linux-stable.git/drivers/mfd, branch v5.4.136

mfd: cpcap: Fix cpcap dmamask not set warnings

2021-07-20T14:10:43+00:00

[ Upstream commit 0b7cbe811ca524295ea43d9a4d73d3427e419c54 ]

We have started to get a bunch of pointless dmamask not set warnings
that makes the output of dmesg -l err,warn hard to read with many
extra warnings:

cpcap-regulator cpcap-regulator.0: DMA mask not set
cpcap_adc cpcap_adc.0: DMA mask not set
cpcap_battery cpcap_battery.0: DMA mask not set
cpcap-charger cpcap-charger.0: DMA mask not set
cpcap-pwrbutton cpcap-pwrbutton.0: DMA mask not set
cpcap-led cpcap-led.0: DMA mask not set
cpcap-led cpcap-led.1: DMA mask not set
cpcap-led cpcap-led.2: DMA mask not set
cpcap-led cpcap-led.3: DMA mask not set
cpcap-led cpcap-led.4: DMA mask not set
cpcap-rtc cpcap-rtc.0: DMA mask not set
cpcap-usb-phy cpcap-usb-phy.0: DMA mask not set

This seems to have started with commit 4d8bde883bfb ("OF: Don't set
default coherent DMA mask"). We have the parent SPI controller use
DMA, while CPCAP driver and it's children do not. For audio, the
DMA is handled over I2S bus with the McBSP driver.

Cc: Carl Philipp Klemm 
Cc: Ivan Jelincic 
Cc: Merlijn Wajer 
Cc: Pavel Machek 
Cc: Sebastian Reichel 
Cc: Sicelo A. Mhlongo 
Signed-off-by: Tony Lindgren 
Signed-off-by: Lee Jones 
Signed-off-by: Sasha Levin

mfd: da9052/stmpe: Add and modify MODULE_DEVICE_TABLE

2021-07-20T14:10:43+00:00

[ Upstream commit 4700ef326556ed74aba188f12396740a8c1c21dd ]

This patch adds/modifies MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.

Reported-by: Hulk Robot 
Signed-off-by: Zou Wei 
Signed-off-by: Lee Jones 
Signed-off-by: Sasha Levin

mfd: stm32-timers: Avoid clearing auto reload register

2021-05-14T07:44:25+00:00

[ Upstream commit 4917e498c6894ba077867aff78f82cffd5ffbb5c ]

The ARR register is cleared unconditionally upon probing, after the maximum
value has been read. This initial condition is rather not intuitive, when
considering the counter child driver. It rather expects the maximum value
by default:
- The counter interface shows a zero value by default for 'ceiling'
  attribute.
- Enabling the counter without any prior configuration makes it doesn't
  count.

The reset value of ARR register is the maximum. So Choice here
is to backup it, and restore it then, instead of clearing its value.
It also fixes the initial condition seen by the counter driver.

Fixes: d0f949e220fd ("mfd: Add STM32 Timers driver")
Signed-off-by: Fabrice Gasnier 
Acked-by: William Breathitt Gray 
Signed-off-by: Lee Jones 
Signed-off-by: Sasha Levin

mfd: arizona: Fix rumtime PM imbalance on error

2021-05-11T12:04:12+00:00

[ Upstream commit fe6df2b48043bbe1e852b2320501d3b169363c35 ]

pm_runtime_get_sync() will increase the rumtime PM counter
even it returns an error. Thus a pairing decrement is needed
to prevent refcount leak. Fix this by replacing this API with
pm_runtime_resume_and_get(), which will not change the runtime
PM counter on error.

Signed-off-by: Dinghao Liu 
Acked-by: Charles Keepax 
Signed-off-by: Lee Jones 
Signed-off-by: Sasha Levin

mfd: wm831x-auxadc: Prevent use after free in wm831x_auxadc_read_irq()

2021-03-04T09:26:33+00:00

[ Upstream commit 26783d74cc6a440ee3ef9836a008a697981013d0 ]

The "req" struct is always added to the "wm831x->auxadc_pending" list,
but it's only removed from the list on the success path.  If a failure
occurs then the "req" struct is freed but it's still on the list,
leading to a use after free.

Fixes: 78bb3688ea18 ("mfd: Support multiple active WM831x AUXADC conversions")
Signed-off-by: Dan Carpenter 
Acked-by: Charles Keepax 
Signed-off-by: Lee Jones 
Signed-off-by: Sasha Levin

mfd: bd9571mwv: Use devm_mfd_add_devices()

2021-03-04T09:26:28+00:00

[ Upstream commit c58ad0f2b052b5675d6394e03713ee41e721b44c ]

To remove mfd devices when unload this driver, should use
devm_mfd_add_devices() instead.

Fixes: d3ea21272094 ("mfd: Add ROHM BD9571MWV-M MFD PMIC driver")
Signed-off-by: Yoshihiro Shimoda 
Acked-for-MFD-by: Lee Jones 
Reviewed-by: Geert Uytterhoeven 
Reviewed-by: Matti Vaittinen 
Signed-off-by: Lee Jones 
Signed-off-by: Sasha Levin

mfd: sprd: Add wakeup capability for PMIC IRQ

2020-11-18T18:20:26+00:00

commit a75bfc824a2d33f57ebdc003bfe6b7a9e11e9cb9 upstream.

When changing to use suspend-to-idle to save power, the PMIC irq can not
wakeup the system due to lack of wakeup capability, which will cause
the sub-irqs (such as power key) of the PMIC can not wake up the system.
Thus we can add the wakeup capability for PMIC irq to solve this issue,
as well as removing the IRQF_NO_SUSPEND flag to allow PMIC irq to be
a wakeup source.

Reported-by: Chunyan Zhang 
Signed-off-by: Baolin Wang 
Tested-by: Chunyan Zhang 
Signed-off-by: Lee Jones 
Signed-off-by: Greg Kroah-Hartman

mfd: sm501: Fix leaks in probe()

2020-10-29T08:57:43+00:00

[ Upstream commit 8ce24f8967df2836b4557a23e74dc4bb098249f1 ]

This code should clean up if sm501_init_dev() fails.

Fixes: b6d6454fdb66 ("[PATCH] mfd: SM501 core driver")
Signed-off-by: Dan Carpenter 
Signed-off-by: Lee Jones 
Signed-off-by: Sasha Levin

mfd: mfd-core: Protect against NULL call-back function pointer

2020-10-01T11:17:17+00:00

[ Upstream commit b195e101580db390f50b0d587b7f66f241d2bc88 ]

If a child device calls mfd_cell_{en,dis}able() without an appropriate
call-back being set, we are likely to encounter a panic.  Avoid this
by adding suitable checking.

Signed-off-by: Lee Jones 
Reviewed-by: Daniel Thompson 
Reviewed-by: Mark Brown 
Signed-off-by: Sasha Levin

mfd: intel-lpss: Add Intel Tiger Lake PCH-H PCI IDs

2020-09-03T09:26:43+00:00

[ Upstream commit bb7fcad48d3804d814b97c785514e2d1657e157f ]

Intel Tiger Lake PCH-H has the same LPSS than Intel Broxton.
Add the new IDs to the list of supported devices.

Signed-off-by: Andy Shevchenko 
Signed-off-by: Lee Jones 
Signed-off-by: Sasha Levin