This commit adds a cosmetic change to the s3c-hsotg UDC driver.
It moves s3c-hsotg.h to other linux/ related inclusions.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Finally, convert to the new style framework, using udc_start/udc_stop
methods. Since there is no need in the global _udc pointer, remove it.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Currently, endpoints are initialized in gadget start/stop methods, however
for the new style gadgets it is expected that bind() can be called before
controller's start(), and we need endpoints already initialized at that
point. So, move endpoint initialization to controller's probe before we
switch to the "new style" gadget framework.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Logging output in the driver is mostly done using custom err/warn/info
macros which rely on the existence of the global variable _udc, which
is a global reference to the udc controller structure. This reference
will have to go in order to allow us to have more than one chipidea udc
in the system.

Thus, replace custom macros with dev_{err,warn,info} using the platform
device where possible. The trace() macro, which is a nop by default is
left for tracing purposes.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Let's break ci13xxx driver into a separate udc driver and platform
drivers _pci and _msm, which will create a platform device for each pci
(or msm) device found. The approach was introduced by Felipe in dwc3
driver and there seems to be no reason not to use it.

msm related code is only compile-tested.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

After the UDC class conversion, there is no reason to limit the kernel
to have only one UDC controller in the system.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Use lookup table instead of conditional macrodefinitions of register
addresses. With two different possible register layouts and different
register offsets, it's easiest to build a table with register addresses
at probe time, based on the information supplied from the platform and
device capabilities. This way we get rid of branch-per-register-access.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Make global variables that are specific for each UDC instance part of
struct ci13xxx.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Small and self-evident cleanup.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Add pci ids for ChipIdea UDC as found in langwell/penwell SoCs.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Currently, the register prefixes in the driver seem to be mixed: the
capability registers are the ones that contain capability information,
such as number of hardware endpoints, while the registers that are
used to program the controller are called operational registers.

Normally, capability registers start at 0x100 offset of the register
window and are followed by operational registers. In some versions,
however, capability registers start at 0x0 offset.

This patch renames the register and adjusts their offsets appropriately,
leaving the possibility of having a non-standard capability offset.

I couldn't find any mentions of the TESTMODE register anywhere, so I
suspect it might only be enabled in chipidea internal versions of the
controller and I'm really inclined to remove it from the driver or at
least hiding it behind a config option.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Change ep0{out,in} macros into dynamically assigned pointers in
gadget initialization time.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Since ep0{out,in} are never on gadget's ep_list, there's no need to try
to unlink them, even more so because ep_list linkage is not initialized
for these endpoints.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

I previously cleaned up the err() call usage in this driver, but it
really was calling this macro instead.  To remove future confusion, just
delete this unused macro now.

Ideally, the warn() and info() macros should also be removed, and the
"real" dev_warn() and dev_info() calls should be used instead.
Reported-by: NPaul Gortmaker <paul.gortmaker@windriver.com>
Cc: Felipe Balbi <balbi@ti.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Missing handler for freeing requested IRQ added.
Moreover clk_ calls has been reorganized.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

This commit adjust the s3c-hsotg to new clock API.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

This code removes the S3C_ prefix from s3c-hsotg driver. This change
provides more architecture independent code.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

Add release function to prevent kernel warning.
Kfree is performed when all references are gone.
Signed-off-by: NSangwook Lee <sangwook.lee@linaro.org>
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

The our_hsotg global pointer to hsotg USB device state is removed.
It has been replaced with to_hsotg(gadget) function.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

Refactor all comments to comply with kernel codding style.
Moreover doxygen descriptions have been added for selected functions.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

Replace of deprecated start and stop callbacks with a udc_start and
udc_stop ones.

Now the bind from composite driver is NOT called explicitly, so more
work needs to be done at s3c_udc_probe. Especially enabling SoC clocks
and power for runtime determination of EP number.
After probing, those sources are disabled and enabled again at udc_start
and pullup afterwards.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NSangwook Lee <sangwook.lee@linaro.org>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

This commit adds support for determining of EPs number during run time.

Configuration is read from a HW configuration register in a specially
created s3c_hsotg_hw_cfg function.

Moreover it was necessary to defer at probe allocation of the
struct s3c_hsotg_ep instances until number of endpoints is known.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

This code allows Samsung SoC's to recover its state when
device is disconnected and connected during transfer.

It is necessary, in such a scenario, to reinitialize the USB core
to assure correct initial state of the driver.
This operation is needed since the disconnect interrupt is only
available at HOST mode, which is not supported by this driver.

A simple mechanism with jiffies has been used to perform core reset
only once.

Tested with:
- DFU gadget (various size of the sent data - also packet = MPS)
- Ethernet gadget (CDC and RNDIS)
- Multi Function Gadget (g_multi)

HW:
- Samsung's C210 Universal rev.0
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

The s3c_hsotg_disconnect_irq function has been renamed to
reflect, that it can be used not only during the host
disconnect irq.

The s3c_hsotg_disconnect shall be used as a fall back for
scenario when USB cable is unplugged and plugged to the
device.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

The USB Disconnect Interrupt handler, according to specification,
is only working at HOST mode.

Samsung SoCs (e.g. Exynos4) are working at device mode, so
this interrupt is never caught.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

The s3c_hsotg_core_init function has been added to exclude
code responsible for Samsung's SoCs USB core initialization.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

This commit targets following scenarios for IN requests:

1. HOST requests e.g. 256B (which is a multiple of MPS = 64B).
Then NO ZLP shall be sent, since host expects exact number of bytes.

2. HOST requested 4096B, but our data for sending is 256B. In this
situation ZLP shall be send to tell HOST that no more data is available
and it shall not wait for more data. This prevents HOST from hanging.

Tested with:
- DFU gadget (various size of the sent data - also packet = MPS)
- Ethernet gadget (CDC and RNDIS)
- Multi Function Gadget (g_multi)

HW:
- Samsung's C210 Universal rev.0
- Samsung's C110 GONI
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

For SETUP stage of USB control transmission, the NAK shall NOT be
CLEAR.

The SNAK/CNAK control is crucial for this type of driver,
since data arrives to earlier defined requests.

Tested with:
- DFU gadget (various size of the sent data - also packet = MPS)
- Ethernet gadget (CDC and RNDIS)
- Multi Function Gadget (g_multi)

HW:
- Samsung's C210 Universal rev.0
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

This commit adds support for supply voltage management for s3c-hsotg IP
block. For that purpose a convenient regulator_bulk_* functions have been
used.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Cc: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: Liam Girdwood <lrg@ti.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

Wrappers for PHY methods have been added for readability and reduction
of code repetition.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

Two functions - namely: s3c_hsotg_gate and s3c_hsotg_otgreset are platform
dependent and therefore removed from Samsung's generic s3c-hsotg code.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

This code removes platform dependency from s3c-hsotg driver.
Signed-off-by: NLukasz Majewski <l.majewski@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Cc: Kukjin Kim <kgene.kim@samsung.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

functionfs was leaking request objects created by autoconfig.
Signed-off-by: NPeter Korsgaard <peter.korsgaard@barco.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

Add two isochronous endpoints to the gadget zero source/sink
function. They are enabled by selecting alternate interface 1, so
by default they are not enabled. Module parameters for setting all
the isoc endpoint characteristics are also provided.
Signed-off-by: NPratyush Anand <pratyush.anand@st.com>
Signed-off-by: NPaul Zimmerman <paulz@synopsys.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

The original code works fine, but Sparse complains because it isn't
annotated properly.

drivers/usb/gadget/composite.c:793:26: warning: incorrect type in assignment (different base types)
drivers/usb/gadget/composite.c:793:26:    expected unsigned short [unsigned] [usertype] language
devel/drivers/usb/gadget/composite.c:793:26:    got restricted __le16 [usertype] <noident>
devel/drivers/usb/gadget/composite.c:795:29: warning: restricted __le16 degrades to integer
drivers/usb/gadget/composite.c:798:24: warning: incorrect type in assignment (different base types)
drivers/usb/gadget/composite.c:798:24:    expected restricted __le16 [usertype] <noident>
devel/drivers/usb/gadget/composite.c:798:24:    got unsigned short [unsigned] [usertype] language
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

The previous code always set to USB_DEVICE_SELF_POWERED in GET_STATUS.
So, this patch adds set_selfpowered().
Signed-off-by: NYoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

USB_FSL_USB2 driver can be used on PowerPC and i.MX processors.

Include i.MX processors in the USB_FSL_USB2 help text.
Signed-off-by: NFabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

dTD's next dtd pointer need to be updated once CPU writes it, or this
request may not be handled by controller, then host will get NAK from
device forever.

This problem occurs when there is a request is handling, we need to add
a new request to dTD list, if this new request is added before the current
one is finished, the new request is intended to added as next dtd pointer
at current dTD, but without wmb(), the dTD's next dtd pointer may not be
updated when the controller reads it. In that case, the controller will
still get Terminate Bit is 1 at dTD's next dtd pointer, that means there is
no next request, then this new request is missed by controller.

CC: <stable@vger.kernel.org>
Signed-off-by: NPeter Chen <peter.chen@freescale.com>
Acked-by: NLi Yang <leoli@freescale.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

In some USB composite gadget drivers, the configuration's bind function called
by the usb_add_config() calls multiple bind config functions. (for example cdc2
configuration bind function in the cdc_do_config() of the cdc2.c has two
functionality bind config functions.
  - the ecm_bind_config() & the acm_bind_config())

In each functionality bind config function, new instance is allocated and
finally added by the usb_add_function().

So if an error occurred during the second functionality bind config (for
example an error occurred at the acm_bind_config() after succeeding of the
ecm_bind_function()), the instance created by the acm_bind_config() cannot be
freed creating a memory leak.

This patch fixes this issue.
Signed-off-by: NYongsul Oh <yongsul96.oh@samsung.com>
Acked-by: NMichal Nazarewicz <mina86@mina86.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

There are no in-tree fsg_add() users and it has been deprecated
since 2.6.35 [1dc90985: fsg_add() renamed to fsg_bind_config()] so
out-of-tree users had more then enough time to convert.  Removing.
Signed-off-by: NMichal Nazarewicz <mina86@mina86.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>