Commit dd34c37aa3e (gpio: of: Allow -gpio suffix for property names) added parsing for both -gpio and -gpios suffix but also changed the handling for deferred probe unintentionally. Because of the looping the second name will now return -ENOENT instead of -EPROBE_DEFER. Fix the issue by breaking out of the loop if -EPROBE_DEFER is encountered. Signed-off-by: Tony Lindgren <tony@atomide.com> Reviewed-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Pull MFD updates from Lee Jones:
"Changes to existing drivers:
- increase DT coverage: arizona, mc13xxx, stmpe-i2c, syscon,
sun6i-prcm
- regmap use of and/or clean-up: tps65090, twl6040
- basic renaming: max14577
- use new cpufreq helpers: db8500-prcmu
- increase regulator support: stmpe, arizona, wm5102
- reduce legacy GPIO overhead: stmpe
- provide necessary remove path: bcm590xx
- expand sysfs presence: kempld
- move driver specific code out to drivers: rtc-s5m, arizona
- clk handling: twl6040
- use managed (devm_*) resources: ipaq-micro
- clean-up/remove unused/duplicated code: tps65218, sec, pm8921,
abx500-core, db8500-prcmu, menelaus
- build/boot/sematic bug fixes: rtsx_usb, stmpe, bcm590xx, abx500,
mc13xxx, rdc321x-southbridge, mfd-core, sec, max14577, syscon,
cros_ec_spi
- constify stuff: sm501, tps65910, tps6507x, tps6586x, max77686,
max8997, kempld, max77693, max8907, rtsx_usb, db8500-prcmu,
max8998, wm8400, sec, lp3943, max14577, as3711, omap-usb-host,
ipaq-micro
Support for new devices:
- add support for max77836 into max14577
- add support for tps658640 into tps6586x
- add support for cros-ec-i2c-tunnel into cros_ec
- add new driver for rtsx_usb_sdmmc and rtsx_usb_ms
- add new driver for axp20x
- add new driver for sun6i-prcm
- add new driver for ipaq-micro"
* tag 'mfd-for-linus-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd: (77 commits)
mfd: wm5102: Correct default for LDO Control 2 register
mfd: menelaus: Use module_i2c_driver
mfd: tps65218: Terminate of match table
mfd: db8500-prcmu: Remove check for CONFIG_DBX500_PRCMU_DEBUG
mfd: ti-keystone-devctrl: Add bindings for device state control
mfd: palmas: Format the header file
mfd: abx500-core: Remove unused function abx500_dump_all_banks()
mfd: arizona: Correct addresses of always-on trigger registers
mfd: max14577: Cast to architecture agnostic data type
i2c: ChromeOS EC tunnel driver
mfd: cros_ec: Sync to the latest cros_ec_commands.h from EC sources
mfd: cros_ec: spi: Increase cros_ec_spi deadline from 5ms to 100ms
mfd: cros_ec: spi: Make the cros_ec_spi timeout more reliable
mfd: cros_ec: spi: Add mutex to cros_ec_spi
mfd: cros_ec: spi: Calculate delay between transfers correctly
mfd: arizona: Correct error message for addition of main IRQ chip
mfd: wm8997: Add registers for high power mode
mfd: arizona: Add MICVDD to mapped regulators
mfd: ipaq-micro: Make mfd_cell array const
mfd: ipaq-micro: Use devm_ioremap_resource()
...
Pull GPIO updates from Linus Walleij:
"This is the bulk of GPIO changes for the v3.16 series.
There is a lot of action in the GPIO subsystem doing refactorings and
cleanups, almost as many deletions as insertions and minor feature
growth and no new drivers this time. Which is actually pretty nice.
Some GPIO-related stuff will come in through the pin control tree as
well.
Details:
- We are finalizing and fixing up the gpiochip irqchip helpers
bringing a helpful irqchip implementation into the gpiolib core and
avoiding duplicate code and, more importantly, duplicate bug fixes:
* Support for using the helpers with threaded interrupt handlers as
used on sleeping GPIO-irqchips
* Do not set up hardware triggers for edges or levels if the
default IRQ type is IRQ_TYPE_NONE - some drivers would exploit
the fact that you could get default initialization of the IRQ
type from the core at probe() but if no default type is set up
from the helper, we should not call the driver to configure
anything. Wait until a consumer requests the interrupt instead.
* Make the irqchip helpers put the GPIO irqs into their own lock
class. The GPIO irqchips can often emit (harmless, but annoying)
lockdep warnings about recursions when they are in fact just
cascaded IRQs. By putting them into their own lock class we help
the lockdep core to keep track of things.
* Switch the tc3589x GPIO expanders to use the irqchip helpers
* Switch the OMAP GPIO driver to use the irqchip helpers
* Add some documentation for the irqchip helpers
* select IRQ_DOMAIN when using the helpers since some platforms may
not be using this by default and it's a strict dependency.
- Continued GPIO descriptor refactoring:
* Remove the one instance of gpio_to_desc() from the device tree
code, making the OF GPIO code use GPIO descriptors only.
* Introduce gpiod_get_optional() and gpiod_get_optional_index()
akin to the similar regulator functions for cases where the use
of GPIO is optional and not strictly required.
* Make of_get_named_gpiod_flags() private - we do not want to
unnecessarily expose APIs to drivers that make the gpiolib harder
than necessary to maintain and refactor. Privatize this
function.
- Support "-gpio" suffix for the OF GPIO retrieveal path. We used to
look for "foo-gpios" or just "gpios" in device tree nodes, but it
turns out that some drivers with a single GPIO line will just state
"foo-gpio" (singularis). Sigh. Support this with a fallback
looking for it, as this simplifies driver code and handles it in
core code.
- Switch the ACPI GPIO core to fetch GPIOs with the *_cansleep
function variants as the GPIO operation region handler can sleep,
and shall be able to handle gpiochips that sleep.
- Tons of cleanups and janitorial work from Jingoo Han, Axel Lin,
Javier Martinez Canillas and Abdoulaye Berthe. Notably Jingoo cut
off a ton of pointless OOM messages.
- Incremental development and fixes for various drivers, nothing
really special here"
* tag 'gpio-v3.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio: (85 commits)
gpio: select IRQ_DOMAIN for gpiolib irqchip helpers
gpio: pca953x: use gpiolib irqchip helpers
gpio: pcf857x: Add IRQF_SHARED when request irq
gpio: pcf857x: Avoid calling irq_domain_cleanup twice
gpio: mcp23s08: switch chip count to int
gpio: dwapb: use a second irq chip
gpio: ep93xx: Use devm_ioremap_resource()
gpio: mcp23s08: fixed count variable for devicetree probing
gpio: Add run-time dependencies to R-Car driver
gpio: pch: add slab include
Documentation / ACPI: Fix location of GPIO documentation
gpio / ACPI: use *_cansleep version of gpiod_get/set APIs
gpio: generic: add request function pointer
gpio-pch: Fix Kconfig dependencies
gpio: make of_get_named_gpiod_flags() private
gpio: gpioep93xx: use devm functions
gpio: janzttl: use devm function
gpio: timberdale: use devm functions
gpio: bt8xx: use devm function for memory allocation
gpio: include linux/bug.h in interface header
...
These helpers depend on the IRQ_DOMAIN so select it explicitly, as it will not be present on all platforms such as Intel desktops and laptops using Intel-MID. Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
This switches the PCA953x driver over to using the gpiolib irqchip helpers to handle the threaded interrups cascaded off this GPIO chip. Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
It's quite possible that multiple pcf857x can be hooked up to the same interrupt line with the processor. So add IRQF_SHARED in request irq.. Signed-off-by: George Cherian <george.cherian@ti.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Currently irq_domain_cleanup is called twice if irq_domain_init fails. This causes the following crash. Unable to handle kernel paging request at virtual address 00100104 pgd = c0004000 [00100104] *pgd=00000000 Internal error: Oops: 805 [#1] SMP ARM Modules linked in: CPU: 0 PID: 6 Comm: kworker/u4:0 Not tainted 3.12.15-01889-gedd10a8-dirty #4 Workqueue: deferwq deferred_probe_work_func task: ed0ee800 ti: ed116000 task.ti: ed116000 PC is at irq_domain_remove+0x3c/0x8c LR is at 0x0 pc : [<c0089734>] lr : [<00000000>] psr: a0000013 sp : ed117b50 ip : 00100100 fp : ed117b64 r10: ed5d1a04 r9 : 00000008 r8 : 00000000 r7 : ffffffea r6 : ed5d1a20 r5 : ed5d1a00 r4 : ed5e7540 r3 : 00200200 r2 : 00100100 r1 : c08aa180 r0 : 00200200 Flags: NzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c53c7d Table: 8000406a DAC: 00000017 Process kworker/u4:0 (pid: 6, stack limit = 0xed116248) Stack: (0xed117b50 to 0xed118000) 7b40: 0000016b ed5d5f10 ed117b74 ed117b68 7b60: c02c8910 c0089704 ed117bb4 ed117b78 c02c8e14 c02c8900 ed5d1a04 ed5d4e80 ... <snip> ... fe0: 00000000 00000000 00000000 00000000 00000013 00000000 384a13ea 1590210a Backtrace: [<c00896f8>] (irq_domain_remove+0x0/0x8c) from [<c02c8910>] (pcf857x_irq_domain_cleanup+0x1c/0x20) r4:ed5d5f10 r3:0000016b [<c02c88f4>] (pcf857x_irq_domain_cleanup+0x0/0x20) from [<c02c8e14>] (pcf857x_probe+0x2a8/0x364) [<c02c8b6c>] (pcf857x_probe+0x0/0x364) from [<c04787ac>] (i2c_device_probe+0x80/0xc0) [<c047872c>] (i2c_device_probe+0x0/0xc0) from [<c036c33c>] (driver_probe_device+0x104/0x240) r6:00000000 r5:ed5d1a20 r4:c08c709c r3:c047872c [<c036c238>] (driver_probe_device+0x0/0x240) from [<c036c558>] (__device_attach+0x48/0x4c) r7:ed4fc480 r6:c036c510 r5:ed5d1a20 r4:c0866bb8 [<c036c510>] (__device_attach+0x0/0x4c) from [<c036a6d8>] (bus_for_each_drv+0x4c/0x94) r5:ed5d1a20 r4:00000000 [<c036a68c>] (bus_for_each_drv+0x0/0x94) from [<c036c1f4>] (device_attach+0x78/0x90) r6:c087fe50 r5:ed5d1a54 r4:ed5d1a20 [<c036c17c>] (device_attach+0x0/0x90) from [<c036b76c>] (bus_probe_device+0x8c/0xb4) r6:c087fe50 r5:ed5d1a20 r4:ed5d1a20 r3:ed17e1c0 [<c036b6e0>] (bus_probe_device+0x0/0xb4) from [<c0369888>] (device_add+0x34c/0x624) r6:ed5d1a28 r5:00000000 r4:ed5d1a20 r3:fffffffe [<c036953c>] (device_add+0x0/0x624) from [<c0369b7c>] (device_register+0x1c/0x20) ... <snip> ... [<c0060844>] (process_one_work+0x0/0x37c) from [<c0061040>] (worker_thread+0x13c/0x3c4) [<c0060f04>] (worker_thread+0x0/0x3c4) from [<c00670ec>] (kthread+0xac/0xb8) [<c0067040>] (kthread+0x0/0xb8) from [<c00148b8>] (ret_from_fork+0x14/0x3c) r7:00000000 r6:00000000 r5:c0067040 r4:ed105d20 Code: e59fc04c e591e000 e59f0048 e154000e (e5823004) ---[ end trace 59dd1e90032c4217 ]--- Signed-off-by: George Cherian <george.cherian@ti.com> Reviewed-by: Alexandre Courbot <acourbot@nvidia.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Commit 3e3bed913e8bbd78f38cefd5d575475f45c05dd0 "gpio: mcp23s08: fixed count variable for devicetree probing" introduced a loop check to see if the number of chips were unconsistent and going below zero counting downwards, but this requires the counting variable to be able to be negative, so switch the variable from unsigned to int. Cc: Michael Stickel <ms@mycable.de> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Right new have one irq chip running always in level mode. It would nicer to have two irq chips where one is handling level type interrupts and the other one is doing edge interrupts. So we can have at runtime two users where one is using edge and the other level. Acked-by: Alan Tull <delicious.quinoa@gmail.com> Acked-by: Jamie Iles <jamie@jamieiles.com> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>