* [PATCH v6 0/6] New features for the AD5686 IIO driver
@ 2026-07-05 11:38 Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros Rodrigo Alencar via B4 Relay
` (6 more replies)
0 siblings, 7 replies; 13+ messages in thread
From: Rodrigo Alencar via B4 Relay @ 2026-07-05 11:38 UTC (permalink / raw)
To: Michael Auchter, linux, linux-iio, devicetree, linux-kernel,
linux-hardening
Cc: Michael Hennerich, Jonathan Cameron, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva, Rodrigo Alencar,
Maxwell Doose, Joshua Crofts
This is the second series of three on updating the AD5686 driver.
Initially, a big patch series was sent:
https://lore.kernel.org/r/20260422-ad5313r-iio-support-v1-0-ed7dca001d1b@analog.com
Then, the first patch series added fixes and cleanups:
https://lore.kernel.org/linux-iio/20260524-ad5686-fixes-v7-0-b6bf395d08bd@analog.com/
This one is introducing new features:
- Consume optional reset and correct power supplies;
- LDAC GPIO handling (active-low, held low when unused);
- SPI bus sync() implementation for batching multiple transfers;
- Triggered buffer support, leveraging LDAC and sync() to flush
all channel writes atomically;
- Gain control support through the scale property.
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
Changes in v6:
- Refactor command/data macros in favor of FIELD_PREP()
- Link to v5: https://lore.kernel.org/r/20260628-ad5686-new-features-v5-0-577caadbf7c0@analog.com
Changes in v5:
- Create auxiliary handler for the triggered buffer.
- Do not allow modification of double_scale in case gain_gpio is not set.
- Link to v4: https://lore.kernel.org/r/20260623-ad5686-new-features-v4-0-28962a57db0f@analog.com
Changes in v4:
- Replace anyof+const for enum in dt-bindings.
- Address some sashiko's comments.
- Use guard(mutex)() in trigger handler and other misc changes.
- Link to v3: https://lore.kernel.org/r/20260616-ad5686-new-features-v3-0-f829fb7e9262@analog.com
Changes in v3:
- Add range-double property.
- Acquire reset control after power-up delay.
- Include cleanup.h and use guard(mutex)() in read_raw().
- Link to v2: https://lore.kernel.org/r/20260609-ad5686-new-features-v2-0-70b423f5c76d@analog.com
Changes in v2:
- Get reset control deasserted.
- Update entire spi_transfer struct rather than individual fields.
- Replace udelay() for fsleep() in probe().
- Minor changes addressing further feedback.
- Link to v1: https://lore.kernel.org/r/20260602-ad5686-new-features-v1-0-691e01883d27@analog.com
---
Rodrigo Alencar (6):
iio: dac: ad5686: refactor command/data macros
iio: dac: ad5686: introduce sync operation
iio: dac: ad5686: implement new sync() op for the spi bus
iio: dac: ad5686: read_raw/write_raw: use guard(mutex)()
iio: dac: ad5686: add triggered buffer support
iio: dac: ad5686: add gain control support
drivers/iio/dac/Kconfig | 2 +
drivers/iio/dac/ad5686-spi.c | 136 +++++++++++++++++++++-------
drivers/iio/dac/ad5686.c | 209 +++++++++++++++++++++++++++++++++++++++----
drivers/iio/dac/ad5686.h | 43 ++++++---
drivers/iio/dac/ad5696-i2c.c | 13 +--
5 files changed, 334 insertions(+), 69 deletions(-)
---
base-commit: 4c0ecdbdc0d87570f74e656e21d56bae1ab6a8f1
change-id: 20260602-ad5686-new-features-e116c04bddb9
Best regards,
--
Rodrigo Alencar <rodrigo.alencar@analog.com>
^ permalink raw reply [flat|nested] 13+ messages in thread
* [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros
2026-07-05 11:38 [PATCH v6 0/6] New features for the AD5686 IIO driver Rodrigo Alencar via B4 Relay
@ 2026-07-05 11:38 ` Rodrigo Alencar via B4 Relay
2026-07-05 14:24 ` Andy Shevchenko
2026-07-05 23:29 ` Jonathan Cameron
2026-07-05 11:38 ` [PATCH v6 2/6] iio: dac: ad5686: introduce sync operation Rodrigo Alencar via B4 Relay
` (5 subsequent siblings)
6 siblings, 2 replies; 13+ messages in thread
From: Rodrigo Alencar via B4 Relay @ 2026-07-05 11:38 UTC (permalink / raw)
To: Michael Auchter, linux, linux-iio, devicetree, linux-kernel,
linux-hardening
Cc: Michael Hennerich, Jonathan Cameron, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva, Rodrigo Alencar
From: Rodrigo Alencar <rodrigo.alencar@analog.com>
Replace usage of bit shifting macros for FIELD_PREP(), which would not
ignore bit masking when preparing SPI/I2C commands.
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
drivers/iio/dac/ad5686-spi.c | 21 +++++++++++----------
drivers/iio/dac/ad5686.h | 13 ++++++-------
drivers/iio/dac/ad5696-i2c.c | 11 ++++++-----
3 files changed, 23 insertions(+), 22 deletions(-)
diff --git a/drivers/iio/dac/ad5686-spi.c b/drivers/iio/dac/ad5686-spi.c
index 6b6ef1d7071f..d3b64b4361d5 100644
--- a/drivers/iio/dac/ad5686-spi.c
+++ b/drivers/iio/dac/ad5686-spi.c
@@ -9,6 +9,7 @@
*/
#include <linux/array_size.h>
+#include <linux/bitfield.h>
#include <linux/errno.h>
#include <linux/mod_devicetable.h>
#include <linux/module.h>
@@ -26,21 +27,21 @@ static int ad5686_spi_write(struct ad5686_state *st,
switch (st->chip_info->regmap_type) {
case AD5310_REGMAP:
- st->data[0].d16 = cpu_to_be16(AD5310_CMD(cmd) |
- val);
+ st->data[0].d16 = cpu_to_be16(FIELD_PREP(AD5310_CMD_MSK, cmd) |
+ FIELD_PREP(AD5310_DATA_MSK, val));
buf = &st->data[0].d8[0];
tx_len = 2;
break;
case AD5683_REGMAP:
- st->data[0].d32 = cpu_to_be32(AD5686_CMD(cmd) |
- AD5683_DATA(val));
+ st->data[0].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
+ FIELD_PREP(AD5683_DATA_MSK, val));
buf = &st->data[0].d8[1];
tx_len = 3;
break;
case AD5686_REGMAP:
- st->data[0].d32 = cpu_to_be32(AD5686_CMD(cmd) |
- AD5686_ADDR(addr) |
- val);
+ st->data[0].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
+ FIELD_PREP(AD5686_ADDR_MSK, addr) |
+ FIELD_PREP(AD5686_DATA_MSK, val));
buf = &st->data[0].d8[1];
tx_len = 3;
break;
@@ -81,9 +82,9 @@ static int ad5686_spi_read(struct ad5686_state *st, u8 addr)
return -EINVAL;
}
- st->data[0].d32 = cpu_to_be32(AD5686_CMD(cmd) |
- AD5686_ADDR(addr));
- st->data[1].d32 = cpu_to_be32(AD5686_CMD(AD5686_CMD_NOOP));
+ st->data[0].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
+ FIELD_PREP(AD5686_ADDR_MSK, addr));
+ st->data[1].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, AD5686_CMD_NOOP));
ret = spi_sync_transfer(spi, t, ARRAY_SIZE(t));
if (ret < 0)
diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index c424720f8f72..0d1bbf110926 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -14,13 +14,6 @@
#include <linux/iio/iio.h>
-#define AD5310_CMD(x) ((x) << 12)
-
-#define AD5683_DATA(x) ((x) << 4)
-
-#define AD5686_ADDR(x) ((x) << 16)
-#define AD5686_CMD(x) ((x) << 20)
-
#define AD5686_ADDR_DAC(chan) (0x1 << (chan))
#define AD5686_ADDR_ALL_DAC 0xF
@@ -38,12 +31,18 @@
#define AD5686_CMD_CONTROL_REG 0x4
#define AD5686_CMD_READBACK_ENABLE_V2 0x5
+#define AD5310_CMD_MSK GENMASK(15, 12)
+#define AD5310_DATA_MSK GENMASK(11, 0)
#define AD5310_REF_BIT_MSK BIT(8)
#define AD5310_PD_MSK GENMASK(10, 9)
+#define AD5683_DATA_MSK GENMASK(19, 4)
#define AD5683_REF_BIT_MSK BIT(12)
#define AD5683_PD_MSK GENMASK(14, 13)
+#define AD5686_CMD_MSK GENMASK(23, 20)
+#define AD5686_ADDR_MSK GENMASK(19, 16)
+#define AD5686_DATA_MSK GENMASK(15, 0)
#define AD5686_REF_BIT_MSK BIT(0)
#define AD5686_PD_MSK GENMASK(1, 0)
diff --git a/drivers/iio/dac/ad5696-i2c.c b/drivers/iio/dac/ad5696-i2c.c
index 279309329b64..bd8666a02b47 100644
--- a/drivers/iio/dac/ad5696-i2c.c
+++ b/drivers/iio/dac/ad5696-i2c.c
@@ -7,6 +7,7 @@
* Copyright 2018 Analog Devices Inc.
*/
+#include <linux/bitfield.h>
#include <linux/errno.h>
#include <linux/i2c.h>
#include <linux/mod_devicetable.h>
@@ -35,9 +36,8 @@ static int ad5686_i2c_read(struct ad5686_state *st, u8 addr)
};
int ret;
- st->data[0].d32 = cpu_to_be32(AD5686_CMD(AD5686_CMD_NOOP) |
- AD5686_ADDR(addr) |
- 0x00);
+ st->data[0].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, AD5686_CMD_NOOP) |
+ FIELD_PREP(AD5686_ADDR_MSK, addr));
ret = i2c_transfer(i2c->adapter, msg, 2);
if (ret < 0)
@@ -52,8 +52,9 @@ static int ad5686_i2c_write(struct ad5686_state *st,
struct i2c_client *i2c = to_i2c_client(st->dev);
int ret;
- st->data[0].d32 = cpu_to_be32(AD5686_CMD(cmd) | AD5686_ADDR(addr)
- | val);
+ st->data[0].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
+ FIELD_PREP(AD5686_ADDR_MSK, addr) |
+ FIELD_PREP(AD5686_DATA_MSK, val));
ret = i2c_master_send(i2c, &st->data[0].d8[1], 3);
if (ret < 0)
--
2.43.0
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH v6 2/6] iio: dac: ad5686: introduce sync operation
2026-07-05 11:38 [PATCH v6 0/6] New features for the AD5686 IIO driver Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros Rodrigo Alencar via B4 Relay
@ 2026-07-05 11:38 ` Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 3/6] iio: dac: ad5686: implement new sync() op for the spi bus Rodrigo Alencar via B4 Relay
` (4 subsequent siblings)
6 siblings, 0 replies; 13+ messages in thread
From: Rodrigo Alencar via B4 Relay @ 2026-07-05 11:38 UTC (permalink / raw)
To: Michael Auchter, linux, linux-iio, devicetree, linux-kernel,
linux-hardening
Cc: Michael Hennerich, Jonathan Cameron, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva, Rodrigo Alencar
From: Rodrigo Alencar <rodrigo.alencar@analog.com>
Add sync() to operation to ad5686_bus_ops, which can be used to flush
multiple pending data transfers at once. This is going to be used when
implementing triggered buffer support.
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
drivers/iio/dac/ad5686.h | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index 0d1bbf110926..56d37191ab37 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -67,10 +67,12 @@ struct ad5686_state;
* struct ad5686_bus_ops - bus specific read/write operations
* @read: read a register value at the given address
* @write: write a command, address and value to the device
+ * @sync: ensure the completion of the write operation (optional)
*/
struct ad5686_bus_ops {
int (*read)(struct ad5686_state *st, u8 addr);
int (*write)(struct ad5686_state *st, u8 cmd, u8 addr, u16 val);
+ int (*sync)(struct ad5686_state *st);
};
/**
@@ -159,7 +161,13 @@ int ad5686_probe(struct device *dev,
static inline int ad5686_write(struct ad5686_state *st, u8 cmd, u8 addr, u16 val)
{
- return st->ops->write(st, cmd, addr, val);
+ int ret;
+
+ ret = st->ops->write(st, cmd, addr, val);
+ if (ret)
+ return ret;
+
+ return st->ops->sync ? st->ops->sync(st) : 0;
}
static inline int ad5686_read(struct ad5686_state *st, u8 addr)
--
2.43.0
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH v6 3/6] iio: dac: ad5686: implement new sync() op for the spi bus
2026-07-05 11:38 [PATCH v6 0/6] New features for the AD5686 IIO driver Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 2/6] iio: dac: ad5686: introduce sync operation Rodrigo Alencar via B4 Relay
@ 2026-07-05 11:38 ` Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 4/6] iio: dac: ad5686: read_raw/write_raw: use guard(mutex)() Rodrigo Alencar via B4 Relay
` (3 subsequent siblings)
6 siblings, 0 replies; 13+ messages in thread
From: Rodrigo Alencar via B4 Relay @ 2026-07-05 11:38 UTC (permalink / raw)
To: Michael Auchter, linux, linux-iio, devicetree, linux-kernel,
linux-hardening
Cc: Michael Hennerich, Jonathan Cameron, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva, Rodrigo Alencar
From: Rodrigo Alencar <rodrigo.alencar@analog.com>
Use of local SPI bus data to manage a collection of SPI transfers and
flush them to the SPI platform driver with the sync() operation. This
allows for faster handling of multiple channel DAC writes, avoiding kernel
overhead per spi_sync() call, which will be helpful when enabling
triggered buffer support.
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
drivers/iio/dac/ad5686-spi.c | 129 ++++++++++++++++++++++++++++++++-----------
drivers/iio/dac/ad5686.c | 4 +-
drivers/iio/dac/ad5686.h | 8 ++-
drivers/iio/dac/ad5696-i2c.c | 2 +-
4 files changed, 108 insertions(+), 35 deletions(-)
diff --git a/drivers/iio/dac/ad5686-spi.c b/drivers/iio/dac/ad5686-spi.c
index d3b64b4361d5..ae74a17ba48e 100644
--- a/drivers/iio/dac/ad5686-spi.c
+++ b/drivers/iio/dac/ad5686-spi.c
@@ -13,59 +13,95 @@
#include <linux/errno.h>
#include <linux/mod_devicetable.h>
#include <linux/module.h>
+#include <linux/overflow.h>
#include <linux/spi/spi.h>
#include <asm/byteorder.h>
#include "ad5686.h"
+/**
+ * struct ad5686_spi_data - SPI bus specific data
+ * @msg: SPI message used for transfers
+ * @size: number of transfers currently in the message
+ * @capacity: maximum number of transfers that can be added to the message
+ * @xfers: array of SPI transfers, allocated with the provided capacity
+ */
+struct ad5686_spi_data {
+ struct spi_message msg;
+ unsigned int size;
+ unsigned int capacity;
+ struct spi_transfer xfers[] __counted_by(capacity);
+};
+
static int ad5686_spi_write(struct ad5686_state *st,
u8 cmd, u8 addr, u16 val)
{
- struct spi_device *spi = to_spi_device(st->dev);
- u8 tx_len, *buf;
+ struct ad5686_spi_data *bus_data = st->bus_data;
+ struct spi_transfer *xfer;
+ if (bus_data->size >= bus_data->capacity)
+ return -E2BIG;
+
+ if (bus_data->size)
+ bus_data->xfers[bus_data->size - 1].cs_change = 1;
+ else
+ spi_message_init(&bus_data->msg);
+
+ xfer = &bus_data->xfers[bus_data->size];
switch (st->chip_info->regmap_type) {
case AD5310_REGMAP:
- st->data[0].d16 = cpu_to_be16(FIELD_PREP(AD5310_CMD_MSK, cmd) |
- FIELD_PREP(AD5310_DATA_MSK, val));
- buf = &st->data[0].d8[0];
- tx_len = 2;
+ st->data[bus_data->size].d16 =
+ cpu_to_be16(FIELD_PREP(AD5310_CMD_MSK, cmd) |
+ FIELD_PREP(AD5310_DATA_MSK, val));
+ *xfer = (struct spi_transfer) {
+ .tx_buf = &st->data[bus_data->size].d16,
+ .len = sizeof(st->data[bus_data->size].d16),
+ };
break;
case AD5683_REGMAP:
- st->data[0].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
- FIELD_PREP(AD5683_DATA_MSK, val));
- buf = &st->data[0].d8[1];
- tx_len = 3;
+ st->data[bus_data->size].d32 =
+ cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
+ FIELD_PREP(AD5683_DATA_MSK, val));
+ *xfer = (struct spi_transfer) {
+ .tx_buf = &st->data[bus_data->size].d8[1],
+ .len = sizeof(st->data[bus_data->size].d8) - 1,
+ };
break;
case AD5686_REGMAP:
- st->data[0].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
- FIELD_PREP(AD5686_ADDR_MSK, addr) |
- FIELD_PREP(AD5686_DATA_MSK, val));
- buf = &st->data[0].d8[1];
- tx_len = 3;
+ st->data[bus_data->size].d32 =
+ cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
+ FIELD_PREP(AD5686_ADDR_MSK, addr) |
+ FIELD_PREP(AD5686_DATA_MSK, val));
+ *xfer = (struct spi_transfer) {
+ .tx_buf = &st->data[bus_data->size].d8[1],
+ .len = sizeof(st->data[bus_data->size].d8) - 1,
+ };
break;
default:
return -EINVAL;
}
- return spi_write(spi, buf, tx_len);
+ spi_message_add_tail(xfer, &bus_data->msg);
+ bus_data->size++;
+
+ return 0;
+}
+
+static int ad5686_spi_sync(struct ad5686_state *st)
+{
+ struct spi_device *spi = to_spi_device(st->dev);
+ struct ad5686_spi_data *bus_data = st->bus_data;
+
+ bus_data->size = 0; /* always reset, even on sync failure */
+ return spi_sync(spi, &bus_data->msg);
}
static int ad5686_spi_read(struct ad5686_state *st, u8 addr)
{
- struct spi_transfer t[] = {
- {
- .tx_buf = &st->data[0].d8[1],
- .len = 3,
- .cs_change = 1,
- }, {
- .tx_buf = &st->data[1].d8[1],
- .rx_buf = &st->data[2].d8[1],
- .len = 3,
- },
- };
struct spi_device *spi = to_spi_device(st->dev);
+ struct ad5686_spi_data *bus_data = st->bus_data;
+ struct spi_transfer *xfer = &bus_data->xfers[0];
u8 cmd = 0;
int ret;
@@ -86,8 +122,21 @@ static int ad5686_spi_read(struct ad5686_state *st, u8 addr)
FIELD_PREP(AD5686_ADDR_MSK, addr));
st->data[1].d32 = cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, AD5686_CMD_NOOP));
- ret = spi_sync_transfer(spi, t, ARRAY_SIZE(t));
- if (ret < 0)
+ xfer[0] = (struct spi_transfer) {
+ .tx_buf = &st->data[0].d8[1],
+ .len = sizeof(st->data[0].d8) - 1,
+ .cs_change = 1,
+ };
+ xfer[1] = (struct spi_transfer) {
+ .tx_buf = &st->data[1].d8[1],
+ .rx_buf = &st->data[2].d8[1],
+ .len = sizeof(st->data[1].d8) - 1,
+ };
+
+ spi_message_init_with_transfers(&bus_data->msg, xfer, 2);
+
+ ret = spi_sync(spi, &bus_data->msg);
+ if (ret)
return ret;
return be32_to_cpu(st->data[2].d32);
@@ -96,12 +145,30 @@ static int ad5686_spi_read(struct ad5686_state *st, u8 addr)
static const struct ad5686_bus_ops ad5686_spi_ops = {
.write = ad5686_spi_write,
.read = ad5686_spi_read,
+ .sync = ad5686_spi_sync,
};
static int ad5686_spi_probe(struct spi_device *spi)
{
- return ad5686_probe(&spi->dev, spi_get_device_match_data(spi),
- spi->modalias, &ad5686_spi_ops);
+ const struct ad5686_chip_info *info;
+ struct ad5686_spi_data *bus_data;
+ struct device *dev = &spi->dev;
+ unsigned int capacity;
+
+ info = spi_get_device_match_data(spi);
+ if (!info)
+ return -ENODEV;
+
+ /* read operation requires at least 2 transfers */
+ capacity = max(info->num_channels, 2);
+ bus_data = devm_kzalloc(dev, struct_size(bus_data, xfers, capacity),
+ GFP_KERNEL);
+ if (!bus_data)
+ return -ENOMEM;
+
+ bus_data->capacity = capacity;
+
+ return ad5686_probe(dev, info, spi->modalias, &ad5686_spi_ops, bus_data);
}
static const struct spi_device_id ad5686_spi_id[] = {
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 713fe71ad1e7..75dd7921c67b 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -472,7 +472,8 @@ EXPORT_SYMBOL_NS_GPL(ad5679r_chip_info, "IIO_AD5686");
int ad5686_probe(struct device *dev,
const struct ad5686_chip_info *chip_info,
- const char *name, const struct ad5686_bus_ops *ops)
+ const char *name, const struct ad5686_bus_ops *ops,
+ void *bus_data)
{
struct reset_control *rstc;
struct ad5686_state *st;
@@ -487,6 +488,7 @@ int ad5686_probe(struct device *dev,
st->dev = dev;
st->ops = ops;
+ st->bus_data = bus_data;
st->chip_info = chip_info;
rstc = devm_reset_control_get_optional_exclusive(dev, NULL);
diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index 56d37191ab37..b1fd1abfe129 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -16,6 +16,7 @@
#define AD5686_ADDR_DAC(chan) (0x1 << (chan))
#define AD5686_ADDR_ALL_DAC 0xF
+#define AD5686_MAX_CHANNELS 16
#define AD5686_CMD_NOOP 0x0
#define AD5686_CMD_WRITE_INPUT_N 0x1
@@ -129,6 +130,7 @@ extern const struct ad5686_chip_info ad5679r_chip_info;
* @use_internal_vref: set to true if the internal reference voltage is used
* @lock: lock to protect access to state fields, which includes
* the data buffer during regmap ops
+ * @bus_data: bus specific data
* @data: transfer buffers
*/
struct ad5686_state {
@@ -141,6 +143,7 @@ struct ad5686_state {
unsigned int pwr_down_mode;
bool use_internal_vref;
struct mutex lock;
+ void *bus_data;
/*
* DMA (thus cache coherency maintenance) may require the
@@ -151,13 +154,14 @@ struct ad5686_state {
__be32 d32;
__be16 d16;
u8 d8[4];
- } data[3] __aligned(IIO_DMA_MINALIGN);
+ } data[AD5686_MAX_CHANNELS] __aligned(IIO_DMA_MINALIGN);
};
int ad5686_probe(struct device *dev,
const struct ad5686_chip_info *chip_info,
- const char *name, const struct ad5686_bus_ops *ops);
+ const char *name, const struct ad5686_bus_ops *ops,
+ void *bus_data);
static inline int ad5686_write(struct ad5686_state *st, u8 cmd, u8 addr, u16 val)
{
diff --git a/drivers/iio/dac/ad5696-i2c.c b/drivers/iio/dac/ad5696-i2c.c
index bd8666a02b47..3f16127ad495 100644
--- a/drivers/iio/dac/ad5696-i2c.c
+++ b/drivers/iio/dac/ad5696-i2c.c
@@ -71,7 +71,7 @@ static const struct ad5686_bus_ops ad5686_i2c_ops = {
static int ad5686_i2c_probe(struct i2c_client *i2c)
{
return ad5686_probe(&i2c->dev, i2c_get_match_data(i2c),
- i2c->name, &ad5686_i2c_ops);
+ i2c->name, &ad5686_i2c_ops, NULL);
}
static const struct i2c_device_id ad5686_i2c_id[] = {
--
2.43.0
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH v6 4/6] iio: dac: ad5686: read_raw/write_raw: use guard(mutex)()
2026-07-05 11:38 [PATCH v6 0/6] New features for the AD5686 IIO driver Rodrigo Alencar via B4 Relay
` (2 preceding siblings ...)
2026-07-05 11:38 ` [PATCH v6 3/6] iio: dac: ad5686: implement new sync() op for the spi bus Rodrigo Alencar via B4 Relay
@ 2026-07-05 11:38 ` Rodrigo Alencar via B4 Relay
2026-07-05 11:47 ` sashiko-bot
2026-07-05 11:39 ` [PATCH v6 5/6] iio: dac: ad5686: add triggered buffer support Rodrigo Alencar via B4 Relay
` (2 subsequent siblings)
6 siblings, 1 reply; 13+ messages in thread
From: Rodrigo Alencar via B4 Relay @ 2026-07-05 11:38 UTC (permalink / raw)
To: Michael Auchter, linux, linux-iio, devicetree, linux-kernel,
linux-hardening
Cc: Michael Hennerich, Jonathan Cameron, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva, Rodrigo Alencar,
Maxwell Doose, Joshua Crofts
From: Rodrigo Alencar <rodrigo.alencar@analog.com>
Use guarded mutex lock to facilitate code review when adding new
attributes. This will allow for early returns, avoiding error-prone
locking and unlocking in error paths. This also adds missing include
linux/cleanup.h. Gain-control support will allow the scale attribute
to be configurable.
Reviewed-by: Maxwell Doose <m32285159@gmail.com>
Reviewed-by: Joshua Crofts <joshua.crofts1@gmail.com>
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
drivers/iio/dac/ad5686.c | 19 ++++++++-----------
1 file changed, 8 insertions(+), 11 deletions(-)
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 75dd7921c67b..db175e77b0b7 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -8,6 +8,7 @@
#include <linux/array_size.h>
#include <linux/bitfield.h>
#include <linux/bitops.h>
+#include <linux/cleanup.h>
#include <linux/delay.h>
#include <linux/dev_printk.h>
#include <linux/errno.h>
@@ -177,11 +178,11 @@ static int ad5686_read_raw(struct iio_dev *indio_dev,
struct ad5686_state *st = iio_priv(indio_dev);
int ret;
+ guard(mutex)(&st->lock);
+
switch (m) {
case IIO_CHAN_INFO_RAW:
- mutex_lock(&st->lock);
ret = ad5686_read(st, chan->address);
- mutex_unlock(&st->lock);
if (ret < 0)
return ret;
*val = (ret >> chan->scan_type.shift) &
@@ -202,23 +203,19 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
long mask)
{
struct ad5686_state *st = iio_priv(indio_dev);
- int ret;
+
+ guard(mutex)(&st->lock);
switch (mask) {
case IIO_CHAN_INFO_RAW:
if (val >= (1 << chan->scan_type.realbits) || val < 0)
return -EINVAL;
- mutex_lock(&st->lock);
- ret = ad5686_write(st, AD5686_CMD_WRITE_INPUT_N_UPDATE_N,
- chan->address, val << chan->scan_type.shift);
- mutex_unlock(&st->lock);
- break;
+ return ad5686_write(st, AD5686_CMD_WRITE_INPUT_N_UPDATE_N,
+ chan->address, val << chan->scan_type.shift);
default:
- ret = -EINVAL;
+ return -EINVAL;
}
-
- return ret;
}
static const struct iio_info ad5686_info = {
--
2.43.0
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH v6 5/6] iio: dac: ad5686: add triggered buffer support
2026-07-05 11:38 [PATCH v6 0/6] New features for the AD5686 IIO driver Rodrigo Alencar via B4 Relay
` (3 preceding siblings ...)
2026-07-05 11:38 ` [PATCH v6 4/6] iio: dac: ad5686: read_raw/write_raw: use guard(mutex)() Rodrigo Alencar via B4 Relay
@ 2026-07-05 11:39 ` Rodrigo Alencar via B4 Relay
2026-07-05 11:39 ` [PATCH v6 6/6] iio: dac: ad5686: add gain control support Rodrigo Alencar via B4 Relay
2026-07-05 23:30 ` [PATCH v6 0/6] New features for the AD5686 IIO driver Jonathan Cameron
6 siblings, 0 replies; 13+ messages in thread
From: Rodrigo Alencar via B4 Relay @ 2026-07-05 11:39 UTC (permalink / raw)
To: Michael Auchter, linux, linux-iio, devicetree, linux-kernel,
linux-hardening
Cc: Michael Hennerich, Jonathan Cameron, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva, Rodrigo Alencar
From: Rodrigo Alencar <rodrigo.alencar@analog.com>
Implement trigger handler by leveraging the LDAC gpio to update all DAC
channels at once when it is available. Also, the multiple channel writes
can be flushed at once with the sync() operation.
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
drivers/iio/dac/Kconfig | 2 ++
drivers/iio/dac/ad5686.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 68 insertions(+)
diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index 17529509da9d..d6d560c09e25 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -243,6 +243,8 @@ config LTC2688
config AD5686
tristate
+ select IIO_BUFFER
+ select IIO_TRIGGERED_BUFFER
config AD5686_SPI
tristate "Analog Devices AD5686 and similar multi-channel DACs (SPI)"
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index db175e77b0b7..3120e6983d9e 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -21,7 +21,11 @@
#include <linux/sysfs.h>
#include <linux/wordpart.h>
+#include <linux/iio/buffer.h>
#include <linux/iio/iio.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
#include "ad5686.h"
@@ -243,6 +247,7 @@ static const struct iio_chan_spec_ext_info ad5686_ext_info[] = {
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),\
.address = addr, \
+ .scan_index = chan, \
.scan_type = { \
.sign = 'u', \
.realbits = (bits), \
@@ -467,6 +472,60 @@ const struct ad5686_chip_info ad5679r_chip_info = {
};
EXPORT_SYMBOL_NS_GPL(ad5679r_chip_info, "IIO_AD5686");
+static void do_ad5686_trigger_handler(struct iio_dev *indio_dev)
+{
+ struct iio_buffer *buffer = indio_dev->buffer;
+ struct ad5686_state *st = iio_priv(indio_dev);
+ u16 val[AD5686_MAX_CHANNELS] = { };
+ unsigned int scan_count, ch, i;
+ bool async_update;
+ u8 cmd;
+
+ if (iio_pop_from_buffer(buffer, val))
+ return;
+
+ guard(mutex)(&st->lock);
+
+ scan_count = bitmap_weight(indio_dev->active_scan_mask,
+ iio_get_masklength(indio_dev));
+ async_update = st->ldac_gpio && scan_count > 1;
+ if (async_update) {
+ /* use LDAC to update all channels simultaneously */
+ cmd = AD5686_CMD_WRITE_INPUT_N;
+ gpiod_set_value_cansleep(st->ldac_gpio, 0);
+ } else {
+ cmd = AD5686_CMD_WRITE_INPUT_N_UPDATE_N;
+ }
+
+ i = 0;
+ iio_for_each_active_channel(indio_dev, ch) {
+ if (st->ops->write(st, cmd, indio_dev->channels[ch].address, val[i++]))
+ break;
+ }
+
+ /*
+ * If sync() is available, it is called here regardless of write
+ * failure to allow bus implementation to reset. In that case, partial
+ * writes are unlikely as the write operations would just queue up
+ * the transfers.
+ */
+ if (st->ops->sync)
+ st->ops->sync(st);
+
+ if (async_update)
+ gpiod_set_value_cansleep(st->ldac_gpio, 1);
+}
+
+static irqreturn_t ad5686_trigger_handler(int irq, void *p)
+{
+ struct iio_poll_func *pf = p;
+ struct iio_dev *indio_dev = pf->indio_dev;
+
+ do_ad5686_trigger_handler(indio_dev);
+ iio_trigger_notify_done(indio_dev->trig);
+ return IRQ_HANDLED;
+}
+
int ad5686_probe(struct device *dev,
const struct ad5686_chip_info *chip_info,
const char *name, const struct ad5686_bus_ops *ops,
@@ -569,6 +628,13 @@ int ad5686_probe(struct device *dev,
return -EINVAL;
}
+ ret = devm_iio_triggered_buffer_setup_ext(dev, indio_dev, NULL,
+ &ad5686_trigger_handler,
+ IIO_BUFFER_DIRECTION_OUT,
+ NULL, NULL);
+ if (ret)
+ return ret;
+
return devm_iio_device_register(dev, indio_dev);
}
EXPORT_SYMBOL_NS_GPL(ad5686_probe, "IIO_AD5686");
--
2.43.0
^ permalink raw reply related [flat|nested] 13+ messages in thread
* [PATCH v6 6/6] iio: dac: ad5686: add gain control support
2026-07-05 11:38 [PATCH v6 0/6] New features for the AD5686 IIO driver Rodrigo Alencar via B4 Relay
` (4 preceding siblings ...)
2026-07-05 11:39 ` [PATCH v6 5/6] iio: dac: ad5686: add triggered buffer support Rodrigo Alencar via B4 Relay
@ 2026-07-05 11:39 ` Rodrigo Alencar via B4 Relay
2026-07-05 11:50 ` sashiko-bot
2026-07-05 23:30 ` [PATCH v6 0/6] New features for the AD5686 IIO driver Jonathan Cameron
6 siblings, 1 reply; 13+ messages in thread
From: Rodrigo Alencar via B4 Relay @ 2026-07-05 11:39 UTC (permalink / raw)
To: Michael Auchter, linux, linux-iio, devicetree, linux-kernel,
linux-hardening
Cc: Michael Hennerich, Jonathan Cameron, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva, Rodrigo Alencar
From: Rodrigo Alencar <rodrigo.alencar@analog.com>
Most of the supported devices rely on a GAIN pin to control a 2x
multiplier applied to the output voltage. Other devices, e.g. the
single-channel ones, provides a gain control through a bit field in
the control register. Some designs might have the GAIN pin hardwired
to VDD/VLOGIC or GND, which would have no "gain-gpios" device property,
being able to set "adi,range-double" if it is hardwired to VDD. The
vref_mv field is moved down in the struct ad5686_state, so that the
overall size increase is reduced.
Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
---
drivers/iio/dac/ad5686.c | 120 +++++++++++++++++++++++++++++++++++++++++++++--
drivers/iio/dac/ad5686.h | 12 ++++-
2 files changed, 125 insertions(+), 7 deletions(-)
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 3120e6983d9e..9165ee07646a 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -15,10 +15,13 @@
#include <linux/export.h>
#include <linux/gpio/consumer.h>
#include <linux/kstrtox.h>
+#include <linux/math64.h>
#include <linux/module.h>
+#include <linux/property.h>
#include <linux/regulator/consumer.h>
#include <linux/reset.h>
#include <linux/sysfs.h>
+#include <linux/units.h>
#include <linux/wordpart.h>
#include <linux/iio/buffer.h>
@@ -41,7 +44,8 @@ static int ad5310_control_sync(struct ad5686_state *st)
return ad5686_write(st, AD5686_CMD_CONTROL_REG, 0,
FIELD_PREP(AD5310_PD_MSK, pd_val & AD5686_PD_MSK) |
- FIELD_PREP(AD5310_REF_BIT_MSK, st->use_internal_vref ? 0 : 1));
+ FIELD_PREP(AD5310_REF_BIT_MSK, st->use_internal_vref ? 0 : 1) |
+ FIELD_PREP(AD5310_GAIN_BIT_MSK, st->double_scale ? 1 : 0));
}
static int ad5683_control_sync(struct ad5686_state *st)
@@ -50,7 +54,8 @@ static int ad5683_control_sync(struct ad5686_state *st)
return ad5686_write(st, AD5686_CMD_CONTROL_REG, 0,
FIELD_PREP(AD5683_PD_MSK, pd_val & AD5686_PD_MSK) |
- FIELD_PREP(AD5683_REF_BIT_MSK, st->use_internal_vref ? 0 : 1));
+ FIELD_PREP(AD5683_REF_BIT_MSK, st->use_internal_vref ? 0 : 1) |
+ FIELD_PREP(AD5683_GAIN_BIT_MSK, st->double_scale ? 1 : 0));
}
static inline unsigned int ad5686_pd_mask_shift(const struct iio_chan_spec *chan)
@@ -193,9 +198,14 @@ static int ad5686_read_raw(struct iio_dev *indio_dev,
GENMASK(chan->scan_type.realbits - 1, 0);
return IIO_VAL_INT;
case IIO_CHAN_INFO_SCALE:
- *val = st->vref_mv;
- *val2 = chan->scan_type.realbits;
- return IIO_VAL_FRACTIONAL_LOG2;
+ if (st->double_scale) {
+ *val = st->scale_avail[2];
+ *val2 = st->scale_avail[3];
+ } else {
+ *val = st->scale_avail[0];
+ *val2 = st->scale_avail[1];
+ }
+ return IIO_VAL_INT_PLUS_NANO;
}
return -EINVAL;
}
@@ -207,6 +217,8 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
long mask)
{
struct ad5686_state *st = iio_priv(indio_dev);
+ bool double_scale;
+ int ret;
guard(mutex)(&st->lock);
@@ -217,6 +229,82 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
return ad5686_write(st, AD5686_CMD_WRITE_INPUT_N_UPDATE_N,
chan->address, val << chan->scan_type.shift);
+ case IIO_CHAN_INFO_SCALE:
+ if (val == st->scale_avail[0] && val2 == st->scale_avail[1])
+ double_scale = false;
+ else if (val == st->scale_avail[2] && val2 == st->scale_avail[3])
+ double_scale = true;
+ else
+ return -EINVAL;
+
+ if (st->double_scale == double_scale)
+ return 0; /* no change */
+
+ if (st->chip_info->regmap_type == AD5686_REGMAP && !st->gain_gpio)
+ return -EINVAL; /* GAIN pin is board-strapped */
+
+ st->double_scale = double_scale;
+ switch (st->chip_info->regmap_type) {
+ case AD5310_REGMAP:
+ ret = ad5310_control_sync(st);
+ break;
+ case AD5683_REGMAP:
+ ret = ad5683_control_sync(st);
+ break;
+ case AD5686_REGMAP:
+ ret = gpiod_set_value_cansleep(st->gain_gpio,
+ st->double_scale ? 1 : 0);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ if (ret)
+ st->double_scale = !double_scale; /* revert on failure */
+ return ret;
+ default:
+ return -EINVAL;
+ }
+}
+
+static int ad5686_write_raw_get_fmt(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan,
+ long mask)
+{
+ switch (mask) {
+ case IIO_CHAN_INFO_RAW:
+ return IIO_VAL_INT;
+ case IIO_CHAN_INFO_SCALE:
+ return IIO_VAL_INT_PLUS_NANO;
+ default:
+ return -EINVAL;
+ }
+}
+
+static int ad5686_read_avail(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan,
+ const int **vals, int *type, int *length,
+ long mask)
+{
+ struct ad5686_state *st = iio_priv(indio_dev);
+
+ switch (mask) {
+ case IIO_CHAN_INFO_SCALE:
+ *type = IIO_VAL_INT_PLUS_NANO;
+
+ if (st->chip_info->regmap_type == AD5686_REGMAP && !st->gain_gpio) {
+ /*
+ * GAIN pin is board-strapped, so only the current
+ * scale is available.
+ */
+ *vals = st->double_scale ? &st->scale_avail[2] :
+ &st->scale_avail[0];
+ *length = 2;
+ return IIO_AVAIL_LIST;
+ }
+
+ *vals = st->scale_avail;
+ *length = ARRAY_SIZE(st->scale_avail);
+ return IIO_AVAIL_LIST;
default:
return -EINVAL;
}
@@ -225,6 +313,8 @@ static int ad5686_write_raw(struct iio_dev *indio_dev,
static const struct iio_info ad5686_info = {
.read_raw = ad5686_read_raw,
.write_raw = ad5686_write_raw,
+ .write_raw_get_fmt = ad5686_write_raw_get_fmt,
+ .read_avail = ad5686_read_avail,
};
static const struct iio_chan_spec_ext_info ad5686_ext_info[] = {
@@ -246,6 +336,7 @@ static const struct iio_chan_spec_ext_info ad5686_ext_info[] = {
.channel = chan, \
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),\
+ .info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE),\
.address = addr, \
.scan_index = chan, \
.scan_type = { \
@@ -472,6 +563,15 @@ const struct ad5686_chip_info ad5679r_chip_info = {
};
EXPORT_SYMBOL_NS_GPL(ad5679r_chip_info, "IIO_AD5686");
+static void ad5686_init_scale_avail(struct ad5686_state *st)
+{
+ int realbits = st->chip_info->channels[0].scan_type.realbits;
+ s64 tmp = 2ULL * st->vref_mv * NANO >> realbits;
+
+ st->scale_avail[2] = div_s64_rem(tmp, NANO, &st->scale_avail[3]);
+ st->scale_avail[0] = div_s64_rem(tmp >> 1, NANO, &st->scale_avail[1]);
+}
+
static void do_ad5686_trigger_handler(struct iio_dev *indio_dev)
{
struct iio_buffer *buffer = indio_dev->buffer;
@@ -585,6 +685,16 @@ int ad5686_probe(struct device *dev,
return dev_err_probe(dev, PTR_ERR(st->ldac_gpio),
"Failed to get LDAC GPIO\n");
+ st->double_scale = device_property_read_bool(dev, "adi,range-double");
+ st->gain_gpio = devm_gpiod_get_optional(dev, "gain",
+ st->double_scale ? GPIOD_OUT_HIGH :
+ GPIOD_OUT_LOW);
+ if (IS_ERR(st->gain_gpio))
+ return dev_err_probe(dev, PTR_ERR(st->gain_gpio),
+ "Failed to get GAIN GPIO\n");
+
+ ad5686_init_scale_avail(st);
+
/* Initialize masks to all ones */
st->pwr_down_mask = ~0;
st->pwr_down_mode = ~0;
diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index b1fd1abfe129..6847ab14315b 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -34,10 +34,12 @@
#define AD5310_CMD_MSK GENMASK(15, 12)
#define AD5310_DATA_MSK GENMASK(11, 0)
+#define AD5310_GAIN_BIT_MSK BIT(7)
#define AD5310_REF_BIT_MSK BIT(8)
#define AD5310_PD_MSK GENMASK(10, 9)
#define AD5683_DATA_MSK GENMASK(19, 4)
+#define AD5683_GAIN_BIT_MSK BIT(11)
#define AD5683_REF_BIT_MSK BIT(12)
#define AD5683_PD_MSK GENMASK(14, 13)
@@ -124,9 +126,12 @@ extern const struct ad5686_chip_info ad5679r_chip_info;
* @chip_info: chip model specific constants, available modes etc
* @ops: bus specific operations
* @ldac_gpio: LDAC pin GPIO descriptor
- * @vref_mv: actual reference voltage used
+ * @gain_gpio: GAIN pin GPIO descriptor
* @pwr_down_mask: power down mask
* @pwr_down_mode: current power down mode
+ * @scale_avail: pre-calculated available scale values
+ * @vref_mv: actual reference voltage used
+ * @double_scale: flag to indicate the gain multiplier is applied
* @use_internal_vref: set to true if the internal reference voltage is used
* @lock: lock to protect access to state fields, which includes
* the data buffer during regmap ops
@@ -138,9 +143,12 @@ struct ad5686_state {
const struct ad5686_chip_info *chip_info;
const struct ad5686_bus_ops *ops;
struct gpio_desc *ldac_gpio;
- unsigned short vref_mv;
+ struct gpio_desc *gain_gpio;
unsigned int pwr_down_mask;
unsigned int pwr_down_mode;
+ int scale_avail[4];
+ unsigned short vref_mv;
+ bool double_scale;
bool use_internal_vref;
struct mutex lock;
void *bus_data;
--
2.43.0
^ permalink raw reply related [flat|nested] 13+ messages in thread
* Re: [PATCH v6 4/6] iio: dac: ad5686: read_raw/write_raw: use guard(mutex)()
2026-07-05 11:38 ` [PATCH v6 4/6] iio: dac: ad5686: read_raw/write_raw: use guard(mutex)() Rodrigo Alencar via B4 Relay
@ 2026-07-05 11:47 ` sashiko-bot
0 siblings, 0 replies; 13+ messages in thread
From: sashiko-bot @ 2026-07-05 11:47 UTC (permalink / raw)
To: Rodrigo Alencar; +Cc: devicetree, robh, conor+dt
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] Incorrect return value check for i2c_transfer() causes silent failures and bogus data returns.
--
commit 93acc0420c1accec74aba11d13ed25dc18d01455
Author: Rodrigo Alencar <rodrigo.alencar@analog.com>
iio: dac: ad5686: read_raw/write_raw: use guard(mutex)()
This commit transitions the read_raw and write_raw functions in the AD5686
driver to use guard(mutex) for locking. This simplifies the error paths by
allowing early returns without explicit unlock calls.
> diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
> index 75dd7921c67b8..db175e77b0b7c 100644
> --- a/drivers/iio/dac/ad5686.c
> +++ b/drivers/iio/dac/ad5686.c
[ ... ]
> @@ -177,11 +178,11 @@ static int ad5686_read_raw(struct iio_dev *indio_dev,
> struct ad5686_state *st = iio_priv(indio_dev);
> int ret;
>
> + guard(mutex)(&st->lock);
> +
> switch (m) {
> case IIO_CHAN_INFO_RAW:
> - mutex_lock(&st->lock);
> ret = ad5686_read(st, chan->address);
[Severity: High]
This isn't a bug introduced by this patch, but looking at ad5686_read()
which calls into ad5686_i2c_read() for I2C devices, is there an issue with
the return value check for i2c_transfer()?
drivers/iio/dac/ad5696-i2c.c:ad5686_i2c_read() {
...
ret = i2c_transfer(i2c->adapter, msg, 2);
if (ret < 0)
return ret;
return be16_to_cpu(st->data[0].d16);
}
If the first message (write) succeeds but the second (read) fails,
i2c_transfer() returns 1 (the number of successfully transferred messages).
Since 1 is not less than 0, the check passes and the function erroneously
returns the contents of st->data[0].d16, which holds the command bytes that
were written to the buffer just before the transfer.
Should this check verify that all 2 expected messages were transferred
instead, such as checking if (ret != 2)?
> - mutex_unlock(&st->lock);
> if (ret < 0)
> return ret;
> *val = (ret >> chan->scan_type.shift) &
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260705-ad5686-new-features-v6-0-269594c7aae5@analog.com?part=4
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH v6 6/6] iio: dac: ad5686: add gain control support
2026-07-05 11:39 ` [PATCH v6 6/6] iio: dac: ad5686: add gain control support Rodrigo Alencar via B4 Relay
@ 2026-07-05 11:50 ` sashiko-bot
0 siblings, 0 replies; 13+ messages in thread
From: sashiko-bot @ 2026-07-05 11:50 UTC (permalink / raw)
To: Rodrigo Alencar; +Cc: conor+dt, devicetree, robh
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Setting double_scale for AD5683_REGMAP SPI devices inadvertently triggers a hardware software reset.
--
commit 4e6717d62a587bcb6ce7e79580f4db51a50f4e5d
Author: Rodrigo Alencar <rodrigo.alencar@analog.com>
iio: dac: ad5686: add gain control support
This commit adds support for gain control on AD5686 and related DACs. It
adds a double_scale flag and updates the control sync functions to configure
the GAIN pin or the internal gain control bit accordingly.
> diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
> index 3120e6983d9e4..9165ee07646a0 100644
> --- a/drivers/iio/dac/ad5686.c
> +++ b/drivers/iio/dac/ad5686.c
[ ... ]
> @@ -50,7 +54,8 @@ static int ad5683_control_sync(struct ad5686_state *st)
>
> return ad5686_write(st, AD5686_CMD_CONTROL_REG, 0,
> FIELD_PREP(AD5683_PD_MSK, pd_val & AD5686_PD_MSK) |
> - FIELD_PREP(AD5683_REF_BIT_MSK, st->use_internal_vref ? 0 : 1));
> + FIELD_PREP(AD5683_REF_BIT_MSK, st->use_internal_vref ? 0 : 1) |
> + FIELD_PREP(AD5683_GAIN_BIT_MSK, st->double_scale ? 1 : 0));
[Severity: High]
Could setting this gain bit inadvertently trigger a hardware software reset on
SPI devices?
AD5683_GAIN_BIT_MSK is defined as BIT(11) in ad5686.h. When this value is
passed to the SPI backend, ad5686_spi_write() unconditionally shifts all
AD5683_REGMAP values left by 4 bits:
drivers/iio/dac/ad5686-spi.c:ad5686_spi_write()
cpu_to_be32(FIELD_PREP(AD5686_CMD_MSK, cmd) |
FIELD_PREP(AD5683_DATA_MSK, val));
Since AD5683_DATA_MSK is GENMASK(19, 4), the gain bit at position 11 gets
shifted to position 15. According to the AD5683 datasheet, DB15 of the Control
Register is the Software Reset bit.
Does the SPI backend need to be adjusted so that control register writes aren't
improperly shifted?
> }
>
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260705-ad5686-new-features-v6-0-269594c7aae5@analog.com?part=6
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros
2026-07-05 11:38 ` [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros Rodrigo Alencar via B4 Relay
@ 2026-07-05 14:24 ` Andy Shevchenko
2026-07-05 23:09 ` Jonathan Cameron
2026-07-05 23:29 ` Jonathan Cameron
1 sibling, 1 reply; 13+ messages in thread
From: Andy Shevchenko @ 2026-07-05 14:24 UTC (permalink / raw)
To: rodrigo.alencar
Cc: Michael Auchter, linux, linux-iio, devicetree, linux-kernel,
linux-hardening, Michael Hennerich, Jonathan Cameron,
David Lechner, Andy Shevchenko, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Philipp Zabel, Kees Cook, Gustavo A. R. Silva
On Sun, Jul 05, 2026 at 12:38:56PM +0100, Rodrigo Alencar via B4 Relay wrote:
> Replace usage of bit shifting macros for FIELD_PREP(), which would not
> ignore bit masking when preparing SPI/I2C commands.
It's not marked as a fix and has no explanation why.
--
With Best Regards,
Andy Shevchenko
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros
2026-07-05 14:24 ` Andy Shevchenko
@ 2026-07-05 23:09 ` Jonathan Cameron
0 siblings, 0 replies; 13+ messages in thread
From: Jonathan Cameron @ 2026-07-05 23:09 UTC (permalink / raw)
To: Andy Shevchenko
Cc: rodrigo.alencar, Michael Auchter, linux, linux-iio, devicetree,
linux-kernel, linux-hardening, Michael Hennerich, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva
On Sun, 5 Jul 2026 17:24:11 +0300
Andy Shevchenko <andriy.shevchenko@intel.com> wrote:
> On Sun, Jul 05, 2026 at 12:38:56PM +0100, Rodrigo Alencar via B4 Relay wrote:
>
> > Replace usage of bit shifting macros for FIELD_PREP(), which would not
> > ignore bit masking when preparing SPI/I2C commands.
>
> It's not marked as a fix and has no explanation why.
>
Agreed - this needs to stand on its own as a description, without needing
to know this is both hardening code and closing down real issues with debugfs
(IIRC from the sashiko reports that lead to this).
Maybe sensible to add both a tag for sashiko suggesting / reporting it
and a link to that review.
Thanks,
Jonathan
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros
2026-07-05 11:38 ` [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros Rodrigo Alencar via B4 Relay
2026-07-05 14:24 ` Andy Shevchenko
@ 2026-07-05 23:29 ` Jonathan Cameron
1 sibling, 0 replies; 13+ messages in thread
From: Jonathan Cameron @ 2026-07-05 23:29 UTC (permalink / raw)
To: Rodrigo Alencar via B4 Relay
Cc: rodrigo.alencar, Michael Auchter, linux, linux-iio, devicetree,
linux-kernel, linux-hardening, Michael Hennerich, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva
On Sun, 05 Jul 2026 12:38:56 +0100
Rodrigo Alencar via B4 Relay <devnull+rodrigo.alencar.analog.com@kernel.org> wrote:
> From: Rodrigo Alencar <rodrigo.alencar@analog.com>
>
> Replace usage of bit shifting macros for FIELD_PREP(), which would not
> ignore bit masking when preparing SPI/I2C commands.
>
> Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
...
> diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
> index c424720f8f72..0d1bbf110926 100644
> --- a/drivers/iio/dac/ad5686.h
> +++ b/drivers/iio/dac/ad5686.h
> @@ -14,13 +14,6 @@
>
> #include <linux/iio/iio.h>
>
> -#define AD5310_CMD(x) ((x) << 12)
> -
> -#define AD5683_DATA(x) ((x) << 4)
> -
> -#define AD5686_ADDR(x) ((x) << 16)
> -#define AD5686_CMD(x) ((x) << 20)
> -
> #define AD5686_ADDR_DAC(chan) (0x1 << (chan))
> #define AD5686_ADDR_ALL_DAC 0xF
>
> @@ -38,12 +31,18 @@
> #define AD5686_CMD_CONTROL_REG 0x4
> #define AD5686_CMD_READBACK_ENABLE_V2 0x5
>
> +#define AD5310_CMD_MSK GENMASK(15, 12)
> +#define AD5310_DATA_MSK GENMASK(11, 0)
There is a sashiko bug report on the final patch that got me looking at
these - it's a false positive but took some time to figure out why
it was getting confused. I think we need to do something to make it
more obvious what is going on..
> #define AD5310_REF_BIT_MSK BIT(8)
This is bit 8 of DATA - here DATA is 0 aligned so no mismatch.
> #define AD5310_PD_MSK GENMASK(10, 9)
>
> +#define AD5683_DATA_MSK GENMASK(19, 4)
> #define AD5683_REF_BIT_MSK BIT(12)
and this is bit 12 of AD5683_DATA rather than BIT(12) of the the whole thing
(given the 4 don't care bits.)
Could either rename things to
#define AD5683_DATA_REF_BIT_MSK() or add a comment on the bit positions
in the overall message - which will then align with the ones of the datasheet.
where ref is DB16.
> #define AD5683_PD_MSK GENMASK(14, 13)
>
> +#define AD5686_CMD_MSK GENMASK(23, 20)
> +#define AD5686_ADDR_MSK GENMASK(19, 16)
> +#define AD5686_DATA_MSK GENMASK(15, 0)
> #define AD5686_REF_BIT_MSK BIT(0)
> #define AD5686_PD_MSK GENMASK(1, 0)
>
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH v6 0/6] New features for the AD5686 IIO driver
2026-07-05 11:38 [PATCH v6 0/6] New features for the AD5686 IIO driver Rodrigo Alencar via B4 Relay
` (5 preceding siblings ...)
2026-07-05 11:39 ` [PATCH v6 6/6] iio: dac: ad5686: add gain control support Rodrigo Alencar via B4 Relay
@ 2026-07-05 23:30 ` Jonathan Cameron
6 siblings, 0 replies; 13+ messages in thread
From: Jonathan Cameron @ 2026-07-05 23:30 UTC (permalink / raw)
To: Rodrigo Alencar via B4 Relay
Cc: rodrigo.alencar, Michael Auchter, linux, linux-iio, devicetree,
linux-kernel, linux-hardening, Michael Hennerich, David Lechner,
Andy Shevchenko, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Philipp Zabel, Kees Cook, Gustavo A. R. Silva, Maxwell Doose,
Joshua Crofts
On Sun, 05 Jul 2026 12:38:55 +0100
Rodrigo Alencar via B4 Relay <devnull+rodrigo.alencar.analog.com@kernel.org> wrote:
> This is the second series of three on updating the AD5686 driver.
>
> Initially, a big patch series was sent:
> https://lore.kernel.org/r/20260422-ad5313r-iio-support-v1-0-ed7dca001d1b@analog.com
>
> Then, the first patch series added fixes and cleanups:
> https://lore.kernel.org/linux-iio/20260524-ad5686-fixes-v7-0-b6bf395d08bd@analog.com/
>
> This one is introducing new features:
> - Consume optional reset and correct power supplies;
> - LDAC GPIO handling (active-low, held low when unused);
> - SPI bus sync() implementation for batching multiple transfers;
> - Triggered buffer support, leveraging LDAC and sync() to flush
> all channel writes atomically;
> - Gain control support through the scale property.
>
> Signed-off-by: Rodrigo Alencar <rodrigo.alencar@analog.com>
I took another look through and also checked Sashiko output.
https://sashiko.dev/#/patchset/20260705-ad5686-new-features-v6-0-269594c7aae5%40analog.com
The i2c short access thing seems real so would be a nice additional trivial patch.
The other report is a false positive but I can see we have a naming
convention that is less than clear after the changes in patch 1.
Jonathan
^ permalink raw reply [flat|nested] 13+ messages in thread
end of thread, other threads:[~2026-07-05 23:30 UTC | newest]
Thread overview: 13+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-05 11:38 [PATCH v6 0/6] New features for the AD5686 IIO driver Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 1/6] iio: dac: ad5686: refactor command/data macros Rodrigo Alencar via B4 Relay
2026-07-05 14:24 ` Andy Shevchenko
2026-07-05 23:09 ` Jonathan Cameron
2026-07-05 23:29 ` Jonathan Cameron
2026-07-05 11:38 ` [PATCH v6 2/6] iio: dac: ad5686: introduce sync operation Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 3/6] iio: dac: ad5686: implement new sync() op for the spi bus Rodrigo Alencar via B4 Relay
2026-07-05 11:38 ` [PATCH v6 4/6] iio: dac: ad5686: read_raw/write_raw: use guard(mutex)() Rodrigo Alencar via B4 Relay
2026-07-05 11:47 ` sashiko-bot
2026-07-05 11:39 ` [PATCH v6 5/6] iio: dac: ad5686: add triggered buffer support Rodrigo Alencar via B4 Relay
2026-07-05 11:39 ` [PATCH v6 6/6] iio: dac: ad5686: add gain control support Rodrigo Alencar via B4 Relay
2026-07-05 11:50 ` sashiko-bot
2026-07-05 23:30 ` [PATCH v6 0/6] New features for the AD5686 IIO driver Jonathan Cameron
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox