* Re: [PATCH v2 8/8] iio: adc: ti-ads112c14: add measurement channel support
From: sashiko-bot @ 2026-06-25 22:11 UTC (permalink / raw)
Cc: conor+dt, devicetree, robh
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-8-ceb9b0b561cb@baylibre.com>
Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:
New issues:
- [Medium] The parsed burnout current configuration (`measurement->burnout`) is never applied to the hardware.
- [Medium] Directly checking `fwnode_find_reference` for `avdd-supply` bypasses the regulator framework's dummy fallback, causing probe to fail if the supply is omitted from the devicetree.
- [Medium] Calculation of `ext_ref_uV` can underflow, leading to garbage scaling values and bypassing validation checks.
Pre-existing issues:
- [High] Short reads from `i2c_smbus_read_i2c_block_data()` are not correctly identified as errors, exposing uninitialized kernel stack memory to userspace.
--
commit 61a17369383e7866b0adf6d21770ae99f4aca379
Author: David Lechner (TI) <dlechner@baylibre.com>
iio: adc: ti-ads112c14: add measurement channel support
Add support for parsing devicetree properties for measurement channels
and doing direct reads on these.
Channels are created dynamically since the number of possibilities is
unreasonably large.
> diff --git a/drivers/iio/adc/ti-ads112c14.c b/drivers/iio/adc/ti-ads112c14.c
> --- a/drivers/iio/adc/ti-ads112c14.c
> +++ b/drivers/iio/adc/ti-ads112c14.c
> @@ -308,106 +463,6 @@ static int ads112c14_prepare_measurement_channel(struct ads112c14_data *data,
> const struct iio_chan_spec *chan)
> {
> struct ads112c14_measurement *measurement = &data->measurements[chan->scan_index];
> u32 refp_buf_en, refn_buf_en, ref_val, ref_sel;
> int ret;
>
[ ... ]
> ret = regmap_update_bits(data->regmap, ADS112C14_REG_DATA_RATE_CFG,
> ADS112C14_DATA_RATE_CFG_GC_EN,
> FIELD_PREP(ADS112C14_DATA_RATE_CFG_GC_EN,
> measurement->global_chop));
> if (ret)
> return ret;
[Severity: Medium]
Is the burnout configuration supposed to be applied to the hardware here?
The parsed burn-out-current-nanoamp is saved to measurement->burnout in
ads112c14_parse_channels(), but this function does not appear to write it
to the ADS112C14_REG_DEVICE_CFG register. This might cause the feature to
be silently ignored even when configured in the devicetree.
[ ... ]
> @@ -494,7 +670,6 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
> case IIO_CHAN_INFO_RAW: {
> u8 buf[3];
> int ret;
>
> if (!iio_device_claim_direct(indio_dev))
> return -EBUSY;
>
> ret = ads112c14_single_conversion(data, chan, buf);
> iio_device_release_direct(indio_dev);
> if (ret < 0)
> return ret;
>
> switch (data->chip_info->resolution_bits) {
> case 16:
> *val = get_unaligned_be16(buf);
[Severity: High]
This isn't a bug introduced by this patch, but does this adequately handle
short reads?
The i2c_smbus_read_i2c_block_data() function called by
ads112c14_single_conversion() returns the positive number of bytes read on
success. If a short read occurs, ret will be positive and bypass the
ret < 0 check.
Could this proceed to process a partially uninitialized buf array and expose
kernel stack memory to userspace?
[ ... ]
> @@ -1021,76 +1142,6 @@ static int ads112c14_probe(struct i2c_client *client)
> if (device_property_present(dev, "refp-supply")) {
> ret = devm_regulator_get_enable_read_voltage(dev, "refp");
> if (ret < 0)
> return dev_err_probe(dev, ret, "failed to get refp voltage\n");
>
> refp_uV = ret;
>
> struct fwnode_handle *refp_fwnode __free(fwnode_handle) =
> fwnode_find_reference(dev->fwnode, "refp-supply", 0);
> if (IS_ERR(refp_fwnode))
> return dev_err_probe(dev, PTR_ERR(refp_fwnode),
> "failed to get refp fwnode\n");
>
> struct fwnode_handle *avdd_fwnode __free(fwnode_handle) =
> fwnode_find_reference(dev->fwnode, "avdd-supply", 0);
> if (IS_ERR(avdd_fwnode))
> return dev_err_probe(dev, PTR_ERR(avdd_fwnode),
> "failed to get avdd fwnode\n");
[Severity: Medium]
Will this rigidly fail the probe if the avdd-supply is absent?
By directly using fwnode_find_reference(), it seems we bypass the regulator
framework's dummy fallback. If the devicetree omits avdd-supply, this
appears to return -ENOENT and fail unconditionally rather than treating
the missing reference as simply not matching refp_fwnode.
>
> /* REFP buffer should not be enabled when connected to AVDD */
> data->refp_is_avdd = refp_fwnode == avdd_fwnode;
> }
>
> if (device_property_present(dev, "refn-supply")) {
> ret = devm_regulator_get_enable_read_voltage(dev, "refn");
> if (ret < 0)
> return dev_err_probe(dev, ret, "failed to get refn voltage\n");
>
> refn_uV = ret;
> } else {
> data->refn_is_gnd = true;
> }
>
> data->ext_ref_uV = refp_uV - refn_uV;
>
> if (data->ext_ref_uV && data->ext_ref_ohms)
> return dev_err_probe(dev, -EINVAL,
> "ti,refp-refn-resistor-ohms property should not be present when refp-supply or refn-supply is present\n");
>
> if (need_ext_ref && !data->ext_ref_uV && !data->ext_ref_ohms)
> return dev_err_probe(dev, -EINVAL,
> "external reference measurements require either refp-supply or ti,refp-refn-resistor-ohms property\n");
[Severity: Medium]
Can this subtraction underflow if refp-supply is missing but refn-supply is
present?
If refp_uV is 0 and refn_uV is greater than 0, subtracting them as unsigned
32-bit integers will wrap to a large positive number. This seems like it
would bypass the subsequent !data->ext_ref_uV validation check and lead to
incorrect values when computing full_scale in ads112c14_populate_tables().
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com?part=8
^ permalink raw reply
* Re: [PATCH v2 7/8] iio: adc: ti-ads112c14: implement gain on internal short SYS_MON channel
From: sashiko-bot @ 2026-06-25 22:08 UTC (permalink / raw)
Cc: robh, conor+dt, devicetree
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-7-ceb9b0b561cb@baylibre.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] Unlocked concurrent accesses to `gain_val` variables can result in data races and potentially corrupted scale values being returned to userspace.
--
commit d2600e3b47039aca86a7fafcbbec65c4180a38f5
Author: David Lechner (TI) <dlechner@baylibre.com>
iio: adc: ti-ads112c14: implement gain on internal short SYS_MON channel
Implement support for the programmable gain amplifier on the internal short
SYS_MON channel. This channel is used for calibration, so it is useful to be
able to set the PGA to the same gain as the external channels.
> diff --git a/drivers/iio/adc/ti-ads112c14.c b/drivers/iio/adc/ti-ads112c14.c
> index c61d472447325..0e775dbc8d50b 100644
> --- a/drivers/iio/adc/ti-ads112c14.c
> +++ b/drivers/iio/adc/ti-ads112c14.c
[ ... ]
> @@ -371,6 +401,17 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
> return IIO_VAL_FRACTIONAL_LOG2;
> }
>
> + if (chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT) {
> + u8 idx = data->sys_mon_chan_short_gain_val;
> +
> + scale_avail = data->sys_mon_chan_short_scale_available[idx];
> +
> + *val = scale_avail[0];
> + *val2 = scale_avail[1];
> +
> + return IIO_VAL_INT_PLUS_NANO;
> + }
> +
[Severity: Medium]
Is it possible for a concurrent write from ads112c14_write_raw() to cause a
data race here?
Since this read side in ads112c14_read_raw() does not acquire the IIO direct
mode lock or use READ_ONCE(), the compiler could reload
data->sys_mon_chan_short_gain_val.
If the value gets reloaded between the assignments of *val and *val2, the
function might fetch the integer and fractional parts from different gain
configurations, returning a corrupted scale to userspace.
[ ... ]
> +static int ads112c14_write_raw(struct iio_dev *indio_dev,
> + struct iio_chan_spec const *chan, int val,
> + int val2, long mask)
> +{
[ ... ]
> + IIO_DEV_ACQUIRE_DIRECT_MODE(indio_dev, claim);
> + if (IIO_DEV_ACQUIRE_FAILED(claim))
> + return -EBUSY;
> +
> + for (u32 i = 0; i < ARRAY_SIZE(ads112c14_pga_gains_x10); i++) {
> + if (val == scale_avail[i][0] && val2 == scale_avail[i][1]) {
> + *gain_val = i;
> + return 0;
> + }
> + }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com?part=7
^ permalink raw reply
* Re: [PATCH 4/4] PCI: mediatek-gen3: Add 2-lanes mode support for Airoha AN7581
From: sashiko-bot @ 2026-06-25 22:07 UTC (permalink / raw)
To: Christian Marangi; +Cc: linux-pci, conor+dt, robh, devicetree
In-Reply-To: <20260625215741.3253212-5-ansuelsmth@gmail.com>
Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:
New issues:
- [High] Calling devm_ioremap_resource() inside the .power_up() callback breaks system resume with -EBUSY.
- [High] Unvalidated num_lanes > 2 causes a NULL pointer dereference in the hardware configuration loop.
- [High] Missing clock disable on error path in mtk_pcie_en7581_power_up().
Pre-existing issues:
- [High] The return value of pm_runtime_get_sync() is ignored, leading to hardware access on suspended devices.
--
commit c4659641288856a22fb57ae4fe5c48d43375cff0
Author: Christian Marangi <ansuelsmth@gmail.com>
PCI: mediatek-gen3: Add 2-lanes mode support for Airoha AN7581
This commit adds 2-lanes mode support for the Airoha AN7581 SoC by
configuring the PCIe MUX in the SCU register. It introduces secondary PCIe
MAC memory mapping, SCU regmap parsing, and additional PERSTOUT reset logic.
> diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
> index b0accd8285892..f750759bbc1d8 100644
> --- a/drivers/pci/controller/pcie-mediatek-gen3.c
> +++ b/drivers/pci/controller/pcie-mediatek-gen3.c
[ ... ]
> @@ -955,12 +974,29 @@ static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie)
> static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie)
> {
> struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
> + unsigned int num_lanes = max(1, pcie->num_lanes);
> struct device *dev = pcie->dev;
> struct resource_entry *entry;
> struct regmap *pbus_regmap;
> u32 val, args[2], size;
> resource_size_t addr;
> - int err;
> + int i, err;
> +
> + if (num_lanes == 2) {
> + struct platform_device *pdev = to_platform_device(dev);
> + struct resource *regs;
> +
> + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sec-pcie-mac");
> + if (!regs)
> + return -EINVAL;
> + pcie->sec_base = devm_ioremap_resource(dev, regs);
[Severity: High]
Since mtk_pcie_en7581_power_up() is assigned as the .power_up callback and
executes during both probe and resume_noirq(), won't calling
devm_ioremap_resource() here cause a conflict on system resume?
The devm-managed resources persist across suspend/resume cycles, so
devm_request_mem_region() will detect a conflict and cause
devm_ioremap_resource() to return -EBUSY. Could this mapping be moved
to the probe path, such as mtk_pcie_parse_port(), to avoid resume failures?
> + if (IS_ERR(pcie->sec_base))
> + return dev_err_probe(dev, PTR_ERR(pcie->sec_base), "failed to map secondary register base\n");
[ ... ]
> @@ -1024,34 +1060,60 @@ static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie)
> pm_runtime_enable(dev);
> pm_runtime_get_sync(dev);
[Severity: High]
This is a pre-existing issue, but should the return value
of pm_runtime_get_sync() be checked?
If the device power domain fails to transition to an active state,
pm_runtime_get_sync() will return a negative error code. Proceeding to access
registers on suspended hardware could trigger a synchronous external abort or
system crash.
> - val = FIELD_PREP(PCIE_VAL_LN0_DOWNSTREAM, 0x47) |
> - FIELD_PREP(PCIE_VAL_LN1_DOWNSTREAM, 0x47) |
> - FIELD_PREP(PCIE_VAL_LN0_UPSTREAM, 0x41) |
> - FIELD_PREP(PCIE_VAL_LN1_UPSTREAM, 0x41);
> - writel_relaxed(val, pcie->base + PCIE_EQ_PRESET_01_REG);
[ ... ]
> + /* Wait for refclk to stabilize */
> msleep(PCIE_T_PVPERL_MS);
>
> + /* Configure all the lines to the same EQ config */
> + for (i = 0; i < num_lanes; i++) {
> + void __iomem *base = pcie->base;
> +
> + if (i == 1)
> + base = pcie->sec_base;
> +
> + val = FIELD_PREP(PCIE_VAL_LN0_DOWNSTREAM, 0x47) |
> + FIELD_PREP(PCIE_VAL_LN1_DOWNSTREAM, 0x47) |
> + FIELD_PREP(PCIE_VAL_LN0_UPSTREAM, 0x41) |
> + FIELD_PREP(PCIE_VAL_LN1_UPSTREAM, 0x41);
> + writel_relaxed(val, base + PCIE_EQ_PRESET_01_REG);
[Severity: High]
If the Device Tree specifies a valid num-lanes value greater than 2 (e.g.,
4 or 8), will this loop dereference a NULL pointer?
Earlier in this function, pcie->sec_base is exclusively mapped when
num_lanes == 2. If num_lanes is greater than 2, pcie->sec_base remains NULL.
When i == 1, base becomes NULL, and writel_relaxed() will panic. Should
there be explicit bounds validation before writing to sec_base?
> + val = PCIE_K_PHYPARAM_QUERY | PCIE_K_QUERY_TIMEOUT |
> + FIELD_PREP(PCIE_K_PRESET_TO_USE_16G, 0x80) |
> + FIELD_PREP(PCIE_K_PRESET_TO_USE, 0x2) |
> + FIELD_PREP(PCIE_K_FINETUNE_MAX, 0xf);
> + writel_relaxed(val, base + PCIE_PIPE4_PIE8_REG);
> + }
> +
> + /* Deassert PERSTOUT for all relevant lines */
> + err = reset_control_bulk_deassert(MAX_NUM_PERSTOUT_RESETS,
> + pcie->perstout_resets);
> + if (err) {
> + dev_err(dev, "failed to deassert PERSTOUTs\n");
> + goto err_perstout_assert;
> + }
> +
> return 0;
>
> -err_clk_prepare_enable:
> +err_perstout_assert:
> pm_runtime_put_sync(dev);
> pm_runtime_disable(dev);
[Severity: High]
If reset_control_bulk_deassert() fails, won't jumping to this label leak
the clock prepare/enable references?
The function successfully enables clocks earlier with
clk_bulk_prepare_enable(), but err_perstout_assert entirely omits calling
clk_bulk_disable_unprepare(), which will leave the hardware clocks
permanently running.
> reset_control_bulk_assert(pcie->soc->phy_resets.num_resets,
> pcie->phy_resets);
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260625215741.3253212-1-ansuelsmth@gmail.com?part=4
^ permalink raw reply
* Re: [PATCH 1/4] dt-bindings: clock: airoha: Add additional reset for PCIe PERSTOUT
From: sashiko-bot @ 2026-06-25 22:07 UTC (permalink / raw)
To: Christian Marangi; +Cc: conor+dt, linux-pci, robh, devicetree
In-Reply-To: <20260625215741.3253212-2-ansuelsmth@gmail.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Data race between direct MMIO and regmap accesses on the SCU_PCIC register.
--
commit 900fc8364d6744e062fdb68cdff6066cb3ba875d
Author: Christian Marangi <ansuelsmth@gmail.com>
dt-bindings: clock: airoha: Add additional reset for PCIe PERSTOUT
Add additional reset to control PCIe PERSTOUT reset line for each of the 3
PCIe lines.
> diff --git a/include/dt-bindings/reset/airoha,en7581-reset.h b/include/dt-bindings/reset/airoha,en7581-reset.h
> --- a/include/dt-bindings/reset/airoha,en7581-reset.h
> +++ b/include/dt-bindings/reset/airoha,en7581-reset.h
[ ... ]
> @@ -62,5 +62,9 @@
> #define EN7581_CPU_TIMER_RST 50
> #define EN7581_PCIE_HB_RST 51
> #define EN7581_XPON_MAC_RST 52
> +/* RST_PCIC */
> +#define EN7581_PCIC_PERSTOUT0_RST 53
> +#define EN7581_PCIC_PERSTOUT1_RST 54
> +#define EN7581_PCIC_PERSTOUT2_RST 55
[Severity: High]
Will adding these resets expose a data race between the reset controller and
the PCIe controller during link bring-up?
When these resets are asserted, en7523_reset_update() in clk-en7523.c
performs an unlocked direct MMIO read-modify-write on the SCU_PCIC register:
drivers/clk/clk-en7523.c:en7523_reset_update() {
...
val = readl(addr);
val &= ~BIT(id % RST_NR_PER_BANK);
...
writel(val, addr);
}
At the same time, mtk_pcie_en7581_power_up() in pcie-mediatek-gen3.c
modifies the same SCU_PCIC register using a regmap:
drivers/pci/controller/pcie-mediatek-gen3.c:mtk_pcie_en7581_power_up() {
...
regmap_update_bits(pcie->scu, SCU_PCIC, SCU_PCIC_PCIE_CTRL,
FIELD_PREP(SCU_PCIC_PCIE_CTRL, BIT(1)));
}
Since the regmap internal lock does not protect against direct MMIO accesses
from clk-en7523.c, could concurrent operations (like one port triggering a
reset while another powers up) silently corrupt the SCU_PCIC hardware
register state and cause PCIe links to fail?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260625215741.3253212-1-ansuelsmth@gmail.com?part=1
^ permalink raw reply
* Re: [PATCH v2 6/8] iio: adc: add ti-ads112c14 driver
From: sashiko-bot @ 2026-06-25 22:07 UTC (permalink / raw)
Cc: conor+dt, robh, devicetree
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-6-ceb9b0b561cb@baylibre.com>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Short I2C reads lead to the use of uninitialized stack memory for ADC readings.
- [High] The driver inadvertently sets the device into Continuous Conversion mode instead of the intended Single-Shot mode.
--
commit 610f816911f47ce29d3c83f300222d6ab72f8820
Author: David Lechner (TI) <dlechner@baylibre.com>
iio: adc: add ti-ads112c14 driver
Add a new driver for the TI ADS112C14/ADS122C14 ADC chips.
This first step is adding a very basic driver that only supports power
on/reset and reading the system monitor channels.
> diff --git a/drivers/iio/adc/ti-ads112c14.c b/drivers/iio/adc/ti-ads112c14.c
> new file mode 100644
> index 0000000000000..c61d472447325
> --- /dev/null
> +++ b/drivers/iio/adc/ti-ads112c14.c
[ ... ]
> +static int ads112c14_single_conversion(struct ads112c14_data *data,
> + const struct iio_chan_spec *chan,
> + u8 *buf)
> +{
[ ... ]
> + return i2c_smbus_read_i2c_block_data(client, ADS112C14_CMD_RDATA,
> + BITS_TO_BYTES(data->chip_info->resolution_bits),
> + buf);
> +}
> +
> +static int ads112c14_read_raw(struct iio_dev *indio_dev,
> + struct iio_chan_spec const *chan, int *val,
> + int *val2, long mask)
> +{
[ ... ]
> + switch (mask) {
> + case IIO_CHAN_INFO_RAW: {
> + u8 buf[3];
> + int ret;
> +
> + if (!iio_device_claim_direct(indio_dev))
> + return -EBUSY;
> +
> + ret = ads112c14_single_conversion(data, chan, buf);
> + iio_device_release_direct(indio_dev);
> + if (ret < 0)
> + return ret;
[Severity: High]
Does this code handle short I2C reads correctly?
i2c_smbus_read_i2c_block_data() returns the positive byte count on success.
If the device returns fewer bytes than requested, ret will be positive but
less than BITS_TO_BYTES(data->chip_info->resolution_bits).
Since ads112c14_read_raw() only checks if (ret < 0), won't a short read
bypass error handling and cause it to process uninitialized stack memory from
buf, leading to an information leak and corrupted ADC readings?
> +
> + switch (data->chip_info->resolution_bits) {
> + case 16:
> + *val = get_unaligned_be16(buf);
[ ... ]
> +static int ads112c14_probe(struct i2c_client *client)
> +{
[ ... ]
> + /* Place in single-shot conversion mode to make ready for raw read. */
> + ret = regmap_set_bits(data->regmap, ADS112C14_REG_DEVICE_CFG,
> + ADS112C14_DEVICE_CFG_CONV_MODE);
[Severity: High]
Does setting ADS112C14_DEVICE_CFG_CONV_MODE actually put the device into
continuous conversion mode instead of the intended single-shot mode?
According to the comment, the intention is to use single-shot mode (which is
typically the default value of 0). Setting the bit to 1 appears to enable
continuous conversion mode, which could cause hardware race conditions and
corrupted data when multiplexer settings are changed for new sysfs readings.
> + if (ret)
> + return ret;
> +
> + indio_dev->name = info->name;
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com?part=6
^ permalink raw reply
* Re: [PATCH 3/4] dt-bindings: PCI: mediatek-gen3: Split Airoha schema and document 2-lanes
From: sashiko-bot @ 2026-06-25 22:04 UTC (permalink / raw)
To: Christian Marangi; +Cc: devicetree, robh, conor+dt, linux-pci
In-Reply-To: <20260625215741.3253212-4-ansuelsmth@gmail.com>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] The schema incorrectly uses `regs` instead of `reg` in the `allOf` conditional block for `num-lanes == 2`, failing to enforce the requirement for a secondary register region.
- [Medium] Typographical error `phy-lan2` instead of `phy-lane2` in the `reset-names` enum constraint for the 1-lane fallback block.
--
commit bb5683e00f2f10ba9133fc862deba2acbfb939ed
Author: Christian Marangi <ansuelsmth@gmail.com>
dt-bindings: PCI: mediatek-gen3: Split Airoha schema and document 2-lanes
This commit splits the Airoha PCIe schema from the mediatek-gen3 schema into
a dedicated file. This allows documenting the required properties for PCIe
configured in 2-lanes mode, while cleaning up the mediatek-gen3 schema.
> diff --git a/Documentation/devicetree/bindings/pci/airoha,en7581-pcie.yaml b/Documentation/devicetree/bindings/pci/airoha,en7581-pcie.yaml
> new file mode 100644
> index 0000000000000..977c1816572cc
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/pci/airoha,en7581-pcie.yaml
[ ... ]
> +allOf:
> + - $ref: /schemas/pci/pci-host-bridge.yaml#
> + - if:
> + properties:
> + num-lanes:
> + const: 2
> + then:
> + properties:
> + regs:
> + minItems: 2
[Severity: Medium]
Does this schema enforce the minItems constraint as intended? It looks like
there's a typo where "regs" is used instead of "reg". This might allow a
node with num-lanes = <2> but only a single register region to silently pass
validation.
> +
> + reg-names:
> + items:
> + - const: pcie-mac
> + - const: sec-pcie-mac
[ ... ]
> + else:
> + properties:
> + reg:
> + maxItems: 1
> +
> + reg-names:
> + items:
> + - const: pcie-mac
> +
> + resets:
> + minItems: 2
> + maxItems: 3
> +
> + reset-names:
> + minItems: 2
> + items:
> + - enum: [ phy-lane0, phy-lane1, phy-lan2 ]
[Severity: Medium]
Will this properly validate phy-lane2? It appears there is a typo here
(phy-lan2 instead of phy-lane2) which would cause valid configurations
to fail schema validation while accepting the misspelled name.
> + - enum: [ phy-lane1, perstout ]
> + - const: phy-lane2
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260625215741.3253212-1-ansuelsmth@gmail.com?part=3
^ permalink raw reply
* [PATCH 4/4] PCI: mediatek-gen3: Add 2-lanes mode support for Airoha AN7581
From: Christian Marangi @ 2026-06-25 21:57 UTC (permalink / raw)
To: Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley, Ryder Lee, Michael Turquette,
Stephen Boyd, Brian Masney, Philipp Zabel, Matthias Brugger,
AngeloGioacchino Del Regno, Christian Marangi, Jianjun Wang,
linux-pci, devicetree, linux-kernel, linux-mediatek, linux-clk,
linux-arm-kernel
In-Reply-To: <20260625215741.3253212-1-ansuelsmth@gmail.com>
The Airoha AN7581 SoC supports configuring the first PCIe0 line to 2-lanes
mode by bonding it with the second PCIe line. This is done by configuring
the PCIe MUX in the SCU register.
To correctly configure the line for 2-lanes mode, it's required to define
in DT an additional reg, 'sec-pcie-mac' for the secondary PCIe.
It's also needed to define the additional reset and the PERSTOUT reset.
Also 'airoha,scu' property is mandatory to correctly configure the SCU
register for the PCIe MUX.
Finally to toggle 2-lanes mode, it's needed to define in DT 'num-lanes' as
2.
In such configuration the EQ preset are configured to the same values.
To permit correct configuration of the PCIe line, additional logic is added
to assert and deassert the PERSTOUT resets.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
---
drivers/pci/controller/pcie-mediatek-gen3.c | 98 +++++++++++++++++----
1 file changed, 80 insertions(+), 18 deletions(-)
diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index b0accd828589..f750759bbc1d 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -32,6 +32,11 @@
#include "../pci.h"
+/* AN7581 SCU register */
+#define SCU_PCIC 0x88
+#define SCU_PCIC_PCIE_CTRL GENMASK(7, 0)
+
+/* PCIe register */
#define PCIE_BASE_CFG_REG 0x14
#define PCIE_BASE_CFG_SPEED GENMASK(15, 8)
@@ -131,6 +136,7 @@
#define PCIE_ATR_TLP_TYPE_IO PCIE_ATR_TLP_TYPE(2)
#define MAX_NUM_PHY_RESETS 3
+#define MAX_NUM_PERSTOUT_RESETS 2
#define PCIE_MTK_RESET_TIME_US 10
@@ -203,9 +209,11 @@ struct mtk_msi_set {
struct mtk_gen3_pcie {
struct device *dev;
void __iomem *base;
+ void __iomem *sec_base;
phys_addr_t reg_base;
struct reset_control *mac_reset;
struct reset_control_bulk_data phy_resets[MAX_NUM_PHY_RESETS];
+ struct reset_control_bulk_data perstout_resets[MAX_NUM_PERSTOUT_RESETS];
struct phy *phy;
struct clk_bulk_data *clks;
int num_clks;
@@ -222,6 +230,9 @@ struct mtk_gen3_pcie {
DECLARE_BITMAP(msi_irq_in_use, PCIE_MSI_IRQS_NUM);
const struct mtk_gen3_pcie_pdata *soc;
+
+ /* AN7581 specific */
+ struct regmap *scu;
};
/* LTSSM state in PCIE_LTSSM_STATUS_REG bit[28:24] */
@@ -928,6 +939,14 @@ static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie)
if (ret)
return dev_err_probe(dev, ret, "failed to get PHY bulk reset\n");
+ pcie->perstout_resets[0].id = "perstout";
+ pcie->perstout_resets[1].id = "sec-perstout";
+
+ ret = devm_reset_control_bulk_get_optional_exclusive(dev, MAX_NUM_PERSTOUT_RESETS,
+ pcie->perstout_resets);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to get PERSTOUT bulk reset\n");
+
pcie->mac_reset = devm_reset_control_get_optional_exclusive(dev, "mac");
if (IS_ERR(pcie->mac_reset))
return dev_err_probe(dev, PTR_ERR(pcie->mac_reset), "failed to get MAC reset\n");
@@ -955,12 +974,29 @@ static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie)
static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie)
{
struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
+ unsigned int num_lanes = max(1, pcie->num_lanes);
struct device *dev = pcie->dev;
struct resource_entry *entry;
struct regmap *pbus_regmap;
u32 val, args[2], size;
resource_size_t addr;
- int err;
+ int i, err;
+
+ if (num_lanes == 2) {
+ struct platform_device *pdev = to_platform_device(dev);
+ struct resource *regs;
+
+ regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sec-pcie-mac");
+ if (!regs)
+ return -EINVAL;
+ pcie->sec_base = devm_ioremap_resource(dev, regs);
+ if (IS_ERR(pcie->sec_base))
+ return dev_err_probe(dev, PTR_ERR(pcie->sec_base), "failed to map secondary register base\n");
+
+ pcie->scu = syscon_regmap_lookup_by_phandle(dev->of_node, "airoha,scu");
+ if (IS_ERR(pcie->scu))
+ return dev_err_probe(dev, PTR_ERR(pcie->scu), "failed to map SCU regmap\n");
+ }
/*
* The controller may have been left out of reset by the bootloader
@@ -1024,34 +1060,60 @@ static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie)
pm_runtime_enable(dev);
pm_runtime_get_sync(dev);
- val = FIELD_PREP(PCIE_VAL_LN0_DOWNSTREAM, 0x47) |
- FIELD_PREP(PCIE_VAL_LN1_DOWNSTREAM, 0x47) |
- FIELD_PREP(PCIE_VAL_LN0_UPSTREAM, 0x41) |
- FIELD_PREP(PCIE_VAL_LN1_UPSTREAM, 0x41);
- writel_relaxed(val, pcie->base + PCIE_EQ_PRESET_01_REG);
+ /* Assert PERSTOUT for all relevant lines */
+ err = reset_control_bulk_assert(MAX_NUM_PERSTOUT_RESETS,
+ pcie->perstout_resets);
+ if (err) {
+ dev_err(dev, "failed to assert PERSTOUTs\n");
+ goto err_perstout_assert;
+ }
+
+ /* Configure SCU MUX to disable PCIE1 for 2 lines mode */
+ if (num_lanes == 2)
+ regmap_update_bits(pcie->scu, SCU_PCIC, SCU_PCIC_PCIE_CTRL,
+ FIELD_PREP(SCU_PCIC_PCIE_CTRL, BIT(1)));
- val = PCIE_K_PHYPARAM_QUERY | PCIE_K_QUERY_TIMEOUT |
- FIELD_PREP(PCIE_K_PRESET_TO_USE_16G, 0x80) |
- FIELD_PREP(PCIE_K_PRESET_TO_USE, 0x2) |
- FIELD_PREP(PCIE_K_FINETUNE_MAX, 0xf);
- writel_relaxed(val, pcie->base + PCIE_PIPE4_PIE8_REG);
err = clk_bulk_prepare_enable(pcie->num_clks, pcie->clks);
if (err) {
dev_err(dev, "failed to prepare clock\n");
- goto err_clk_prepare_enable;
+ goto err_perstout_assert;
}
- /*
- * Airoha EN7581 performs PCIe reset via clk callbacks since it has a
- * hw issue with PCIE_PE_RSTB signal. Add wait for the time needed to
- * complete the PCIe reset.
- */
+ /* Wait for refclk to stabilize */
msleep(PCIE_T_PVPERL_MS);
+ /* Configure all the lines to the same EQ config */
+ for (i = 0; i < num_lanes; i++) {
+ void __iomem *base = pcie->base;
+
+ if (i == 1)
+ base = pcie->sec_base;
+
+ val = FIELD_PREP(PCIE_VAL_LN0_DOWNSTREAM, 0x47) |
+ FIELD_PREP(PCIE_VAL_LN1_DOWNSTREAM, 0x47) |
+ FIELD_PREP(PCIE_VAL_LN0_UPSTREAM, 0x41) |
+ FIELD_PREP(PCIE_VAL_LN1_UPSTREAM, 0x41);
+ writel_relaxed(val, base + PCIE_EQ_PRESET_01_REG);
+
+ val = PCIE_K_PHYPARAM_QUERY | PCIE_K_QUERY_TIMEOUT |
+ FIELD_PREP(PCIE_K_PRESET_TO_USE_16G, 0x80) |
+ FIELD_PREP(PCIE_K_PRESET_TO_USE, 0x2) |
+ FIELD_PREP(PCIE_K_FINETUNE_MAX, 0xf);
+ writel_relaxed(val, base + PCIE_PIPE4_PIE8_REG);
+ }
+
+ /* Deassert PERSTOUT for all relevant lines */
+ err = reset_control_bulk_deassert(MAX_NUM_PERSTOUT_RESETS,
+ pcie->perstout_resets);
+ if (err) {
+ dev_err(dev, "failed to deassert PERSTOUTs\n");
+ goto err_perstout_assert;
+ }
+
return 0;
-err_clk_prepare_enable:
+err_perstout_assert:
pm_runtime_put_sync(dev);
pm_runtime_disable(dev);
reset_control_bulk_assert(pcie->soc->phy_resets.num_resets,
--
2.53.0
^ permalink raw reply related
* [PATCH 3/4] dt-bindings: PCI: mediatek-gen3: Split Airoha schema and document 2-lanes
From: Christian Marangi @ 2026-06-25 21:57 UTC (permalink / raw)
To: Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley, Ryder Lee, Michael Turquette,
Stephen Boyd, Brian Masney, Philipp Zabel, Matthias Brugger,
AngeloGioacchino Del Regno, Christian Marangi, Jianjun Wang,
linux-pci, devicetree, linux-kernel, linux-mediatek, linux-clk,
linux-arm-kernel
In-Reply-To: <20260625215741.3253212-1-ansuelsmth@gmail.com>
To permit proper documentation of required property to support PCIe
configured for 2-lanes mode, split the Airoha schema part from the
mediatek-gen3 schema to a dedicated schema.
A PCIe configured for 2-lanes mode require an additional reg for the
secondary PCIe to be configured and the airoha,scu phandle to correctly
configure the PCIe MUX.
Rework the mediatek-gen3 schema to drop any redundant constraint previsouly
introduced for Airoha PCIe properties.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
---
.../bindings/pci/airoha,en7581-pcie.yaml | 251 ++++++++++++++++++
.../bindings/pci/mediatek-pcie-gen3.yaml | 77 +-----
2 files changed, 256 insertions(+), 72 deletions(-)
create mode 100644 Documentation/devicetree/bindings/pci/airoha,en7581-pcie.yaml
diff --git a/Documentation/devicetree/bindings/pci/airoha,en7581-pcie.yaml b/Documentation/devicetree/bindings/pci/airoha,en7581-pcie.yaml
new file mode 100644
index 000000000000..977c1816572c
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/airoha,en7581-pcie.yaml
@@ -0,0 +1,251 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/airoha,en7581-pcie.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Gen3 PCIe controller on Airoha SoCs
+
+maintainers:
+ - Christian Marangi <ansuelsmth@gmail.com>
+
+description: |+
+ PCIe Gen3 MAC controller for Airoha SoCs, it supports Gen3 speed
+ and compatible with Gen2, Gen1 speed.
+
+ This PCIe controller supports up to 256 MSI vectors, the MSI hardware
+ block diagram is as follows:
+
+ +-----+
+ | GIC |
+ +-----+
+ ^
+ |
+ port->irq
+ |
+ +-+-+-+-+-+-+-+-+
+ |0|1|2|3|4|5|6|7| (PCIe intc)
+ +-+-+-+-+-+-+-+-+
+ ^ ^ ^
+ | | ... |
+ +-------+ +------+ +-----------+
+ | | |
+ +-+-+---+--+--+ +-+-+---+--+--+ +-+-+---+--+--+
+ |0|1|...|30|31| |0|1|...|30|31| |0|1|...|30|31| (MSI sets)
+ +-+-+---+--+--+ +-+-+---+--+--+ +-+-+---+--+--+
+ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^
+ | | | | | | | | | | | | (MSI vectors)
+ | | | | | | | | | | | |
+
+ (MSI SET0) (MSI SET1) ... (MSI SET7)
+
+ With 256 MSI vectors supported, the MSI vectors are composed of 8 sets,
+ each set has its own address for MSI message, and supports 32 MSI vectors
+ to generate interrupt.
+
+properties:
+ compatible:
+ const: airoha,en7581-pcie
+
+ reg:
+ minItems: 1
+ maxItems: 2
+
+ reg-names:
+ minItems: 1
+ maxItems: 2
+
+ interrupts:
+ maxItems: 1
+
+ ranges:
+ minItems: 1
+ maxItems: 8
+
+ iommu-map:
+ maxItems: 1
+
+ iommu-map-mask:
+ const: 0
+
+ resets:
+ minItems: 1
+ maxItems: 4
+
+ reset-names:
+ minItems: 1
+ maxItems: 4
+
+ clocks:
+ maxItems: 1
+
+ clock-names:
+ items:
+ - const: sys-ck
+
+ phys:
+ maxItems: 1
+
+ phy-names:
+ items:
+ - const: pcie-phy
+
+ num-lanes:
+ enum: [1, 2]
+
+ mediatek,pbus-csr:
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ items:
+ - items:
+ - description: phandle to pbus-csr syscon
+ - description: offset of pbus-csr base address register
+ - description: offset of pbus-csr base address mask register
+ description:
+ Phandle with two arguments to the syscon node used to detect if
+ a given address is accessible on PCIe controller.
+
+ airoha,scu:
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ items:
+ - items:
+ - description: phandle to airoha SCU syscon
+ description:
+ Phandle to SCU syscon to configure PCIe MUX for 2 lines support.
+
+ '#interrupt-cells':
+ const: 1
+
+ interrupt-controller:
+ description: Interrupt controller node for handling legacy PCI interrupts.
+ type: object
+ properties:
+ '#address-cells':
+ const: 0
+ '#interrupt-cells':
+ const: 1
+ interrupt-controller: true
+
+ required:
+ - '#address-cells'
+ - '#interrupt-cells'
+ - interrupt-controller
+
+ additionalProperties: false
+
+required:
+ - compatible
+ - reg
+ - reg-names
+ - interrupts
+ - ranges
+ - clocks
+ - clock-names
+ - '#interrupt-cells'
+ - interrupt-controller
+
+allOf:
+ - $ref: /schemas/pci/pci-host-bridge.yaml#
+ - if:
+ properties:
+ num-lanes:
+ const: 2
+ then:
+ properties:
+ regs:
+ minItems: 2
+
+ reg-names:
+ items:
+ - const: pcie-mac
+ - const: sec-pcie-mac
+
+ resets:
+ minItems: 4
+
+ reset-names:
+ items:
+ - const: phy-lane0
+ - const: phy-lane1
+ - const: perstout
+ - const: sec-perstout
+
+ required:
+ - airoha,scu
+
+ else:
+ properties:
+ reg:
+ maxItems: 1
+
+ reg-names:
+ items:
+ - const: pcie-mac
+
+ resets:
+ minItems: 2
+ maxItems: 3
+
+ reset-names:
+ minItems: 2
+ items:
+ - enum: [ phy-lane0, phy-lane1, phy-lan2 ]
+ - enum: [ phy-lane1, perstout ]
+ - const: phy-lane2
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/interrupt-controller/arm-gic.h>
+ #include <dt-bindings/interrupt-controller/irq.h>
+
+ bus {
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ pcie@1fc00000 {
+ compatible = "airoha,en7581-pcie";
+ device_type = "pci";
+ #address-cells = <3>;
+ #size-cells = <2>;
+
+ reg = <0x0 0x1fc00000 0x0 0x1670>,
+ <0x0 0x1fc20000 0x0 0x1670>;
+ reg-names = "pcie-mac", "sec-pcie-mac";
+
+ clocks = <&scuclk 7>;
+ clock-names = "sys-ck";
+
+ phys = <&pciephy>;
+ phy-names = "pcie-phy";
+
+ ranges = <0x02000000 0 0x20000000 0x0 0x20000000 0 0x4000000>;
+
+ resets = <&scuclk 48>,
+ <&scuclk 49>,
+ <&scuclk 53>,
+ <&scuclk 54>;
+ reset-names = "phy-lane0", "phy-lane1",
+ "perstout", "sec-perstout";
+
+ num-lanes = <2>;
+
+ mediatek,pbus-csr = <&pbus_csr 0x0 0x4>;
+
+ airoha,scu = <&scuclk>;
+
+ interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
+ bus-range = <0x00 0xff>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 0 0x7>;
+ interrupt-map = <0 0 0 1 &pcie_intc 0>,
+ <0 0 0 2 &pcie_intc 1>,
+ <0 0 0 3 &pcie_intc 2>,
+ <0 0 0 4 &pcie_intc 3>;
+ pcie_intc: interrupt-controller {
+ #address-cells = <0>;
+ #interrupt-cells = <1>;
+ interrupt-controller;
+ };
+ };
+ };
diff --git a/Documentation/devicetree/bindings/pci/mediatek-pcie-gen3.yaml b/Documentation/devicetree/bindings/pci/mediatek-pcie-gen3.yaml
index 4db700fc36ba..510f1f2b1c5a 100644
--- a/Documentation/devicetree/bindings/pci/mediatek-pcie-gen3.yaml
+++ b/Documentation/devicetree/bindings/pci/mediatek-pcie-gen3.yaml
@@ -59,7 +59,6 @@ properties:
- const: mediatek,mt8196-pcie
- const: mediatek,mt8192-pcie
- const: mediatek,mt8196-pcie
- - const: airoha,en7581-pcie
reg:
maxItems: 1
@@ -83,20 +82,20 @@ properties:
resets:
minItems: 1
- maxItems: 3
+ maxItems: 2
reset-names:
minItems: 1
- maxItems: 3
+ maxItems: 2
items:
- enum: [ phy, mac, phy-lane0, phy-lane1, phy-lane2 ]
+ enum: [ phy, mac ]
clocks:
- minItems: 1
+ minItems: 4
maxItems: 6
clock-names:
- minItems: 1
+ minItems: 4
maxItems: 6
assigned-clocks:
@@ -115,17 +114,6 @@ properties:
power-domains:
maxItems: 1
- mediatek,pbus-csr:
- $ref: /schemas/types.yaml#/definitions/phandle-array
- items:
- - items:
- - description: phandle to pbus-csr syscon
- - description: offset of pbus-csr base address register
- - description: offset of pbus-csr base address mask register
- description:
- Phandle with two arguments to the syscon node used to detect if
- a given address is accessible on PCIe controller.
-
'#interrupt-cells':
const: 1
@@ -177,16 +165,6 @@ allOf:
- const: peri_26m
- const: top_133m
- resets:
- minItems: 1
- maxItems: 2
-
- reset-names:
- minItems: 1
- maxItems: 2
-
- mediatek,pbus-csr: false
-
- if:
properties:
compatible:
@@ -208,16 +186,6 @@ allOf:
- const: peri_26m
- const: peri_mem
- resets:
- minItems: 1
- maxItems: 2
-
- reset-names:
- minItems: 1
- maxItems: 2
-
- mediatek,pbus-csr: false
-
- if:
properties:
compatible:
@@ -246,8 +214,6 @@ allOf:
- const: phy
- const: mac
- mediatek,pbus-csr: false
-
- if:
properties:
compatible:
@@ -257,7 +223,6 @@ allOf:
then:
properties:
clocks:
- minItems: 4
maxItems: 4
clock-names:
@@ -267,38 +232,6 @@ allOf:
- const: peri_26m
- const: top_133m
- resets:
- minItems: 1
- maxItems: 2
-
- reset-names:
- minItems: 1
- maxItems: 2
-
- mediatek,pbus-csr: false
-
- - if:
- properties:
- compatible:
- const: airoha,en7581-pcie
- then:
- properties:
- clocks:
- maxItems: 1
-
- clock-names:
- items:
- - const: sys-ck
-
- resets:
- minItems: 3
-
- reset-names:
- items:
- - const: phy-lane0
- - const: phy-lane1
- - const: phy-lane2
-
unevaluatedProperties: false
examples:
--
2.53.0
^ permalink raw reply related
* [PATCH 2/4] clk: en7523: add support for dedicated PCIe PERSTOUT reset
From: Christian Marangi @ 2026-06-25 21:57 UTC (permalink / raw)
To: Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley, Ryder Lee, Michael Turquette,
Stephen Boyd, Brian Masney, Philipp Zabel, Matthias Brugger,
AngeloGioacchino Del Regno, Christian Marangi, Jianjun Wang,
linux-pci, devicetree, linux-kernel, linux-mediatek, linux-clk,
linux-arm-kernel
In-Reply-To: <20260625215741.3253212-1-ansuelsmth@gmail.com>
Add support for resetting the PCIe lines with the PERSTOUT reset. These
special reset are controlled by the PCIC register and are specific to each
of the 3 PCIe lines.
Notice that reset logic is inverted for these bit where 0 is assert and 1
deassert. This is intenrally handled in the reset function.
PCI enable/disable are updated to drop PERSTOUT bits in favor dedicated
reset handling.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
---
drivers/clk/clk-en7523.c | 27 ++++++++++++++++++---------
1 file changed, 18 insertions(+), 9 deletions(-)
diff --git a/drivers/clk/clk-en7523.c b/drivers/clk/clk-en7523.c
index 1ab0e2eca5d3..a33cf2e1b76f 100644
--- a/drivers/clk/clk-en7523.c
+++ b/drivers/clk/clk-en7523.c
@@ -338,6 +338,7 @@ static const struct en_clk_desc en7581_base_clks[] = {
static const u16 en7581_rst_ofs[] = {
REG_RST_CTRL2,
REG_RST_CTRL1,
+ REG_NP_SCU_PCIC,
};
static const u16 en751221_rst_ofs[] = {
@@ -450,6 +451,11 @@ static const u16 en7581_rst_map[] = {
[EN7581_CPU_TIMER_RST] = RST_NR_PER_BANK + 28,
[EN7581_PCIE_HB_RST] = RST_NR_PER_BANK + 29,
[EN7581_XPON_MAC_RST] = RST_NR_PER_BANK + 31,
+
+ /* RST_PCIC */
+ [EN7581_PCIC_PERSTOUT0_RST] = 2 * RST_NR_PER_BANK + 29,
+ [EN7581_PCIC_PERSTOUT1_RST] = 2 * RST_NR_PER_BANK + 26,
+ [EN7581_PCIC_PERSTOUT2_RST] = 2 * RST_NR_PER_BANK + 16,
};
static const u16 en751221_rst_map[] = {
@@ -635,9 +641,7 @@ static int en7581_pci_enable(struct clk_hw *hw)
void __iomem *np_base = cg->base;
u32 val, mask;
- mask = REG_PCI_CONTROL_REFCLK_EN0 | REG_PCI_CONTROL_REFCLK_EN1 |
- REG_PCI_CONTROL_PERSTOUT1 | REG_PCI_CONTROL_PERSTOUT2 |
- REG_PCI_CONTROL_PERSTOUT;
+ mask = REG_PCI_CONTROL_REFCLK_EN0 | REG_PCI_CONTROL_REFCLK_EN1;
val = readl(np_base + REG_PCI_CONTROL);
writel(val | mask, np_base + REG_PCI_CONTROL);
@@ -650,9 +654,7 @@ static void en7581_pci_disable(struct clk_hw *hw)
void __iomem *np_base = cg->base;
u32 val, mask;
- mask = REG_PCI_CONTROL_REFCLK_EN0 | REG_PCI_CONTROL_REFCLK_EN1 |
- REG_PCI_CONTROL_PERSTOUT1 | REG_PCI_CONTROL_PERSTOUT2 |
- REG_PCI_CONTROL_PERSTOUT;
+ mask = REG_PCI_CONTROL_REFCLK_EN0 | REG_PCI_CONTROL_REFCLK_EN1;
val = readl(np_base + REG_PCI_CONTROL);
writel(val & ~mask, np_base + REG_PCI_CONTROL);
usleep_range(1000, 2000);
@@ -754,14 +756,21 @@ static int en7523_reset_update(struct reset_controller_dev *rcdev,
unsigned long id, bool assert)
{
struct en_rst_data *rst_data = container_of(rcdev, struct en_rst_data, rcdev);
- void __iomem *addr = rst_data->base + rst_data->bank_ofs[id / RST_NR_PER_BANK];
+ u32 offset = rst_data->bank_ofs[id / RST_NR_PER_BANK];
+ void __iomem *addr = rst_data->base + offset;
+ bool inverted = false;
u32 val;
+ /* For PCIC reset logic is inverted, 0:assert 1:deassert*/
+ if (offset == REG_NP_SCU_PCIC)
+ inverted = true;
+
val = readl(addr);
+ val &= ~BIT(id % RST_NR_PER_BANK);
if (assert)
- val |= BIT(id % RST_NR_PER_BANK);
+ val |= inverted ? 0 : BIT(id % RST_NR_PER_BANK);
else
- val &= ~BIT(id % RST_NR_PER_BANK);
+ val |= inverted ? BIT(id % RST_NR_PER_BANK) : 0;
writel(val, addr);
return 0;
--
2.53.0
^ permalink raw reply related
* [PATCH 1/4] dt-bindings: clock: airoha: Add additional reset for PCIe PERSTOUT
From: Christian Marangi @ 2026-06-25 21:57 UTC (permalink / raw)
To: Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley, Ryder Lee, Michael Turquette,
Stephen Boyd, Brian Masney, Philipp Zabel, Matthias Brugger,
AngeloGioacchino Del Regno, Christian Marangi, Jianjun Wang,
linux-pci, devicetree, linux-kernel, linux-mediatek, linux-clk,
linux-arm-kernel
In-Reply-To: <20260625215741.3253212-1-ansuelsmth@gmail.com>
Add additional reset to control PCIe PERSTOUT reset line for each of the 3
PCIe lines.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
---
include/dt-bindings/reset/airoha,en7581-reset.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/include/dt-bindings/reset/airoha,en7581-reset.h b/include/dt-bindings/reset/airoha,en7581-reset.h
index 6544a1790b83..25e75534daa9 100644
--- a/include/dt-bindings/reset/airoha,en7581-reset.h
+++ b/include/dt-bindings/reset/airoha,en7581-reset.h
@@ -62,5 +62,9 @@
#define EN7581_CPU_TIMER_RST 50
#define EN7581_PCIE_HB_RST 51
#define EN7581_XPON_MAC_RST 52
+/* RST_PCIC */
+#define EN7581_PCIC_PERSTOUT0_RST 53
+#define EN7581_PCIC_PERSTOUT1_RST 54
+#define EN7581_PCIC_PERSTOUT2_RST 55
#endif /* __DT_BINDINGS_RESET_CONTROLLER_AIROHA_EN7581_H_ */
--
2.53.0
^ permalink raw reply related
* [PATCH 0/4] PCI: mediatek-gen3: Add 2-lanes mode support + clock
From: Christian Marangi @ 2026-06-25 21:57 UTC (permalink / raw)
To: Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley, Ryder Lee, Michael Turquette,
Stephen Boyd, Brian Masney, Philipp Zabel, Matthias Brugger,
AngeloGioacchino Del Regno, Christian Marangi, Jianjun Wang,
linux-pci, devicetree, linux-kernel, linux-mediatek, linux-clk,
linux-arm-kernel
This small series introduce support for 2-lanes mode for Airoha AN7581
SoC. This is needed for correctly functionality of Eagle WiFi Card
normally attached to this SoC that require a 2-line PCIe card to
correctly work (and give the proper performance)
The first 2 patch address a limitation of the PCIe implementation
where the PERSTOUT reset were indirectly asserted and deasserted
all at the same time (for all the 3 PCIe card) with PCIe
enable and disable.
The 2 patch address this and introduce correct reset to control
reset line for the relevant PCIe line.
The last 2 patch add additional logic and support to assert
and deassert the PERSTOUT and also apply the required configuration
for 2-lanes mode.
2-lanes mode is implemented in DT by adding the required property
and by defining the "num-lanes" to 2.
Christian Marangi (4):
dt-bindings: clock: airoha: Add additional reset for PCIe PERSTOUT
clk: en7523: add support for dedicated PCIe PERSTOUT reset
dt-bindings: PCI: mediatek-gen3: Split Airoha schema and document
2-lanes
PCI: mediatek-gen3: Add 2-lanes mode support for Airoha AN7581
.../bindings/pci/airoha,en7581-pcie.yaml | 251 ++++++++++++++++++
.../bindings/pci/mediatek-pcie-gen3.yaml | 77 +-----
drivers/clk/clk-en7523.c | 27 +-
drivers/pci/controller/pcie-mediatek-gen3.c | 98 +++++--
.../dt-bindings/reset/airoha,en7581-reset.h | 4 +
5 files changed, 358 insertions(+), 99 deletions(-)
create mode 100644 Documentation/devicetree/bindings/pci/airoha,en7581-pcie.yaml
--
2.53.0
^ permalink raw reply
* [PATCH v2 8/8] iio: adc: ti-ads112c14: add measurement channel support
From: David Lechner (TI) @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com>
Add support for parsing devicetree properties for measurement channels
and doing direct reads on these.
There are quite a lot of conditions that have to be met for each
measurement to be made, so quite a bit of state and algorithms are
required to handle it.
Channels are created dynamically since the number of possibilities is
unreasonably large.
Signed-off-by: David Lechner (TI) <dlechner@baylibre.com>
---
v2 changes:
* Adapted for changes in DT bindings.
* Fixed bug in IDAC current register value calculation.
* Fix uninitialized variable bug.
* Fix bug in data->num_measurements calculation.
* Use IIO_RESISTANCE instead of IIO_VOLTAGE when external reference is
used and it is a resistor rather than a voltage source.
* Fix bug with negative input mux selection on single-ended measurements.
* Fixed return checks of devm_regulator_get_enable_read_voltage().
---
drivers/iio/adc/ti-ads112c14.c | 523 ++++++++++++++++++++++++++++++++++++++++-
1 file changed, 512 insertions(+), 11 deletions(-)
diff --git a/drivers/iio/adc/ti-ads112c14.c b/drivers/iio/adc/ti-ads112c14.c
index 0e775dbc8d50..05d9670c72a4 100644
--- a/drivers/iio/adc/ti-ads112c14.c
+++ b/drivers/iio/adc/ti-ads112c14.c
@@ -9,11 +9,14 @@
*/
#include <linux/bitfield.h>
+#include <linux/cleanup.h>
#include <linux/delay.h>
#include <linux/dev_printk.h>
+#include <linux/device/devres.h>
#include <linux/i2c.h>
#include <linux/iio/iio.h>
#include <linux/math64.h>
+#include <linux/minmax.h>
#include <linux/mod_devicetable.h>
#include <linux/module.h>
#include <linux/property.h>
@@ -62,6 +65,10 @@
#define ADS112C14_DEVICE_CFG_PWDN BIT(7)
#define ADS112C14_DEVICE_CFG_STBY_MODE BIT(6)
#define ADS112C14_DEVICE_CFG_BOCS GENMASK(5, 4)
+#define ADS112C14_DEVICE_CFG_BOCS_DISABLED 0
+#define ADS112C14_DEVICE_CFG_BOCS_200_nA 1
+#define ADS112C14_DEVICE_CFG_BOCS_1_uA 2
+#define ADS112C14_DEVICE_CFG_BOCS_10_uA 3
#define ADS112C14_DEVICE_CFG_CLK_SEL BIT(3)
#define ADS112C14_DEVICE_CFG_CONV_MODE BIT(2)
#define ADS112C14_DEVICE_CFG_SPEED_MODE GENMASK(1, 0)
@@ -74,6 +81,7 @@
#define ADS112C14_REG_MUX_CFG 0x07
#define ADS112C14_MUX_CFG_AINP GENMASK(7, 4)
#define ADS112C14_MUX_CFG_AINN GENMASK(3, 0)
+#define ADS112C14_MUX_CFG_AIN_GND 0x8
#define ADS112C14_REG_GAIN_CFG 0x08
#define ADS112C14_GAIN_CFG_SPARE BIT(7)
@@ -88,6 +96,9 @@
#define ADS112C14_REFERENCE_CFG_REF_VAL_1_25V 0
#define ADS112C14_REFERENCE_CFG_REF_VAL_2_5V 1
#define ADS112C14_REFERENCE_CFG_REF_SEL GENMASK(1, 0)
+#define ADS112C14_REFERENCE_CFG_REF_SEL_INTERNAL 0
+#define ADS112C14_REFERENCE_CFG_REF_SEL_EXTERNAL 1
+#define ADS112C14_REFERENCE_CFG_REF_SEL_AVDD 2
#define ADS112C14_REG_DIGITAL_CFG 0x0A
#define ADS112C14_DIGITAL_CFG_REG_MAP_CRC_EN BIT(6)
@@ -124,6 +135,20 @@
#define ADS112C14_INT_REF0_mV 1250
#define ADS112C14_INT_REF1_mV 2500
+enum {
+ ADS112C14_VREF_SOURCE_INTERNAL_2_5V,
+ ADS112C14_VREF_SOURCE_INTERNAL_1_25V,
+ ADS112C14_VREF_SOURCE_EXTERNAL,
+ ADS112C14_VREF_SOURCE_AVDD,
+};
+
+static const char * const ads112c14_vref_source_names[] = {
+ [ADS112C14_VREF_SOURCE_INTERNAL_2_5V] = "internal-2.5v",
+ [ADS112C14_VREF_SOURCE_INTERNAL_1_25V] = "internal-1.25v",
+ [ADS112C14_VREF_SOURCE_EXTERNAL] = "external",
+ [ADS112C14_VREF_SOURCE_AVDD] = "avdd",
+};
+
/* Available gains as tenths (x10) */
static const u32 ads112c14_pga_gains_x10[] = {
5, /* 0.5 */
@@ -199,9 +224,32 @@ struct ads112c14_chip_info {
u32 resolution_bits;
};
+struct ads112c14_measurement {
+ const char *label;
+ u32 vref_source;
+ u8 iunit;
+ u8 idac1_mag;
+ u8 idac2_mag;
+ u8 idac1_mux;
+ u8 idac2_mux;
+ u8 iadc_count;
+ u8 gain_val;
+ u8 burnout;
+ bool global_chop;
+ bool bipolar;
+ int scale_available[ARRAY_SIZE(ads112c14_pga_gains_x10)][2];
+};
+
struct ads112c14_data {
const struct ads112c14_chip_info *chip_info;
struct regmap *regmap;
+ u32 avdd_uV;
+ u32 ext_ref_uV;
+ bool refp_is_avdd;
+ bool refn_is_gnd;
+ u32 ext_ref_ohms;
+ struct ads112c14_measurement *measurements;
+ u32 num_measurements;
u8 sys_mon_chan_short_gain_val;
int sys_mon_chan_short_scale_available[ARRAY_SIZE(ads112c14_pga_gains_x10)][2];
};
@@ -260,12 +308,106 @@ static const struct iio_chan_spec ads112c14_sys_mon_channels[] = {
},
};
+static int ads112c14_prepare_measurement_channel(struct ads112c14_data *data,
+ const struct iio_chan_spec *chan)
+{
+ struct ads112c14_measurement *measurement = &data->measurements[chan->scan_index];
+ u32 refp_buf_en, refn_buf_en, ref_val, ref_sel;
+ int ret;
+
+ ret = regmap_write(data->regmap, ADS112C14_REG_MUX_CFG,
+ FIELD_PREP(ADS112C14_MUX_CFG_AINP, chan->channel) |
+ FIELD_PREP(ADS112C14_MUX_CFG_AINN, chan->channel2));
+ if (ret)
+ return ret;
+
+ ret = regmap_update_bits(data->regmap, ADS112C14_REG_DIGITAL_CFG,
+ ADS112C14_DIGITAL_CFG_CODING,
+ FIELD_PREP(ADS112C14_DIGITAL_CFG_CODING,
+ measurement->bipolar ? 0 : 1));
+ if (ret)
+ return ret;
+
+ ret = regmap_update_bits(data->regmap, ADS112C14_REG_GAIN_CFG,
+ ADS112C14_GAIN_CFG_SYS_MON | ADS112C14_GAIN_CFG_GAIN,
+ FIELD_PREP(ADS112C14_GAIN_CFG_SYS_MON, 0) |
+ FIELD_PREP(ADS112C14_GAIN_CFG_GAIN,
+ measurement->gain_val));
+ if (ret)
+ return ret;
+
+ ret = regmap_write(data->regmap, ADS112C14_REG_IDAC_MAG_CFG,
+ FIELD_PREP(ADS112C14_IDAC_MAG_CFG_I2MAG,
+ measurement->idac2_mag) |
+ FIELD_PREP(ADS112C14_IDAC_MAG_CFG_I1MAG,
+ measurement->idac1_mag));
+ if (ret)
+ return ret;
+
+ ret = regmap_write(data->regmap, ADS112C14_REG_IDAC_MUX_CFG,
+ FIELD_PREP(ADS112C14_IDAC_MUX_CFG_IUNIT,
+ measurement->iunit) |
+ FIELD_PREP(ADS112C14_IDAC_MUX_CFG_I2MUX,
+ measurement->idac2_mux) |
+ FIELD_PREP(ADS112C14_IDAC_MUX_CFG_I1MUX,
+ measurement->idac1_mux));
+ if (ret)
+ return ret;
+
+ ret = regmap_update_bits(data->regmap, ADS112C14_REG_DATA_RATE_CFG,
+ ADS112C14_DATA_RATE_CFG_GC_EN,
+ FIELD_PREP(ADS112C14_DATA_RATE_CFG_GC_EN,
+ measurement->global_chop));
+ if (ret)
+ return ret;
+
+ refp_buf_en = !data->refp_is_avdd &&
+ measurement->vref_source == ADS112C14_VREF_SOURCE_EXTERNAL;
+ refn_buf_en = !data->refn_is_gnd &&
+ measurement->vref_source == ADS112C14_VREF_SOURCE_EXTERNAL;
+
+ ref_val = measurement->vref_source == ADS112C14_VREF_SOURCE_INTERNAL_2_5V ?
+ ADS112C14_REFERENCE_CFG_REF_VAL_2_5V :
+ ADS112C14_REFERENCE_CFG_REF_VAL_1_25V;
+
+ switch (measurement->vref_source) {
+ case ADS112C14_VREF_SOURCE_AVDD:
+ ref_sel = ADS112C14_REFERENCE_CFG_REF_SEL_AVDD;
+ break;
+ case ADS112C14_VREF_SOURCE_EXTERNAL:
+ ref_sel = ADS112C14_REFERENCE_CFG_REF_SEL_EXTERNAL;
+ break;
+ default:
+ ref_sel = ADS112C14_REFERENCE_CFG_REF_SEL_INTERNAL;
+ break;
+ }
+
+ return regmap_update_bits(data->regmap, ADS112C14_REG_REFERENCE_CFG,
+ ADS112C14_REFERENCE_CFG_REFP_BUF_EN |
+ ADS112C14_REFERENCE_CFG_REFN_BUF_EN |
+ ADS112C14_REFERENCE_CFG_REF_VAL |
+ ADS112C14_REFERENCE_CFG_REF_SEL,
+ FIELD_PREP(ADS112C14_REFERENCE_CFG_REFP_BUF_EN,
+ refp_buf_en) |
+ FIELD_PREP(ADS112C14_REFERENCE_CFG_REFN_BUF_EN,
+ refn_buf_en) |
+ FIELD_PREP(ADS112C14_REFERENCE_CFG_REF_VAL,
+ ref_val) |
+ FIELD_PREP(ADS112C14_REFERENCE_CFG_REF_SEL,
+ ref_sel));
+}
+
static int ads112c14_prepare_sys_mon_channel(struct ads112c14_data *data,
const struct iio_chan_spec *chan)
{
u32 gain_val;
int ret;
+ /*
+ * NB: IDAC registers are left as-is in case they are generating current
+ * needed for the external reference measurement.
+ */
+
/*
* All SYS_MON channels use GAIN of 1 to keep it simple. Other than
* the internal short channel, where it is useful in practice.
@@ -321,8 +463,9 @@ static int ads112c14_single_conversion(struct ads112c14_data *data,
int ret;
if (chan->channel < 100) {
- /* Not implemented yet. */
- return -EINVAL;
+ ret = ads112c14_prepare_measurement_channel(data, chan);
+ if (ret)
+ return ret;
} else {
ret = ads112c14_prepare_sys_mon_channel(data, chan);
if (ret)
@@ -351,6 +494,7 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
int *val2, long mask)
{
struct ads112c14_data *data = iio_priv(indio_dev);
+ struct ads112c14_measurement *measurement = NULL;
u32 vref_uV, fsr_bits;
int *scale_avail;
@@ -358,8 +502,8 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
vref_uV = ADS112C14_INT_REF1_mV * (MICRO / MILLI);
if (chan->channel < 100) {
- /* Not implemented yet. */
- return -EINVAL;
+ measurement = &data->measurements[chan->scan_index];
+ fsr_bits = data->chip_info->resolution_bits - measurement->bipolar;
} else {
/* All SYS_MON channels are using signed coding. */
fsr_bits = data->chip_info->resolution_bits - 1;
@@ -389,7 +533,8 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
return -EINVAL;
}
- *val = sign_extend32(*val, fsr_bits);
+ if (!measurement || measurement->bipolar)
+ *val = sign_extend32(*val, fsr_bits);
return IIO_VAL_INT;
}
@@ -401,6 +546,14 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
return IIO_VAL_FRACTIONAL_LOG2;
}
+ if (chan->channel < 100) {
+ scale_avail = measurement->scale_available[measurement->gain_val];
+ *val = scale_avail[0];
+ *val2 = scale_avail[1];
+
+ return IIO_VAL_INT_PLUS_NANO;
+ }
+
if (chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT) {
u8 idx = data->sys_mon_chan_short_gain_val;
@@ -441,6 +594,16 @@ static int ads112c14_read_avail(struct iio_dev *indio_dev,
{
struct ads112c14_data *data = iio_priv(indio_dev);
+ if (chan->channel < 100) {
+ struct ads112c14_measurement *measurement;
+
+ measurement = &data->measurements[chan->scan_index];
+ *vals = (const int *)measurement->scale_available;
+ *length = 2 * ARRAY_SIZE(measurement->scale_available);
+ *type = IIO_VAL_INT_PLUS_NANO;
+ return IIO_AVAIL_LIST;
+ }
+
if (chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT) {
*vals = (const int *)data->sys_mon_chan_short_scale_available;
*length = 2 * ARRAY_SIZE(data->sys_mon_chan_short_scale_available);
@@ -461,7 +624,13 @@ static int ads112c14_write_raw(struct iio_dev *indio_dev,
switch (mask) {
case IIO_CHAN_INFO_SCALE: {
- if (chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT) {
+ if (chan->channel < 100) {
+ struct ads112c14_measurement *measurement;
+
+ measurement = &data->measurements[chan->scan_index];
+ scale_avail = measurement->scale_available;
+ gain_val = &measurement->gain_val;
+ } else if (chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT) {
scale_avail = data->sys_mon_chan_short_scale_available;
gain_val = &data->sys_mon_chan_short_gain_val;
} else {
@@ -501,8 +670,21 @@ static int ads112c14_write_raw_get_fmt(struct iio_dev *indio_dev,
static int ads112c14_read_label(struct iio_dev *indio_dev,
struct iio_chan_spec const *chan, char *label)
{
+ struct ads112c14_data *data = iio_priv(indio_dev);
const char *label_source;
+ /* measurement channels */
+ if (chan->channel < 100) {
+ struct ads112c14_measurement *measurement;
+
+ measurement = &data->measurements[chan->scan_index];
+
+ if (!measurement->label)
+ return -EINVAL;
+
+ return sysfs_emit(label, "%s\n", measurement->label);
+ }
+
/* System monitor channels. */
switch (chan->channel) {
case ADS112C14_SYS_MON_CHANNEL_TEMP:
@@ -535,6 +717,234 @@ static const struct iio_info ads112c14_info = {
.read_label = ads112c14_read_label,
};
+static int ads112c14_populate_idac_mag(u32 current_nA, u8 *idac_mag)
+{
+ u32 current_uA = current_nA / (NANO / MICRO);
+
+ /* Convert microamps to IMAG bits */
+ if (current_uA == 1)
+ *idac_mag = 1;
+ else if (in_range(current_uA, 10, 100) && current_uA % 10 == 0)
+ *idac_mag = current_uA / 10 + 1;
+ else
+ return dev_err_probe(NULL, -EINVAL,
+ "invalid excitation-current-nanoamp value\n");
+
+ return 0;
+}
+
+static int ads112c14_parse_channels(struct iio_dev *indio_dev,
+ bool *need_avdd_ref, bool *need_ext_ref)
+{
+ struct ads112c14_data *data = iio_priv(indio_dev);
+ struct device *dev = indio_dev->dev.parent;
+ struct iio_chan_spec *channels;
+ u32 num_child_nodes, i, pair[2];
+ int ret;
+
+ *need_avdd_ref = false;
+ *need_ext_ref = false;
+
+ num_child_nodes = device_get_named_child_node_count(dev, "channel");
+
+ data->measurements = devm_kcalloc(dev, num_child_nodes,
+ sizeof(*data->measurements), GFP_KERNEL);
+ if (!data->measurements)
+ return -ENOMEM;
+
+ channels = devm_kcalloc(dev, num_child_nodes +
+ ARRAY_SIZE(ads112c14_sys_mon_channels),
+ sizeof(*channels), GFP_KERNEL);
+ if (!channels)
+ return -ENOMEM;
+
+ i = 0;
+ device_for_each_named_child_node_scoped(dev, child, "channel") {
+ struct ads112c14_measurement *measurement = &data->measurements[i];
+ struct iio_chan_spec *spec = &channels[i];
+
+ if (!fwnode_device_is_available(child))
+ continue;
+
+ spec->indexed = 1;
+ spec->scan_index = i;
+ measurement->gain_val = 1;
+
+ fwnode_property_read_string(child, "label", &measurement->label);
+
+ if (fwnode_property_present(child, "single-channel")) {
+ ret = fwnode_property_read_u32(child, "single-channel",
+ &pair[0]);
+ if (ret)
+ return dev_err_probe(dev, ret,
+ "failed to read single-channel property\n");
+
+ if (pair[0] >= 8)
+ return dev_err_probe(dev, -EINVAL,
+ "single-channel value must be between 0 and 7\n");
+
+ spec->channel = pair[0];
+ /* NB: channel2 is unused by iio core code in this case. */
+ spec->channel2 = ADS112C14_MUX_CFG_AIN_GND;
+ } else if (fwnode_property_present(child, "diff-channels")) {
+ ret = fwnode_property_read_u32_array(child, "diff-channels",
+ pair, ARRAY_SIZE(pair));
+ if (ret)
+ return dev_err_probe(dev, ret,
+ "failed to read diff-channels property\n");
+
+ if (pair[0] >= 8 || pair[1] >= 8)
+ return dev_err_probe(dev, -EINVAL,
+ "diff-channels values must be between 0 and 7\n");
+
+ spec->differential = 1;
+ spec->channel = pair[0];
+ spec->channel2 = pair[1];
+ } else {
+ return dev_err_probe(dev, -EINVAL,
+ "channel node missing channel type property\n");
+ }
+
+ if (fwnode_property_present(child, "excitation-channels")) {
+ ret = fwnode_property_count_u32(child, "excitation-channels");
+ if (ret < 0)
+ return dev_err_probe(dev, ret,
+ "failed to read excitation-channels property\n");
+
+ if (ret < 1 || ret > 2)
+ return dev_err_probe(dev, -EINVAL,
+ "excitation-channels property must have 1 or 2 values\n");
+
+ measurement->iadc_count = ret;
+ pair[1] = 0;
+
+ ret = fwnode_property_read_u32_array(child, "excitation-channels",
+ pair, measurement->iadc_count);
+ if (ret)
+ return dev_err_probe(dev, ret,
+ "failed to read excitation-channels property\n");
+
+ if (pair[0] >= 8 || pair[1] >= 8)
+ return dev_err_probe(dev, -EINVAL,
+ "excitation-channels values must be between 0 and 7\n");
+
+ measurement->idac1_mux = pair[0];
+ measurement->idac2_mux = measurement->iadc_count > 1 ? pair[1] : 0;
+
+ ret = fwnode_property_read_u32_array(child, "excitation-current-nanoamp",
+ pair, measurement->iadc_count);
+ if (ret)
+ return dev_err_probe(dev, ret,
+ "failed to read excitation-current-nanoamp property\n");
+
+ if (pair[0] <= 100000 && (measurement->iadc_count == 1 || pair[1] <= 100000)) {
+ /*
+ * If both values are 100uA or less, then we can
+ * use IUNIT = 1uA for better precision.
+ */
+ ret = ads112c14_populate_idac_mag(pair[0],
+ &measurement->idac1_mag);
+ if (ret)
+ return ret;
+
+ if (measurement->iadc_count > 1) {
+ ret = ads112c14_populate_idac_mag(pair[1],
+ &measurement->idac2_mag);
+ if (ret)
+ return ret;
+ }
+ } else {
+ /*
+ * Otherwise, IUINT is 10uA (flag set) and so
+ * IxMAG is 1/10 of the actual current.
+ */
+ measurement->iunit = 1;
+
+ ret = ads112c14_populate_idac_mag(pair[0] / 10,
+ &measurement->idac1_mag);
+ if (ret)
+ return ret;
+
+ if (measurement->iadc_count > 1) {
+ ret = ads112c14_populate_idac_mag(pair[1] / 10,
+ &measurement->idac2_mag);
+ if (ret)
+ return ret;
+ }
+ }
+ }
+
+ measurement->global_chop = fwnode_property_read_bool(child,
+ "input-channel-rotation");
+
+ if (fwnode_property_present(child, "burn-out-current-nanoamp")) {
+ u32 burnout_nA;
+
+ ret = fwnode_property_read_u32(child, "burn-out-current-nanoamp",
+ &burnout_nA);
+ if (ret)
+ return dev_err_probe(dev, ret,
+ "failed to read burn-out-current-nanoamp property\n");
+
+ switch (burnout_nA) {
+ case 200:
+ measurement->burnout = ADS112C14_DEVICE_CFG_BOCS_200_nA;
+ break;
+ case 1000:
+ measurement->burnout = ADS112C14_DEVICE_CFG_BOCS_1_uA;
+ break;
+ case 10000:
+ measurement->burnout = ADS112C14_DEVICE_CFG_BOCS_10_uA;
+ break;
+ default:
+ return dev_err_probe(dev, -EINVAL,
+ "invalid burn-out-current-nanoamp value\n");
+ }
+ }
+
+ measurement->bipolar = fwnode_property_read_bool(child, "bipolar");
+
+ if (fwnode_property_present(child, "reference-sources")) {
+ ret = fwnode_property_match_property_string(child,
+ "reference-sources", ads112c14_vref_source_names,
+ ARRAY_SIZE(ads112c14_vref_source_names));
+ if (ret < 0)
+ return dev_err_probe(dev, ret,
+ "invalid reference-sources value\n");
+
+ measurement->vref_source = ret;
+ }
+
+ if (measurement->vref_source == ADS112C14_VREF_SOURCE_AVDD)
+ *need_avdd_ref = true;
+ if (measurement->vref_source == ADS112C14_VREF_SOURCE_EXTERNAL)
+ *need_ext_ref = true;
+
+ spec->info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE);
+ spec->info_mask_separate_available = BIT(IIO_CHAN_INFO_SCALE);
+
+ /*
+ * If reference source is resistor rather than voltage supply,
+ * then the measurement is effectively a resistance measurement.
+ */
+ spec->type = (measurement->vref_source == ADS112C14_VREF_SOURCE_EXTERNAL &&
+ data->ext_ref_ohms) ? IIO_RESISTANCE : IIO_VOLTAGE;
+
+ if (spec->type == IIO_RESISTANCE)
+ spec->differential = 0;
+
+ i++;
+ }
+
+ data->num_measurements = i;
+ memcpy(channels + i, ads112c14_sys_mon_channels, sizeof(ads112c14_sys_mon_channels));
+
+ indio_dev->channels = channels;
+ indio_dev->num_channels = i + ARRAY_SIZE(ads112c14_sys_mon_channels);
+
+ return 0;
+}
+
static void ads112c14_populate_scale_available(int scale_avail[][2],
u32 full_scale, u32 fsr_bits)
{
@@ -553,6 +963,33 @@ static void ads112c14_populate_tables(struct ads112c14_data *data)
{
u32 full_scale, fsr_bits;
+ for (u32 i = 0; i < data->num_measurements; i++) {
+ struct ads112c14_measurement *measurement = &data->measurements[i];
+
+ switch (measurement->vref_source) {
+ case ADS112C14_VREF_SOURCE_EXTERNAL:
+ if (data->ext_ref_ohms)
+ full_scale = data->ext_ref_ohms;
+ else
+ full_scale = data->ext_ref_uV / (MICRO / MILLI);
+ break;
+ case ADS112C14_VREF_SOURCE_AVDD:
+ full_scale = data->avdd_uV / (MICRO / MILLI);
+ break;
+ case ADS112C14_VREF_SOURCE_INTERNAL_1_25V:
+ full_scale = ADS112C14_INT_REF0_mV;
+ break;
+ default:
+ full_scale = ADS112C14_INT_REF1_mV;
+ break;
+ }
+
+ fsr_bits = data->chip_info->resolution_bits - measurement->bipolar;
+
+ ads112c14_populate_scale_available(measurement->scale_available,
+ full_scale, fsr_bits);
+ }
+
/* For now, assuming all sys_mon channels are using 2.5V reference. */
full_scale = ADS112C14_INT_REF1_mV;
fsr_bits = data->chip_info->resolution_bits - 1;
@@ -567,6 +1004,9 @@ static int ads112c14_probe(struct i2c_client *client)
const struct ads112c14_chip_info *info;
struct iio_dev *indio_dev;
struct ads112c14_data *data;
+ bool need_avdd_ref, need_ext_ref;
+ u32 refp_uV = 0;
+ u32 refn_uV = 0;
u32 reg_val;
int ret;
@@ -581,13 +1021,76 @@ static int ads112c14_probe(struct i2c_client *client)
data = iio_priv(indio_dev);
data->chip_info = info;
+ if (device_property_present(dev, "ti,refp-refn-resistor-ohms")) {
+ ret = device_property_read_u32(dev, "ti,refp-refn-resistor-ohms",
+ &data->ext_ref_ohms);
+ if (ret)
+ return dev_err_probe(dev, ret,
+ "failed to read ti,refp-refn-resistor-ohms property\n");
+ }
+
+ ret = ads112c14_parse_channels(indio_dev, &need_avdd_ref, &need_ext_ref);
+ if (ret)
+ return ret;
+
ret = devm_regulator_get_enable(dev, "dvdd");
if (ret)
return dev_err_probe(dev, ret, "failed to get dvdd regulator\n");
- ret = devm_regulator_get_enable(dev, "avdd");
- if (ret)
- return dev_err_probe(dev, ret, "failed to get avdd regulator\n");
+ if (need_avdd_ref) {
+ ret = devm_regulator_get_enable_read_voltage(dev, "avdd");
+ if (ret < 0)
+ return dev_err_probe(dev, ret, "failed to get avdd voltage\n");
+
+ data->avdd_uV = ret;
+ } else {
+ ret = devm_regulator_get_enable(dev, "avdd");
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to get avdd regulator\n");
+ }
+
+ if (device_property_present(dev, "refp-supply")) {
+ ret = devm_regulator_get_enable_read_voltage(dev, "refp");
+ if (ret < 0)
+ return dev_err_probe(dev, ret, "failed to get refp voltage\n");
+
+ refp_uV = ret;
+
+ struct fwnode_handle *refp_fwnode __free(fwnode_handle) =
+ fwnode_find_reference(dev->fwnode, "refp-supply", 0);
+ if (IS_ERR(refp_fwnode))
+ return dev_err_probe(dev, PTR_ERR(refp_fwnode),
+ "failed to get refp fwnode\n");
+
+ struct fwnode_handle *avdd_fwnode __free(fwnode_handle) =
+ fwnode_find_reference(dev->fwnode, "avdd-supply", 0);
+ if (IS_ERR(avdd_fwnode))
+ return dev_err_probe(dev, PTR_ERR(avdd_fwnode),
+ "failed to get avdd fwnode\n");
+
+ /* REFP buffer should not be enabled when connected to AVDD */
+ data->refp_is_avdd = refp_fwnode == avdd_fwnode;
+ }
+
+ if (device_property_present(dev, "refn-supply")) {
+ ret = devm_regulator_get_enable_read_voltage(dev, "refn");
+ if (ret < 0)
+ return dev_err_probe(dev, ret, "failed to get refn voltage\n");
+
+ refn_uV = ret;
+ } else {
+ data->refn_is_gnd = true;
+ }
+
+ data->ext_ref_uV = refp_uV - refn_uV;
+
+ if (data->ext_ref_uV && data->ext_ref_ohms)
+ return dev_err_probe(dev, -EINVAL,
+ "ti,refp-refn-resistor-ohms property should not be present when refp-supply or refn-supply is present\n");
+
+ if (need_ext_ref && !data->ext_ref_uV && !data->ext_ref_ohms)
+ return dev_err_probe(dev, -EINVAL,
+ "external reference measurements require either refp-supply or ti,refp-refn-resistor-ohms property\n");
data->regmap = devm_regmap_init_i2c(client, &ads112c14_regmap_config);
if (IS_ERR(data->regmap))
@@ -639,8 +1142,6 @@ static int ads112c14_probe(struct i2c_client *client)
indio_dev->name = info->name;
indio_dev->modes = INDIO_DIRECT_MODE;
- indio_dev->channels = ads112c14_sys_mon_channels;
- indio_dev->num_channels = ARRAY_SIZE(ads112c14_sys_mon_channels);
indio_dev->info = &ads112c14_info;
return devm_iio_device_register(dev, indio_dev);
--
2.43.0
^ permalink raw reply related
* [PATCH v2 6/8] iio: adc: add ti-ads112c14 driver
From: David Lechner (TI) @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com>
Add a new driver for the TI ADS112C14/ADS122C14 ADC chips.
This first step is adding a very basic driver that only supports power
on/reset and reading the system monitor channels.
ADS112C14_SYS_MON_CHANNEL_SHORT is the last channel rather than being in
logical order by address to keep the voltage channels together and in
case we find we need to add variants of this channel with different
voltage reference later.
Signed-off-by: David Lechner (TI) <dlechner@baylibre.com>
---
A few other notes for review that didn't seem worth putting in the
commit message:
* I intentionally did not use bulk regmap because later we may need to
get the voltage of the avdd supply.
* I left some comments in the code where the code might look funny (e.g.
to reduce future diff) or does not exactly match the datasheet, in
which case later changes will address that.
v2 changes:
* Add some indent to register field macro defines.
* Drop ads112c14_internal_ref_uV array (use macros instead).
* Don't keep pointer to i2c client.
* Consistently check channel < 100 instead of >= 100 sometimes.
* Check return of i2c_get_match_data().
* Fix bug on checking -EREMOTEIO.
* Don't use &client->dev when we already have dev local variable.
* Make some changes to reduce diff in later patches.
---
MAINTAINERS | 1 +
drivers/iio/adc/Kconfig | 12 +
drivers/iio/adc/Makefile | 1 +
drivers/iio/adc/ti-ads112c14.c | 547 +++++++++++++++++++++++++++++++++++++++++
4 files changed, 561 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 0ac9f44c7096..92746892f6b3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -26940,6 +26940,7 @@ M: David Lechner <dlechner@baylibre.com>
L: linux-iio@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/iio/adc/ti,ads112c14.yaml
+F: drivers/iio/adc/ti-ads112c14.c
TI ADS1018 ADC DRIVER
M: Kurt Borja <kuurtb@gmail.com>
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 6fb0766ca27a..bfcaecc85f24 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -1787,6 +1787,18 @@ config TI_ADS1119
This driver can also be built as a module. If so, the module will be
called ti-ads1119.
+config TI_ADS112C14
+ tristate "Texas Instruments ADS112C14/ADS122C14"
+ depends on I2C
+ select REGMAP
+ select REGMAP_I2C
+ help
+ If you say yes here you get support for Texas Instruments ADS112C14,
+ ADS122C14 ADC chips.
+
+ This driver can also be built as a module. If so, the module will be
+ called ti-ads112c14.
+
config TI_ADS124S08
tristate "Texas Instruments ADS124S08"
depends on SPI
diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile
index 707dd708912f..72f4c6b33ca8 100644
--- a/drivers/iio/adc/Makefile
+++ b/drivers/iio/adc/Makefile
@@ -153,6 +153,7 @@ obj-$(CONFIG_TI_ADS1015) += ti-ads1015.o
obj-$(CONFIG_TI_ADS1018) += ti-ads1018.o
obj-$(CONFIG_TI_ADS1100) += ti-ads1100.o
obj-$(CONFIG_TI_ADS1119) += ti-ads1119.o
+obj-$(CONFIG_TI_ADS112C14) += ti-ads112c14.o
obj-$(CONFIG_TI_ADS124S08) += ti-ads124s08.o
obj-$(CONFIG_TI_ADS1298) += ti-ads1298.o
obj-$(CONFIG_TI_ADS131E08) += ti-ads131e08.o
diff --git a/drivers/iio/adc/ti-ads112c14.c b/drivers/iio/adc/ti-ads112c14.c
new file mode 100644
index 000000000000..c61d47244732
--- /dev/null
+++ b/drivers/iio/adc/ti-ads112c14.c
@@ -0,0 +1,547 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IIO driver for Texas Instruments ADS112C14 and similar ADCs.
+ *
+ * Copyright (C) 2026 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2026 Baylibre Inc.
+ *
+ * Datasheet: https://www.ti.com/lit/ds/symlink/ads122c14.pdf
+ */
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/dev_printk.h>
+#include <linux/i2c.h>
+#include <linux/iio/iio.h>
+#include <linux/math64.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/sysfs.h>
+#include <linux/time64.h>
+#include <linux/types.h>
+#include <linux/unaligned.h>
+#include <linux/units.h>
+
+/* Datasheet t_d(RST) - time to wait after reset before next I2C use. */
+#define ADS112C14_DELAY_RESET_US 500
+
+#define ADS112C14_CMD_RDATA 0x00
+#define ADS112C14_CMD_RREG 0x40
+#define ADS112C14_CMD_WREG 0x80
+
+#define ADS112C14_REG_DEVICE_ID 0x00
+#define ADS112C14_DEVICE_ID_BITS GENMASK(3, 0)
+
+#define ADS112C14_REG_REVISION_ID 0x01
+
+#define ADS112C14_REG_STATUS_MSB 0x02
+#define ADS112C14_STATUS_MSB_RESETN BIT(7)
+#define ADS112C14_STATUS_MSB_AVDD_UVN BIT(6)
+#define ADS112C14_STATUS_MSB_REF_UVN BIT(5)
+#define ADS112C14_STATUS_MSB_REG_MAP_CRC_FAULTN BIT(3)
+#define ADS112C14_STATUS_MSB_MEM_FAULTN BIT(2)
+#define ADS112C14_STATUS_MSB_REG_WRITE_FAULTN BIT(1)
+#define ADS112C14_STATUS_MSB_DRDY BIT(0)
+
+#define ADS112C14_REG_STATUS_LSB 0x03
+#define ADS112C14_STATUS_LSB_CONV_COUNT GENMASK(7, 4)
+#define ADS112C14_STATUS_LSB_GPIO3_DAT_IN BIT(3)
+#define ADS112C14_STATUS_LSB_GPIO2_DAT_IN BIT(2)
+#define ADS112C14_STATUS_LSB_GPIO1_DAT_IN BIT(1)
+#define ADS112C14_STATUS_LSB_GPIO0_DAT_IN BIT(0)
+
+#define ADS112C14_REG_CONVERSION_CTRL 0x04
+#define ADS112C14_CONVERSION_CTRL_RESET GENMASK(7, 2)
+#define ADS112C14_CONVERSION_CTRL_START BIT(1)
+#define ADS112C14_CONVERSION_CTRL_STOP BIT(0)
+
+#define ADS112C14_REG_DEVICE_CFG 0x05
+#define ADS112C14_DEVICE_CFG_PWDN BIT(7)
+#define ADS112C14_DEVICE_CFG_STBY_MODE BIT(6)
+#define ADS112C14_DEVICE_CFG_BOCS GENMASK(5, 4)
+#define ADS112C14_DEVICE_CFG_CLK_SEL BIT(3)
+#define ADS112C14_DEVICE_CFG_CONV_MODE BIT(2)
+#define ADS112C14_DEVICE_CFG_SPEED_MODE GENMASK(1, 0)
+
+#define ADS112C14_REG_DATA_RATE_CFG 0x06
+#define ADS112C14_DATA_RATE_CFG_DELAY GENMASK(7, 4)
+#define ADS112C14_DATA_RATE_CFG_GC_EN BIT(3)
+#define ADS112C14_DATA_RATE_CFG_FLTR_OSR GENMASK(2, 0)
+
+#define ADS112C14_REG_MUX_CFG 0x07
+#define ADS112C14_MUX_CFG_AINP GENMASK(7, 4)
+#define ADS112C14_MUX_CFG_AINN GENMASK(3, 0)
+
+#define ADS112C14_REG_GAIN_CFG 0x08
+#define ADS112C14_GAIN_CFG_SPARE BIT(7)
+#define ADS112C14_GAIN_CFG_SYS_MON GENMASK(6, 4)
+#define ADS112C14_GAIN_CFG_GAIN GENMASK(3, 0)
+
+#define ADS112C14_REG_REFERENCE_CFG 0x09
+#define ADS112C14_REFERENCE_CFG_REF_UV_EN BIT(7)
+#define ADS112C14_REFERENCE_CFG_REFP_BUF_EN BIT(5)
+#define ADS112C14_REFERENCE_CFG_REFN_BUF_EN BIT(4)
+#define ADS112C14_REFERENCE_CFG_REF_VAL BIT(2)
+#define ADS112C14_REFERENCE_CFG_REF_VAL_1_25V 0
+#define ADS112C14_REFERENCE_CFG_REF_VAL_2_5V 1
+#define ADS112C14_REFERENCE_CFG_REF_SEL GENMASK(1, 0)
+
+#define ADS112C14_REG_DIGITAL_CFG 0x0A
+#define ADS112C14_DIGITAL_CFG_REG_MAP_CRC_EN BIT(6)
+#define ADS112C14_DIGITAL_CFG_I2C_CRC_EN BIT(5)
+#define ADS112C14_DIGITAL_CFG_STATUS_EN BIT(4)
+#define ADS112C14_DIGITAL_CFG_FAULT_PIN_BEHAVIOR BIT(3)
+#define ADS112C14_DIGITAL_CFG_CODING BIT(1)
+
+#define ADS112C14_REG_GPIO_CFG 0x0B
+#define ADS112C14_GPIO_CFG_GPIO3_CFG GENMASK(7, 6)
+#define ADS112C14_GPIO_CFG_GPIO2_CFG GENMASK(5, 4)
+#define ADS112C14_GPIO_CFG_GPIO1_CFG GENMASK(3, 2)
+#define ADS112C14_GPIO_CFG_GPIO0_CFG GENMASK(1, 0)
+
+#define ADS112C14_REG_GPIO_DATA_OUTPUT 0x0C
+#define ADS112C14_GPIO_DATA_OUTPUT_GPIO3_SRC BIT(7)
+#define ADS112C14_GPIO_DATA_OUTPUT_GPIO2_SRC BIT(6)
+#define ADS112C14_GPIO_DATA_OUTPUT_GPIO3_DAT_OUT BIT(3)
+#define ADS112C14_GPIO_DATA_OUTPUT_GPIO2_DAT_OUT BIT(2)
+#define ADS112C14_GPIO_DATA_OUTPUT_GPIO1_DAT_OUT BIT(1)
+#define ADS112C14_GPIO_DATA_OUTPUT_GPIO0_DAT_OUT BIT(0)
+
+#define ADS112C14_REG_IDAC_MAG_CFG 0x0D
+#define ADS112C14_IDAC_MAG_CFG_I2MAG GENMASK(7, 4)
+#define ADS112C14_IDAC_MAG_CFG_I1MAG GENMASK(3, 0)
+
+#define ADS112C14_REG_IDAC_MUX_CFG 0x0E
+#define ADS112C14_IDAC_MUX_CFG_IUNIT BIT(7)
+#define ADS112C14_IDAC_MUX_CFG_I2MUX GENMASK(6, 4)
+#define ADS112C14_IDAC_MUX_CFG_I1MUX GENMASK(2, 0)
+
+#define ADS112C14_REG_REG_MAP_CRC 0x0F
+
+#define ADS112C14_INT_REF0_mV 1250
+#define ADS112C14_INT_REF1_mV 2500
+
+static bool ads112c14_writeable_reg(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case ADS112C14_REG_DEVICE_ID:
+ case ADS112C14_REG_REVISION_ID:
+ case ADS112C14_REG_STATUS_LSB:
+ return false;
+ default:
+ return true;
+ }
+}
+
+static bool ads112c14_volatile_reg(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case ADS112C14_REG_STATUS_MSB:
+ case ADS112C14_REG_STATUS_LSB:
+ case ADS112C14_REG_CONVERSION_CTRL:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static const struct reg_default ads112c14_reg_defaults[] = {
+ { ADS112C14_REG_DEVICE_CFG, 0 },
+ { ADS112C14_REG_DATA_RATE_CFG, 0 },
+ { ADS112C14_REG_MUX_CFG, 0 },
+ { ADS112C14_REG_GAIN_CFG, FIELD_PREP_CONST(ADS112C14_GAIN_CFG_GAIN, 1) },
+ { ADS112C14_REG_REFERENCE_CFG, 0 },
+ { ADS112C14_REG_DIGITAL_CFG, 0 },
+ { ADS112C14_REG_GPIO_CFG, 0 },
+ { ADS112C14_REG_GPIO_DATA_OUTPUT, 0 },
+ { ADS112C14_REG_IDAC_MAG_CFG, 0 },
+ { ADS112C14_REG_IDAC_MUX_CFG, FIELD_PREP_CONST(ADS112C14_IDAC_MUX_CFG_I2MUX, 1) },
+};
+
+static const struct regmap_config ads112c14_regmap_config = {
+ .reg_bits = 8,
+ .val_bits = 8,
+ .read_flag_mask = ADS112C14_CMD_RREG,
+ .write_flag_mask = ADS112C14_CMD_WREG,
+ .max_register = ADS112C14_REG_REG_MAP_CRC,
+ .writeable_reg = ads112c14_writeable_reg,
+ .volatile_reg = ads112c14_volatile_reg,
+ .reg_defaults = ads112c14_reg_defaults,
+ .num_reg_defaults = ARRAY_SIZE(ads112c14_reg_defaults),
+ .cache_type = REGCACHE_MAPLE,
+};
+
+struct ads112c14_chip_info {
+ const char *name;
+ u32 resolution_bits;
+};
+
+struct ads112c14_data {
+ const struct ads112c14_chip_info *chip_info;
+ struct regmap *regmap;
+};
+
+/* Fixed channels for system monitor measurements. */
+#define ADS112C14_SYS_MON_CHANNEL_TEMP 100
+#define ADS112C14_SYS_MON_CHANNEL_EXT_REF 101
+#define ADS112C14_SYS_MON_CHANNEL_AVDD 102
+#define ADS112C14_SYS_MON_CHANNEL_DVDD 103
+#define ADS112C14_SYS_MON_CHANNEL_SHORT 104
+
+static const struct iio_chan_spec ads112c14_sys_mon_channels[] = {
+ {
+ .type = IIO_TEMP,
+ .indexed = 1,
+ .channel = ADS112C14_SYS_MON_CHANNEL_TEMP,
+ .address = 2,
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW)
+ | BIT(IIO_CHAN_INFO_SCALE)
+ | BIT(IIO_CHAN_INFO_OFFSET),
+ },
+ {
+ .type = IIO_VOLTAGE,
+ .indexed = 1,
+ .channel = ADS112C14_SYS_MON_CHANNEL_EXT_REF,
+ .address = 3,
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW)
+ | BIT(IIO_CHAN_INFO_SCALE),
+ },
+ {
+ .type = IIO_VOLTAGE,
+ .indexed = 1,
+ .channel = ADS112C14_SYS_MON_CHANNEL_AVDD,
+ .address = 4,
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW)
+ | BIT(IIO_CHAN_INFO_SCALE),
+ },
+ {
+ .type = IIO_VOLTAGE,
+ .indexed = 1,
+ .channel = ADS112C14_SYS_MON_CHANNEL_DVDD,
+ .address = 5,
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW)
+ | BIT(IIO_CHAN_INFO_SCALE),
+ },
+ {
+ .type = IIO_VOLTAGE,
+ .indexed = 1,
+ .channel = ADS112C14_SYS_MON_CHANNEL_SHORT,
+ .channel2 = ADS112C14_SYS_MON_CHANNEL_SHORT,
+ .differential = 1,
+ .address = 1,
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW)
+ | BIT(IIO_CHAN_INFO_SCALE),
+ },
+};
+
+static int ads112c14_prepare_sys_mon_channel(struct ads112c14_data *data,
+ const struct iio_chan_spec *chan)
+{
+ int ret;
+
+ /* TODO: GAIN is useful for shorted PGA inputs. */
+ /* All SYS_MON channels use GAIN of 1 to keep it simple. */
+ ret = regmap_update_bits(data->regmap, ADS112C14_REG_GAIN_CFG,
+ ADS112C14_GAIN_CFG_SYS_MON |
+ ADS112C14_GAIN_CFG_GAIN,
+ FIELD_PREP(ADS112C14_GAIN_CFG_SYS_MON, chan->address) |
+ FIELD_PREP(ADS112C14_GAIN_CFG_GAIN, 1));
+ if (ret)
+ return ret;
+
+ /* All SYS_MON channels use signed data to keep it simple. */
+ ret = regmap_clear_bits(data->regmap, ADS112C14_REG_DIGITAL_CFG,
+ ADS112C14_DIGITAL_CFG_CODING);
+ if (ret)
+ return ret;
+
+ /*
+ * REVISIT: if we implement regulator support for the REFOUT pin, we
+ * might need to make this voltage match what is required by that. In
+ * that case, we could also adjust GAIN so that we still get the same
+ * range.
+ */
+ /*
+ * NB: SYS_MON channels ignore REF_SEL except for the shorted input
+ * channel, so we set it here to internal reference to be consistent.
+ * If we ever need to make a measurement of shorted input with other
+ * reference source, we could add additional channels for that.
+ */
+ ret = regmap_update_bits(data->regmap, ADS112C14_REG_REFERENCE_CFG,
+ ADS112C14_REFERENCE_CFG_REF_VAL |
+ ADS112C14_REFERENCE_CFG_REF_SEL,
+ FIELD_PREP(ADS112C14_REFERENCE_CFG_REF_VAL,
+ ADS112C14_REFERENCE_CFG_REF_VAL_2_5V) |
+ FIELD_PREP(ADS112C14_REFERENCE_CFG_REF_SEL,
+ ADS112C14_REFERENCE_CFG_REF_SEL_INTERNAL));
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static int ads112c14_single_conversion(struct ads112c14_data *data,
+ const struct iio_chan_spec *chan,
+ u8 *buf)
+{
+ struct i2c_client *client = to_i2c_client(regmap_get_device(data->regmap));
+ u32 reg_val;
+ int ret;
+
+ if (chan->channel < 100) {
+ /* Not implemented yet. */
+ return -EINVAL;
+ } else {
+ ret = ads112c14_prepare_sys_mon_channel(data, chan);
+ if (ret)
+ return ret;
+ }
+
+ ret = regmap_write(data->regmap, ADS112C14_REG_CONVERSION_CTRL,
+ ADS112C14_CONVERSION_CTRL_START);
+ if (ret)
+ return ret;
+
+ ret = regmap_read_poll_timeout(data->regmap,
+ ADS112C14_REG_STATUS_MSB, reg_val,
+ FIELD_GET(ADS112C14_STATUS_MSB_DRDY, reg_val),
+ 1 * USEC_PER_MSEC, 100 * USEC_PER_MSEC);
+ if (ret)
+ return ret;
+
+ return i2c_smbus_read_i2c_block_data(client, ADS112C14_CMD_RDATA,
+ BITS_TO_BYTES(data->chip_info->resolution_bits),
+ buf);
+}
+
+static int ads112c14_read_raw(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan, int *val,
+ int *val2, long mask)
+{
+ struct ads112c14_data *data = iio_priv(indio_dev);
+ u32 vref_uV, fsr_bits;
+
+ /* Selecting V_REF source is not implemented yet. */
+ vref_uV = ADS112C14_INT_REF1_mV * (MICRO / MILLI);
+
+ if (chan->channel < 100) {
+ /* Not implemented yet. */
+ return -EINVAL;
+ } else {
+ /* All SYS_MON channels are using signed coding. */
+ fsr_bits = data->chip_info->resolution_bits - 1;
+ }
+
+ switch (mask) {
+ case IIO_CHAN_INFO_RAW: {
+ u8 buf[3];
+ int ret;
+
+ if (!iio_device_claim_direct(indio_dev))
+ return -EBUSY;
+
+ ret = ads112c14_single_conversion(data, chan, buf);
+ iio_device_release_direct(indio_dev);
+ if (ret < 0)
+ return ret;
+
+ switch (data->chip_info->resolution_bits) {
+ case 16:
+ *val = get_unaligned_be16(buf);
+ break;
+ case 24:
+ *val = get_unaligned_be24(buf);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ *val = sign_extend32(*val, fsr_bits);
+
+ return IIO_VAL_INT;
+ }
+ case IIO_CHAN_INFO_SCALE:
+ if (chan->type == IIO_TEMP) {
+ /* TS_TC (typical) = 405 uV/°C */
+ *val = MILLI * vref_uV / 405;
+ *val2 = fsr_bits;
+ return IIO_VAL_FRACTIONAL_LOG2;
+ }
+
+ *val = vref_uV / (MICRO / MILLI);
+ /*
+ * Last 3 SYS_MON channels (ext ref, AVDD, DVDD) need to be
+ * multiplied by 8 to account for internal attenuation of / 8.
+ */
+ *val2 = fsr_bits - (chan->address >= 3 ? 3 : 0);
+ return IIO_VAL_FRACTIONAL_LOG2;
+ case IIO_CHAN_INFO_OFFSET:
+ /* Only the temperature channel has an offset. */
+ if (chan->type != IIO_TEMP)
+ return -EINVAL;
+ /*
+ * Die temperature [°C] = 25°C + (Measured voltage – TS_Offset) / TS_TC
+ * TS_TC (typical) = 405 uV/°C
+ * TS_Offset (typical) = 119.5 mV
+ */
+ *val = div_s64((s64)(25 * 405 - 119500) * BIT(fsr_bits), vref_uV);
+ return IIO_VAL_INT;
+ default:
+ return -EINVAL;
+ }
+}
+
+static int ads112c14_read_label(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan, char *label)
+{
+ const char *label_source;
+
+ /* System monitor channels. */
+ switch (chan->channel) {
+ case ADS112C14_SYS_MON_CHANNEL_TEMP:
+ label_source = "Internal temperature sensor";
+ break;
+ case ADS112C14_SYS_MON_CHANNEL_EXT_REF:
+ label_source = "External reference";
+ break;
+ case ADS112C14_SYS_MON_CHANNEL_AVDD:
+ label_source = "AVDD";
+ break;
+ case ADS112C14_SYS_MON_CHANNEL_DVDD:
+ label_source = "DVDD";
+ break;
+ case ADS112C14_SYS_MON_CHANNEL_SHORT:
+ label_source = "Internal short (internal reference source)";
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return sysfs_emit(label, "%s\n", label_source);
+}
+
+static const struct iio_info ads112c14_info = {
+ .read_raw = ads112c14_read_raw,
+ .read_label = ads112c14_read_label,
+};
+
+static int ads112c14_probe(struct i2c_client *client)
+{
+ struct device *dev = &client->dev;
+ const struct ads112c14_chip_info *info;
+ struct iio_dev *indio_dev;
+ struct ads112c14_data *data;
+ u32 reg_val;
+ int ret;
+
+ info = i2c_get_match_data(client);
+ if (!info)
+ return dev_err_probe(dev, -EINVAL, "missing match data\n");
+
+ indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
+ if (!indio_dev)
+ return -ENOMEM;
+
+ data = iio_priv(indio_dev);
+ data->chip_info = info;
+
+ ret = devm_regulator_get_enable(dev, "dvdd");
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to get dvdd regulator\n");
+
+ ret = devm_regulator_get_enable(dev, "avdd");
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to get avdd regulator\n");
+
+ data->regmap = devm_regmap_init_i2c(client, &ads112c14_regmap_config);
+ if (IS_ERR(data->regmap))
+ return dev_err_probe(dev, PTR_ERR(data->regmap),
+ "failed to init regmap\n");
+
+ /* Write magic reset value (0x16) to ensure known state.*/
+ ret = regmap_write(data->regmap, ADS112C14_REG_CONVERSION_CTRL,
+ FIELD_PREP(ADS112C14_CONVERSION_CTRL_RESET, 0x16));
+ /*
+ * The reset may cause an -EREMOTEIO error because of failing to get the
+ * I2C ACK at the end of the message. The device still gets reset so it
+ * is safe to ignore this error.
+ */
+ if (ret == -EREMOTEIO)
+ ret = 0;
+ if (ret)
+ return ret;
+
+ fsleep(ADS112C14_DELAY_RESET_US);
+
+ ret = regmap_read(data->regmap, ADS112C14_REG_STATUS_MSB, ®_val);
+ if (ret)
+ return ret;
+
+ if (FIELD_GET(ADS112C14_STATUS_MSB_RESETN, reg_val))
+ return dev_err_probe(dev, -EIO, "reset failed\n");
+
+ /*
+ * Clear reset bit to prepare for next probe. And clear AVDD fault since
+ * that happens on every reset.
+ */
+ ret = regmap_write(data->regmap, ADS112C14_REG_STATUS_MSB,
+ ADS112C14_STATUS_MSB_RESETN |
+ ADS112C14_STATUS_MSB_AVDD_UVN);
+ if (ret)
+ return ret;
+
+ /* Place in single-shot conversion mode to make ready for raw read. */
+ ret = regmap_set_bits(data->regmap, ADS112C14_REG_DEVICE_CFG,
+ ADS112C14_DEVICE_CFG_CONV_MODE);
+ if (ret)
+ return ret;
+
+ indio_dev->name = info->name;
+ indio_dev->modes = INDIO_DIRECT_MODE;
+ indio_dev->channels = ads112c14_sys_mon_channels;
+ indio_dev->num_channels = ARRAY_SIZE(ads112c14_sys_mon_channels);
+ indio_dev->info = &ads112c14_info;
+
+ return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct ads112c14_chip_info ads112c14_chip_info = {
+ .name = "ads112c14",
+ .resolution_bits = 16,
+};
+
+static const struct ads112c14_chip_info ads122c14_chip_info = {
+ .name = "ads122c14",
+ .resolution_bits = 24,
+};
+
+static const struct of_device_id ads112c14_of_match[] = {
+ { .compatible = "ti,ads112c14", .data = &ads112c14_chip_info },
+ { .compatible = "ti,ads122c14", .data = &ads122c14_chip_info },
+ { }
+};
+MODULE_DEVICE_TABLE(of, ads112c14_of_match);
+
+static const struct i2c_device_id ads112c14_id[] = {
+ { .name = "ads112c14", .driver_data = (kernel_ulong_t)&ads112c14_chip_info },
+ { .name = "ads122c14", .driver_data = (kernel_ulong_t)&ads122c14_chip_info },
+ { }
+};
+MODULE_DEVICE_TABLE(i2c, ads112c14_id);
+
+static struct i2c_driver ads112c14_driver = {
+ .driver = {
+ .name = "ads112c14",
+ .of_match_table = ads112c14_of_match,
+ },
+ .probe = ads112c14_probe,
+ .id_table = ads112c14_id,
+};
+module_i2c_driver(ads112c14_driver);
+
+MODULE_AUTHOR("David Lechner (TI) <dlechner@baylibre.com>");
+MODULE_DESCRIPTION("TI ADS112C14 I2C ADC driver");
+MODULE_LICENSE("GPL");
--
2.43.0
^ permalink raw reply related
* [PATCH v2 7/8] iio: adc: ti-ads112c14: implement gain on internal short SYS_MON channel
From: David Lechner (TI) @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com>
Implement support for the programmable gain amplifier on the internal
short SYS_MON channel. This channel is used for calibration, so it is
useful to be able to set the PGA to the same gain as the external
channels. The gain setting is implemented via the `_scale` attribute.
In the future, we may want to support different reference voltages for
this channel, so the scale_available table is populated during probe
rather than being a static table.
Signed-off-by: David Lechner (TI) <dlechner@baylibre.com>
---
v2 changes:
* Make some changes to reduce diff in next patch.
* Add some local variables to reduce line wrap.
---
drivers/iio/adc/ti-ads112c14.c | 144 ++++++++++++++++++++++++++++++++++++++++-
1 file changed, 141 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/adc/ti-ads112c14.c b/drivers/iio/adc/ti-ads112c14.c
index c61d47244732..0e775dbc8d50 100644
--- a/drivers/iio/adc/ti-ads112c14.c
+++ b/drivers/iio/adc/ti-ads112c14.c
@@ -124,6 +124,26 @@
#define ADS112C14_INT_REF0_mV 1250
#define ADS112C14_INT_REF1_mV 2500
+/* Available gains as tenths (x10) */
+static const u32 ads112c14_pga_gains_x10[] = {
+ 5, /* 0.5 */
+ 10, /* 1 */
+ 20, /* 2 */
+ 40, /* 4 */
+ 50, /* 5 */
+ 80, /* 8 */
+ 100, /* 10 */
+ 160, /* 16 */
+ 200, /* 20 */
+ 320, /* 32 */
+ 500, /* 50 */
+ 640, /* 64 */
+ 1000, /* 100 */
+ 1280, /* 128 */
+ 2000, /* 200 */
+ 2560, /* 256 */
+};
+
static bool ads112c14_writeable_reg(struct device *dev, unsigned int reg)
{
switch (reg) {
@@ -182,6 +202,8 @@ struct ads112c14_chip_info {
struct ads112c14_data {
const struct ads112c14_chip_info *chip_info;
struct regmap *regmap;
+ u8 sys_mon_chan_short_gain_val;
+ int sys_mon_chan_short_scale_available[ARRAY_SIZE(ads112c14_pga_gains_x10)][2];
};
/* Fixed channels for system monitor measurements. */
@@ -234,21 +256,28 @@ static const struct iio_chan_spec ads112c14_sys_mon_channels[] = {
.address = 1,
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW)
| BIT(IIO_CHAN_INFO_SCALE),
+ .info_mask_separate_available = BIT(IIO_CHAN_INFO_SCALE),
},
};
static int ads112c14_prepare_sys_mon_channel(struct ads112c14_data *data,
const struct iio_chan_spec *chan)
{
+ u32 gain_val;
int ret;
- /* TODO: GAIN is useful for shorted PGA inputs. */
- /* All SYS_MON channels use GAIN of 1 to keep it simple. */
+ /*
+ * All SYS_MON channels use GAIN of 1 to keep it simple. Other than
+ * the internal short channel, where it is useful in practice.
+ */
+ gain_val = chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT ?
+ data->sys_mon_chan_short_gain_val : 1;
+
ret = regmap_update_bits(data->regmap, ADS112C14_REG_GAIN_CFG,
ADS112C14_GAIN_CFG_SYS_MON |
ADS112C14_GAIN_CFG_GAIN,
FIELD_PREP(ADS112C14_GAIN_CFG_SYS_MON, chan->address) |
- FIELD_PREP(ADS112C14_GAIN_CFG_GAIN, 1));
+ FIELD_PREP(ADS112C14_GAIN_CFG_GAIN, gain_val));
if (ret)
return ret;
@@ -323,6 +352,7 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
{
struct ads112c14_data *data = iio_priv(indio_dev);
u32 vref_uV, fsr_bits;
+ int *scale_avail;
/* Selecting V_REF source is not implemented yet. */
vref_uV = ADS112C14_INT_REF1_mV * (MICRO / MILLI);
@@ -371,6 +401,17 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
return IIO_VAL_FRACTIONAL_LOG2;
}
+ if (chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT) {
+ u8 idx = data->sys_mon_chan_short_gain_val;
+
+ scale_avail = data->sys_mon_chan_short_scale_available[idx];
+
+ *val = scale_avail[0];
+ *val2 = scale_avail[1];
+
+ return IIO_VAL_INT_PLUS_NANO;
+ }
+
*val = vref_uV / (MICRO / MILLI);
/*
* Last 3 SYS_MON channels (ext ref, AVDD, DVDD) need to be
@@ -394,6 +435,69 @@ static int ads112c14_read_raw(struct iio_dev *indio_dev,
}
}
+static int ads112c14_read_avail(struct iio_dev *indio_dev,
+ const struct iio_chan_spec *chan, const int **vals,
+ int *type, int *length, long mask)
+{
+ struct ads112c14_data *data = iio_priv(indio_dev);
+
+ if (chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT) {
+ *vals = (const int *)data->sys_mon_chan_short_scale_available;
+ *length = 2 * ARRAY_SIZE(data->sys_mon_chan_short_scale_available);
+ *type = IIO_VAL_INT_PLUS_NANO;
+ return IIO_AVAIL_LIST;
+ }
+
+ return -EINVAL;
+}
+
+static int ads112c14_write_raw(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan, int val,
+ int val2, long mask)
+{
+ struct ads112c14_data *data = iio_priv(indio_dev);
+ const int (*scale_avail)[2];
+ u8 *gain_val;
+
+ switch (mask) {
+ case IIO_CHAN_INFO_SCALE: {
+ if (chan->channel == ADS112C14_SYS_MON_CHANNEL_SHORT) {
+ scale_avail = data->sys_mon_chan_short_scale_available;
+ gain_val = &data->sys_mon_chan_short_gain_val;
+ } else {
+ return -EINVAL;
+ }
+
+ IIO_DEV_ACQUIRE_DIRECT_MODE(indio_dev, claim);
+ if (IIO_DEV_ACQUIRE_FAILED(claim))
+ return -EBUSY;
+
+ for (u32 i = 0; i < ARRAY_SIZE(ads112c14_pga_gains_x10); i++) {
+ if (val == scale_avail[i][0] && val2 == scale_avail[i][1]) {
+ *gain_val = i;
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+ }
+ default:
+ return -EINVAL;
+ }
+}
+
+static int ads112c14_write_raw_get_fmt(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan,
+ long mask)
+{
+ switch (mask) {
+ case IIO_CHAN_INFO_SCALE:
+ return IIO_VAL_INT_PLUS_NANO;
+ default:
+ return IIO_VAL_INT_PLUS_MICRO;
+ }
+}
+
static int ads112c14_read_label(struct iio_dev *indio_dev,
struct iio_chan_spec const *chan, char *label)
{
@@ -425,9 +529,38 @@ static int ads112c14_read_label(struct iio_dev *indio_dev,
static const struct iio_info ads112c14_info = {
.read_raw = ads112c14_read_raw,
+ .read_avail = ads112c14_read_avail,
+ .write_raw = ads112c14_write_raw,
+ .write_raw_get_fmt = ads112c14_write_raw_get_fmt,
.read_label = ads112c14_read_label,
};
+static void ads112c14_populate_scale_available(int scale_avail[][2],
+ u32 full_scale, u32 fsr_bits)
+{
+ for (u32 i = 0; i < ARRAY_SIZE(ads112c14_pga_gains_x10); i++) {
+ int *entry = scale_avail[i];
+ u64 gain_x10, nano_scale;
+
+ gain_x10 = ads112c14_pga_gains_x10[i];
+ nano_scale = div64_u64((u64)NANO * 10U * full_scale,
+ gain_x10 * BIT(fsr_bits));
+ entry[0] = div_u64_rem(nano_scale, NANO, &entry[1]);
+ }
+}
+
+static void ads112c14_populate_tables(struct ads112c14_data *data)
+{
+ u32 full_scale, fsr_bits;
+
+ /* For now, assuming all sys_mon channels are using 2.5V reference. */
+ full_scale = ADS112C14_INT_REF1_mV;
+ fsr_bits = data->chip_info->resolution_bits - 1;
+
+ ads112c14_populate_scale_available(data->sys_mon_chan_short_scale_available,
+ full_scale, fsr_bits);
+}
+
static int ads112c14_probe(struct i2c_client *client)
{
struct device *dev = &client->dev;
@@ -483,6 +616,9 @@ static int ads112c14_probe(struct i2c_client *client)
if (FIELD_GET(ADS112C14_STATUS_MSB_RESETN, reg_val))
return dev_err_probe(dev, -EIO, "reset failed\n");
+ /* Default gain after reset is 1. */
+ data->sys_mon_chan_short_gain_val = 1;
+
/*
* Clear reset bit to prepare for next probe. And clear AVDD fault since
* that happens on every reset.
@@ -499,6 +635,8 @@ static int ads112c14_probe(struct i2c_client *client)
if (ret)
return ret;
+ ads112c14_populate_tables(data);
+
indio_dev->name = info->name;
indio_dev->modes = INDIO_DIRECT_MODE;
indio_dev->channels = ads112c14_sys_mon_channels;
--
2.43.0
^ permalink raw reply related
* [PATCH v2 5/8] dt-bindings: iio: adc: add ti,ads122c14
From: David Lechner (TI) @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com>
Add new bindings for ti,ads122c14 and similar devices.
This is an ADC that is primarily intended for use with temperature
sensors. There are a few unusual properties because of this. In
particular, the reference voltage source and current output requirements
can be different for each measurement, so these are included in the
channel bindings.
The REFP/REFN reference voltage is usually just connected to a resistor
that is being driven by the ADC's current outputs, so there is special
property for this case rather than requiring a regulator to be defined
to represent that.
ti,vref-source is reused from ti,tlv320adcx140.yaml (otherwise might
have preferred an enum of strings).
Signed-off-by: David Lechner (TI) <dlechner@baylibre.com>
---
v2 changes:
* Added ti, vendor prefix when appropriate.
* Others are now standardized properties from adc.yaml.
* Moved top-level unevaluatedProperties.
* Fixed some issues with the channel@ matching and reg property.
* Dropped description on bipolar property.
* Renamed currnet-chopping to input-channel-rotation.
* Drop header file and use string enum instead for reference-sources.
* Added burn-out-current-nanoamp property.
* Drop allOf: and just use oneOf: directly.
* Fix inconsistent indentation in the examples.
---
.../devicetree/bindings/iio/adc/ti,ads112c14.yaml | 205 +++++++++++++++++++++
MAINTAINERS | 6 +
2 files changed, 211 insertions(+)
diff --git a/Documentation/devicetree/bindings/iio/adc/ti,ads112c14.yaml b/Documentation/devicetree/bindings/iio/adc/ti,ads112c14.yaml
new file mode 100644
index 000000000000..59ee4d652a08
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/ti,ads112c14.yaml
@@ -0,0 +1,205 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/adc/ti,ads112c14.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments' ADS112C14 and similar ADC chips
+
+description: |
+ Supports the following Texas Instruments' ADC chips:
+ - ADS112C14 (16-bit)
+ - ADS122C14 (24-bit)
+
+ https://www.ti.com/lit/ds/symlink/ads122c14.pdf
+
+ These chips are primarily designed for use with temperature sensors such as
+ RTDs and thermocouples. The channel bindings reflect this in that each channel
+ represents the conditions required to make a measurement rather than strictly
+ just the physical input channels.
+
+maintainers:
+ - David Lechner <dlechner@baylibre.com>
+
+properties:
+ compatible:
+ enum:
+ - ti,ads112c14
+ - ti,ads122c14
+
+ reg:
+ items:
+ - minimum: 0x40
+ maximum: 0x47
+
+ clocks:
+ maxItems: 1
+ description: Optional external clock connected to GPIO3 pin.
+
+ avdd-supply: true
+ dvdd-supply: true
+
+ refp-supply: true
+ refn-supply: true
+
+ ti,refp-refn-resistor-ohms:
+ description:
+ The resistance of the external resistor between REFP and REFN when using
+ resistor bridge driven by current outputs for RTD measurements.
+
+ interrupts:
+ minItems: 1
+ items:
+ - description: FAULT interrupt (GPIO2 pin)
+ - description: DRDY interrupt (GPIO3 pin)
+
+ interrupt-names:
+ minItems: 1
+ maxItems: 2
+ items:
+ enum: [fault, drdy]
+
+ gpio-controller: true
+ '#gpio-cells':
+ const: 2
+
+ '#address-cells':
+ const: 1
+
+ '#size-cells':
+ const: 0
+
+patternProperties:
+ ^channel@[0-7a-f]$:
+ $ref: adc.yaml
+
+ unevaluatedProperties: false
+
+ properties:
+ reg:
+ items:
+ - maximum: 15 # arbitrary limit, channel@ can be any combination of AIN0-AIN7
+
+ single-channel:
+ maximum: 7
+
+ diff-channels:
+ items:
+ maximum: 7
+
+ bipolar: true
+
+ input-channel-rotation: true
+
+ excitation-channels:
+ maxItems: 2
+ items:
+ maximum: 7
+
+ excitation-current-nanoamp:
+ maxItems: 2
+ items:
+ enum: [1000, 10000, 20000, 30000, 40000, 50000, 60000, 70000, 80000,
+ 90000, 100000, 200000, 300000, 400000, 500000, 600000, 700000,
+ 800000, 900000, 1000000]
+
+ burn-out-current-nanoamp:
+ enum: [200, 1000, 10000]
+
+ reference-sources:
+ items:
+ - enum: [internal-2.5v, internal-1.25v, external, avdd]
+ default: internal-2.5v
+
+ dependencies:
+ excitation-channels: [ excitation-current-nanoamp ]
+ excitation-current-nanoamp: [ excitation-channels ]
+
+ oneOf:
+ - required: [ single-channel ]
+ - required: [ diff-channels ]
+
+unevaluatedProperties: false
+
+required:
+ - compatible
+ - avdd-supply
+ - dvdd-supply
+
+dependencies:
+ refn-supply: [ refp-supply ]
+
+oneOf:
+ - required: [ refp-supply ]
+ - required: [ "ti,refp-refn-resistor-ohms" ]
+ - properties:
+ refp-supply: false
+ refn-supply: false
+ ti,refp-refn-resistor-ohms: false
+
+examples:
+ - |
+ i2c {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ adc@40 {
+ compatible = "ti,ads112c14";
+ reg = <0x40>;
+
+ avdd-supply = <&avdd>;
+ dvdd-supply = <&dvdd>;
+
+ /* 3-Wire RTD: Two IDACs, One Measurement (AIN1-AIN2) */
+
+ ti,refp-refn-resistor-ohms = <500>;
+
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ channel@0 {
+ reg = <0>;
+ diff-channels = <1>, <2>;
+ input-channel-rotation;
+ excitation-channels = <0>, <3>;
+ excitation-current-nanoamp = <500000>, <500000>;
+ reference-sources = "external";
+ label = "rtd";
+ };
+ };
+ };
+ - |
+ i2c {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ adc@40 {
+ compatible = "ti,ads112c14";
+ reg = <0x40>;
+
+ avdd-supply = <&avdd>;
+ dvdd-supply = <&dvdd>;
+
+ /* Resistive Bridge Measurement With a Thermistor for Temperature Compensation*/
+
+ refp-supply = <&avdd>;
+
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ channel@0 {
+ reg = <0>;
+ diff-channels = <6>, <7>;
+ bipolar;
+ reference-sources = "external";
+ label = "bridge";
+ };
+
+ channel@1 {
+ reg = <1>;
+ diff-channels = <1>, <2>;
+ reference-sources = "internal-2.5v";
+ label = "thermistor";
+ };
+ };
+ };
diff --git a/MAINTAINERS b/MAINTAINERS
index 895a87b571c3..0ac9f44c7096 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -26935,6 +26935,12 @@ S: Maintained
F: Documentation/devicetree/bindings/iio/adc/ti,ads1119.yaml
F: drivers/iio/adc/ti-ads1119.c
+TI ADS112C14 ADC DRIVER
+M: David Lechner <dlechner@baylibre.com>
+L: linux-iio@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/iio/adc/ti,ads112c14.yaml
+
TI ADS1018 ADC DRIVER
M: Kurt Borja <kuurtb@gmail.com>
L: linux-iio@vger.kernel.org
--
2.43.0
^ permalink raw reply related
* [PATCH v2 4/8] dt-bindings: iio: adc: add input-channel-rotation property
From: David Lechner (TI) @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com>
Add a generic input-channel-rotation property to adc.yaml. This is a
feature seen frequently in ADCs that are designed to measure resistive
loads, such as RTDs and strain gauges. Enabling this can reduce offset
errors by swapping the positive and negative input channels on every
other conversion. This can have side-effects in timing and filter
response, so it is not always desirable to enable this feature in some
applications. Therefore, it is best to make this a property that can be
enabled or disabled in the device tree.
Signed-off-by: David Lechner (TI) <dlechner@baylibre.com>
---
v2 changes:
* New patch.
---
Documentation/devicetree/bindings/iio/adc/adc.yaml | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/Documentation/devicetree/bindings/iio/adc/adc.yaml b/Documentation/devicetree/bindings/iio/adc/adc.yaml
index 9ec1f447b565..3d52c00922c9 100644
--- a/Documentation/devicetree/bindings/iio/adc/adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adc.yaml
@@ -81,6 +81,13 @@ properties:
ADCs usually allow choosing between internal reference sources or a pair
of external pins.
+ input-channel-rotation:
+ type: boolean
+ description:
+ If set, the positive and negative input channels are allowed to be swapped
+ on every other conversion to reduce offset errors. This is also referred
+ to as "chop" in some datasheets.
+
excitation-channels:
$ref: /schemas/types.yaml#/definitions/uint32-array
description:
--
2.43.0
^ permalink raw reply related
* [PATCH v2 3/8] dt-bindings: iio: adc: Add burn-out current properties
From: David Lechner @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com>
From: Kurt Borja <kuurtb@gmail.com>
Some ADCs incorporate burn-out current sources that provide current to
the channel's input pins for open-circuit or short-circuit detection.
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Signed-off-by: David Lechner (TI) <dlechner@baylibre.com>
---
v2 changes (compared to Kurt's RFC v2):
* Changed units from microamps to nanoamps to fit known devices.
---
Documentation/devicetree/bindings/iio/adc/adc.yaml | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/Documentation/devicetree/bindings/iio/adc/adc.yaml b/Documentation/devicetree/bindings/iio/adc/adc.yaml
index 860601ec5334..9ec1f447b565 100644
--- a/Documentation/devicetree/bindings/iio/adc/adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adc.yaml
@@ -101,6 +101,12 @@ properties:
sources. The index in the array corresponds to the same index in the
excitation-channels array.
+ burn-out-current-nanoamp:
+ maxItems: 1
+ description:
+ Burn-out current sources provide current to the channel's input pins for
+ open-circuit or short-circuit detection.
+
anyOf:
- oneOf:
- required:
--
2.43.0
^ permalink raw reply related
* [PATCH v2 2/8] dt-bindings: iio: adc: Add excitation current sources properties
From: David Lechner @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com>
From: Kurt Borja <kuurtb@gmail.com>
Some ADCs incorporate current sources that provide excitation current to
resistive temperature devices (RTDs), thermistors, diodes and other
resistive sensors that require constant current biasing.
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Signed-off-by: David Lechner (TI) <dlechner@baylibre.com>
---
v2 changes (compared to Kurt's RFC v2):
* Make units nanoamps instead of microamps to fit known devices.
* Drop bit about allowing single value for multiple channels.
* Add bit about semantics of the array index.
---
Documentation/devicetree/bindings/iio/adc/adc.yaml | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/Documentation/devicetree/bindings/iio/adc/adc.yaml b/Documentation/devicetree/bindings/iio/adc/adc.yaml
index 12800737d4fb..860601ec5334 100644
--- a/Documentation/devicetree/bindings/iio/adc/adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adc.yaml
@@ -81,6 +81,26 @@ properties:
ADCs usually allow choosing between internal reference sources or a pair
of external pins.
+ excitation-channels:
+ $ref: /schemas/types.yaml#/definitions/uint32-array
+ description:
+ Excitation current sources provide current to resistive temperature
+ devices (RTDs), thermistors, diodes and other resistive sensors that
+ require constant current biasing.
+
+ This array describes the mux configuration of the excitation current
+ sources.
+
+ excitation-current-nanoamp:
+ description:
+ Excitation current sources provide current to resistive temperature
+ devices (RTDs), thermistors, diodes and other resistive sensors that
+ require constant current biasing.
+
+ This array describes the current configuration of the excitation current
+ sources. The index in the array corresponds to the same index in the
+ excitation-channels array.
+
anyOf:
- oneOf:
- required:
--
2.43.0
^ permalink raw reply related
* [PATCH v2 0/8] iio: adc: new ti-ads112c14 driver
From: David Lechner @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
This adds support for TI ADS112C14 and ADS122C14 ADC chips.
The closest thing we've seen to this in the kernel already is ads124s08.
However, that has a completely different register map and the DT
bindings are incomplete and the driver is extremely basic. So I've just
started from scratch here.
We've also had a similar submission recently for ADS1220 [1]. That chip
is in a similar situation to ads124s08 in that it has a different
register map (but the submitted DT bindings are better than the ones for
ads124s08, even if still a bit incomplete). And literally as I was
writing the previous sentence, another series [2] was sent for yet
another similar family of chips (ADS1262). That one is even more complex
in the feature set than the ones I am working on. I was going to polish
up the driver a bit more before submitting it, but now it seems more
urgent to coordinate with the other two series to align on how we would
like to handle all of these.
[1]: https://lore.kernel.org/linux-iio/20260610151342.44274-1-zizuzacker@gmail.com/
[2]: https://lore.kernel.org/linux-iio/20260612-ads126x-v1-0-894c788d03ed@gmail.com/
All of these chips have in common that they are designed for use with
RTDs and thermocouples and so they look very similar to each other in
terms of wiring and feature set, even if the register maps are
different. They are in the gray area where we could either keep them
separate because they are just different enough, or we could do like
we've done before with ad_sigma_delta and have a bit of an abstraction
layer for the register differences and otherwise try to share as much
code as possible. Normally, I would lean towards keeping them separate,
but in this case, I'm considering trying to share code because the
devicetree bindings for the inputs is complex and is going to be mostly
the same across all of these chips.
If we decide to go the route of sharing code, we could still merge this
series as-is and then do the refactoring to add the abstraction layer in
a follow-up series that also adds support for the first of the other
chips.
This series includes just basic support for reading single measurements
from the ADC and gain selection via the scale attribute. I plan to
follow this up with additional series to add support for buffered reads,
filtering/oversampling configuration, event support, gpio controller
support and perhaps a few other things that are slipping my mind right
now.
The most interesting part about this (that I alluded to above) is the
way channels are handled. These are multipling ADCs with differential
and single-ended inputs. But what sets them apart from other similar
chips is that since they are designed for use with RTDs, there can also
be a current output required to excite the RTD and this current output
might be different for different channels. So the way I conceptualized
the channels is that the devicetree specifies the conditions needed
to take a particular measurement rather than being purely a physical
channel.
This makes things more flexible, but does make the driver a bit more
complex. For example, knowing when the current output needs to be
enabled or disabled. For now, I have chosen a lazy-enable where they
are not turned on until the first measurement is taken that requires
them, but then they stay on until another measurement is taken that
doesn't require them. This can lead to some oddness with the diagnostic
channels that may be measuring something that indirectly requires the
current output (i.e. the external reference voltage when it is connected
to a resistor rather than a power supply). This means you need to take
a measurement that requires the current output to be enabled before the
diagnostic channels will give accurate readings.
I have also pushed a branch to [3] that contains the start of some
documentation for this driver that can give some more insight into how
the implementation works. It still needs some work and also documents
some things that haven't been implemented yet, so I haven't included it
in this series yet.
[3]: https://github.com/dlech/linux/blob/b4/iio-adc-ti-ads122c14/Documentation/iio/ads112c14.rst
Signed-off-by: David Lechner <dlechner@baylibre.com>
---
Changes in v2:
- Added patches for adding properties to adc.yaml.
- Some of these are coming from: https://lore.kernel.org/linux-iio/20260622-new-channel-props-v2-0-aafd5369f253@gmail.com/
- For now, I have stuck with one channel per single-channel pin or
diff-channels pin pair rather than some of the other ideas that were
discussed. Handling burn out current enable will be handled in a later
series. I'm leaning towards something like the _burnoutraw attribute
that Jonathan suggested.
- See individual patches for details of changes (mostly renaming DT
properties, fixing some driver bugs and style issues).
- Link to v1: https://patch.msgid.link/20260615-iio-adc-ti-ads122c14-v1-0-e6bdadf7cb2b@baylibre.com
---
David Lechner (TI) (5):
dt-bindings: iio: adc: add input-channel-rotation property
dt-bindings: iio: adc: add ti,ads122c14
iio: adc: add ti-ads112c14 driver
iio: adc: ti-ads112c14: implement gain on internal short SYS_MON channel
iio: adc: ti-ads112c14: add measurement channel support
Kurt Borja (3):
dt-bindings: iio: adc: Add reference-sources property
dt-bindings: iio: adc: Add excitation current sources properties
dt-bindings: iio: adc: Add burn-out current properties
Documentation/devicetree/bindings/iio/adc/adc.yaml | 41 +
.../devicetree/bindings/iio/adc/ti,ads112c14.yaml | 205 ++++
MAINTAINERS | 7 +
drivers/iio/adc/Kconfig | 12 +
drivers/iio/adc/Makefile | 1 +
drivers/iio/adc/ti-ads112c14.c | 1186 ++++++++++++++++++++
6 files changed, 1452 insertions(+)
---
base-commit: 948efecf22e49aa4bf55bb73ec79a0ddcfd38571
change-id: 20260514-iio-adc-ti-ads122c14-d0b92479334e
Best regards,
--
David Lechner (TI) <dlechner@baylibre.com>
^ permalink raw reply
* [PATCH v2 1/8] dt-bindings: iio: adc: Add reference-sources property
From: David Lechner @ 2026-06-25 21:55 UTC (permalink / raw)
To: Jonathan Cameron, Nuno Sá, Andy Shevchenko, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: Chris Hall, Patrick Edwards, Kurt Borja, Nguyen Minh Tien,
linux-iio, devicetree, linux-kernel, David Lechner
In-Reply-To: <20260625-iio-adc-ti-ads122c14-v2-0-ceb9b0b561cb@baylibre.com>
From: Kurt Borja <kuurtb@gmail.com>
Some ADCs have configurable voltage reference sources for each channel.
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Signed-off-by: David Lechner (TI) <dlechner@baylibre.com>
---
v2 changes (compared to Kurt's RFC v2):
* Drop maxItems.
* Drop 2nd paragraph of description.
* Make reference-sources plural since it is an array.
---
Documentation/devicetree/bindings/iio/adc/adc.yaml | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/Documentation/devicetree/bindings/iio/adc/adc.yaml b/Documentation/devicetree/bindings/iio/adc/adc.yaml
index b9bc02b5b07a..12800737d4fb 100644
--- a/Documentation/devicetree/bindings/iio/adc/adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adc.yaml
@@ -73,6 +73,14 @@ properties:
device design and can interact with other characteristics such as
settling time.
+ reference-sources:
+ $ref: /schemas/types.yaml#/definitions/string-array
+ minItems: 1
+ description:
+ Indicates the voltage reference source or sources for this channel. Some
+ ADCs usually allow choosing between internal reference sources or a pair
+ of external pins.
+
anyOf:
- oneOf:
- required:
--
2.43.0
^ permalink raw reply related
* Re: [PATCH 17/19] Documentation: ioctl: add CMH ioctl documentation and register 'J'
From: Krishnamoorthy, Saravanakrishnan @ 2026-06-25 21:21 UTC (permalink / raw)
To: Randy Dunlap, Albert Ou, Ousherovitch, Alex, Conor Dooley,
David S. Miller, Herbert Xu, Jonathan Corbet, Krzysztof Kozlowski,
Palmer Dabbelt, Paul Walmsley, Rob Herring, Shuah Khan
Cc: Alexandre Ghiti, devicetree@vger.kernel.org, Wittenauer, Joel,
linux-api@vger.kernel.org, linux-crypto@vger.kernel.org,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-kselftest@vger.kernel.org, linux-riscv@lists.infradead.org,
Shuah Khan, SIPSupport, Nguyen, Thi
In-Reply-To: <60a7850d-1527-4517-aae8-cd5cbebcb9b5@infradead.org>
Thanks for catching this, Randy. You're right. cmh_mgmt.rst isn't pulled into any toctree. We will fix it in v2 by adding cmh_mgmt to the toctree in Documentation/userspace-api/ioctl/index.rst (alongside cdrom/hdio).
Krishnan
________________________________________
From: Randy Dunlap <rdunlap@infradead.org>
Sent: Thursday, June 25, 2026 11:29 AM
To: Krishnamoorthy, Saravanakrishnan; Albert Ou; Ousherovitch, Alex; Conor Dooley; David S. Miller; Herbert Xu; Jonathan Corbet; Krzysztof Kozlowski; Palmer Dabbelt; Paul Walmsley; Rob Herring; Shuah Khan
Cc: Alexandre Ghiti; devicetree@vger.kernel.org; Wittenauer, Joel; linux-api@vger.kernel.org; linux-crypto@vger.kernel.org; linux-doc@vger.kernel.org; linux-kernel@vger.kernel.org; linux-kselftest@vger.kernel.org; linux-riscv@lists.infradead.org; Shuah Khan; SIPSupport; Nguyen, Thi
Subject: Re: [PATCH 17/19] Documentation: ioctl: add CMH ioctl documentation and register 'J'
[Some people who received this message don't often get email from rdunlap@infradead.org. Learn why this is important at https://aka.ms/LearnAboutSenderIdentification ]
Caution: < External Email >
On 6/25/26 10:33 AM, Saravanakrishnan Krishnamoorthy wrote:
> From: Alex Ousherovitch <aousherovitch@rambus.com>
>
> Add Documentation/userspace-api/ioctl/cmh_mgmt.rst documenting the
> ioctl commands on the /dev/cmh_mgmt misc device for the CRI
> CryptoManager Hub (CMH) hardware crypto accelerator driver. Covers
> key management, KIC key derivation, PKE (RSA, ECDSA, ECDH, EdDSA),
> PQC (ML-KEM, ML-DSA, SLH-DSA), SM2, EAC, and DRBG.
>
> Register ioctl magic number 'J' (0x4A) in ioctl-number.rst. The
> driver uses ioctls 0x01-0x40.
>
> Co-developed-by: Saravanakrishnan Krishnamoorthy <skrishnamoorthy@rambus.com>
> Signed-off-by: Saravanakrishnan Krishnamoorthy <skrishnamoorthy@rambus.com>
> Signed-off-by: Alex Ousherovitch <aousherovitch@rambus.com>
> Reviewed-by: Joel Wittenauer <Joel.Wittenauer@cryptography.com>
> Reviewed-by: Thi Nguyen <thin@rambus.com>
> ---
> .../userspace-api/ioctl/cmh_mgmt.rst | 941 ++++++++++++++++++
> .../userspace-api/ioctl/ioctl-number.rst | 1 +
> 2 files changed, 942 insertions(+)
> create mode 100644 Documentation/userspace-api/ioctl/cmh_mgmt.rst
>
One docs build warning:
Documentation/userspace-api/ioctl/cmh_mgmt.rst: WARNING: document isn't included in any toctree [toc.not_included]
--
~Randy
^ permalink raw reply
* Re: [PATCH v4 1/2] dt-bindings: PCI: qcom: Document the Hawi PCIe Controller
From: sashiko-bot @ 2026-06-25 20:53 UTC (permalink / raw)
To: Matthew Leung; +Cc: devicetree, conor+dt, linux-pci, robh
In-Reply-To: <20260625-hawi-pcie-v4-1-1a578603cd86@oss.qualcomm.com>
> Add a dedicated schema for the PCIe controllers found on the Hawi
> platform.
>
> Signed-off-by: Matthew Leung <matthew.leung@oss.qualcomm.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260625-hawi-pcie-v4-0-1a578603cd86@oss.qualcomm.com?part=1
^ permalink raw reply
* Re: [PATCH v4 2/2] PCI: qcom: Add support for Hawi
From: sashiko-bot @ 2026-06-25 20:52 UTC (permalink / raw)
To: Matthew Leung; +Cc: linux-pci, robh, conor+dt, devicetree
In-Reply-To: <20260625-hawi-pcie-v4-2-1a578603cd86@oss.qualcomm.com>
> Add support for the Hawi platform which has two PCIe controllers: one
> capable of Gen3 x2 operation and one capable of Gen4 x1 operation.
>
> Signed-off-by: Matthew Leung <matthew.leung@oss.qualcomm.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260625-hawi-pcie-v4-0-1a578603cd86@oss.qualcomm.com?part=2
^ permalink raw reply
* Re: [PATCH] arm64: dts: ti: k3-am62a7-sk: Add bootph-all property in cpsw_mac_syscon node
From: Andrew Davis @ 2026-06-25 20:48 UTC (permalink / raw)
To: Chintan Vankar, Conor Dooley, Krzysztof Kozlowski, Rob Herring,
Tero Kristo, Vignesh Raghavendra, Nishanth Menon
Cc: linux-kernel, devicetree, linux-arm-kernel
In-Reply-To: <20260625113223.1711052-1-c-vankar@ti.com>
On 6/25/26 6:32 AM, Chintan Vankar wrote:
> Ethernet boot requires CPSW node to be present starting from R5 SPL stage.
> Add "bootph-all" property in CPSW MAC's eFuse node "cpsw_mac_syscon" to
> enable this node during SPL stage along with later boot stage so that CPSW
> port will get static MAC address.
>
> Signed-off-by: Chintan Vankar <c-vankar@ti.com>
> ---
>
> Hello All,
>
> This patch is based on linux-next tagged next-20260623.
>
> arch/arm64/boot/dts/ti/k3-am62a7-sk.dts | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
> index 821a9705bb7d..d3b3675e7a8f 100644
> --- a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
> +++ b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
> @@ -230,6 +230,10 @@ AM62AX_MCU_IOPAD(0x0030, PIN_OUTPUT, 0) /* (C8) WKUP_UART0_RTSn */
> };
> };
>
> +&cpsw_mac_syscon {
> + bootph-all;
Seems you need this because cpsw_port1 uses it though a phandle reference.
cpsw_port1 has bootph-all, why is this property not transitive though
phandles? Would not having that cause missing references when the phandles
are resolved to nodes that get dropped for some given boot stage?
Andrew
> +};
> +
> /* WKUP UART0 is used for DM firmware logs */
> &wkup_uart0 {
> pinctrl-names = "default";
^ permalink raw reply
* [PATCH v4 1/2] dt-bindings: PCI: qcom: Document the Hawi PCIe Controller
From: Matthew Leung @ 2026-06-25 20:38 UTC (permalink / raw)
To: Bjorn Helgaas, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Bjorn Andersson
Cc: linux-arm-msm, linux-pci, devicetree, linux-kernel, Matthew Leung
In-Reply-To: <20260625-hawi-pcie-v4-0-1a578603cd86@oss.qualcomm.com>
Add a dedicated schema for the PCIe controllers found on the Hawi
platform.
Signed-off-by: Matthew Leung <matthew.leung@oss.qualcomm.com>
---
.../devicetree/bindings/pci/qcom,hawi-pcie.yaml | 196 +++++++++++++++++++++
1 file changed, 196 insertions(+)
diff --git a/Documentation/devicetree/bindings/pci/qcom,hawi-pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,hawi-pcie.yaml
new file mode 100644
index 000000000000..2c999ca6b205
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/qcom,hawi-pcie.yaml
@@ -0,0 +1,196 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/qcom,hawi-pcie.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Hawi PCI Express Root Complex
+
+maintainers:
+ - Bjorn Andersson <andersson@kernel.org>
+ - Manivannan Sadhasivam <mani@kernel.org>
+
+description:
+ Qualcomm Hawi SoC (and compatible) PCIe root complex controller is based on
+ the Synopsys DesignWare PCIe IP.
+
+properties:
+ compatible:
+ const: qcom,hawi-pcie
+
+ reg:
+ items:
+ - description: Qualcomm specific registers
+ - description: DesignWare PCIe registers
+ - description: External local bus interface registers
+ - description: ATU address space
+ - description: PCIe configuration space
+ - description: MHI registers
+
+ reg-names:
+ items:
+ - const: parf
+ - const: dbi
+ - const: elbi
+ - const: atu
+ - const: config
+ - const: mhi
+
+ clocks:
+ items:
+ - description: PCIe Auxiliary clock
+ - description: PCIe Configuration clock
+ - description: PCIe Master AXI clock
+ - description: PCIe Slave AXI clock
+ - description: PCIe Slave Q2A AXI clock
+ - description: PCIe Aggre NoC AXI clock
+ - description: PCIe Config NoC AXI clock
+
+ clock-names:
+ items:
+ - const: aux
+ - const: cfg
+ - const: bus_master
+ - const: bus_slave
+ - const: slave_q2a
+ - const: noc_aggr
+ - const: cnoc_sf_axi
+
+ interrupts:
+ minItems: 9
+ maxItems: 9
+
+ interrupt-names:
+ items:
+ - const: msi0
+ - const: msi1
+ - const: msi2
+ - const: msi3
+ - const: msi4
+ - const: msi5
+ - const: msi6
+ - const: msi7
+ - const: global
+
+ resets:
+ items:
+ - description: PCIe core reset
+ - description: PCIe link down reset
+
+ reset-names:
+ items:
+ - const: pci
+ - const: link_down
+
+required:
+ - power-domains
+ - resets
+ - reset-names
+
+allOf:
+ - $ref: qcom,pcie-common.yaml#
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/gpio/gpio.h>
+ #include <dt-bindings/interconnect/qcom,icc.h>
+ #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+ soc {
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ pcie@1c00000 {
+ compatible = "qcom,hawi-pcie";
+ reg = <0 0x01c00000 0 0x3000>,
+ <0 0x40000000 0 0xf1d>,
+ <0 0x40000f20 0 0xa8>,
+ <0 0x40001000 0 0x1000>,
+ <0 0x40100000 0 0x100000>,
+ <0 0x01c03000 0 0x1000>;
+ reg-names = "parf", "dbi", "elbi", "atu", "config", "mhi";
+ ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>,
+ <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x3d00000>;
+
+ bus-range = <0x00 0xff>;
+ device_type = "pci";
+ linux,pci-domain = <0>;
+ num-lanes = <2>;
+
+ #address-cells = <3>;
+ #size-cells = <2>;
+
+ clocks = <&gcc_pcie_0_aux_clk>,
+ <&gcc_pcie_0_cfg_ahb_clk>,
+ <&gcc_pcie_0_mstr_axi_clk>,
+ <&gcc_pcie_0_slv_axi_clk>,
+ <&gcc_pcie_0_slv_q2a_axi_clk>,
+ <&gcc_aggre_noc_pcie_axi_clk>,
+ <&gcc_cnoc_pcie_sf_axi_clk>;
+ clock-names = "aux",
+ "cfg",
+ "bus_master",
+ "bus_slave",
+ "slave_q2a",
+ "noc_aggr",
+ "cnoc_sf_axi";
+
+ dma-coherent;
+
+ interrupts = <GIC_ESPI 205 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_ESPI 206 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_ESPI 207 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_ESPI 208 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_ESPI 209 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_ESPI 210 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_ESPI 211 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_ESPI 212 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_ESPI 204 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "msi0", "msi1", "msi2", "msi3",
+ "msi4", "msi5", "msi6", "msi7", "global";
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 0 0x7>;
+ interrupt-map = <0 0 0 1 &intc 0 0 GIC_ESPI 213 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+ <0 0 0 2 &intc 0 0 GIC_ESPI 214 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+ <0 0 0 3 &intc 0 0 GIC_ESPI 215 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+ <0 0 0 4 &intc 0 0 GIC_ESPI 216 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+
+ interconnects = <&pcie_anoc_master_pcie_0 QCOM_ICC_TAG_ALWAYS
+ &mc_virt_slave_ebi1 QCOM_ICC_TAG_ALWAYS>,
+ <&gem_noc_master_appss_proc QCOM_ICC_TAG_ACTIVE_ONLY
+ &cnoc_main_slave_pcie_0 QCOM_ICC_TAG_ACTIVE_ONLY>;
+ interconnect-names = "pcie-mem", "cpu-pcie";
+
+ iommu-map = <0x0 &apps_smmu 0x1000 0x1>,
+ <0x100 &apps_smmu 0x1001 0x1>;
+
+ pinctrl-0 = <&pcie0_default_state>;
+ pinctrl-names = "default";
+
+ power-domains = <&gcc_pcie_0_phy_gdsc>;
+
+ resets = <&gcc_pcie_0_bcr>,
+ <&gcc_pcie_0_link_down_bcr>;
+ reset-names = "pci", "link_down";
+
+ msi-map = <0x0 &gic_its 0x1000 0x1>,
+ <0x100 &gic_its 0x1001 0x1>;
+ msi-map-mask = <0xff00>;
+
+ pcie@0 {
+ device_type = "pci";
+ reg = <0x0 0x0 0x0 0x0 0x0>;
+ bus-range = <0x01 0xff>;
+
+ #address-cells = <3>;
+ #size-cells = <2>;
+ ranges;
+
+ phys = <&pcie0_phy>;
+ wake-gpios = <&tlmm 104 GPIO_ACTIVE_HIGH>;
+ reset-gpios = <&tlmm 102 GPIO_ACTIVE_LOW>;
+ };
+ };
+ };
--
2.34.1
^ permalink raw reply related
page: next (older) | 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