc
driver.
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: NAlan Stern <stern@rowland.harvard.edu>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

g_printer reqiured "set interface" request from host. Not all hosts send
this request.  This patch enable the interface when it get "set
configuration" request from host.
Signed-off-by: NJonas Andersson <jonas@microbit.se>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Stripping the direction bit off will produce an
invalid descriptor.
Signed-off-by: NSven Schnelle <svens@stackframe.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The current code doesn't set it, so linux complains about
it when connected, and ignores the device:

[104611.068082] usb 1-5: new high speed USB device using ehci_hcd and address 127
[104611.088368] usb 1-5: Invalid ep0 maxpacket: 0
Signed-off-by: NSven Schnelle <svens@stackframe.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Current code returns 0 even if it can't handle the request.
This leads to timeouts when an unhandled request is sent:

Bus 001 Device 003: ID 0525:c0de Netchip Technology, Inc.
Device Descriptor:
[..]
can't get device qualifier: Connection timed out
[..]

change the code to return EOPNOTSUPP in such cases.
Signed-off-by: NSven Schnelle <svens@stackframe.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This reverts commit 806e8f8f.

To quote Alan Stern:
	The necessity for this patch has been under discussion.

	It turns out the UDC that Mian has been working on and Felipe's
	UDC have contradictory requirements.  Mian's UDC driver wants a
	bulk-OUT transfer length to be shorter than the maxpacket size
	if a short packet is expected, whereas Felipe's UDC hardware
	always needs bulk-OUT transfer lengths to be evenly divisible by
	the maxpacket size.

	Mian has agreed to go back over the driver to resolve this
	conflict.  This means we probably will not want this patch after
	all.  (In fact, we may ultimately decide to change the gadget
	framework to require that bulk-OUT transfer lengths _always_ be
	divisible by the maxpacket size -- only the g_file_storage and
	g_mass_storage gadgets would need to be changed.)

Cc: Mian Yousaf Kaukab <mian.yousaf.kaukab@stericsson.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>