* Re: [PATCH 2/8] dt-bindings: mfd: ROHM BD73800 PMIC
From: Linus Walleij @ 2026-07-03 20:46 UTC (permalink / raw)
To: Matti Vaittinen
Cc: Matti Vaittinen, Matti Vaittinen, Lee Jones, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Liam Girdwood, Mark Brown,
Michael Turquette, Stephen Boyd, Brian Masney,
Bartosz Golaszewski, Alexandre Belloni, devicetree, linux-kernel,
linux-clk, linux-gpio, linux-rtc
In-Reply-To: <3e700a3fa7872a96257ff25a77670ec05cfd239c.1782909323.git.mazziesaccount@gmail.com>
Hi Matti,
thanks for your patch!
I have some inevitable pin control nitpicks!
On Wed, Jul 1, 2026 at 2:41 PM Matti Vaittinen
<matti.vaittinen@linux.dev> wrote:
> + # The GPIO1, CLKOUT (GPIO2), FAULT_B and EXTEN_OUT pins can be
> + # configured to interrupt pins by OTP.
Maybe move this helpful comment into the top description: instead?
It's kind of generic helpful info.
> +# The GPIO1, CLKOUT, FAULT_B and EXTEN_OUT pins may be configured for a
> +# specific purpose (like ADC input, 32.768 clk output, fault indicator or
> +# delivering power sequence to a companion PMIC when multiple PMICs are
> +# used) - but also to be either a GPO or GPI. (When used as a GPI the pin
> +# can also be used as an IRQ source). The pin purpose is determined by
> +# OTP (One Time Programmable memory), typically during device manufacturing.
> +# The OTP can't be read at runtime so device-tree should describe the pins.
> + rohm,pin-gpio1:
> + $ref: /schemas/types.yaml#/definitions/string
> + description:
> + Indicate if the GPIO1 pin has been set to GPI or GPO at manufacturing.
> + enum: [gpi, gpo]
> +
> + rohm,pin-clkout:
> + $ref: /schemas/types.yaml#/definitions/string
> + description:
> + Indicate if the CLKOUT pin has been set to GPI or GPO at manufacturing.
> + enum: [gpi, gpo]
> +
> + rohm,pin-fault-b:
> + $ref: /schemas/types.yaml#/definitions/string
> + description:
> + Indicate if the FAULT_B pin has been set to GPI or GPO at manufacturing.
> + enum: [gpi, gpo]
> +
> + rohm,pin-exten:
> + $ref: /schemas/types.yaml#/definitions/string
> + description:
> + Indicate if the EXTEN_OUT pin has been set to GPI or GPO at
> + manufacturing.
> + enum: [gpi, gpo]
Can we explain what "GPI" and "GPO" means in this context?
I read it as "general purpose input" and "general purpose output", but...
you just describe the exact purpose? So what is "general purpose"
about them in that case?
I would re-use "input-enable" and "output-enable" from:
Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml
(I mean don't $rf that, just use these strings).
I suppose:
enum: [input-enable, output-enable]
> + rohm,clkout-open-drain:
> + description: clk32kout mode. Set to 1 for "open-drain" or 0 for "cmos".
> + $ref: /schemas/types.yaml#/definitions/uint32
> + minimum: 0
> + maximum: 1
Here I would also reuse the generic pinconf properties,
something like;
rohm,clkout-drive-type:
enum: [drive-push-pull, drive-open-drain]
(Push-pull is what is colloquially referred to as "cmos".)
> + rohm,pin-gpio1 = "gpo";
> + rohm,pin-exten = "gpi";
If you instead use nodes with properties you can do this:
rohm,pin-clkout {
output-enable;
drive-push-pull;
};
This collects the clkout config in one place and make
it obvious what is going on. But I don't know what the DT
maintainers think about this idea.
Yours,
Linus Walleij
^ permalink raw reply
* Re: [PATCH v3 6/8] clk: sunxi-ng: div: add read-only operation support
From: Chen-Yu Tsai @ 2026-07-04 8:25 UTC (permalink / raw)
To: Jerome Brunet
Cc: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Jernej Skrabec, Samuel Holland, Michael Turquette,
Stephen Boyd, Maxime Ripard, linux-rtc, devicetree,
linux-arm-kernel, linux-sunxi, linux-kernel, linux-clk
In-Reply-To: <20260702-a733-rtc-v3-6-eb2580374de6@baylibre.com>
On Thu, Jul 2, 2026 at 4:11 PM Jerome Brunet <jbrunet@baylibre.com> wrote:
>
> Add support for sunxi-ng read-only dividers. This will be
> useful to the a733 oscillator detection logic.
>
> Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
> ---
> drivers/clk/sunxi-ng/ccu_div.c | 42 ++++++++++++++++++++++++++++++++++++++++++
> drivers/clk/sunxi-ng/ccu_div.h | 1 +
> drivers/clk/sunxi-ng/ccu_mux.c | 3 ++-
> drivers/clk/sunxi-ng/ccu_mux.h | 4 ++++
> 4 files changed, 49 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/clk/sunxi-ng/ccu_div.c b/drivers/clk/sunxi-ng/ccu_div.c
> index 62d680ccb524..d1c8c7baa12d 100644
> --- a/drivers/clk/sunxi-ng/ccu_div.c
> +++ b/drivers/clk/sunxi-ng/ccu_div.c
> @@ -84,6 +84,36 @@ static int ccu_div_determine_rate(struct clk_hw *hw,
> req, ccu_div_determine_rate_helper, cd);
> }
>
> +static int ccu_rodiv_determine_rate(struct clk_hw *hw,
> + struct clk_rate_request *req)
> +{
> + struct ccu_div *cd = hw_to_ccu_div(hw);
> + unsigned long val;
> + u32 reg;
> + int ret;
> +
> + reg = readl(cd->common.base + cd->common.reg);
> + val = reg >> cd->div.shift;
> + val &= (1 << cd->div.width) - 1;
> +
> + req->rate = ccu_mux_helper_unapply_prediv(&cd->common, &cd->mux, -1,
> + req->rate);
> +
> + if (cd->common.features & CCU_FEATURE_FIXED_POSTDIV)
> + req->rate *= cd->fixed_post_div;
> +
> + ret = divider_ro_determine_rate(hw, req, cd->div.table,
> + cd->div.width, cd->div.flags, val);
> +
> + if (cd->common.features & CCU_FEATURE_FIXED_POSTDIV)
> + req->rate /= cd->fixed_post_div;
> +
> + req->rate = ccu_mux_helper_apply_prediv(&cd->common, &cd->mux, -1,
> + req->rate);
> +
> + return ret;
> +}
> +
> static int ccu_div_set_rate(struct clk_hw *hw, unsigned long rate,
> unsigned long parent_rate)
> {
> @@ -143,3 +173,15 @@ const struct clk_ops ccu_div_ops = {
> .set_rate = ccu_div_set_rate,
> };
> EXPORT_SYMBOL_NS_GPL(ccu_div_ops, "SUNXI_CCU");
> +
> +const struct clk_ops ccu_rodiv_ops = {
> + .disable = ccu_div_disable,
> + .enable = ccu_div_enable,
> + .is_enabled = ccu_div_is_enabled,
> +
> + .get_parent = ccu_div_get_parent,
> +
> + .determine_rate = ccu_rodiv_determine_rate,
> + .recalc_rate = ccu_div_recalc_rate,
> +};
> +EXPORT_SYMBOL_NS_GPL(ccu_rodiv_ops, "SUNXI_CCU");
> diff --git a/drivers/clk/sunxi-ng/ccu_div.h b/drivers/clk/sunxi-ng/ccu_div.h
> index be00b3277e97..a30a92780a05 100644
> --- a/drivers/clk/sunxi-ng/ccu_div.h
> +++ b/drivers/clk/sunxi-ng/ccu_div.h
> @@ -300,5 +300,6 @@ static inline struct ccu_div *hw_to_ccu_div(struct clk_hw *hw)
> }
>
> extern const struct clk_ops ccu_div_ops;
> +extern const struct clk_ops ccu_rodiv_ops;
>
> #endif /* _CCU_DIV_H_ */
> diff --git a/drivers/clk/sunxi-ng/ccu_mux.c b/drivers/clk/sunxi-ng/ccu_mux.c
> index 766f27cff748..e2d6833a6d33 100644
> --- a/drivers/clk/sunxi-ng/ccu_mux.c
> +++ b/drivers/clk/sunxi-ng/ccu_mux.c
> @@ -68,13 +68,14 @@ unsigned long ccu_mux_helper_apply_prediv(struct ccu_common *common,
> }
> EXPORT_SYMBOL_NS_GPL(ccu_mux_helper_apply_prediv, "SUNXI_CCU");
>
> -static unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
> +unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
> struct ccu_mux_internal *cm,
> int parent_index,
> unsigned long parent_rate)
> {
> return parent_rate * ccu_mux_get_prediv(common, cm, parent_index);
> }
> +EXPORT_SYMBOL_NS_GPL(ccu_mux_helper_unapply_prediv, "SUNXI_CCU");
This does not need to be exported since all the base clocks build into
one module. And maybe it shouldn't as we probably don't want individual
clock drivers implementing ops.
Otherwise,
Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
> int ccu_mux_helper_determine_rate(struct ccu_common *common,
> struct ccu_mux_internal *cm,
> diff --git a/drivers/clk/sunxi-ng/ccu_mux.h b/drivers/clk/sunxi-ng/ccu_mux.h
> index c94a4bde5d01..272a2c36a8f2 100644
> --- a/drivers/clk/sunxi-ng/ccu_mux.h
> +++ b/drivers/clk/sunxi-ng/ccu_mux.h
> @@ -134,6 +134,10 @@ unsigned long ccu_mux_helper_apply_prediv(struct ccu_common *common,
> struct ccu_mux_internal *cm,
> int parent_index,
> unsigned long parent_rate);
> +unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
> + struct ccu_mux_internal *cm,
> + int parent_index,
> + unsigned long parent_rate);
> int ccu_mux_helper_determine_rate(struct ccu_common *common,
> struct ccu_mux_internal *cm,
> struct clk_rate_request *req,
>
> --
> 2.47.3
>
^ permalink raw reply
* [PATCH] rtc: brcmstb-waketimer: add missing MODULE_DEVICE_TABLE()
From: Pengpeng Hou @ 2026-07-04 12:17 UTC (permalink / raw)
To: Alexandre Belloni, Florian Fainelli,
Broadcom internal kernel review list
Cc: Pengpeng Hou, linux-rtc, linux-arm-kernel, linux-kernel
The driver has an OF match table wired to .of_match_table, but does
not export the table with MODULE_DEVICE_TABLE().
Add the missing MODULE_DEVICE_TABLE(of, ...) entry so module alias
information is generated for OF based module autoloading.
This is a source-level fix. It does not claim dynamic hardware
reproduction; the evidence is the driver-owned match table, its use by
the platform driver, and the missing module alias publication.
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
---
drivers/rtc/rtc-brcmstb-waketimer.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/rtc/rtc-brcmstb-waketimer.c b/drivers/rtc/rtc-brcmstb-waketimer.c
index fb47c32ab5ff..55c15aad42cf 100644
--- a/drivers/rtc/rtc-brcmstb-waketimer.c
+++ b/drivers/rtc/rtc-brcmstb-waketimer.c
@@ -413,6 +413,7 @@ static const __maybe_unused struct of_device_id brcmstb_waketmr_of_match[] = {
{ .compatible = "brcm,brcmstb-waketimer" },
{ /* sentinel */ },
};
+MODULE_DEVICE_TABLE(of, brcmstb_waketmr_of_match);
static struct platform_driver brcmstb_waketmr_driver = {
.probe = brcmstb_waketmr_probe,
^ permalink raw reply related
* Re: [PATCH] rtc: brcmstb-waketimer: add missing MODULE_DEVICE_TABLE()
From: sashiko-bot @ 2026-07-04 12:19 UTC (permalink / raw)
To: Pengpeng Hou; +Cc: linux-rtc, Alexandre Belloni
In-Reply-To: <20260704121734.54941-1-pengpeng@iscas.ac.cn>
> The driver has an OF match table wired to .of_match_table, but does
> not export the table with MODULE_DEVICE_TABLE().
>
> Add the missing MODULE_DEVICE_TABLE(of, ...) entry so module alias
> information is generated for OF based module autoloading.
>
> This is a source-level fix. It does not claim dynamic hardware
> reproduction; the evidence is the driver-owned match table, its use by
> the platform driver, and the missing module alias publication.
>
> Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260704121734.54941-1-pengpeng@iscas.ac.cn?part=1
^ permalink raw reply
* [PATCH] rtc: s32g: add missing MODULE_DEVICE_TABLE()
From: Pengpeng Hou @ 2026-07-04 12:20 UTC (permalink / raw)
To: Chester Lin, Matthias Brugger, Ghennadi Procopciuc,
NXP S32 Linux Team, Alexandre Belloni
Cc: Pengpeng Hou, linux-arm-kernel, linux-rtc, linux-kernel
The driver has an OF match table wired to .of_match_table, but does
not export the table with MODULE_DEVICE_TABLE().
Add the missing MODULE_DEVICE_TABLE(of, ...) entry so module alias
information is generated for OF based module autoloading.
This is a source-level fix. It does not claim dynamic hardware
reproduction; the evidence is the driver-owned match table, its use by
the platform driver, and the missing module alias publication.
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
---
drivers/rtc/rtc-s32g.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/rtc/rtc-s32g.c b/drivers/rtc/rtc-s32g.c
index 3a0818e972eb..86716192d10f 100644
--- a/drivers/rtc/rtc-s32g.c
+++ b/drivers/rtc/rtc-s32g.c
@@ -366,6 +366,7 @@ static const struct of_device_id rtc_dt_ids[] = {
{ .compatible = "nxp,s32g2-rtc", .data = &rtc_s32g2_data },
{ /* sentinel */ },
};
+MODULE_DEVICE_TABLE(of, rtc_dt_ids);
static DEFINE_SIMPLE_DEV_PM_OPS(s32g_rtc_pm_ops,
s32g_rtc_suspend, s32g_rtc_resume);
^ permalink raw reply related
* Re: [PATCH] rtc: s32g: add missing MODULE_DEVICE_TABLE()
From: sashiko-bot @ 2026-07-04 12:22 UTC (permalink / raw)
To: Pengpeng Hou; +Cc: linux-rtc, Alexandre Belloni
In-Reply-To: <20260704122003.70108-1-pengpeng@iscas.ac.cn>
> The driver has an OF match table wired to .of_match_table, but does
> not export the table with MODULE_DEVICE_TABLE().
>
> Add the missing MODULE_DEVICE_TABLE(of, ...) entry so module alias
> information is generated for OF based module autoloading.
>
> This is a source-level fix. It does not claim dynamic hardware
> reproduction; the evidence is the driver-owned match table, its use by
> the platform driver, and the missing module alias publication.
>
> Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260704122003.70108-1-pengpeng@iscas.ac.cn?part=1
^ permalink raw reply
* [PATCH] rtc: ab-eoz9: add missing MODULE_DEVICE_TABLE()
From: Pengpeng Hou @ 2026-07-04 15:25 UTC (permalink / raw)
To: Alexandre Belloni
Cc: Pengpeng Hou, open list:REAL TIME CLOCK (RTC) SUBSYSTEM,
linux-kernel
The driver has a match table for the i2c bus wired into its driver
structure, but the table is not exported with MODULE_DEVICE_TABLE().
Add the missing MODULE_DEVICE_TABLE() entry so module alias information
is generated for automatic module loading.
This is a source-level fix. It does not claim dynamic hardware
reproduction; the evidence is the driver-owned match table, its use by
the driver registration structure, and the missing module alias
publication.
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
---
drivers/rtc/rtc-ab-eoz9.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/rtc/rtc-ab-eoz9.c b/drivers/rtc/rtc-ab-eoz9.c
index de002f7a39bf..8dc656bb78bf 100644
--- a/drivers/rtc/rtc-ab-eoz9.c
+++ b/drivers/rtc/rtc-ab-eoz9.c
@@ -549,6 +549,7 @@ static const struct i2c_device_id abeoz9_id[] = {
{ "abeoz9" },
{ }
};
+MODULE_DEVICE_TABLE(i2c, abeoz9_id);
static struct i2c_driver abeoz9_driver = {
.driver = {
--
2.53.0
^ permalink raw reply related
* Re: [PATCH] rtc: ab-eoz9: add missing MODULE_DEVICE_TABLE()
From: sashiko-bot @ 2026-07-04 15:28 UTC (permalink / raw)
To: Pengpeng Hou; +Cc: Alexandre Belloni, linux-rtc
In-Reply-To: <20260704152528.53258-1-pengpeng@iscas.ac.cn>
> The driver has a match table for the i2c bus wired into its driver
> structure, but the table is not exported with MODULE_DEVICE_TABLE().
>
> Add the missing MODULE_DEVICE_TABLE() entry so module alias information
> is generated for automatic module loading.
>
> This is a source-level fix. It does not claim dynamic hardware
> reproduction; the evidence is the driver-owned match table, its use by
> the driver registration structure, and the missing module alias
> publication.
>
> Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260704152528.53258-1-pengpeng@iscas.ac.cn?part=1
^ permalink raw reply
* [PATCH] rtc: armada38x: do not advertise update interrupt (UIE) support
From: Ioannis Fountzoulas @ 2026-07-04 21:07 UTC (permalink / raw)
To: Alexandre Belloni, Andrew Lunn, Gregory Clement,
Sebastian Hesselbarth
Cc: linux-arm-kernel, linux-rtc, linux-kernel, Ioannis Fountzoulas
Problem:
chrony enables RTC update interrupts via the RTC_UIE_ON ioctl to track
RTC drift. On the armada38x driver this request is served by the RTC
core's native path, which arms a 1 second periodic timer that is
re-programmed on the alarm and serviced by rtc_timer_do_work().
If the RTC time is then stepped forward by a large amount while this
timer is active, its scheduled expiry ends up far in the past compared
to the freshly read time.
Why the CPU hangs:
When rtc_timer_do_work() runs, it expires every timer whose expiry is
not in the future, advancing periodic timers by one period each pass:
while ((next = timerqueue_getnext(&rtc->timerqueue))) {
if (next->expires > now)
break;
...
timer->node.expires += timer->period; /* += 1s */
timerqueue_add(&rtc->timerqueue, &timer->node);
}
With a large forward step (seen when the RTC starts far in the past and
chrony corrects it after the first NTP sync), the periodic UIE timer is
overdue by the size of the jump, so this loop must run one iteration per
elapsed second before it can exit.
It never yields in that time, so the workqueue worker pins the CPU and
the watchdog reports a soft lockup / RCU stall, after which the
board reboots:
watchdog: BUG: soft lockup - CPU#1 stuck for 48s! [kworker/1:3:432]
Kernel panic - not syncing: softlockup: hung tasks
Workqueue: events rtc_timer_do_work
rtc_handle_legacy_irq from rtc_timer_do_work
rtc_timer_do_work from process_one_work
process_one_work from worker_thread
Fix:
Clear RTC_FEATURE_UPDATE_INTERRUPT at probe time so the driver stops
advertising native UIE. RTC_UIE_ON is then served by the poll-based UIE
emulation in rtc-dev (CONFIG_RTC_INTF_DEV_UIE_EMUL), which delivers the
1 Hz update notifications chrony needs without ever queuing the runaway
periodic timer.
Testing:
Tested on a Marvell Armada 38x board (ARM Cortex-A9). Before the change,
stepping the clock forward while UIE was enabled reproduced the soft
lockup (about 1 in 4 boots). After the change, rtc_timer_do_work() runs
zero loop iterations and returns immediately, chrony still receives
update interrupts via emulation, and no lockups occur over repeated
reboot cycles.
Signed-off-by: Ioannis Fountzoulas <ioannis.fountzoulas@nokia.com>
---
drivers/rtc/rtc-armada38x.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
index 245290ae1a8d..da036d819649 100644
--- a/drivers/rtc/rtc-armada38x.c
+++ b/drivers/rtc/rtc-armada38x.c
@@ -526,6 +526,14 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev)
else
clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features);
+ /*
+ * A large forward step of the RTC time makes
+ * rtc_timer_do_work() replay one period per elapsed second and can
+ * loop long enough to trigger a soft lockup. Do not advertise
+ * native UIE; RTC_UIE_ON then uses the poll-based emulation.
+ */
+ clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtc_dev->features);
+
/* Update RTC-MBUS bridge timing parameters */
rtc->data->update_mbus_timing(rtc);
--
2.34.1
^ permalink raw reply related
* Re: [PATCH] rtc: armada38x: do not advertise update interrupt (UIE) support
From: sashiko-bot @ 2026-07-04 21:23 UTC (permalink / raw)
To: Ioannis Fountzoulas; +Cc: Alexandre Belloni, linux-rtc
In-Reply-To: <20260704210710.658574-1-ioannis.fountzoulas@nokia.com>
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
New issues:
- [Medium] Clearing RTC_FEATURE_UPDATE_INTERRUPT degrades UIE performance to software polling and introduces a silent dependency on CONFIG_RTC_INTF_DEV_UIE_EMUL, risking ABI breakage.
Pre-existing issues:
- [High] The patch implements a driver-specific workaround for a core RTC subsystem vulnerability, masking the issue in armada38x while leaving all other native UIE-capable RTC drivers vulnerable to a DoS (soft lockup).
- [High] Unprotected hardware register writes in armada38x_rtc_set_offset and armada38x_rtc_reset break hardware write protocol when preempted by an alarm interrupt, potentially causing silent RTC write failures.
--
commit e4e1f958746b053e26726c0a8b1203537d9bd06e
Author: Ioannis Fountzoulas <ioannis.fountzoulas@nokia.com>
rtc: armada38x: do not advertise update interrupt (UIE) support
chrony enables RTC update interrupts via the RTC_UIE_ON ioctl to track
RTC drift. On the armada38x driver this request is served by the RTC
core's native path, which arms a 1 second periodic timer that is
re-programmed on the alarm and serviced by rtc_timer_do_work().
> diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
> index 245290ae1a8de..da036d819649c 100644
> --- a/drivers/rtc/rtc-armada38x.c
> +++ b/drivers/rtc/rtc-armada38x.c
> @@ -526,6 +526,14 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev)
> else
> clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features);
>
> + /*
> + * A large forward step of the RTC time makes
> + * rtc_timer_do_work() replay one period per elapsed second and can
> + * loop long enough to trigger a soft lockup. Do not advertise
> + * native UIE; RTC_UIE_ON then uses the poll-based emulation.
> + */
> + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtc_dev->features);
[Severity: High]
This is a pre-existing issue, but does this driver-specific workaround
mask a core RTC subsystem vulnerability, leaving all other native UIE-capable
RTC drivers vulnerable to a soft lockup?
If a userspace process with CAP_SYS_TIME initiates a large forward time jump,
a lockless TOCTOU race can occur in drivers/rtc/interface.c:rtc_set_time().
rtc_set_time() checks rtc->uie_rtctimer.enabled, which can read as 0 if
rtc_timer_do_work() is concurrently processing the timer.
rtc_set_time() then updates the hardware time without re-arming the timer
to the new time.
The subsequent run of rtc_timer_do_work() finds the timer expiry far in the
past and enters an unbounded while-loop, advancing the timer by 1 second per
iteration, pinning the CPU.
Could we fix this race in the core RTC subsystem rather than disabling native
UIE in this driver?
[Severity: Medium]
Will clearing this feature bit introduce a regression by degrading UIE
performance to software polling and adding a silent dependency on
CONFIG_RTC_INTF_DEV_UIE_EMUL?
If the kernel lacks CONFIG_RTC_INTF_DEV_UIE_EMUL, RTC_UIE_ON will fail and
return -EINVAL, potentially breaking userspace tools like chrony.
If it is enabled, it uses CPU-intensive polling instead of hardware interrupts.
[Severity: High]
This isn't a bug introduced by this patch, but do unprotected hardware register
writes in armada38x_rtc_set_offset() and armada38x_rtc_reset() break the
hardware write protocol if preempted by an alarm interrupt?
Both functions call rtc_delayed_write() without holding rtc->lock or disabling
interrupts.
If an RTC alarm interrupt fires during this time, the interrupt handler
interleaves its own rtc_delayed_write().
When the interrupt returns, the interrupted write executes without the required
preceding dummy writes to RTC_STATUS (hardware erratum workaround RES-3124064),
potentially causing silent RTC write failures.
> +
> /* Update RTC-MBUS bridge timing parameters */
> rtc->data->update_mbus_timing(rtc);
>
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260704210710.658574-1-ioannis.fountzoulas@nokia.com?part=1
^ permalink raw reply
* Re: [PATCH] rtc: armada38x: do not advertise update interrupt (UIE) support
From: Alexandre Belloni @ 2026-07-04 22:13 UTC (permalink / raw)
To: Ioannis Fountzoulas
Cc: Andrew Lunn, Gregory Clement, Sebastian Hesselbarth,
linux-arm-kernel, linux-rtc, linux-kernel
In-Reply-To: <20260704210710.658574-1-ioannis.fountzoulas@nokia.com>
On 04/07/2026 17:07:10-0400, Ioannis Fountzoulas wrote:
> Problem:
> chrony enables RTC update interrupts via the RTC_UIE_ON ioctl to track
> RTC drift. On the armada38x driver this request is served by the RTC
> core's native path, which arms a 1 second periodic timer that is
> re-programmed on the alarm and serviced by rtc_timer_do_work().
> If the RTC time is then stepped forward by a large amount while this
> timer is active, its scheduled expiry ends up far in the past compared
> to the freshly read time.
>
> Why the CPU hangs:
> When rtc_timer_do_work() runs, it expires every timer whose expiry is
> not in the future, advancing periodic timers by one period each pass:
> while ((next = timerqueue_getnext(&rtc->timerqueue))) {
> if (next->expires > now)
> break;
> ...
> timer->node.expires += timer->period; /* += 1s */
> timerqueue_add(&rtc->timerqueue, &timer->node);
> }
> With a large forward step (seen when the RTC starts far in the past and
> chrony corrects it after the first NTP sync), the periodic UIE timer is
> overdue by the size of the jump, so this loop must run one iteration per
> elapsed second before it can exit.
This is not correct because the core ensures that UIE is disable before
changing the RTC time and enables it afterwards so the jump doesn't have
any impact on UIE. So what you need to explain is why UIE is not synced
with the RTC time after it has been set. My guess is RES-3124064 is the
culprit.
> It never yields in that time, so the workqueue worker pins the CPU and
> the watchdog reports a soft lockup / RCU stall, after which the
> board reboots:
> watchdog: BUG: soft lockup - CPU#1 stuck for 48s! [kworker/1:3:432]
> Kernel panic - not syncing: softlockup: hung tasks
> Workqueue: events rtc_timer_do_work
> rtc_handle_legacy_irq from rtc_timer_do_work
> rtc_timer_do_work from process_one_work
> process_one_work from worker_thread
>
> Fix:
> Clear RTC_FEATURE_UPDATE_INTERRUPT at probe time so the driver stops
> advertising native UIE. RTC_UIE_ON is then served by the poll-based UIE
> emulation in rtc-dev (CONFIG_RTC_INTF_DEV_UIE_EMUL), which delivers the
> 1 Hz update notifications chrony needs without ever queuing the runaway
> periodic timer.
>
> Testing:
> Tested on a Marvell Armada 38x board (ARM Cortex-A9). Before the change,
> stepping the clock forward while UIE was enabled reproduced the soft
> lockup (about 1 in 4 boots). After the change, rtc_timer_do_work() runs
> zero loop iterations and returns immediately, chrony still receives
> update interrupts via emulation, and no lockups occur over repeated
> reboot cycles.
>
> Signed-off-by: Ioannis Fountzoulas <ioannis.fountzoulas@nokia.com>
> ---
> drivers/rtc/rtc-armada38x.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
> index 245290ae1a8d..da036d819649 100644
> --- a/drivers/rtc/rtc-armada38x.c
> +++ b/drivers/rtc/rtc-armada38x.c
> @@ -526,6 +526,14 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev)
> else
> clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features);
>
> + /*
> + * A large forward step of the RTC time makes
> + * rtc_timer_do_work() replay one period per elapsed second and can
> + * loop long enough to trigger a soft lockup. Do not advertise
> + * native UIE; RTC_UIE_ON then uses the poll-based emulation.
> + */
> + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtc_dev->features);
> +
> /* Update RTC-MBUS bridge timing parameters */
> rtc->data->update_mbus_timing(rtc);
>
> --
> 2.34.1
>
--
Alexandre Belloni, co-owner and COO, Bootlin
Embedded Linux and Kernel engineering
https://bootlin.com
^ permalink raw reply
* Re: [PATCH v3 1/8] dt-bindings: rtc: sun6i: no clock-output-names on h616/r329
From: Alexandre Belloni @ 2026-07-05 21:38 UTC (permalink / raw)
To: Jerome Brunet
Cc: Junhui Liu, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Chen-Yu Tsai, Jernej Skrabec, Samuel Holland, Michael Turquette,
Stephen Boyd, Maxime Ripard, linux-rtc, devicetree,
linux-arm-kernel, linux-sunxi, linux-kernel, linux-clk, Sashiko
In-Reply-To: <20260702-a733-rtc-v3-1-eb2580374de6@baylibre.com>
On 02/07/2026 10:10:00+0200, Jerome Brunet wrote:
> On h616 and r329 chips, clock output names are never defined through DT and
> are not meant to be. Just disallow the property for those chips.
>
> Reported-by: Sashiko <sashiko-bot@kernel.org>
> Closes: http://lore.kernel.org/r/20260629125305.0DF981F000E9@smtp.kernel.org
> Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
> ---
> .../devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml | 12 ++++++++++++
> 1 file changed, 12 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
> index 9df5cdb6f63f..959a012c626f 100644
> --- a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
> +++ b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
> @@ -175,6 +175,18 @@ allOf:
> interrupts:
> minItems: 2
>
> + - if:
> + properties:
> + compatible:
> + contains:
> + enum:
> + - allwinner,sun50i-h616-rtc
> + - allwinner,sun50i-r329-rtc
> +
> + then:
> + properties:
> + clock-output-names: false
> +
> required:
> - "#clock-cells"
> - compatible
>
> --
> 2.47.3
>
--
Alexandre Belloni, co-owner and COO, Bootlin
Embedded Linux and Kernel engineering
https://bootlin.com
^ permalink raw reply
* Re: [PATCH v3 2/8] dt-bindings: rtc: sun6i: add sun60i-a733 support
From: Alexandre Belloni @ 2026-07-05 21:38 UTC (permalink / raw)
To: Jerome Brunet
Cc: Junhui Liu, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Chen-Yu Tsai, Jernej Skrabec, Samuel Holland, Michael Turquette,
Stephen Boyd, Maxime Ripard, linux-rtc, devicetree,
linux-arm-kernel, linux-sunxi, linux-kernel, linux-clk
In-Reply-To: <20260702-a733-rtc-v3-2-eb2580374de6@baylibre.com>
On 02/07/2026 10:10:01+0200, Jerome Brunet wrote:
> Add a new rtc compatible for the sun60i-a733 SoC and new IDs for the
> peripheral oscillator clock gates of this SoC.
>
> Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
> ---
> Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml | 1 +
> include/dt-bindings/clock/sun6i-rtc.h | 4 ++++
> 2 files changed, 5 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
> index 959a012c626f..f2b91186ed37 100644
> --- a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
> +++ b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
> @@ -33,6 +33,7 @@ properties:
> - enum:
> - allwinner,sun20i-d1-rtc
> - allwinner,sun55i-a523-rtc
> + - allwinner,sun60i-a733-rtc
> - const: allwinner,sun50i-r329-rtc
>
> reg:
> diff --git a/include/dt-bindings/clock/sun6i-rtc.h b/include/dt-bindings/clock/sun6i-rtc.h
> index 3bd3aa3d57ce..5132a393ca4b 100644
> --- a/include/dt-bindings/clock/sun6i-rtc.h
> +++ b/include/dt-bindings/clock/sun6i-rtc.h
> @@ -6,5 +6,9 @@
> #define CLK_OSC32K 0
> #define CLK_OSC32K_FANOUT 1
> #define CLK_IOSC 2
> +#define CLK_HOSC_UFS 8
> +#define CLK_HOSC_HDMI 9
> +#define CLK_HOSC_SERDES0 10
> +#define CLK_HOSC_SERDES1 11
>
> #endif /* _DT_BINDINGS_CLK_SUN6I_RTC_H_ */
>
> --
> 2.47.3
>
--
Alexandre Belloni, co-owner and COO, Bootlin
Embedded Linux and Kernel engineering
https://bootlin.com
^ permalink raw reply
* Re: [PATCH v3 6/8] clk: sunxi-ng: div: add read-only operation support
From: Jerome Brunet @ 2026-07-06 9:16 UTC (permalink / raw)
To: Chen-Yu Tsai
Cc: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Jernej Skrabec, Samuel Holland, Michael Turquette,
Stephen Boyd, Maxime Ripard, linux-rtc, devicetree,
linux-arm-kernel, linux-sunxi, linux-kernel, linux-clk
In-Reply-To: <CAGb2v64C4Xn=V5NQcqZQa=v0KsemsVh+_6g7ed0kHz6C_bzmww@mail.gmail.com>
On sam. 04 juil. 2026 at 16:25, Chen-Yu Tsai <wens@kernel.org> wrote:
>>
>> extern const struct clk_ops ccu_div_ops;
>> +extern const struct clk_ops ccu_rodiv_ops;
>>
>> #endif /* _CCU_DIV_H_ */
>> diff --git a/drivers/clk/sunxi-ng/ccu_mux.c b/drivers/clk/sunxi-ng/ccu_mux.c
>> index 766f27cff748..e2d6833a6d33 100644
>> --- a/drivers/clk/sunxi-ng/ccu_mux.c
>> +++ b/drivers/clk/sunxi-ng/ccu_mux.c
>> @@ -68,13 +68,14 @@ unsigned long ccu_mux_helper_apply_prediv(struct ccu_common *common,
>> }
>> EXPORT_SYMBOL_NS_GPL(ccu_mux_helper_apply_prediv, "SUNXI_CCU");
>>
>> -static unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
>> +unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
>> struct ccu_mux_internal *cm,
>> int parent_index,
>> unsigned long parent_rate)
>> {
>> return parent_rate * ccu_mux_get_prediv(common, cm, parent_index);
>> }
>> +EXPORT_SYMBOL_NS_GPL(ccu_mux_helper_unapply_prediv, "SUNXI_CCU");
>
> This does not need to be exported since all the base clocks build into
> one module. And maybe it shouldn't as we probably don't want individual
> clock drivers implementing ops.
Indeed, I'll add a patch to remove the export of
ccu_mux_helper_apply_prediv() as well, for consistency. It does not
appear to used out of that module either.
>
>
> Otherwise,
>
> Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
>
--
Jerome
^ permalink raw reply
* [PATCH v4 0/9] clk: sun6i-rtc: Add support for Allwinner A733 SoC
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Sashiko, Conor Dooley, Jerome Brunet
Add support for the Allwinner A733 RTC and its internal Clock Control
Unit (CCU). Reuse the rtc-sun6i rtc driver while introducing a new
SoC-specific RTC CCU driver to handle the hardware's evolved clock
structure.
The A733 implementation supports hardware detection of three external
crystal frequencies (19.2MHz, 24MHz and 26MHz), which is represented in
the driver via read-only divider operations. Implement logic to derive a
normalized 32kHz reference from these DCXO sources using fixed
pre-dividers. Additionally, provide several new DCXO gate clocks for
peripherals, including SerDes, HDMI, and UFS.
This was tested on a Raxda Cubie A7A.
Changes in v4:
- Remove unneeded export of mux prediv helpers
- Link to v3: https://patch.msgid.link/20260702-a733-rtc-v3-0-eb2580374de6@baylibre.com
Changes in v3:
- Disallow clock-output-names DT property for h616/r329 chips
- Fix ccu probe helper to properly unregister clocks on error
- Implement .determine_rate for ccu divider RO ops
- Drop unused DCXO_CTRL_REG_EN define
- Link to v2: https://patch.msgid.link/20260629-a733-rtc-v2-0-7b72112784f8@baylibre.com
Changes in v2:
* Changed DT bindings as suggested. Those have changed significantly
since v1 so I did not pick up Rob's review trailer
* Support added in the existing RTC CCU driver rather than a separate driver
* Added DT parsing clean up of the existing driver
* Xtal detection exposed by RO divider rather than a MUX.
* Dropped conversion to aux device for now. This is not strictly related
the a733 support and will submitted again later on.
* Link to v1: https://lore.kernel.org/r/20260121-a733-rtc-v1-0-d359437f23a7@pigmoral.tech
---
Jerome Brunet (8):
dt-bindings: rtc: sun6i: no clock-output-names on h616/r329
dt-bindings: rtc: sun6i: add sun60i-a733 support
clk: sunxi-ng: fix ccu probe clock unregister on error
clk: sunxi-ng: sun6i-rtc: clean up DT usage
clk: sunxi-ng: div: add read-only operation support
clk: sunxi-ng: mux: remove unneeded export
clk: sunxi-ng: sun6i-rtc: split main oscillator div and gate.
clk: sunxi-ng: sun6i-rtc: add a733 support
Junhui Liu (1):
clk: sunxi-ng: sun6i-rtc: Add feature bit for IOSC calibration
.../bindings/rtc/allwinner,sun6i-a31-rtc.yaml | 13 +++
drivers/clk/sunxi-ng/ccu-sun6i-rtc.c | 123 +++++++++++++++------
drivers/clk/sunxi-ng/ccu-sun6i-rtc.h | 3 +-
drivers/clk/sunxi-ng/ccu_common.c | 12 +-
drivers/clk/sunxi-ng/ccu_common.h | 1 +
drivers/clk/sunxi-ng/ccu_div.c | 42 +++++++
drivers/clk/sunxi-ng/ccu_div.h | 1 +
drivers/clk/sunxi-ng/ccu_mux.c | 3 +-
drivers/clk/sunxi-ng/ccu_mux.h | 4 +
include/dt-bindings/clock/sun6i-rtc.h | 4 +
10 files changed, 162 insertions(+), 44 deletions(-)
---
base-commit: dc59e4fea9d83f03bad6bddf3fa2e52491777482
change-id: 20251226-a733-rtc-c5167df14e6e
Best regards,
--
Jerome
^ permalink raw reply
* [PATCH v4 1/9] dt-bindings: rtc: sun6i: no clock-output-names on h616/r329
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Sashiko, Conor Dooley, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
On h616 and r329 chips, clock output names are never defined through DT and
are not meant to be. Just disallow the property for those chips.
Reported-by: Sashiko <sashiko-bot@kernel.org>
Closes: http://lore.kernel.org/r/20260629125305.0DF981F000E9@smtp.kernel.org
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
.../devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
index 9df5cdb6f63f..959a012c626f 100644
--- a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
@@ -175,6 +175,18 @@ allOf:
interrupts:
minItems: 2
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - allwinner,sun50i-h616-rtc
+ - allwinner,sun50i-r329-rtc
+
+ then:
+ properties:
+ clock-output-names: false
+
required:
- "#clock-cells"
- compatible
--
2.47.3
^ permalink raw reply related
* [PATCH v4 2/9] dt-bindings: rtc: sun6i: add sun60i-a733 support
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Conor Dooley, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
Add a new rtc compatible for the sun60i-a733 SoC and new IDs for the
peripheral oscillator clock gates of this SoC.
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml | 1 +
include/dt-bindings/clock/sun6i-rtc.h | 4 ++++
2 files changed, 5 insertions(+)
diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
index 959a012c626f..f2b91186ed37 100644
--- a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml
@@ -33,6 +33,7 @@ properties:
- enum:
- allwinner,sun20i-d1-rtc
- allwinner,sun55i-a523-rtc
+ - allwinner,sun60i-a733-rtc
- const: allwinner,sun50i-r329-rtc
reg:
diff --git a/include/dt-bindings/clock/sun6i-rtc.h b/include/dt-bindings/clock/sun6i-rtc.h
index 3bd3aa3d57ce..5132a393ca4b 100644
--- a/include/dt-bindings/clock/sun6i-rtc.h
+++ b/include/dt-bindings/clock/sun6i-rtc.h
@@ -6,5 +6,9 @@
#define CLK_OSC32K 0
#define CLK_OSC32K_FANOUT 1
#define CLK_IOSC 2
+#define CLK_HOSC_UFS 8
+#define CLK_HOSC_HDMI 9
+#define CLK_HOSC_SERDES0 10
+#define CLK_HOSC_SERDES1 11
#endif /* _DT_BINDINGS_CLK_SUN6I_RTC_H_ */
--
2.47.3
^ permalink raw reply related
* [PATCH v4 3/9] clk: sunxi-ng: fix ccu probe clock unregister on error
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Sashiko, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
When registering clocks with sunxi_ccu_probe(), the number of ccu_clocks
and the number of hw clocks might be different, eventhough they usually are
the same.
If they are different, it could lead to out-of-bound access or registered
clock left behind on error.
Use a different variable when iterating on hw clocks so every registered
clock, and only those, gets unregistered on error.
Reported-by: Sashiko <sashiko-bot@kernel.org>
Closes: https://lore.kernel.org/r/20260629131254.7E34C1F00A3A@smtp.kernel.org
Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
drivers/clk/sunxi-ng/ccu_common.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c
index 1c083b4d0b7e..43d8eca6abee 100644
--- a/drivers/clk/sunxi-ng/ccu_common.c
+++ b/drivers/clk/sunxi-ng/ccu_common.c
@@ -114,7 +114,7 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev,
const struct sunxi_ccu_desc *desc)
{
struct ccu_reset *reset;
- int i, ret;
+ int i, j, ret;
ccu->desc = desc;
@@ -130,8 +130,8 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev,
cclk->lock = &ccu->lock;
}
- for (i = 0; i < desc->hw_clks->num ; i++) {
- struct clk_hw *hw = desc->hw_clks->hws[i];
+ for (j = 0; j < desc->hw_clks->num ; j++) {
+ struct clk_hw *hw = desc->hw_clks->hws[j];
const char *name;
if (!hw)
@@ -143,7 +143,7 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev,
else
ret = of_clk_hw_register(node, hw);
if (ret) {
- pr_err("Couldn't register clock %d - %s\n", i, name);
+ pr_err("Couldn't register clock %d - %s\n", j, name);
goto err_clk_unreg;
}
}
@@ -186,8 +186,8 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev,
err_del_provider:
of_clk_del_provider(node);
err_clk_unreg:
- while (--i >= 0) {
- struct clk_hw *hw = desc->hw_clks->hws[i];
+ while (--j >= 0) {
+ struct clk_hw *hw = desc->hw_clks->hws[j];
if (!hw)
continue;
--
2.47.3
^ permalink raw reply related
* [PATCH v4 4/9] clk: sunxi-ng: sun6i-rtc: clean up DT usage
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
With sun6i-rtc compatible devices, the "ext-osc32k" clock input
is optional for the devices that support this input (r329 and onward).
Probably preparing for older SoC support, the driver does something funny
when parsing DT. It check if "ext-osc32k" is present in the clock-names and
if it is not, it uses the first clock as "ext-osc32k". This clock will
actually be the rtc bus clock so what the driver does is wrong.
At the moment, the driver does not support the older SoCs that would have
an external 32k clock provided on index #0 so just remove this quirk.
Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
drivers/clk/sunxi-ng/ccu-sun6i-rtc.c | 23 +++--------------------
1 file changed, 3 insertions(+), 20 deletions(-)
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
index f6bfeba009e8..0f528bfaed00 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
@@ -191,10 +191,8 @@ static struct ccu_common iosc_32k_clk = {
CLK_GET_RATE_NOCACHE),
};
-static const struct clk_hw *ext_osc32k[] = { NULL }; /* updated during probe */
-
-static SUNXI_CCU_GATE_HWS(ext_osc32k_gate_clk, "ext-osc32k-gate",
- ext_osc32k, 0x0, BIT(4), 0);
+static SUNXI_CCU_GATE_FW(ext_osc32k_gate_clk, "ext-osc32k-gate",
+ "ext-osc32k", 0x0, BIT(4), 0);
static const struct clk_hw *osc32k_parents[] = {
&iosc_32k_clk.hw,
@@ -352,7 +350,6 @@ MODULE_DEVICE_TABLE(of, sun6i_rtc_ccu_match);
int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg)
{
const struct sun6i_rtc_match_data *data;
- struct clk *ext_osc32k_clk = NULL;
const struct of_device_id *match;
/* This driver is only used for newer variants of the hardware. */
@@ -363,21 +360,7 @@ int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg)
data = match->data;
have_iosc_calibration = data->have_iosc_calibration;
- if (data->have_ext_osc32k) {
- const char *fw_name;
-
- /* ext-osc32k was the only input clock in the old binding. */
- fw_name = of_property_present(dev->of_node, "clock-names")
- ? "ext-osc32k" : NULL;
- ext_osc32k_clk = devm_clk_get_optional(dev, fw_name);
- if (IS_ERR(ext_osc32k_clk))
- return PTR_ERR(ext_osc32k_clk);
- }
-
- if (ext_osc32k_clk) {
- /* Link ext-osc32k-gate to its parent. */
- *ext_osc32k = __clk_get_hw(ext_osc32k_clk);
- } else {
+ if (!data->have_ext_osc32k) {
/* ext-osc32k-gate is an orphan, so do not register it. */
sun6i_rtc_ccu_hw_clks.hws[CLK_EXT_OSC32K_GATE] = NULL;
osc32k_init_data.num_parents = 1;
--
2.47.3
^ permalink raw reply related
* [PATCH v4 5/9] clk: sunxi-ng: sun6i-rtc: Add feature bit for IOSC calibration
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
From: Junhui Liu <junhui.liu@pigmoral.tech>
The sun6i-rtc CCU driver currently uses a global static variable to
denote whether calibration is supported, which makes IOSC operations
tightly coupled to this file.
Convert this into a feature bit to decouple the logic. This allows the
IOSC clock code to be moved into a shared module for reuse by other SoCs.
Signed-off-by: Junhui Liu <junhui.liu@pigmoral.tech>
Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
drivers/clk/sunxi-ng/ccu-sun6i-rtc.c | 17 +++++++++--------
drivers/clk/sunxi-ng/ccu_common.h | 1 +
2 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
index 0f528bfaed00..b24c8b196e66 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
@@ -52,8 +52,6 @@ struct sun6i_rtc_match_data {
u8 osc32k_fanout_nparents;
};
-static bool have_iosc_calibration;
-
static int ccu_iosc_enable(struct clk_hw *hw)
{
struct ccu_common *cm = hw_to_ccu_common(hw);
@@ -80,7 +78,7 @@ static unsigned long ccu_iosc_recalc_rate(struct clk_hw *hw,
{
struct ccu_common *cm = hw_to_ccu_common(hw);
- if (have_iosc_calibration) {
+ if (cm->features & CCU_FEATURE_IOSC_CALIBRATION) {
u32 reg = readl(cm->base + IOSC_CLK_CALI_REG);
/*
@@ -119,7 +117,7 @@ static int ccu_iosc_32k_prepare(struct clk_hw *hw)
struct ccu_common *cm = hw_to_ccu_common(hw);
u32 val;
- if (!have_iosc_calibration)
+ if (!(cm->features & CCU_FEATURE_IOSC_CALIBRATION))
return 0;
val = readl(cm->base + IOSC_CLK_CALI_REG);
@@ -134,7 +132,7 @@ static void ccu_iosc_32k_unprepare(struct clk_hw *hw)
struct ccu_common *cm = hw_to_ccu_common(hw);
u32 val;
- if (!have_iosc_calibration)
+ if (!(cm->features & CCU_FEATURE_IOSC_CALIBRATION))
return;
val = readl(cm->base + IOSC_CLK_CALI_REG);
@@ -148,7 +146,7 @@ static unsigned long ccu_iosc_32k_recalc_rate(struct clk_hw *hw,
struct ccu_common *cm = hw_to_ccu_common(hw);
u32 val;
- if (have_iosc_calibration) {
+ if (cm->features & CCU_FEATURE_IOSC_CALIBRATION) {
val = readl(cm->base + IOSC_CLK_CALI_REG);
/* Assume the calibrated 32k clock is accurate. */
@@ -167,7 +165,7 @@ static unsigned long ccu_iosc_32k_recalc_accuracy(struct clk_hw *hw,
struct ccu_common *cm = hw_to_ccu_common(hw);
u32 val;
- if (have_iosc_calibration) {
+ if (cm->features & CCU_FEATURE_IOSC_CALIBRATION) {
val = readl(cm->base + IOSC_CLK_CALI_REG);
/* Assume the calibrated 32k clock is accurate. */
@@ -358,7 +356,10 @@ int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg)
return 0;
data = match->data;
- have_iosc_calibration = data->have_iosc_calibration;
+ if (data->have_iosc_calibration) {
+ iosc_clk.features |= CCU_FEATURE_IOSC_CALIBRATION;
+ iosc_32k_clk.features |= CCU_FEATURE_IOSC_CALIBRATION;
+ }
if (!data->have_ext_osc32k) {
/* ext-osc32k-gate is an orphan, so do not register it. */
diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h
index bbec283b9d99..d9dc24ad5503 100644
--- a/drivers/clk/sunxi-ng/ccu_common.h
+++ b/drivers/clk/sunxi-ng/ccu_common.h
@@ -21,6 +21,7 @@
#define CCU_FEATURE_CLOSEST_RATE BIT(9)
#define CCU_FEATURE_DUAL_DIV BIT(10)
#define CCU_FEATURE_UPDATE_BIT BIT(11)
+#define CCU_FEATURE_IOSC_CALIBRATION BIT(12)
/* MMC timing mode switch bit */
#define CCU_MMC_NEW_TIMING_MODE BIT(30)
--
2.47.3
^ permalink raw reply related
* [PATCH v4 6/9] clk: sunxi-ng: div: add read-only operation support
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
Add support for sunxi-ng read-only dividers. This will be
useful to the a733 oscillator detection logic.
Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
drivers/clk/sunxi-ng/ccu_div.c | 42 ++++++++++++++++++++++++++++++++++++++++++
drivers/clk/sunxi-ng/ccu_div.h | 1 +
drivers/clk/sunxi-ng/ccu_mux.c | 2 +-
drivers/clk/sunxi-ng/ccu_mux.h | 4 ++++
4 files changed, 48 insertions(+), 1 deletion(-)
diff --git a/drivers/clk/sunxi-ng/ccu_div.c b/drivers/clk/sunxi-ng/ccu_div.c
index 62d680ccb524..d1c8c7baa12d 100644
--- a/drivers/clk/sunxi-ng/ccu_div.c
+++ b/drivers/clk/sunxi-ng/ccu_div.c
@@ -84,6 +84,36 @@ static int ccu_div_determine_rate(struct clk_hw *hw,
req, ccu_div_determine_rate_helper, cd);
}
+static int ccu_rodiv_determine_rate(struct clk_hw *hw,
+ struct clk_rate_request *req)
+{
+ struct ccu_div *cd = hw_to_ccu_div(hw);
+ unsigned long val;
+ u32 reg;
+ int ret;
+
+ reg = readl(cd->common.base + cd->common.reg);
+ val = reg >> cd->div.shift;
+ val &= (1 << cd->div.width) - 1;
+
+ req->rate = ccu_mux_helper_unapply_prediv(&cd->common, &cd->mux, -1,
+ req->rate);
+
+ if (cd->common.features & CCU_FEATURE_FIXED_POSTDIV)
+ req->rate *= cd->fixed_post_div;
+
+ ret = divider_ro_determine_rate(hw, req, cd->div.table,
+ cd->div.width, cd->div.flags, val);
+
+ if (cd->common.features & CCU_FEATURE_FIXED_POSTDIV)
+ req->rate /= cd->fixed_post_div;
+
+ req->rate = ccu_mux_helper_apply_prediv(&cd->common, &cd->mux, -1,
+ req->rate);
+
+ return ret;
+}
+
static int ccu_div_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned long parent_rate)
{
@@ -143,3 +173,15 @@ const struct clk_ops ccu_div_ops = {
.set_rate = ccu_div_set_rate,
};
EXPORT_SYMBOL_NS_GPL(ccu_div_ops, "SUNXI_CCU");
+
+const struct clk_ops ccu_rodiv_ops = {
+ .disable = ccu_div_disable,
+ .enable = ccu_div_enable,
+ .is_enabled = ccu_div_is_enabled,
+
+ .get_parent = ccu_div_get_parent,
+
+ .determine_rate = ccu_rodiv_determine_rate,
+ .recalc_rate = ccu_div_recalc_rate,
+};
+EXPORT_SYMBOL_NS_GPL(ccu_rodiv_ops, "SUNXI_CCU");
diff --git a/drivers/clk/sunxi-ng/ccu_div.h b/drivers/clk/sunxi-ng/ccu_div.h
index be00b3277e97..a30a92780a05 100644
--- a/drivers/clk/sunxi-ng/ccu_div.h
+++ b/drivers/clk/sunxi-ng/ccu_div.h
@@ -300,5 +300,6 @@ static inline struct ccu_div *hw_to_ccu_div(struct clk_hw *hw)
}
extern const struct clk_ops ccu_div_ops;
+extern const struct clk_ops ccu_rodiv_ops;
#endif /* _CCU_DIV_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_mux.c b/drivers/clk/sunxi-ng/ccu_mux.c
index 766f27cff748..775d396ccf31 100644
--- a/drivers/clk/sunxi-ng/ccu_mux.c
+++ b/drivers/clk/sunxi-ng/ccu_mux.c
@@ -68,7 +68,7 @@ unsigned long ccu_mux_helper_apply_prediv(struct ccu_common *common,
}
EXPORT_SYMBOL_NS_GPL(ccu_mux_helper_apply_prediv, "SUNXI_CCU");
-static unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
+unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
struct ccu_mux_internal *cm,
int parent_index,
unsigned long parent_rate)
diff --git a/drivers/clk/sunxi-ng/ccu_mux.h b/drivers/clk/sunxi-ng/ccu_mux.h
index c94a4bde5d01..272a2c36a8f2 100644
--- a/drivers/clk/sunxi-ng/ccu_mux.h
+++ b/drivers/clk/sunxi-ng/ccu_mux.h
@@ -134,6 +134,10 @@ unsigned long ccu_mux_helper_apply_prediv(struct ccu_common *common,
struct ccu_mux_internal *cm,
int parent_index,
unsigned long parent_rate);
+unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
+ struct ccu_mux_internal *cm,
+ int parent_index,
+ unsigned long parent_rate);
int ccu_mux_helper_determine_rate(struct ccu_common *common,
struct ccu_mux_internal *cm,
struct clk_rate_request *req,
--
2.47.3
^ permalink raw reply related
* [PATCH v4 7/9] clk: sunxi-ng: mux: remove unneeded export
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
The export ccu_mux_helper_apply_prediv() symbol is actually not
necessary. No module other than sunxi-ccu would use it at the moment
so just remove the export.
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
drivers/clk/sunxi-ng/ccu_mux.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/clk/sunxi-ng/ccu_mux.c b/drivers/clk/sunxi-ng/ccu_mux.c
index 775d396ccf31..1a441745e796 100644
--- a/drivers/clk/sunxi-ng/ccu_mux.c
+++ b/drivers/clk/sunxi-ng/ccu_mux.c
@@ -66,7 +66,6 @@ unsigned long ccu_mux_helper_apply_prediv(struct ccu_common *common,
{
return parent_rate / ccu_mux_get_prediv(common, cm, parent_index);
}
-EXPORT_SYMBOL_NS_GPL(ccu_mux_helper_apply_prediv, "SUNXI_CCU");
unsigned long ccu_mux_helper_unapply_prediv(struct ccu_common *common,
struct ccu_mux_internal *cm,
--
2.47.3
^ permalink raw reply related
* [PATCH v4 8/9] clk: sunxi-ng: sun6i-rtc: split main oscillator div and gate.
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
On the a733 the "osc24M-32k" clock has the same gate bits as the previously
supported SoC but a different divider implementation.
Instead of a fixed 750 divider, the divider is selected based on the
rate of the oscillator. It can be seen as a simple read-only divider.
To easily replace the divider part depending the SoC, split the divider
and gate into two separate clock entities.
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
drivers/clk/sunxi-ng/ccu-sun6i-rtc.c | 20 +++++++++++---------
drivers/clk/sunxi-ng/ccu-sun6i-rtc.h | 3 ++-
2 files changed, 13 insertions(+), 10 deletions(-)
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
index b24c8b196e66..25dd87e78eb7 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
@@ -218,17 +218,18 @@ static const struct clk_parent_data osc24M[] = {
{ .fw_name = "hosc", .name = "osc24M" }
};
-static struct ccu_gate osc24M_32k_clk = {
- .enable = BIT(16),
- .common = {
- .reg = LOSC_OUT_GATING_REG,
- .prediv = 750,
- .features = CCU_FEATURE_ALL_PREDIV,
- .hw.init = CLK_HW_INIT_PARENTS_DATA("osc24M-32k", osc24M,
- &ccu_gate_ops, 0),
- },
+static struct clk_fixed_factor osc24M_32k_div_clk = {
+ .mult = 1,
+ .div = 750,
+ .hw.init = CLK_HW_INIT_PARENTS_DATA("osc24M-32k-div",
+ osc24M,
+ &clk_fixed_factor_ops,
+ 0),
};
+static SUNXI_CCU_GATE_HW(osc24M_32k_clk, "osc24M-32k", &osc24M_32k_div_clk.hw,
+ LOSC_OUT_GATING_REG, BIT(16), 0);
+
static const struct clk_hw *rtc_32k_parents[] = {
&osc32k_clk.common.hw,
&osc24M_32k_clk.common.hw
@@ -286,6 +287,7 @@ static struct clk_hw_onecell_data sun6i_rtc_ccu_hw_clks = {
[CLK_EXT_OSC32K_GATE] = &ext_osc32k_gate_clk.common.hw,
[CLK_OSC24M_32K] = &osc24M_32k_clk.common.hw,
[CLK_RTC_32K] = &rtc_32k_clk.common.hw,
+ [CLK_OSC24M_32K_DIV] = &osc24M_32k_div_clk.hw,
},
};
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h
index 9ae821fc2599..ab7b92b47f59 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h
@@ -9,7 +9,8 @@
#define CLK_EXT_OSC32K_GATE 4
#define CLK_OSC24M_32K 5
#define CLK_RTC_32K 6
+#define CLK_OSC24M_32K_DIV 7
-#define CLK_NUMBER (CLK_RTC_32K + 1)
+#define CLK_NUMBER (CLK_OSC24M_32K_DIV + 1)
#endif /* _CCU_SUN6I_RTC_H */
--
2.47.3
^ permalink raw reply related
* [PATCH v4 9/9] clk: sunxi-ng: sun6i-rtc: add a733 support
From: Jerome Brunet @ 2026-07-06 9:32 UTC (permalink / raw)
To: Junhui Liu, Alexandre Belloni, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Chen-Yu Tsai, Jernej Skrabec, Samuel Holland,
Michael Turquette, Stephen Boyd, Maxime Ripard
Cc: linux-rtc, devicetree, linux-arm-kernel, linux-sunxi,
linux-kernel, linux-clk, Jerome Brunet
In-Reply-To: <20260706-a733-rtc-v4-0-f330728db3d3@baylibre.com>
Add support for the sun60i a733 CCU RTC.
Compared to the a523, this SoC has a different input oscillator divider
which auto-detects the oscillator rate and select a divider to provide
a fixed 32768Hz clock. It also provides several phy reference clocks
with dedicated clock gates.
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
drivers/clk/sunxi-ng/ccu-sun6i-rtc.c | 73 ++++++++++++++++++++++++++++++++++--
drivers/clk/sunxi-ng/ccu-sun6i-rtc.h | 2 +-
2 files changed, 71 insertions(+), 4 deletions(-)
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
index 25dd87e78eb7..6b71bbd80255 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c
@@ -44,9 +44,13 @@
#define DCXO_CTRL_REG 0x160
#define DCXO_CTRL_CLK16M_RC_EN BIT(0)
+#define DCXO_GATING_REG 0x16c
+
struct sun6i_rtc_match_data {
bool have_ext_osc32k : 1;
bool have_iosc_calibration : 1;
+ bool have_dcxo_status : 1;
+ bool have_phy_ref_gates : 1;
bool rtc_32k_single_parent : 1;
const struct clk_parent_data *osc32k_fanout_parents;
u8 osc32k_fanout_nparents;
@@ -213,7 +217,12 @@ static struct ccu_mux osc32k_clk = {
},
};
-/* This falls back to the global name for fwnodes without a named reference. */
+/*
+ * This falls back to the global name for fwnodes without a named reference.
+ * NOTE: osc24M name might be misleading the oscillator could also be a 26MHz
+ * or a 19.2MHz one starting with the a733. The original name is kept anyway
+ * in case anything is relying on it.
+ */
static const struct clk_parent_data osc24M[] = {
{ .fw_name = "hosc", .name = "osc24M" }
};
@@ -227,8 +236,28 @@ static struct clk_fixed_factor osc24M_32k_div_clk = {
0),
};
-static SUNXI_CCU_GATE_HW(osc24M_32k_clk, "osc24M-32k", &osc24M_32k_div_clk.hw,
- LOSC_OUT_GATING_REG, BIT(16), 0);
+static struct clk_div_table osc24M_32k_div_a733_table[] = {
+ { .val = 0, .div = 732 },
+ { .val = 1, .div = 586 },
+ { .val = 2, .div = 793 },
+ { .val = 3, .div = 732 },
+ { /* Sentinel */ },
+};
+
+static struct ccu_div osc24M_32k_div_a733_clk = {
+ .enable = BIT(1),
+ .div = _SUNXI_CCU_DIV_TABLE(14, 2, osc24M_32k_div_a733_table),
+ .common = {
+ .reg = DCXO_CTRL_REG,
+ .hw.init = CLK_HW_INIT_PARENTS_DATA("osc24M-32k-div",
+ osc24M,
+ &ccu_rodiv_ops,
+ 0),
+ },
+};
+
+static SUNXI_CCU_GATE(osc24M_32k_clk, "osc24M-32k", "osc24M-32k-div",
+ LOSC_OUT_GATING_REG, BIT(16), 0);
static const struct clk_hw *rtc_32k_parents[] = {
&osc32k_clk.common.hw,
@@ -267,6 +296,15 @@ static struct ccu_mux osc32k_fanout_clk = {
},
};
+static SUNXI_CCU_GATE_FW(hosc_serdes1_clk, "hosc-serdes1", "hosc",
+ DCXO_GATING_REG, BIT(5), 0);
+static SUNXI_CCU_GATE_FW(hosc_serdes0_clk, "hosc-serdes0", "hosc",
+ DCXO_GATING_REG, BIT(4), 0);
+static SUNXI_CCU_GATE_FW(hosc_hdmi_clk, "hosc-hdmi", "hosc",
+ DCXO_GATING_REG, BIT(1), 0);
+static SUNXI_CCU_GATE_FW(hosc_ufs_clk, "hosc-ufs", "hosc",
+ DCXO_GATING_REG, BIT(0), 0);
+
static struct ccu_common *sun6i_rtc_ccu_clks[] = {
&iosc_clk,
&iosc_32k_clk,
@@ -275,6 +313,11 @@ static struct ccu_common *sun6i_rtc_ccu_clks[] = {
&osc24M_32k_clk.common,
&rtc_32k_clk.common,
&osc32k_fanout_clk.common,
+ &osc24M_32k_div_a733_clk.common,
+ &hosc_serdes1_clk.common,
+ &hosc_serdes0_clk.common,
+ &hosc_hdmi_clk.common,
+ &hosc_ufs_clk.common,
};
static struct clk_hw_onecell_data sun6i_rtc_ccu_hw_clks = {
@@ -288,6 +331,10 @@ static struct clk_hw_onecell_data sun6i_rtc_ccu_hw_clks = {
[CLK_OSC24M_32K] = &osc24M_32k_clk.common.hw,
[CLK_RTC_32K] = &rtc_32k_clk.common.hw,
[CLK_OSC24M_32K_DIV] = &osc24M_32k_div_clk.hw,
+ [CLK_HOSC_UFS] = &hosc_ufs_clk.common.hw,
+ [CLK_HOSC_HDMI] = &hosc_hdmi_clk.common.hw,
+ [CLK_HOSC_SERDES0] = &hosc_serdes0_clk.common.hw,
+ [CLK_HOSC_SERDES1] = &hosc_serdes1_clk.common.hw,
},
};
@@ -330,6 +377,15 @@ static const struct sun6i_rtc_match_data sun55i_a523_rtc_ccu_data = {
.osc32k_fanout_nparents = ARRAY_SIZE(sun50i_r329_osc32k_fanout_parents),
};
+static const struct sun6i_rtc_match_data sun60i_a733_rtc_ccu_data = {
+ .have_ext_osc32k = true,
+ .have_iosc_calibration = true,
+ .have_dcxo_status = true,
+ .have_phy_ref_gates = true,
+ .osc32k_fanout_parents = sun50i_r329_osc32k_fanout_parents,
+ .osc32k_fanout_nparents = ARRAY_SIZE(sun50i_r329_osc32k_fanout_parents),
+};
+
static const struct of_device_id sun6i_rtc_ccu_match[] = {
{
.compatible = "allwinner,sun50i-h616-rtc",
@@ -343,6 +399,10 @@ static const struct of_device_id sun6i_rtc_ccu_match[] = {
.compatible = "allwinner,sun55i-a523-rtc",
.data = &sun55i_a523_rtc_ccu_data,
},
+ {
+ .compatible = "allwinner,sun60i-a733-rtc",
+ .data = &sun60i_a733_rtc_ccu_data,
+ },
{},
};
MODULE_DEVICE_TABLE(of, sun6i_rtc_ccu_match);
@@ -375,6 +435,13 @@ int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg)
osc32k_fanout_init_data.parent_data = data->osc32k_fanout_parents;
osc32k_fanout_init_data.num_parents = data->osc32k_fanout_nparents;
+ if (data->have_dcxo_status)
+ sun6i_rtc_ccu_hw_clks.hws[CLK_OSC24M_32K_DIV] =
+ &osc24M_32k_div_a733_clk.common.hw;
+
+ if (!data->have_phy_ref_gates)
+ sun6i_rtc_ccu_hw_clks.num = CLK_OSC24M_32K_DIV + 1;
+
return devm_sunxi_ccu_probe(dev, reg, &sun6i_rtc_ccu_desc);
}
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h
index ab7b92b47f59..4f4f4cb00f1d 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h
@@ -11,6 +11,6 @@
#define CLK_RTC_32K 6
#define CLK_OSC24M_32K_DIV 7
-#define CLK_NUMBER (CLK_OSC24M_32K_DIV + 1)
+#define CLK_NUMBER (CLK_HOSC_SERDES1 + 1)
#endif /* _CCU_SUN6I_RTC_H */
--
2.47.3
^ permalink raw reply related
page: | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox