12 Jun, 2024
1 commit
-
[ Upstream commit 4b653e82ae18f2dc91c7132b54f5785c4d56bab4 ]
kernel-doc validator is not happy:
warning: Function parameter or struct member 'fotg' not described in 'fotg210_vbus'
Add missing description.
Fixes: 3e679bde529e ("usb: fotg210-udc: Implement VBUS session")
Signed-off-by: Andy Shevchenko
Reviewed-by: Linus Walleij
Link: https://lore.kernel.org/r/20240510152641.2421298-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman
Signed-off-by: Sasha Levin
01 Jan, 2024
1 commit
-
commit 7fbcd195e2b8cc952e4aeaeb50867b798040314c upstream.
Here "temp" is the number of characters that we have written and "size"
is the size of the buffer. The intent was clearly to say that if we have
written to the end of the buffer then stop.However, for that to work the comparison should have been done on the
original "size" value instead of the "size -= temp" value. Not only
will that not trigger when we want to, but there is a small chance that
it will trigger incorrectly before we want it to and we break from the
loop slightly earlier than intended.This code was recently changed from using snprintf() to scnprintf(). With
snprintf() we likely would have continued looping and passed a negative
size parameter to snprintf(). This would have triggered an annoying
WARN(). Now that we have converted to scnprintf() "size" will never
drop below 1 and there is no real need for this test. We could change
the condition to "if (temp
Signed-off-by: Dan Carpenter
Reviewed-by: Linus Walleij
Reviewed-by: Lee Jones
Link: https://lore.kernel.org/r/ZXmwIwHe35wGfgzu@suswa
Signed-off-by: Greg Kroah-Hartman
28 May, 2023
1 commit
-
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart from
emitting a warning) and this typically results in resource leaks. To improve
here there is a quest to make the remove callback return void. In the first
step of this quest all drivers are converted to .remove_new() which already
returns void. Eventually after all drivers are converted, .remove_new() is
renamed to .remove().Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.Signed-off-by: Uwe Kleine-König
Acked-by: Linus Walleij
Link: https://lore.kernel.org/r/20230517230239.187727-24-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman
06 Feb, 2023
2 commits
-
When calling debugfs_lookup() the result must have dput() called on it,
otherwise the memory will leak over time. To make things simpler, just
call debugfs_lookup_and_remove() instead which handles all of the logic
at once.Reviewed-by: Linus Walleij
Link: https://lore.kernel.org/r/20230202153235.2412790-5-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman -
We need the USB fixes in here, and this resolves a merge conflict with
the i915 driver as reported in linux-nextSigned-off-by: Greg Kroah-Hartman
02 Feb, 2023
1 commit
-
Before the commit fc274c1e9973 ("USB: gadget: Add a new bus for gadgets")
gadget driver.bus was unused. For whatever reason, many UDC drivers set
this field explicitly to NULL in udc_start(). With the newly added gadget
bus, doing this will crash the driver during the attach.The problem was first reported, fixed and tested with OMAP UDC and g_ether.
Other drivers are changed based on code analysis only.Fixes: fc274c1e9973 ("USB: gadget: Add a new bus for gadgets")
Cc: stable
Signed-off-by: Aaro Koskinen
Acked-by: Alan Stern
Link: https://lore.kernel.org/r/20230201220125.GD2415@darkstar.musicnaut.iki.fi
Signed-off-by: Greg Kroah-Hartman
31 Jan, 2023
1 commit
-
devm_platform_get_and_ioremap_resource() never returns NULL pointer,
it will return ERR_PTR() when it fails, so replace the check with
IS_ERR().Fixes: baef5330d35b ("usb: fotg210: Acquire memory resource in core")
Signed-off-by: Yang Yingliang
Reviewed-by: Linus Walleij
Link: https://lore.kernel.org/r/20230130120633.3342285-1-yangyingliang@huawei.com
Signed-off-by: Greg Kroah-Hartman
25 Jan, 2023
9 commits
-
Correct a spelling mistake (reported by codespell).
Signed-off-by: Randy Dunlap
Reviewed-by: Linus Walleij
Link: https://lore.kernel.org/r/20230124233511.23616-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman -
Convert platform_get_resource(), devm_ioremap_resource() to a single
call to devm_platform_get_and_ioremap_resource(), as this is exactly
what this function does.Signed-off-by: Andy Shevchenko
Link: https://lore.kernel.org/r/20230120154437.22025-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman -
Switch to use dev_err_probe() to simplify the error paths and
unify message template.Signed-off-by: Andy Shevchenko
Link: https://lore.kernel.org/r/20230120154437.22025-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman -
A call to platform_get_irq() already prints an error on failure within
its own implementation. So printing another error based on its return
value in the caller is redundant and should be removed. The clean up
also makes if condition block braces unnecessary. Remove that as well.Signed-off-by: Andy Shevchenko
Link: https://lore.kernel.org/r/20230120154437.22025-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman -
kstrtox() along with regmap API can return different error codes based on
circumstances.Don't shadow them when returning to the caller.
Signed-off-by: Andy Shevchenko
Link: https://lore.kernel.org/r/20230120154437.22025-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman -
Follow the advice of the Documentation/filesystems/sysfs.rst and show()
should only use sysfs_emit() or sysfs_emit_at() when formatting the
value to be returned to user space.Signed-off-by: Andy Shevchenko
Link: https://lore.kernel.org/r/20230120154437.22025-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman -
Reset the device explicitly to get into a known state and also set the chip
enable bit. Additionally, mask interrupts which aren't handled.Signed-off-by: Fabian Vogt
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230123073508.2350402-4-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
This is in preparation of support for devices where interrupts are acked
differently.Signed-off-by: Fabian Vogt
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230123073508.2350402-3-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
This is used when responding to GET_STATUS requests. Without this, it
crashes on completion.Fixes: b84a8dee23fd ("usb: gadget: add Faraday fotg210_udc driver")
Signed-off-by: Fabian Vogt
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230123073508.2350402-2-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman
19 Jan, 2023
6 commits
-
Implement VBUS session handling for FOTG210. This is
mainly used by the UDC driver which needs to call down to
the FOTG210 core and enable/disable VBUS, as this needs to be
handled outside of the HCD and UDC drivers, by platform
specific glue code.The Gemini has a special bit in a system register to turn
VBUS on and off so we implement this in the FOTG210 core.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230103-gemini-fotg210-usb-v2-7-100388af9810@linaro.org
Signed-off-by: Greg Kroah-Hartman -
Follow the example set by other drivers to assign of_node
and speed to the driver when binding, also print bound
info akin to other UDC drivers.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230103-gemini-fotg210-usb-v2-6-100388af9810@linaro.org
Signed-off-by: Greg Kroah-Hartman -
Read the role register and check that we are in host/peripheral
mode and issue warnings if we're not in the right role when
probing respective driver.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230103-gemini-fotg210-usb-v2-5-100388af9810@linaro.org
Signed-off-by: Greg Kroah-Hartman -
Grab the optional silicon block clock, prepare and enable it in
the core before proceeding to prepare the host or peripheral
driver. This saves duplicate code and also uses the simple
devm_clk_get_optional_enabled() to do everything we really
want to do.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230103-gemini-fotg210-usb-v2-4-100388af9810@linaro.org
Signed-off-by: Greg Kroah-Hartman -
The subdrivers are obtaining and mapping the memory resource
separately. Create a common state container for the shared
resources and start populating this by acquiring the IO
memory resource and remap it and pass this to the subdrivers
for host and peripheral.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230103-gemini-fotg210-usb-v2-3-100388af9810@linaro.org
Signed-off-by: Greg Kroah-Hartman -
There are at least two variants of the FOTG: FOTG200 and
FOTG210. Handle them in this driver and let's add
more quirks as we go along.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20230103-gemini-fotg210-usb-v2-2-100388af9810@linaro.org
Signed-off-by: Greg Kroah-Hartman
06 Jan, 2023
1 commit
-
After commit 5f217ccd520f ("fotg210-udc: Support optional external PHY"),
the error code is re-assigned to 0 in fotg210_udc_probe(), if allocate or
map memory fails after the assignment, it can't return an error code. Set
the error code to -ENOMEM to fix this problem.Fixes: 5f217ccd520f ("fotg210-udc: Support optional external PHY")
Signed-off-by: Yang Yingliang
Reviewed-by: Linus Walleij
Link: https://lore.kernel.org/r/20221230065427.944586-1-yangyingliang@huawei.com
Signed-off-by: Greg Kroah-Hartman
28 Dec, 2022
1 commit
-
The fotg210 module combines the HCD and OTG drivers, which then
fails to build when only the USB gadget support is enabled
in the kernel but host support is not:aarch64-linux-ld: drivers/usb/fotg210/fotg210-core.o: in function `fotg210_init':
fotg210-core.c:(.init.text+0xc): undefined reference to `usb_disabled'Move the check for usb_disabled() after the check for the HCD module,
and let the OTG driver still be probed in this configuration.A nicer approach might be to have the common portion built as a
library module, with the two platform other files registering
their own platform_driver instances separately.Fixes: ddacd6ef44ca ("usb: fotg210: Fix Kconfig for USB host modules")
Reviewed-by: Linus Walleij
Signed-off-by: Arnd Bergmann
Link: https://lore.kernel.org/r/20221215165728.2062984-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman
08 Dec, 2022
1 commit
-
In fotg210_udc_probe(), if devm_clk_get() or clk_prepare_enable()
fails, 'fotg210' will not be freed, which will lead to a memory leak.
Fix it by moving kfree() to a proper location.In addition，we can use "return -ENOMEM" instead of "goto err"
to simplify the code.Fixes: 718a38d092ec ("fotg210-udc: Handle PCLK")
Reviewed-by: Andrzej Pietrasiewicz
Reviewed-by: Linus Walleij
Signed-off-by: Yi Yang
Link: https://lore.kernel.org/r/20221202012126.246953-1-yiyang13@huawei.com
Signed-off-by: Greg Kroah-Hartman
23 Nov, 2022
7 commits
-
There is no need to use an intermediate array for these memory allocations,
so, axe it.While at it, turn a '== NULL' into a shorter '!' when testing memory
allocation failure.Signed-off-by: Christophe JAILLET
Reviewed-by: Linus Walleij
Link: https://lore.kernel.org/r/deab9696fc4000499470e7ccbca7c36fca17bd4e.1668458274.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman -
The platform_get_irq() is necessary to use to get dynamic
IRQ resolution when instantiating the device from the
device tree. IRQs are not passed as resources in that
case.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221114115201.302887-4-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
This adds optional handling of the peripheral clock PCLK.
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221114115201.302887-3-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
This adds support for an optional external PHY to the FOTG210
UDC driver.Tested with the GPIO VBUS PHY driver on the Gemini SoC.
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221114115201.302887-2-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
Add a local struct device *dev pointer and use dev_err()
etc to report status.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221114115201.302887-1-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
The Faraday Technology FOTG210 USB2 Dual Role Controller is only present
on Cortina Systems Gemini SoCs. Hence add a dependency on ARCH_GEMINI,
to prevent asking the user about its drivers when configuring a kernel
without Cortina Systems Gemini SoC support.Fixes: 1dd33a9f1b95ab59 ("usb: fotg210: Collect pieces of dual mode controller")
Signed-off-by: Geert Uytterhoeven
Reviewed-by: Linus Walleij
Link: https://lore.kernel.org/r/a989b3b798ecaf3b45f35160e30e605636d66a77.1669044086.git.geert+renesas@glider.be
Signed-off-by: Greg Kroah-Hartman -
The kernel robot reports a link failure when activating the
FOTG210 host subdriver with =y on a system where the USB host
core is a module (CONFIG_USB=m).This is a bit of special case, so mimic the Kconfig incantations
from DWC3: let the subdrivers for host or peripheral depend
on the host or gadget support being =y or the same as the
FOTG210 core itself.This should ensure that either:
- The host (CONFIG_USB) or gadget (CONFIG_GADGET) is compiled
in and then the FOTG210 can be either module or compiled
in.- The host or gadget is modular, and then the FOTG210 module
must be a module too, or we cannot resolve the symbols
at link time.Reported-by: kernel test robot
Link: https://lore.kernel.org/linux-usb/202211112132.0BUPGKCd-lkp@intel.com/
Cc: Arnd Bergmann
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221111144821.113665-1-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman
11 Nov, 2022
2 commits
-
The code in the FOTG210 driver isn't entirely endianness-agnostic
as reported by the kernel robot sparse testing. This came to
the surface while moving the files around.The driver is only used on little-endian systems, so this causes
no real-world regression, but it is nice to be strict and have
some compile coverage also on big endian machines, so fix it
up with the right LE accessors.Fixes: b84a8dee23fd ("usb: gadget: add Faraday fotg210_udc driver")
Reported-by: kernel test robot
Link: https://lore.kernel.org/linux-usb/202211110910.0dJ7nZCn-lkp@intel.com/
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221111090317.94228-1-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
The Cortina Systems Gemini has bolted on a PHY inside the
silicon that can be handled by six bits in a MISC register in
the system controller.If we are running on Gemini, look up a syscon regmap through
a phandle and enable VBUS and optionally the Mini-B connector.If the device is flagged as "wakeup-source" using the standard
DT bindings, we also enable this in the global controller for
respective port.Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221109200554.1957185-1-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman
09 Nov, 2022
3 commits
-
Check which mode the hardware is in, and selecte the peripheral
driver if the hardware is in explicit peripheral mode, otherwise
select host mode.This should solve the immediate problem that both subdrivers
can get probed.Cc: Fabian Vogt
Cc: Yuan-Hsin Chen
Cc: Felipe Balbi
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221023144708.3596563-3-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
It is since ages perfectly possible to compile both of these
modules into the same kernel, which makes no sense since it
is one piece of hardware.Compile one module named "fotg210.ko" for both HCD and UDC
drivers by collecting the init calls into a fotg210-core.c
file and start to centralize things handling one and the same
piece of hardware.Stub out the initcalls if one or the other part of the driver
was not selected.Tested by compiling one or the other or both of the drivers
into the kernel and as modules.Cc: Fabian Vogt
Cc: Yuan-Hsin Chen
Cc: Felipe Balbi
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221023144708.3596563-2-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman -
The Faraday FOTG210 is a dual-mode OTG USB controller that can
act as host, peripheral or both. To be able to probe from one
hardware description and to follow the pattern of other dual-
mode controllers such as MUSB or MTU3 we need to collect the
two, currently completely separate drivers in the same
directory.After this, users need to select the main symbol USB_FOTG210
and then each respective subdriver. We pave the road to
compile both drivers into the same kernel and select the
one we want to use at probe() time, and possibly add OTG
support in the end.This patch doesn't do much more than create the new symbol
and collect the drivers in one place. We also add a comment
for the section of dual-mode controllers in the Kconfig
file so people can see what these selections are about.Also add myself as maintainer as there has been little
response on my patches to these drivers.Cc: Fabian Vogt
Cc: Yuan-Hsin Chen
Cc: Felipe Balbi
Signed-off-by: Linus Walleij
Link: https://lore.kernel.org/r/20221023144708.3596563-1-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman