* [PATCH 0/7] spmi: apple: Additional commands and interrupt support.
@ 2026-07-25 13:47 Sasha Finkelstein
2026-07-25 13:47 ` [PATCH 1/7] dt-bindings: spmi: apple,spmi: Add t603x Sasha Finkelstein
` (6 more replies)
0 siblings, 7 replies; 15+ messages in thread
From: Sasha Finkelstein @ 2026-07-25 13:47 UTC (permalink / raw)
To: Sven Peter, Janne Grunau, Neal Gompa, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: asahi, linux-arm-kernel, linux-kernel, devicetree,
Sasha Finkelstein, Alba Mendez
The SPMI bus has grown additional responsibilities in the M3
generation, making the current driver insufficient. Add M3 comatibles,
support for slave-sent interrupts, FIFO interrupts, power management
commands, parity validation, and fix locking.
To simplify the merge strategy, the device tree entries will be sent
in a future patch series.
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
Alba Mendez (6):
spmi: apple: Validate FIFO state
spmi: apple: check transaction status
spmi: apple: Implement remaining commands
spmi: apple: lock around FIFOs
spmi: apple: use IRQ for RX FIFO if possible
spmi: apple: interrupt controller functionality
Sasha Finkelstein (1):
dt-bindings: spmi: apple,spmi: Add t603x
Documentation/devicetree/bindings/spmi/apple,spmi.yaml | 14 +++++
drivers/spmi/Kconfig | 1 +
drivers/spmi/spmi-apple-controller.c | 367 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----------
3 files changed, 353 insertions(+), 29 deletions(-)
---
base-commit: 0ce37745d4bfbc493f718169c3974898ffec8ee7
change-id: 20260725-t603x-spmi-74630bf1b0a0
Best regards,
--
Sasha Finkelstein <k@chaosmail.tech>
^ permalink raw reply [flat|nested] 15+ messages in thread
* [PATCH 1/7] dt-bindings: spmi: apple,spmi: Add t603x
2026-07-25 13:47 [PATCH 0/7] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
@ 2026-07-25 13:47 ` Sasha Finkelstein
2026-07-25 13:52 ` sashiko-bot
2026-07-25 13:47 ` [PATCH 2/7] spmi: apple: Validate FIFO state Sasha Finkelstein
` (5 subsequent siblings)
6 siblings, 1 reply; 15+ messages in thread
From: Sasha Finkelstein @ 2026-07-25 13:47 UTC (permalink / raw)
To: Sven Peter, Janne Grunau, Neal Gompa, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: asahi, linux-arm-kernel, linux-kernel, devicetree,
Sasha Finkelstein
Add t603x compatibles, interrupt support, and support for SPMI
controllers that are not always-on
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
Documentation/devicetree/bindings/spmi/apple,spmi.yaml | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/Documentation/devicetree/bindings/spmi/apple,spmi.yaml b/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
index 3e5b14bc8c31..9fc511bb0cb8 100644
--- a/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
+++ b/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
@@ -20,6 +20,8 @@ properties:
- items:
- enum:
- apple,t6020-spmi
+ - apple,t6030-spmi
+ - apple,t6031-spmi
- apple,t8012-spmi
- apple,t8015-spmi
- const: apple,t8103-spmi
@@ -34,6 +36,18 @@ properties:
reg:
maxItems: 1
+ interrupts:
+ maxItems: 1
+ description: Optional, operates in polled mode if not present
+
+ interrupt-controller: true
+
+ "#interrupt-cells":
+ const: 2
+
+ power-domains:
+ maxItems: 1
+
required:
- compatible
- reg
--
2.55.0
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 2/7] spmi: apple: Validate FIFO state
2026-07-25 13:47 [PATCH 0/7] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
2026-07-25 13:47 ` [PATCH 1/7] dt-bindings: spmi: apple,spmi: Add t603x Sasha Finkelstein
@ 2026-07-25 13:47 ` Sasha Finkelstein
2026-07-25 14:00 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 3/7] spmi: apple: check transaction status Sasha Finkelstein
` (4 subsequent siblings)
6 siblings, 1 reply; 15+ messages in thread
From: Sasha Finkelstein @ 2026-07-25 13:47 UTC (permalink / raw)
To: Sven Peter, Janne Grunau, Neal Gompa, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: asahi, linux-arm-kernel, linux-kernel, devicetree,
Sasha Finkelstein, Alba Mendez
From: Alba Mendez <me@alba.sh>
Check for data before reading the body of a reply, and check for
end of data afterwards.
Signed-off-by: Alba Mendez <me@alba.sh>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/spmi-apple-controller.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index 376cf682c43e..b4f442d0b4ad 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -78,6 +78,10 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
/* Read SPMI data reply */
while (len_read < len) {
+ if (readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY) {
+ dev_err(&ctrl->dev, "FIFO lacks reply data, controller stuck?\n");
+ return -EIO;
+ }
rsp = readl(spmi->regs + SPMI_RSP_REG);
i = 0;
while ((len_read < len) && (i < 4)) {
@@ -86,6 +90,9 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
}
}
+ if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
+ dev_warn(&ctrl->dev, "FIFO has extra data\n");
+
return 0;
}
@@ -115,6 +122,9 @@ static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
/* Discard */
readl(spmi->regs + SPMI_RSP_REG);
+ if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
+ dev_warn(&ctrl->dev, "FIFO has extra data\n");
+
return 0;
}
--
2.55.0
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 3/7] spmi: apple: check transaction status
2026-07-25 13:47 [PATCH 0/7] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
2026-07-25 13:47 ` [PATCH 1/7] dt-bindings: spmi: apple,spmi: Add t603x Sasha Finkelstein
2026-07-25 13:47 ` [PATCH 2/7] spmi: apple: Validate FIFO state Sasha Finkelstein
@ 2026-07-25 13:48 ` Sasha Finkelstein
2026-07-25 14:02 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 4/7] spmi: apple: Implement remaining commands Sasha Finkelstein
` (3 subsequent siblings)
6 siblings, 1 reply; 15+ messages in thread
From: Sasha Finkelstein @ 2026-07-25 13:48 UTC (permalink / raw)
To: Sven Peter, Janne Grunau, Neal Gompa, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: asahi, linux-arm-kernel, linux-kernel, devicetree,
Sasha Finkelstein, Alba Mendez
From: Alba Mendez <me@alba.sh>
Check for parity errors and missing command ACKs
Signed-off-by: Alba Mendez <me@alba.sh>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/spmi-apple-controller.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index b4f442d0b4ad..4678a9e5270a 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -22,6 +22,12 @@
#define SPMI_CMD_REG 0x4
#define SPMI_RSP_REG 0x8
+/* SPMI_RSP_REG reply word */
+#define SPMI_REPLY_FRAME_PARITY_OFFSET 16
+#define SPMI_REPLY_ACK BIT(15)
+#define SPMI_REPLY_SLAVE_ID GENMASK(14, 8)
+#define SPMI_REPLY_CMD GENMASK(7, 0)
+
#define SPMI_RX_FIFO_EMPTY BIT(24)
#define REG_POLL_INTERVAL_US 10000
@@ -62,7 +68,7 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
{
struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, saddr, len);
- u32 rsp;
+ u32 reply, rsp;
size_t len_read = 0;
u8 i;
int ret;
@@ -73,8 +79,7 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
if (ret)
return ret;
- /* Discard SPMI reply status */
- readl(spmi->regs + SPMI_RSP_REG);
+ reply = readl(spmi->regs + SPMI_RSP_REG);
/* Read SPMI data reply */
while (len_read < len) {
@@ -93,6 +98,10 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
dev_warn(&ctrl->dev, "FIFO has extra data\n");
+ if ((~reply >> SPMI_REPLY_FRAME_PARITY_OFFSET) & ((1 << len) - 1)) {
+ dev_err(&ctrl->dev, "some frames failed parity check\n");
+ return -EIO;
+ }
return 0;
}
@@ -101,6 +110,7 @@ static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
{
struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, saddr, len);
+ u32 reply;
size_t i = 0, j;
int ret;
@@ -119,12 +129,15 @@ static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
if (ret)
return ret;
- /* Discard */
- readl(spmi->regs + SPMI_RSP_REG);
+ reply = readl(spmi->regs + SPMI_RSP_REG);
if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
dev_warn(&ctrl->dev, "FIFO has extra data\n");
+ if (!(reply & SPMI_REPLY_ACK)) {
+ dev_err(&ctrl->dev, "command not acknowledged\n");
+ return -EIO;
+ }
return 0;
}
--
2.55.0
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 4/7] spmi: apple: Implement remaining commands
2026-07-25 13:47 [PATCH 0/7] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
` (2 preceding siblings ...)
2026-07-25 13:48 ` [PATCH 3/7] spmi: apple: check transaction status Sasha Finkelstein
@ 2026-07-25 13:48 ` Sasha Finkelstein
2026-07-25 14:02 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 5/7] spmi: apple: lock around FIFOs Sasha Finkelstein
` (2 subsequent siblings)
6 siblings, 1 reply; 15+ messages in thread
From: Sasha Finkelstein @ 2026-07-25 13:48 UTC (permalink / raw)
To: Sven Peter, Janne Grunau, Neal Gompa, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: asahi, linux-arm-kernel, linux-kernel, devicetree,
Sasha Finkelstein, Alba Mendez
From: Alba Mendez <me@alba.sh>
Add support for zero write and power management commands
Signed-off-by: Alba Mendez <me@alba.sh>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/spmi-apple-controller.c | 106 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--------------------------------------
1 file changed, 68 insertions(+), 38 deletions(-)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index 4678a9e5270a..d69d16665ce8 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -41,9 +41,9 @@ struct apple_spmi {
readl_poll_timeout((spmi)->regs + (reg), (val), (cond), \
REG_POLL_INTERVAL_US, REG_POLL_TIMEOUT_US)
-static inline u32 apple_spmi_pack_cmd(u8 opc, u8 sid, u16 saddr, size_t len)
+static inline u32 apple_spmi_pack_cmd(u8 opc, u8 sid, u16 param)
{
- return opc | sid << 8 | saddr << 16 | (len - 1) | (1 << 15);
+ return opc | sid << 8 | param << 16 | (1 << 15);
}
/* Wait for Rx FIFO to have something */
@@ -63,18 +63,27 @@ static int apple_spmi_wait_rx_not_empty(struct spmi_controller *ctrl)
return 0;
}
-static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
- u16 saddr, u8 *buf, size_t len)
+static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
+ u16 param, const u8 *buf, size_t len, u8 *ibuf, size_t ilen)
{
struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
- u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, saddr, len);
+ u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, param);
u32 reply, rsp;
size_t len_read = 0;
- u8 i;
+ size_t i = 0, j;
int ret;
writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+ while (i < len) {
+ j = 0;
+ spmi_cmd = 0;
+ while ((j < 4) & (i < len))
+ spmi_cmd |= buf[i++] << (j++ * 8);
+
+ writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+ }
+
ret = apple_spmi_wait_rx_not_empty(ctrl);
if (ret)
return ret;
@@ -82,15 +91,15 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
reply = readl(spmi->regs + SPMI_RSP_REG);
/* Read SPMI data reply */
- while (len_read < len) {
+ while (len_read < ilen) {
if (readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY) {
dev_err(&ctrl->dev, "FIFO lacks reply data, controller stuck?\n");
return -EIO;
}
rsp = readl(spmi->regs + SPMI_RSP_REG);
i = 0;
- while ((len_read < len) && (i < 4)) {
- buf[len_read++] = ((0xff << (8 * i)) & rsp) >> (8 * i);
+ while ((len_read < ilen) && (i < 4)) {
+ ibuf[len_read++] = ((0xff << (8 * i)) & rsp) >> (8 * i);
i += 1;
}
}
@@ -98,47 +107,67 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
dev_warn(&ctrl->dev, "FIFO has extra data\n");
- if ((~reply >> SPMI_REPLY_FRAME_PARITY_OFFSET) & ((1 << len) - 1)) {
+ if (!ilen && !(reply & SPMI_REPLY_ACK)) {
+ dev_err(&ctrl->dev, "command not acknowledged\n");
+ return -EIO;
+ }
+ if ((~reply >> SPMI_REPLY_FRAME_PARITY_OFFSET) & ((1 << ilen) - 1)) {
dev_err(&ctrl->dev, "some frames failed parity check\n");
return -EIO;
}
return 0;
}
-static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
- u16 saddr, const u8 *buf, size_t len)
+/* Send a raw command with 1..16 input data frames */
+static int spmi_raw_cmd_input(struct spmi_controller *ctrl, u8 opc, u8 sid,
+ u16 param, u8 *buf, size_t len)
{
- struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
- u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, saddr, len);
- u32 reply;
- size_t i = 0, j;
- int ret;
-
- writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+ return spmi_raw_cmd(ctrl, opc, sid, param, NULL, 0, buf, len);
+}
- while (i < len) {
- j = 0;
- spmi_cmd = 0;
- while ((j < 4) & (i < len))
- spmi_cmd |= buf[i++] << (j++ * 8);
+/* Send a raw command with (optional) body and an input ACK */
+static int spmi_raw_cmd_ack(struct spmi_controller *ctrl, u8 opc, u8 sid,
+ u16 param, const u8 *buf, size_t len)
+{
+ return spmi_raw_cmd(ctrl, opc, sid, param, buf, len, NULL, 0);
+}
- writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
+ u16 saddr, u8 *buf, size_t len)
+{
+ switch (opc) {
+ case SPMI_CMD_EXT_READ:
+ case SPMI_CMD_EXT_READL:
+ return spmi_raw_cmd_input(ctrl, opc | (len - 1), sid, saddr, buf, len);
+ case SPMI_CMD_READ:
+ return spmi_raw_cmd_input(ctrl, opc | saddr, sid, saddr, buf, len);
}
+ return -EINVAL;
+}
- ret = apple_spmi_wait_rx_not_empty(ctrl);
- if (ret)
- return ret;
-
- reply = readl(spmi->regs + SPMI_RSP_REG);
-
- if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
- dev_warn(&ctrl->dev, "FIFO has extra data\n");
-
- if (!(reply & SPMI_REPLY_ACK)) {
- dev_err(&ctrl->dev, "command not acknowledged\n");
- return -EIO;
+static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
+ u16 saddr, const u8 *buf, size_t len)
+{
+ switch (opc) {
+ case SPMI_CMD_WRITE:
+ return spmi_raw_cmd_ack(ctrl, opc | saddr, sid, buf[0] << 8 | saddr, NULL, 0);
+ case SPMI_CMD_ZERO_WRITE:
+ return spmi_raw_cmd_ack(ctrl, opc | buf[0], sid, buf[0] << 8 | saddr, NULL, 0);
+ case SPMI_CMD_EXT_WRITE:
+ case SPMI_CMD_EXT_WRITEL:
+ return spmi_raw_cmd_ack(ctrl, opc | (len - 1), sid, saddr, buf, len);
}
- return 0;
+ return -EINVAL;
+}
+
+static int spmi_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid)
+{
+ if (
+ opc == SPMI_CMD_RESET || opc == SPMI_CMD_SLEEP ||
+ opc == SPMI_CMD_SHUTDOWN || opc == SPMI_CMD_WAKEUP
+ )
+ return spmi_raw_cmd_ack(ctrl, opc, sid, 0, NULL, 0);
+ return -EINVAL;
}
static int apple_spmi_probe(struct platform_device *pdev)
@@ -161,6 +190,7 @@ static int apple_spmi_probe(struct platform_device *pdev)
ctrl->read_cmd = spmi_read_cmd;
ctrl->write_cmd = spmi_write_cmd;
+ ctrl->cmd = spmi_cmd;
ret = devm_spmi_controller_add(&pdev->dev, ctrl);
if (ret)
--
2.55.0
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 5/7] spmi: apple: lock around FIFOs
2026-07-25 13:47 [PATCH 0/7] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
` (3 preceding siblings ...)
2026-07-25 13:48 ` [PATCH 4/7] spmi: apple: Implement remaining commands Sasha Finkelstein
@ 2026-07-25 13:48 ` Sasha Finkelstein
2026-07-25 14:01 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 6/7] spmi: apple: use IRQ for RX FIFO if possible Sasha Finkelstein
2026-07-25 13:48 ` [PATCH 7/7] spmi: apple: interrupt controller functionality Sasha Finkelstein
6 siblings, 1 reply; 15+ messages in thread
From: Sasha Finkelstein @ 2026-07-25 13:48 UTC (permalink / raw)
To: Sven Peter, Janne Grunau, Neal Gompa, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: asahi, linux-arm-kernel, linux-kernel, devicetree,
Sasha Finkelstein, Alba Mendez
From: Alba Mendez <me@alba.sh>
The driver was missing locking around register interactions
Signed-off-by: Alba Mendez <me@alba.sh>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/spmi-apple-controller.c | 18 ++++++++++++++++--
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index d69d16665ce8..d8509f027df6 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -14,6 +14,7 @@
#include <linux/io.h>
#include <linux/iopoll.h>
#include <linux/module.h>
+#include <linux/mutex.h>
#include <linux/platform_device.h>
#include <linux/spmi.h>
@@ -35,6 +36,7 @@
struct apple_spmi {
void __iomem *regs;
+ struct mutex fifo_lock;
};
#define poll_reg(spmi, reg, val, cond) \
@@ -73,6 +75,10 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
size_t i = 0, j;
int ret;
+ ret = mutex_lock_interruptible(&spmi->fifo_lock);
+ if (ret)
+ return ret;
+
writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
while (i < len) {
@@ -86,7 +92,7 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
ret = apple_spmi_wait_rx_not_empty(ctrl);
if (ret)
- return ret;
+ goto out;
reply = readl(spmi->regs + SPMI_RSP_REG);
@@ -94,7 +100,8 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
while (len_read < ilen) {
if (readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY) {
dev_err(&ctrl->dev, "FIFO lacks reply data, controller stuck?\n");
- return -EIO;
+ ret = -EIO;
+ goto out;
}
rsp = readl(spmi->regs + SPMI_RSP_REG);
i = 0;
@@ -107,6 +114,8 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
dev_warn(&ctrl->dev, "FIFO has extra data\n");
+ mutex_unlock(&spmi->fifo_lock);
+
if (!ilen && !(reply & SPMI_REPLY_ACK)) {
dev_err(&ctrl->dev, "command not acknowledged\n");
return -EIO;
@@ -116,6 +125,10 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
return -EIO;
}
return 0;
+
+out:
+ mutex_unlock(&spmi->fifo_lock);
+ return ret;
}
/* Send a raw command with 1..16 input data frames */
@@ -181,6 +194,7 @@ static int apple_spmi_probe(struct platform_device *pdev)
return -ENOMEM;
spmi = spmi_controller_get_drvdata(ctrl);
+ mutex_init(&spmi->fifo_lock);
spmi->regs = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(spmi->regs))
--
2.55.0
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 6/7] spmi: apple: use IRQ for RX FIFO if possible
2026-07-25 13:47 [PATCH 0/7] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
` (4 preceding siblings ...)
2026-07-25 13:48 ` [PATCH 5/7] spmi: apple: lock around FIFOs Sasha Finkelstein
@ 2026-07-25 13:48 ` Sasha Finkelstein
2026-07-25 14:00 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 7/7] spmi: apple: interrupt controller functionality Sasha Finkelstein
6 siblings, 1 reply; 15+ messages in thread
From: Sasha Finkelstein @ 2026-07-25 13:48 UTC (permalink / raw)
To: Sven Peter, Janne Grunau, Neal Gompa, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: asahi, linux-arm-kernel, linux-kernel, devicetree,
Sasha Finkelstein, Alba Mendez
From: Alba Mendez <me@alba.sh>
The IRQ fires as soon as the reply is available, which is usually takes
a few us instead of the 10ms sleep interval for polling
Signed-off-by: Alba Mendez <me@alba.sh>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/spmi-apple-controller.c | 97 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 96 insertions(+), 1 deletion(-)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index d8509f027df6..d627187b3ac0 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -11,6 +11,8 @@
* spmi-pmic-arb.c Copyright (c) 2021, The Linux Foundation.
*/
+#include <linux/completion.h>
+#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iopoll.h>
#include <linux/module.h>
@@ -23,6 +25,12 @@
#define SPMI_CMD_REG 0x4
#define SPMI_RSP_REG 0x8
+#define SPMI_IRQ_MASK_BASE 0x20
+#define SPMI_IRQ_ACK_BASE 0x60
+#define SPMI_IRQ_USER_SIZE 0x20
+
+#define SPMI_IRQ_FIFO_RX 0
+
/* SPMI_RSP_REG reply word */
#define SPMI_REPLY_FRAME_PARITY_OFFSET 16
#define SPMI_REPLY_ACK BIT(15)
@@ -37,6 +45,8 @@
struct apple_spmi {
void __iomem *regs;
struct mutex fifo_lock;
+ bool fifo_rx_irq;
+ struct completion fifo_rx;
};
#define poll_reg(spmi, reg, val, cond) \
@@ -55,7 +65,19 @@ static int apple_spmi_wait_rx_not_empty(struct spmi_controller *ctrl)
int ret;
u32 status;
- ret = poll_reg(spmi, SPMI_STATUS_REG, status, !(status & SPMI_RX_FIFO_EMPTY));
+ if (spmi->fifo_rx_irq) {
+ ret = wait_for_completion_timeout(&spmi->fifo_rx,
+ usecs_to_jiffies(REG_POLL_TIMEOUT_US));
+ if (!ret)
+ ret = -ETIMEDOUT;
+ else if (readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY)
+ ret = -EIO;
+ else
+ ret = 0;
+ } else {
+ ret = poll_reg(spmi, SPMI_STATUS_REG, status, !(status & SPMI_RX_FIFO_EMPTY));
+ }
+
if (ret) {
dev_err(&ctrl->dev,
"failed to wait for RX FIFO not empty\n");
@@ -79,6 +101,8 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
if (ret)
return ret;
+ reinit_completion(&spmi->fifo_rx);
+
writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
while (i < len) {
@@ -183,10 +207,68 @@ static int spmi_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid)
return -EINVAL;
}
+static void apple_spmi_irq_ack_raw(struct apple_spmi *spmi, u32 irq)
+{
+ u32 __iomem *reg = spmi->regs + SPMI_IRQ_ACK_BASE + (irq / 32) * 4;
+
+ writel(BIT(irq % 32), reg);
+}
+
+static void apple_spmi_irq_mask_raw(struct apple_spmi *spmi, u32 irq)
+{
+ u32 __iomem *reg = spmi->regs + SPMI_IRQ_MASK_BASE + (irq / 32) * 4;
+
+ writel(readl(reg) & ~BIT(irq % 32), reg);
+}
+
+static void apple_spmi_irq_unmask_raw(struct apple_spmi *spmi, u32 irq)
+{
+ u32 __iomem *reg = spmi->regs + SPMI_IRQ_MASK_BASE + (irq / 32) * 4;
+
+ writel(readl(reg) | BIT(irq % 32), reg);
+}
+
+static irqreturn_t apple_spmi_irq_handler(int irq, void *dev_id)
+{
+ struct apple_spmi *spmi = dev_id;
+ bool handled = false;
+ u32 val, offset, bit;
+
+ val = readl(spmi->regs + SPMI_IRQ_ACK_BASE + SPMI_IRQ_USER_SIZE);
+ if (val & BIT(SPMI_IRQ_FIFO_RX)) {
+ complete(&spmi->fifo_rx);
+ apple_spmi_irq_ack_raw(spmi, SPMI_IRQ_USER_SIZE * 8 + SPMI_IRQ_FIFO_RX);
+ handled = true;
+ }
+
+ return handled ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static int apple_spmi_init_irq(struct platform_device *pdev,
+ struct apple_spmi *spmi, int irq)
+{
+ int ret;
+
+ for (size_t offset = 0; offset < SPMI_IRQ_USER_SIZE + 4; offset += 4) {
+ writel(0, spmi->regs + SPMI_IRQ_MASK_BASE + offset);
+ writel(U32_MAX, spmi->regs + SPMI_IRQ_ACK_BASE + offset);
+ }
+
+ spmi->fifo_rx_irq = true;
+ apple_spmi_irq_unmask_raw(spmi, SPMI_IRQ_USER_SIZE * 8 + SPMI_IRQ_FIFO_RX);
+
+ ret = devm_request_any_context_irq(&pdev->dev, irq, apple_spmi_irq_handler, 0, NULL, spmi);
+ if (ret < 0)
+ return dev_err_probe(&pdev->dev, ret, "failed to request IRQ\n");
+
+ return 0;
+}
+
static int apple_spmi_probe(struct platform_device *pdev)
{
struct apple_spmi *spmi;
struct spmi_controller *ctrl;
+ int irq;
int ret;
ctrl = devm_spmi_controller_alloc(&pdev->dev, sizeof(*spmi));
@@ -195,6 +277,7 @@ static int apple_spmi_probe(struct platform_device *pdev)
spmi = spmi_controller_get_drvdata(ctrl);
mutex_init(&spmi->fifo_lock);
+ init_completion(&spmi->fifo_rx);
spmi->regs = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(spmi->regs))
@@ -206,11 +289,23 @@ static int apple_spmi_probe(struct platform_device *pdev)
ctrl->write_cmd = spmi_write_cmd;
ctrl->cmd = spmi_cmd;
+ irq = platform_get_irq_optional(pdev, 0);
+ if (irq < 0 && irq != -ENXIO)
+ return irq;
+ if (irq >= 0) {
+ ret = apple_spmi_init_irq(pdev, spmi, irq);
+ if (ret)
+ return ret;
+ }
+
ret = devm_spmi_controller_add(&pdev->dev, ctrl);
if (ret)
return dev_err_probe(&pdev->dev, ret,
"spmi_controller_add failed\n");
+ dev_dbg(&pdev->dev, irq >= 0 ? "Initialized with IRQ" :
+ "Initialized without IRQ, falling back to polling");
+
return 0;
}
--
2.55.0
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 7/7] spmi: apple: interrupt controller functionality
2026-07-25 13:47 [PATCH 0/7] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
` (5 preceding siblings ...)
2026-07-25 13:48 ` [PATCH 6/7] spmi: apple: use IRQ for RX FIFO if possible Sasha Finkelstein
@ 2026-07-25 13:48 ` Sasha Finkelstein
2026-07-25 13:59 ` sashiko-bot
6 siblings, 1 reply; 15+ messages in thread
From: Sasha Finkelstein @ 2026-07-25 13:48 UTC (permalink / raw)
To: Sven Peter, Janne Grunau, Neal Gompa, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley
Cc: asahi, linux-arm-kernel, linux-kernel, devicetree,
Sasha Finkelstein, Alba Mendez
From: Alba Mendez <me@alba.sh>
Add support for interrupts sent by slave devices.
Signed-off-by: Alba Mendez <me@alba.sh>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/Kconfig | 1 +
drivers/spmi/spmi-apple-controller.c | 149 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 149 insertions(+), 1 deletion(-)
diff --git a/drivers/spmi/Kconfig b/drivers/spmi/Kconfig
index a80cf4047b86..c9eff3d470a1 100644
--- a/drivers/spmi/Kconfig
+++ b/drivers/spmi/Kconfig
@@ -13,6 +13,7 @@ if SPMI
config SPMI_APPLE
tristate "Apple SoC SPMI Controller platform driver"
+ select IRQ_DOMAIN_HIERARCHY
depends on ARCH_APPLE || COMPILE_TEST
help
If you say yes to this option, support will be included for the
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index d627187b3ac0..13b48fd66aec 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -15,9 +15,12 @@
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iopoll.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/platform_device.h>
+#include <linux/spinlock.h>
#include <linux/spmi.h>
/* SPMI Controller Registers */
@@ -47,6 +50,9 @@ struct apple_spmi {
struct mutex fifo_lock;
bool fifo_rx_irq;
struct completion fifo_rx;
+ struct irq_domain *irqd;
+ raw_spinlock_t irq_mask_lock;
+ u64 irq_mask_cache[SPMI_IRQ_USER_SIZE / sizeof(u64)];
};
#define poll_reg(spmi, reg, val, cond) \
@@ -228,11 +234,123 @@ static void apple_spmi_irq_unmask_raw(struct apple_spmi *spmi, u32 irq)
writel(readl(reg) | BIT(irq % 32), reg);
}
+static void apple_spmi_irq_ack(struct irq_data *d)
+{
+ struct apple_spmi *spmi = irq_data_get_irq_chip_data(d);
+
+ apple_spmi_irq_ack_raw(spmi, d->hwirq);
+}
+
+static void apple_spmi_irq_mask(struct irq_data *d)
+{
+ struct apple_spmi *spmi = irq_data_get_irq_chip_data(d);
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&spmi->irq_mask_lock, flags);
+ apple_spmi_irq_mask_raw(spmi, d->hwirq);
+ spmi->irq_mask_cache[d->hwirq / 64] &= ~BIT(d->hwirq % 64);
+ raw_spin_unlock_irqrestore(&spmi->irq_mask_lock, flags);
+}
+
+static void apple_spmi_irq_unmask(struct irq_data *d)
+{
+ struct apple_spmi *spmi = irq_data_get_irq_chip_data(d);
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&spmi->irq_mask_lock, flags);
+ apple_spmi_irq_unmask_raw(spmi, d->hwirq);
+ spmi->irq_mask_cache[d->hwirq / 64] |= BIT(d->hwirq % 64);
+ raw_spin_unlock_irqrestore(&spmi->irq_mask_lock, flags);
+}
+
+static int apple_spmi_irq_set_type(struct irq_data *d, unsigned int type)
+{
+ /* all interrupts have MSI semantics */
+ return type == IRQ_TYPE_EDGE_RISING ? 0 : -EINVAL;
+}
+
+static struct irq_chip apple_spmi_irq_chip = {
+ .name = "apple_spmi",
+ .irq_mask = apple_spmi_irq_mask,
+ .irq_unmask = apple_spmi_irq_unmask,
+ .irq_ack = apple_spmi_irq_ack,
+ .irq_set_type = apple_spmi_irq_set_type,
+ .flags = IRQCHIP_ONESHOT_SAFE,
+};
+
+static int apple_spmi_irq_domain_map(struct irq_domain *irqd,
+ unsigned int irq, irq_hw_number_t hw)
+{
+ irq_domain_set_info(irqd, irq, hw, &apple_spmi_irq_chip, irqd->host_data,
+ handle_edge_irq, NULL, NULL);
+ return 0;
+}
+
+static int apple_spmi_irq_domain_translate(struct irq_domain *irqd,
+ struct irq_fwspec *fwspec,
+ unsigned long *hwirq,
+ unsigned int *type)
+{
+ u32 *args = fwspec->param;
+
+ if (fwspec->param_count != 2)
+ return -EINVAL;
+
+ if (args[0] >= SPMI_IRQ_USER_SIZE * 8)
+ return -EINVAL;
+ *hwirq = args[0];
+ *type = args[1] & IRQ_TYPE_SENSE_MASK;
+ return 0;
+}
+
+static int apple_spmi_irq_domain_alloc(struct irq_domain *irqd, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ unsigned int type = IRQ_TYPE_NONE;
+ struct irq_fwspec *fwspec = arg;
+ irq_hw_number_t hwirq;
+ int i, ret;
+
+ ret = apple_spmi_irq_domain_translate(irqd, fwspec, &hwirq, &type);
+ if (ret)
+ return ret;
+
+ if (hwirq + nr_irqs > SPMI_IRQ_USER_SIZE * 8)
+ return -EINVAL;
+
+ for (i = 0; i < nr_irqs; i++) {
+ ret = apple_spmi_irq_domain_map(irqd, virq + i, hwirq + i);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static void apple_spmi_irq_domain_free(struct irq_domain *irqd, unsigned int virq,
+ unsigned int nr_irqs)
+{
+ int i;
+
+ for (i = 0; i < nr_irqs; i++) {
+ struct irq_data *d = irq_domain_get_irq_data(irqd, virq + i);
+
+ irq_set_handler(virq + i, NULL);
+ irq_domain_reset_irq_data(d);
+ }
+}
+
+static const struct irq_domain_ops apple_spmi_irq_domain_ops = {
+ .translate = apple_spmi_irq_domain_translate,
+ .alloc = apple_spmi_irq_domain_alloc,
+ .free = apple_spmi_irq_domain_free,
+};
+
static irqreturn_t apple_spmi_irq_handler(int irq, void *dev_id)
{
struct apple_spmi *spmi = dev_id;
bool handled = false;
- u32 val, offset, bit;
+ u64 val, offset, bit;
val = readl(spmi->regs + SPMI_IRQ_ACK_BASE + SPMI_IRQ_USER_SIZE);
if (val & BIT(SPMI_IRQ_FIFO_RX)) {
@@ -241,6 +359,23 @@ static irqreturn_t apple_spmi_irq_handler(int irq, void *dev_id)
handled = true;
}
+ for (offset = 0; offset < SPMI_IRQ_USER_SIZE; offset += sizeof(val)) {
+ val = readq(spmi->regs + SPMI_IRQ_ACK_BASE + offset);
+ /**
+ * because of other masters in the bus, we're going to get a multitude of
+ * interrupts we're not interested in. irq_resolve_mapping isn't very
+ * optimized for the nonexistent path, so instead we mask with (a locally
+ * cached version of) the IRQ mask
+ */
+ val &= spmi->irq_mask_cache[offset / sizeof(val)];
+ while (val) {
+ bit = __builtin_ctzll(val);
+ generic_handle_domain_irq(spmi->irqd, offset * 8 + bit);
+ handled = true;
+ val &= ~BIT(bit);
+ }
+ }
+
return handled ? IRQ_HANDLED : IRQ_NONE;
}
@@ -248,12 +383,24 @@ static int apple_spmi_init_irq(struct platform_device *pdev,
struct apple_spmi *spmi, int irq)
{
int ret;
+ struct irq_domain_info info = {
+ .fwnode = pdev->dev.fwnode,
+ .hwirq_max = ~0U,
+ .ops = &apple_spmi_irq_domain_ops,
+ .host_data = spmi,
+ };
+
+ raw_spin_lock_init(&spmi->irq_mask_lock);
for (size_t offset = 0; offset < SPMI_IRQ_USER_SIZE + 4; offset += 4) {
writel(0, spmi->regs + SPMI_IRQ_MASK_BASE + offset);
writel(U32_MAX, spmi->regs + SPMI_IRQ_ACK_BASE + offset);
}
+ spmi->irqd = devm_irq_domain_instantiate(&pdev->dev, &info);
+ if (IS_ERR(spmi->irqd))
+ return PTR_ERR(spmi->irqd);
+
spmi->fifo_rx_irq = true;
apple_spmi_irq_unmask_raw(spmi, SPMI_IRQ_USER_SIZE * 8 + SPMI_IRQ_FIFO_RX);
--
2.55.0
^ permalink raw reply related [flat|nested] 15+ messages in thread
* Re: [PATCH 1/7] dt-bindings: spmi: apple,spmi: Add t603x
2026-07-25 13:47 ` [PATCH 1/7] dt-bindings: spmi: apple,spmi: Add t603x Sasha Finkelstein
@ 2026-07-25 13:52 ` sashiko-bot
0 siblings, 0 replies; 15+ messages in thread
From: sashiko-bot @ 2026-07-25 13:52 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: devicetree, conor+dt, robh
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The binding adds interrupt controller capabilities but fails to add `interrupt-controller` and `#interrupt-cells` to the `required` list and example.
--
--- Patch [1]: [PATCH 1/7] dt-bindings: spmi: apple,spmi: Add t603x ---
commit 66ad58d37c9aac7f4dc961a6e2efa29feb72a053
Author: Sasha Finkelstein <k@chaosmail.tech>
dt-bindings: spmi: apple,spmi: Add t603x
This commit adds t603x compatibles, interrupt support, and support for SPMI
controllers that are not always-on.
> diff --git a/Documentation/devicetree/bindings/spmi/apple,spmi.yaml b/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
> index 3e5b14bc8c317..9fc511bb0cb88 100644
> --- a/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
> +++ b/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
[ ... ]
> @@ -34,6 +36,18 @@ properties:
> reg:
> maxItems: 1
>
> + interrupts:
> + maxItems: 1
> + description: Optional, operates in polled mode if not present
> +
> + interrupt-controller: true
> +
> + "#interrupt-cells":
> + const: 2
> +
> + power-domains:
> + maxItems: 1
> +
> required:
> - compatible
> - reg
[Severity: Medium]
Should interrupt-controller and #interrupt-cells be added to the required
list here, either globally or conditionally in an allOf block if they only
apply to certain variants?
When hardware gains new provider capabilities, the corresponding properties
must be added to the required list to prevent incomplete device tree nodes
from silently passing schema validation.
Additionally, does the example node need to be updated to include these
new properties?
Documentation/devicetree/bindings/spmi/apple,spmi.yaml:examples() {
...
spmi@920a1300 {
compatible = "apple,t6000-spmi", "apple,spmi";
reg = <0x920a1300 0x100>;
#address-cells = <2>;
#size-cells = <0>;
...
}
If the properties become required, omitting them from the example will cause
the example to fail schema validation.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260725-t603x-spmi-v1-0-e1a29fcd2d38@chaosmail.tech?part=1
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 7/7] spmi: apple: interrupt controller functionality
2026-07-25 13:48 ` [PATCH 7/7] spmi: apple: interrupt controller functionality Sasha Finkelstein
@ 2026-07-25 13:59 ` sashiko-bot
0 siblings, 0 replies; 15+ messages in thread
From: sashiko-bot @ 2026-07-25 13:59 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: devicetree, robh, conor+dt
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Using the 32-bit `BIT()` macro with 64-bit integers causes data truncation and undefined behavior on 32-bit architectures.
- [Low] Missing inclusion of `<linux/io-64-nonatomic-lo-hi.h>` causes build failures on 32-bit architectures under `COMPILE_TEST`.
--
--- Patch [7]: [PATCH 7/7] spmi: apple: interrupt controller functionality ---
commit d1caa99a04e657899090218f53dc529fd1b04548
Author: Alba Mendez <me@alba.sh>
spmi: apple: interrupt controller functionality
Add support for interrupts sent by slave devices.
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> index d627187b3ac00..13b48fd66aec4 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -228,11 +234,123 @@ static void apple_spmi_irq_unmask_raw(struct apple_spmi *spmi, u32 irq)
> writel(readl(reg) | BIT(irq % 32), reg);
> }
>
> +static void apple_spmi_irq_ack(struct irq_data *d)
> +{
> + struct apple_spmi *spmi = irq_data_get_irq_chip_data(d);
> +
> + apple_spmi_irq_ack_raw(spmi, d->hwirq);
> +}
> +
> +static void apple_spmi_irq_mask(struct irq_data *d)
> +{
> + struct apple_spmi *spmi = irq_data_get_irq_chip_data(d);
> + unsigned long flags;
> +
> + raw_spin_lock_irqsave(&spmi->irq_mask_lock, flags);
> + apple_spmi_irq_mask_raw(spmi, d->hwirq);
> + spmi->irq_mask_cache[d->hwirq / 64] &= ~BIT(d->hwirq % 64);
[Severity: High]
Does using BIT() instead of BIT_ULL() here unintentionally clear the upper
32 bits of the 64-bit irq_mask_cache entry on 32-bit systems?
When d->hwirq % 64 is >= 32, this might also cause undefined behavior on
32-bit architectures, which can be reached via COMPILE_TEST.
> + raw_spin_unlock_irqrestore(&spmi->irq_mask_lock, flags);
> +}
> +
> +static void apple_spmi_irq_unmask(struct irq_data *d)
> +{
> + struct apple_spmi *spmi = irq_data_get_irq_chip_data(d);
> + unsigned long flags;
> +
> + raw_spin_lock_irqsave(&spmi->irq_mask_lock, flags);
> + apple_spmi_irq_unmask_raw(spmi, d->hwirq);
> + spmi->irq_mask_cache[d->hwirq / 64] |= BIT(d->hwirq % 64);
[Severity: High]
Similarly, could this cause undefined behavior on 32-bit systems when
d->hwirq % 64 is >= 32?
> + raw_spin_unlock_irqrestore(&spmi->irq_mask_lock, flags);
> +}
[ ... ]
> @@ -241,6 +359,23 @@ static irqreturn_t apple_spmi_irq_handler(int irq, void *dev_id)
> handled = true;
> }
>
> + for (offset = 0; offset < SPMI_IRQ_USER_SIZE; offset += sizeof(val)) {
> + val = readq(spmi->regs + SPMI_IRQ_ACK_BASE + offset);
[Severity: Low]
Does calling readq() here cause a build failure on 32-bit architectures
under COMPILE_TEST since <linux/io-64-nonatomic-lo-hi.h> is not included?
> + /**
> + * because of other masters in the bus, we're going to get a multitude of
> + * interrupts we're not interested in. irq_resolve_mapping isn't very
> + * optimized for the nonexistent path, so instead we mask with (a locally
> + * cached version of) the IRQ mask
> + */
> + val &= spmi->irq_mask_cache[offset / sizeof(val)];
> + while (val) {
> + bit = __builtin_ctzll(val);
> + generic_handle_domain_irq(spmi->irqd, offset * 8 + bit);
> + handled = true;
> + val &= ~BIT(bit);
[Severity: High]
Since val is a 64-bit integer, and bit can range from 0 to 63, would
~BIT(bit) on 32-bit systems produce a 32-bit inverted mask that zero-extends
when promoted to 64 bits? This might unintentionally clear the upper 32 bits
of val.
> + }
> + }
> +
> return handled ? IRQ_HANDLED : IRQ_NONE;
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260725-t603x-spmi-v1-0-e1a29fcd2d38@chaosmail.tech?part=7
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 2/7] spmi: apple: Validate FIFO state
2026-07-25 13:47 ` [PATCH 2/7] spmi: apple: Validate FIFO state Sasha Finkelstein
@ 2026-07-25 14:00 ` sashiko-bot
0 siblings, 0 replies; 15+ messages in thread
From: sashiko-bot @ 2026-07-25 14:00 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: conor+dt, devicetree, robh
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Pre-existing issues:
- [High] The driver detects unexpected extra data in the RX FIFO but fails to drain it, leaving the hardware permanently desynchronized for subsequent SPMI commands.
- [High] The driver lacks synchronization locks, allowing concurrent SPMI bus transactions to interleave and corrupt the command and FIFO state.
--
--- Patch [2]: [PATCH 2/7] spmi: apple: Validate FIFO state ---
commit c5c6cb6b2f161dd887167b0a07acf4d194f4cc70
Author: Alba Mendez <me@alba.sh>
spmi: apple: Validate FIFO state
This patch adds checks to ensure there is data before reading the body of a
reply, and checks for the end of data afterwards.
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> index 376cf682c43e0..b4f442d0b4ad7 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
> @@ -78,6 +78,10 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
[Severity: High]
This isn't a bug introduced by this patch, but I noticed spmi_read_cmd()
performs a multi-step bus transaction without acquiring any locks to prevent
concurrent interleaving.
Since the SPMI subsystem core does not serialize callbacks across different
slave devices, if two threads concurrently initiate SPMI transactions, could
their command writes and FIFO reads interleave? This might lead to data
corruption or misdirected responses on a busy bus.
> /* Read SPMI data reply */
> while (len_read < len) {
> + if (readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY) {
> + dev_err(&ctrl->dev, "FIFO lacks reply data, controller stuck?\n");
> + return -EIO;
> + }
> rsp = readl(spmi->regs + SPMI_RSP_REG);
[ ... ]
> }
> }
>
> + if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
> + dev_warn(&ctrl->dev, "FIFO has extra data\n");
[Severity: High]
This is a pre-existing issue, but since we are now checking for extra data
at the end of spmi_read_cmd(), shouldn't we also drain the FIFO here?
If a device misbehaves and leaves extra data in the RX FIFO, the next SPMI
read or write will immediately see this stale data. It could consume it as
its own response, leaving its actual response in the FIFO, creating a
permanent cascading desynchronization on the bus.
> return 0;
> }
>
> @@ -115,6 +122,9 @@ static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
[Severity: High]
This is a pre-existing issue, but similar to the read command above,
spmi_write_cmd() also appears to lack synchronization locks.
Would it be safer to wrap the entire transaction in a mutex to prevent
concurrent bus transactions from corrupting the command and FIFO state?
> /* Discard */
> readl(spmi->regs + SPMI_RSP_REG);
>
> + if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
> + dev_warn(&ctrl->dev, "FIFO has extra data\n");
[Severity: High]
This isn't a bug introduced by this patch, but does this code need to loop
and read from the FIFO until it is actually empty? Otherwise, the hardware
may remain permanently desynchronized for subsequent commands.
> return 0;
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260725-t603x-spmi-v1-0-e1a29fcd2d38@chaosmail.tech?part=2
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 6/7] spmi: apple: use IRQ for RX FIFO if possible
2026-07-25 13:48 ` [PATCH 6/7] spmi: apple: use IRQ for RX FIFO if possible Sasha Finkelstein
@ 2026-07-25 14:00 ` sashiko-bot
0 siblings, 0 replies; 15+ messages in thread
From: sashiko-bot @ 2026-07-25 14:00 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: conor+dt, devicetree, robh
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [High] Data race between lockless reinit_completion() and concurrent complete() from late interrupts.
- [High] Race condition in interrupt handler due to calling complete() before acknowledging the hardware interrupt.
- [Low] Unused variables `offset` and `bit` in `apple_spmi_irq_handler`.
--
--- Patch [6]: [PATCH 6/7] spmi: apple: use IRQ for RX FIFO if possible ---
commit 42f2435868ad30ce7de25280762bfba2c6169e13
Author: Alba Mendez <me@alba.sh>
spmi: apple: use IRQ for RX FIFO if possible
The IRQ fires as soon as the reply is available, which is usually takes
a few us instead of the 10ms sleep interval for polling
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> index d8509f027df69..d627187b3ac00 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -79,6 +101,8 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> if (ret)
> return ret;
>
> + reinit_completion(&spmi->fifo_rx);
> +
[Severity: High]
Does this code risk a data race if a previous SPMI command timed out?
If a prior command times out, it returns without masking the interrupt or
flushing the hardware. When a subsequent command acquires fifo_lock and
calls reinit_completion(), a delayed interrupt from the previous command
might concurrently execute complete().
Since reinit_completion() modifies the completion state locklessly without
taking the waitqueue lock, this race could corrupt the completion structure
or cause premature returns.
> writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
>
> while (i < len) {
[ ... ]
> @@ -183,10 +207,68 @@ static int spmi_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid)
[ ... ]
> +static irqreturn_t apple_spmi_irq_handler(int irq, void *dev_id)
> +{
> + struct apple_spmi *spmi = dev_id;
> + bool handled = false;
> + u32 val, offset, bit;
^^^^^^^^^^^
[Severity: Low]
Are offset and bit intended to be used here?
They appear to be declared but never used in the function body, which might
cause unused variable compiler warnings.
> +
> + val = readl(spmi->regs + SPMI_IRQ_ACK_BASE + SPMI_IRQ_USER_SIZE);
> + if (val & BIT(SPMI_IRQ_FIFO_RX)) {
> + complete(&spmi->fifo_rx);
> + apple_spmi_irq_ack_raw(spmi, SPMI_IRQ_USER_SIZE * 8 + SPMI_IRQ_FIFO_RX);
[Severity: High]
Could acknowledging the hardware interrupt after calling complete() cause
subsequent interrupts to be dropped?
The complete() call wakes up the waiting thread, which can immediately issue
a new SPMI command. If the hardware completes this new command and re-asserts
the IRQ before the handler executes apple_spmi_irq_ack_raw(), the ack
operation might clear the new interrupt assertion.
The second command would then time out indefinitely. Should the interrupt
be acknowledged before calling complete()?
> + handled = true;
> + }
> +
> + return handled ? IRQ_HANDLED : IRQ_NONE;
> +}
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260725-t603x-spmi-v1-0-e1a29fcd2d38@chaosmail.tech?part=6
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 5/7] spmi: apple: lock around FIFOs
2026-07-25 13:48 ` [PATCH 5/7] spmi: apple: lock around FIFOs Sasha Finkelstein
@ 2026-07-25 14:01 ` sashiko-bot
0 siblings, 0 replies; 15+ messages in thread
From: sashiko-bot @ 2026-07-25 14:01 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: conor+dt, devicetree, robh
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Using an interruptible mutex for a fast hardware bus lock introduces unexpected I/O failures.
--
--- Patch [5]: [PATCH 5/7] spmi: apple: lock around FIFOs ---
commit c446ad8ec5411cb7c1e85b2172699c9fc3a53edd
Author: Alba Mendez <me@alba.sh>
spmi: apple: lock around FIFOs
The driver was missing locking around register interactions.
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> index d69d16665ce85..d8509f027df69 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -73,6 +75,10 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> size_t i = 0, j;
> int ret;
>
> + ret = mutex_lock_interruptible(&spmi->fifo_lock);
> + if (ret)
> + return ret;
[Severity: High]
Can using an interruptible lock here cause unexpected I/O failures?
If an SPMI read or write blocks on this lock while another transaction is
ongoing, and the blocking process receives a signal, the lock acquisition
fails and returns -EINTR.
Higher-level frameworks like regulators or PMIC subsystems generally do not
expect or retry hardware bus operations failing with -EINTR. This could
cause critical operations, such as CPU voltage changes during cpufreq scaling,
to fail randomly if a signal is pending.
Would it be safer to use a standard uninterruptible mutex_lock() to serialize
this fast hardware bus I/O and prevent these systemic side effects?
> +
> writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
>
> while (i < len) {
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260725-t603x-spmi-v1-0-e1a29fcd2d38@chaosmail.tech?part=5
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 4/7] spmi: apple: Implement remaining commands
2026-07-25 13:48 ` [PATCH 4/7] spmi: apple: Implement remaining commands Sasha Finkelstein
@ 2026-07-25 14:02 ` sashiko-bot
0 siblings, 0 replies; 15+ messages in thread
From: sashiko-bot @ 2026-07-25 14:02 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: robh, devicetree, conor+dt
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] Concurrent SPMI commands from different contexts will interleave I/O register accesses, corrupting the hardware FIFO.
--
--- Patch [4]: [PATCH 4/7] spmi: apple: Implement remaining commands ---
commit 98224e3bba3190837586da097a367e28d4210468
Author: Alba Mendez <me@alba.sh>
spmi: apple: Implement remaining commands
Add support for zero write and power management commands to the Apple SPMI
controller.
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> index 4678a9e5270aa..d69d16665ce85 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -63,18 +63,27 @@ static int apple_spmi_wait_rx_not_empty(struct spmi_controller *ctrl)
> return 0;
> }
>
> -static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> - u16 saddr, u8 *buf, size_t len)
> +static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> + u16 param, const u8 *buf, size_t len, u8 *ibuf, size_t ilen)
> {
> struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
> - u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, saddr, len);
> + u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, param);
> u32 reply, rsp;
> size_t len_read = 0;
> - u8 i;
> + size_t i = 0, j;
> int ret;
>
> writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
>
> + while (i < len) {
> + j = 0;
> + spmi_cmd = 0;
> + while ((j < 4) & (i < len))
> + spmi_cmd |= buf[i++] << (j++ * 8);
> +
> + writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
> + }
[Severity: High]
This is a pre-existing issue, but can concurrent SPMI commands from different
contexts interleave I/O register accesses here and corrupt the hardware FIFO?
Multiple client drivers registered on the same SPMI bus might perform
concurrent reads and writes using their own regmap instances.
Because spmi_raw_cmd() is entered concurrently by multiple threads, it issues
multiple sequential writel() and readl() calls to the shared hardware FIFOs
without holding a bus-level spinlock or mutex.
Could this lead to malformed SPMI bus transactions if thread writes get
interleaved in this loop?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260725-t603x-spmi-v1-0-e1a29fcd2d38@chaosmail.tech?part=4
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 3/7] spmi: apple: check transaction status
2026-07-25 13:48 ` [PATCH 3/7] spmi: apple: check transaction status Sasha Finkelstein
@ 2026-07-25 14:02 ` sashiko-bot
0 siblings, 0 replies; 15+ messages in thread
From: sashiko-bot @ 2026-07-25 14:02 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: robh, devicetree, conor+dt
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Pre-existing issues:
- [High] Missing serialization locks for SPMI transactions leads to hardware state corruption.
- [High] Missing RX FIFO flush on timeouts and extra data permanently corrupts bus state.
--
--- Patch [3]: [PATCH 3/7] spmi: apple: check transaction status ---
commit acc23a1dd1c948ebf37045f3db6e344612bde6a3
Author: Alba Mendez <me@alba.sh>
spmi: apple: check transaction status
This commit adds parity error checks and command acknowledgement checks for
SPMI read and write transactions. It ensures the reply frame is read instead
of being discarded to properly evaluate the transaction status.
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> index b4f442d0b4ad7..4678a9e5270aa 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -73,8 +79,7 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> if (ret)
> return ret;
[Severity: High]
This isn't a bug introduced by this patch, but does this function need a
serialization lock for the full multi-step transaction?
The SPMI core subsystem does not serialize read_cmd and write_cmd callbacks,
leaving locking to the controller driver. If multiple threads concurrently
issue SPMI reads or writes via independent client drivers on the same bus,
could their sequences of writing to SPMI_CMD_REG and reading SPMI_RSP_REG
interleave, resulting in hardware state corruption?
Additionally, as another pre-existing issue, if a call to
apple_spmi_wait_rx_not_empty() times out due to a delayed hardware response,
the driver returns an error but doesn't appear to reset the controller or
flush the late response.
If a late response eventually fills the RX FIFO, will the next command's wait
for RX FIFO incorrectly succeed and consume the stale data as its own reply,
corrupting the bus state?
>
> - /* Discard SPMI reply status */
> - readl(spmi->regs + SPMI_RSP_REG);
> + reply = readl(spmi->regs + SPMI_RSP_REG);
>
> /* Read SPMI data reply */
> while (len_read < len) {
[ ... ]
> @@ -93,6 +98,10 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
> dev_warn(&ctrl->dev, "FIFO has extra data\n");
[Severity: High]
This is a pre-existing issue, but if extra data is detected in the FIFO, the
driver logs a warning but doesn't appear to drain the remaining words.
Since stale data is left in the RX FIFO, couldn't this guarantee corruption
of the next transaction on the bus?
> + if ((~reply >> SPMI_REPLY_FRAME_PARITY_OFFSET) & ((1 << len) - 1)) {
> + dev_err(&ctrl->dev, "some frames failed parity check\n");
> + return -EIO;
> + }
> return 0;
> }
[ ... ]
> @@ -101,6 +110,7 @@ static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> {
> struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
> u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, saddr, len);
> + u32 reply;
> size_t i = 0, j;
> int ret;
[Severity: High]
This is a pre-existing issue, but similar to spmi_read_cmd(), does this
function need a serialization lock for its multi-step write sequence?
Since there is no synchronization around the hardware interactions, multiple
un-synchronized writes to the shared SPMI_CMD_REG from concurrent threads
could interleave and destroy the controller's state machine.
> @@ -119,12 +129,15 @@ static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> if (ret)
> return ret;
>
> - /* Discard */
> - readl(spmi->regs + SPMI_RSP_REG);
> + reply = readl(spmi->regs + SPMI_RSP_REG);
>
> if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY))
> dev_warn(&ctrl->dev, "FIFO has extra data\n");
>
> + if (!(reply & SPMI_REPLY_ACK)) {
> + dev_err(&ctrl->dev, "command not acknowledged\n");
> + return -EIO;
> + }
> return 0;
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260725-t603x-spmi-v1-0-e1a29fcd2d38@chaosmail.tech?part=3
^ permalink raw reply [flat|nested] 15+ messages in thread
end of thread, other threads:[~2026-07-25 14:02 UTC | newest]
Thread overview: 15+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-25 13:47 [PATCH 0/7] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
2026-07-25 13:47 ` [PATCH 1/7] dt-bindings: spmi: apple,spmi: Add t603x Sasha Finkelstein
2026-07-25 13:52 ` sashiko-bot
2026-07-25 13:47 ` [PATCH 2/7] spmi: apple: Validate FIFO state Sasha Finkelstein
2026-07-25 14:00 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 3/7] spmi: apple: check transaction status Sasha Finkelstein
2026-07-25 14:02 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 4/7] spmi: apple: Implement remaining commands Sasha Finkelstein
2026-07-25 14:02 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 5/7] spmi: apple: lock around FIFOs Sasha Finkelstein
2026-07-25 14:01 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 6/7] spmi: apple: use IRQ for RX FIFO if possible Sasha Finkelstein
2026-07-25 14:00 ` sashiko-bot
2026-07-25 13:48 ` [PATCH 7/7] spmi: apple: interrupt controller functionality Sasha Finkelstein
2026-07-25 13:59 ` sashiko-bot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox