* [PATCH v7 0/6] spmi: apple: Additional commands and interrupt support.
@ 2026-08-18 18:32 Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 1/6] dt-bindings: spmi: apple,spmi: Add t603x and t8122 Sasha Finkelstein
` (5 more replies)
0 siblings, 6 replies; 11+ messages in thread
From: Sasha Finkelstein @ 2026-08-18 18:32 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>
---
Changes in v7:
- Require interrupt support on M3+
- Link to v6: https://patch.msgid.link/20260816-t603x-spmi-v6-0-c5ab87aa447b@chaosmail.tech
Changes in v6:
- Fix interrupt controller teardown
- Link to v5: https://patch.msgid.link/20260808-t603x-spmi-v5-0-553c5ac2f137@chaosmail.tech
Changes in v5:
- Style fixes per review
- Fix fifo flush
- Link to v4: https://patch.msgid.link/20260805-t603x-spmi-v4-0-c15a12d9a7d1@chaosmail.tech
Changes in v4:
- Re-do error recovery.
- Fix an address calculation mistake
- Link to v3: https://patch.msgid.link/20260803-t603x-spmi-v3-0-c17b506d91a1@chaosmail.tech
Changes in v3:
- Rework interrupt support
- Address review comments
- Link to v2: https://patch.msgid.link/20260728-t603x-spmi-v2-0-f43e5f10e583@chaosmail.tech
Changes in v2:
- Change locking to non-interruptible
- Reorder irq ack
- Clarify dt binding
- Some data type cleanups
- Link to v1: https://patch.msgid.link/20260725-t603x-spmi-v1-0-e1a29fcd2d38@chaosmail.tech
---
Alba Mendez (5):
spmi: apple: Validate FIFO state
spmi: apple: check transaction status
spmi: apple: Implement remaining commands
spmi: apple: lock around FIFOs
spmi: apple: Add interrupt functionality
Sasha Finkelstein (1):
dt-bindings: spmi: apple,spmi: Add t603x and t8122
Documentation/devicetree/bindings/spmi/apple,spmi.yaml | 37 +++++++++++-
drivers/spmi/Kconfig | 3 +-
drivers/spmi/spmi-apple-controller.c | 389 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----------
3 files changed, 394 insertions(+), 35 deletions(-)
---
base-commit: 0f23d56f17fdfc7db69d51f64c8b91bbab947aa9
change-id: 20260725-t603x-spmi-74630bf1b0a0
Best regards,
--
Sasha Finkelstein <k@chaosmail.tech>
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH v7 1/6] dt-bindings: spmi: apple,spmi: Add t603x and t8122
2026-08-18 18:32 [PATCH v7 0/6] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
@ 2026-08-18 18:32 ` Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 2/6] spmi: apple: Validate FIFO state Sasha Finkelstein
` (4 subsequent siblings)
5 siblings, 0 replies; 11+ messages in thread
From: Sasha Finkelstein @ 2026-08-18 18:32 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 and t8122 compatibles, interrupt support, and support for
SPMI controllers that are not always-on.
Reviewed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
Documentation/devicetree/bindings/spmi/apple,spmi.yaml | 37 ++++++++++++++++++++++++++++++++++---
1 file changed, 34 insertions(+), 3 deletions(-)
diff --git a/Documentation/devicetree/bindings/spmi/apple,spmi.yaml b/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
index 3e5b14bc8c31..1d14025b44c5 100644
--- a/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
+++ b/Documentation/devicetree/bindings/spmi/apple,spmi.yaml
@@ -20,8 +20,11 @@ properties:
- items:
- enum:
- apple,t6020-spmi
+ - apple,t6030-spmi
+ - apple,t6031-spmi
- apple,t8012-spmi
- apple,t8015-spmi
+ - apple,t8122-spmi
- const: apple,t8103-spmi
- items:
- enum:
@@ -34,9 +37,37 @@ properties:
reg:
maxItems: 1
-required:
- - compatible
- - reg
+ interrupts:
+ maxItems: 1
+ description: Optional, operates in polled mode if not present
+
+ interrupt-controller: true
+
+ "#interrupt-cells":
+ const: 2
+
+ power-domains:
+ maxItems: 1
+
+if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - apple,t8122-spmi
+ - apple,t6030-spmi
+ - apple,t6031-spmi
+then:
+ required:
+ - compatible
+ - reg
+ - interrupt-controller
+ - "#interrupt-cells"
+ - interrupts
+else:
+ required:
+ - compatible
+ - reg
unevaluatedProperties: false
--
2.55.0
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH v7 2/6] spmi: apple: Validate FIFO state
2026-08-18 18:32 [PATCH v7 0/6] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 1/6] dt-bindings: spmi: apple,spmi: Add t603x and t8122 Sasha Finkelstein
@ 2026-08-18 18:32 ` Sasha Finkelstein
2026-08-18 18:44 ` sashiko-bot
2026-08-18 18:32 ` [PATCH v7 3/6] spmi: apple: check transaction status Sasha Finkelstein
` (3 subsequent siblings)
5 siblings, 1 reply; 11+ messages in thread
From: Sasha Finkelstein @ 2026-08-18 18:32 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>
Reviewed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/spmi-apple-controller.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index 376cf682c43e..15721cb41d5c 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -21,7 +21,9 @@
#define SPMI_STATUS_REG 0
#define SPMI_CMD_REG 0x4
#define SPMI_RSP_REG 0x8
+#define SPMI_ACT_REG 0xa4
+#define SPMI_ACT_FIFO_FLUSH BIT(0)
#define SPMI_RX_FIFO_EMPTY BIT(24)
#define REG_POLL_INTERVAL_US 10000
@@ -29,6 +31,7 @@
struct apple_spmi {
void __iomem *regs;
+ bool prev_fail;
};
#define poll_reg(spmi, reg, val, cond) \
@@ -49,6 +52,7 @@ static int apple_spmi_wait_rx_not_empty(struct spmi_controller *ctrl)
ret = poll_reg(spmi, SPMI_STATUS_REG, status, !(status & SPMI_RX_FIFO_EMPTY));
if (ret) {
+ spmi->prev_fail = true;
dev_err(&ctrl->dev,
"failed to wait for RX FIFO not empty\n");
return ret;
@@ -67,6 +71,11 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
u8 i;
int ret;
+ if (spmi->prev_fail) {
+ writel(SPMI_ACT_FIFO_FLUSH, spmi->regs + SPMI_ACT_REG);
+ spmi->prev_fail = false;
+ }
+
writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
ret = apple_spmi_wait_rx_not_empty(ctrl);
@@ -78,6 +87,12 @@ 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) {
+ spmi->prev_fail = true;
+ dev_err_ratelimited(&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 +101,11 @@ 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");
+ spmi->prev_fail = true;
+ }
+
return 0;
}
@@ -97,6 +117,11 @@ static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
size_t i = 0, j;
int ret;
+ if (spmi->prev_fail) {
+ writel(SPMI_ACT_FIFO_FLUSH, spmi->regs + SPMI_ACT_REG);
+ spmi->prev_fail = false;
+ }
+
writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
while (i < len) {
@@ -115,6 +140,11 @@ 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");
+ spmi->prev_fail = true;
+ }
+
return 0;
}
--
2.55.0
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH v7 3/6] spmi: apple: check transaction status
2026-08-18 18:32 [PATCH v7 0/6] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 1/6] dt-bindings: spmi: apple,spmi: Add t603x and t8122 Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 2/6] spmi: apple: Validate FIFO state Sasha Finkelstein
@ 2026-08-18 18:32 ` Sasha Finkelstein
2026-08-18 18:46 ` sashiko-bot
2026-08-18 18:32 ` [PATCH v7 4/6] spmi: apple: Implement remaining commands Sasha Finkelstein
` (2 subsequent siblings)
5 siblings, 1 reply; 11+ messages in thread
From: Sasha Finkelstein @ 2026-08-18 18:32 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>
Reviewed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/spmi-apple-controller.c | 25 ++++++++++++++++++++-----
1 file changed, 20 insertions(+), 5 deletions(-)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index 15721cb41d5c..b1c127cf5f44 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/bitfield.h>
+#include <linux/bits.h>
#include <linux/io.h>
#include <linux/iopoll.h>
#include <linux/module.h>
@@ -23,6 +25,12 @@
#define SPMI_RSP_REG 0x8
#define SPMI_ACT_REG 0xa4
+/* SPMI_RSP_REG reply word */
+#define SPMI_REPLY_FRAME_PARITY_STATUS GENMASK(31, 16)
+#define SPMI_REPLY_ACK BIT(15)
+#define SPMI_REPLY_SLAVE_ID GENMASK(14, 8)
+#define SPMI_REPLY_CMD GENMASK(7, 0)
+
#define SPMI_ACT_FIFO_FLUSH BIT(0)
#define SPMI_RX_FIFO_EMPTY BIT(24)
@@ -66,7 +74,7 @@ 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;
@@ -82,8 +90,7 @@ 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) {
@@ -106,6 +113,10 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
spmi->prev_fail = true;
}
+ if (~FIELD_GET(SPMI_REPLY_FRAME_PARITY_STATUS, reply) & ((1 << len) - 1)) {
+ dev_err(&ctrl->dev, "some frames failed parity check\n");
+ return -EIO;
+ }
return 0;
}
@@ -114,6 +125,7 @@ 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;
@@ -137,14 +149,17 @@ 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");
spmi->prev_fail = true;
}
+ if (!FIELD_GET(SPMI_REPLY_ACK, reply)) {
+ dev_err(&ctrl->dev, "command not acknowledged\n");
+ return -EIO;
+ }
return 0;
}
--
2.55.0
^ permalink raw reply related [flat|nested] 11+ messages in thread
* [PATCH v7 4/6] spmi: apple: Implement remaining commands
2026-08-18 18:32 [PATCH v7 0/6] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
` (2 preceding siblings ...)
2026-08-18 18:32 ` [PATCH v7 3/6] spmi: apple: check transaction status Sasha Finkelstein
@ 2026-08-18 18:32 ` Sasha Finkelstein
2026-08-18 18:44 ` sashiko-bot
2026-08-18 18:32 ` [PATCH v7 5/6] spmi: apple: lock around FIFOs Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 6/6] spmi: apple: Add interrupt functionality Sasha Finkelstein
5 siblings, 1 reply; 11+ messages in thread
From: Sasha Finkelstein @ 2026-08-18 18:32 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 | 116 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-----------------------------------------------
1 file changed, 69 insertions(+), 47 deletions(-)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index b1c127cf5f44..9843dc871d6c 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -46,9 +46,9 @@ 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 | (u32)param << 16 | (1 << 15);
}
/* Wait for Rx FIFO to have something */
@@ -69,14 +69,13 @@ 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_wr, size_t len_wr, u8 *buf_rd, size_t len_rd)
{
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;
if (spmi->prev_fail) {
@@ -86,6 +85,14 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+ while (i < len_wr) {
+ j = min_t(size_t, sizeof(spmi_cmd), len_wr - i);
+ spmi_cmd = 0;
+ memcpy(&spmi_cmd, buf_wr + i, j);
+ writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+ i += j;
+ }
+
ret = apple_spmi_wait_rx_not_empty(ctrl);
if (ret)
return ret;
@@ -93,7 +100,8 @@ 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) {
+ i = 0;
+ while (i < len_rd) {
if (readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY) {
spmi->prev_fail = true;
dev_err_ratelimited(&ctrl->dev,
@@ -101,11 +109,9 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
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);
- i += 1;
- }
+ j = min_t(size_t, sizeof(spmi_cmd), len_rd - i);
+ memcpy(buf_rd + i, &rsp, j);
+ i += j;
}
if (!(readl(spmi->regs + SPMI_STATUS_REG) & SPMI_RX_FIFO_EMPTY)) {
@@ -113,54 +119,69 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
spmi->prev_fail = true;
}
- if (~FIELD_GET(SPMI_REPLY_FRAME_PARITY_STATUS, reply) & ((1 << len) - 1)) {
+ if (!len_rd && !FIELD_GET(SPMI_REPLY_ACK, reply)) {
+ dev_err(&ctrl->dev, "command not acknowledged\n");
+ return -EIO;
+ }
+ if (~FIELD_GET(SPMI_REPLY_FRAME_PARITY_STATUS, reply) & ((1 << len_rd) - 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;
-
- if (spmi->prev_fail) {
- writel(SPMI_ACT_FIFO_FLUSH, spmi->regs + SPMI_ACT_REG);
- spmi->prev_fail = false;
- }
-
- 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");
- spmi->prev_fail = true;
+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 -EINVAL;
+}
- if (!FIELD_GET(SPMI_REPLY_ACK, reply)) {
- dev_err(&ctrl->dev, "command not acknowledged\n");
- return -EIO;
+static int spmi_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid)
+{
+ switch (opc) {
+ case SPMI_CMD_RESET:
+ case SPMI_CMD_SLEEP:
+ case SPMI_CMD_SHUTDOWN:
+ case SPMI_CMD_WAKEUP:
+ return spmi_raw_cmd_ack(ctrl, opc, sid, 0, NULL, 0);
}
- return 0;
+ return -EINVAL;
}
static int apple_spmi_probe(struct platform_device *pdev)
@@ -183,6 +204,7 @@ 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] 11+ messages in thread
* [PATCH v7 5/6] spmi: apple: lock around FIFOs
2026-08-18 18:32 [PATCH v7 0/6] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
` (3 preceding siblings ...)
2026-08-18 18:32 ` [PATCH v7 4/6] spmi: apple: Implement remaining commands Sasha Finkelstein
@ 2026-08-18 18:32 ` Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 6/6] spmi: apple: Add interrupt functionality Sasha Finkelstein
5 siblings, 0 replies; 11+ messages in thread
From: Sasha Finkelstein @ 2026-08-18 18:32 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>
Reviewed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/spmi-apple-controller.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index 9843dc871d6c..fabccd25aa0d 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -16,6 +16,7 @@
#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>
@@ -39,6 +40,7 @@
struct apple_spmi {
void __iomem *regs;
+ struct mutex fifo_lock;
bool prev_fail;
};
@@ -78,6 +80,8 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, u16 param,
size_t i = 0, j;
int ret;
+ guard(mutex)(&spmi->fifo_lock);
+
if (spmi->prev_fail) {
writel(SPMI_ACT_FIFO_FLUSH, spmi->regs + SPMI_ACT_REG);
spmi->prev_fail = false;
@@ -195,6 +199,7 @@ 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] 11+ messages in thread
* [PATCH v7 6/6] spmi: apple: Add interrupt functionality
2026-08-18 18:32 [PATCH v7 0/6] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
` (4 preceding siblings ...)
2026-08-18 18:32 ` [PATCH v7 5/6] spmi: apple: lock around FIFOs Sasha Finkelstein
@ 2026-08-18 18:32 ` Sasha Finkelstein
2026-08-18 18:46 ` sashiko-bot
5 siblings, 1 reply; 11+ messages in thread
From: Sasha Finkelstein @ 2026-08-18 18:32 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 and use IRQ for
RX FIFO if possible, as that 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>
Reviewed-by: Janne Grunau <j@jannau.net>
Signed-off-by: Sasha Finkelstein <k@chaosmail.tech>
---
drivers/spmi/Kconfig | 3 +-
drivers/spmi/spmi-apple-controller.c | 257 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 258 insertions(+), 2 deletions(-)
diff --git a/drivers/spmi/Kconfig b/drivers/spmi/Kconfig
index a80cf4047b86..7243863a09b4 100644
--- a/drivers/spmi/Kconfig
+++ b/drivers/spmi/Kconfig
@@ -13,7 +13,8 @@ if SPMI
config SPMI_APPLE
tristate "Apple SoC SPMI Controller platform driver"
- depends on ARCH_APPLE || COMPILE_TEST
+ select IRQ_DOMAIN_HIERARCHY
+ depends on ARCH_APPLE || (COMPILE_TEST && 64BIT)
help
If you say yes to this option, support will be included for the
SPMI controller present on many Apple SoCs, including the
diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
index fabccd25aa0d..2390174452ab 100644
--- a/drivers/spmi/spmi-apple-controller.c
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -13,11 +13,17 @@
#include <linux/bitfield.h>
#include <linux/bits.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iopoll.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_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 */
@@ -26,6 +32,13 @@
#define SPMI_RSP_REG 0x8
#define SPMI_ACT_REG 0xa4
+#define SPMI_IRQ_MASK_BASE 0x20
+#define SPMI_IRQ_ACK_BASE 0x60
+#define SPMI_NUM_PERIPHERAL_IRQS 256
+#define SPMI_NUM_IRQS (SPMI_NUM_PERIPHERAL_IRQS + 32)
+
+#define SPMI_IRQ_NOTIFY 256
+
/* SPMI_RSP_REG reply word */
#define SPMI_REPLY_FRAME_PARITY_STATUS GENMASK(31, 16)
#define SPMI_REPLY_ACK BIT(15)
@@ -41,6 +54,12 @@
struct apple_spmi {
void __iomem *regs;
struct mutex fifo_lock;
+ struct completion fifo_rx;
+ struct irq_domain *irqd;
+ raw_spinlock_t irq_mask_lock;
+ DECLARE_BITMAP(irq_mask_cache, SPMI_NUM_PERIPHERAL_IRQS);
+ int irq;
+ bool notify_irq;
bool prev_fail;
};
@@ -48,6 +67,56 @@ struct apple_spmi {
readl_poll_timeout((spmi)->regs + (reg), (val), (cond), \
REG_POLL_INTERVAL_US, REG_POLL_TIMEOUT_US)
+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 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);
+ clear_bit(d->hwirq, spmi->irq_mask_cache);
+ 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);
+ set_bit(d->hwirq, spmi->irq_mask_cache);
+ apple_spmi_irq_unmask_raw(spmi, d->hwirq);
+ raw_spin_unlock_irqrestore(&spmi->irq_mask_lock, flags);
+}
+
static inline u32 apple_spmi_pack_cmd(u8 opc, u8 sid, u16 param)
{
return opc | sid << 8 | (u32)param << 16 | (1 << 15);
@@ -60,7 +129,19 @@ 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->notify_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) {
spmi->prev_fail = true;
dev_err(&ctrl->dev,
@@ -84,8 +165,10 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, u16 param,
if (spmi->prev_fail) {
writel(SPMI_ACT_FIFO_FLUSH, spmi->regs + SPMI_ACT_REG);
+ apple_spmi_irq_ack_raw(spmi, SPMI_IRQ_NOTIFY);
spmi->prev_fail = false;
}
+ reinit_completion(&spmi->fifo_rx);
writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
@@ -188,6 +271,167 @@ static int spmi_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid)
return -EINVAL;
}
+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_NUM_PERIPHERAL_IRQS)
+ 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_NUM_PERIPHERAL_IRQS)
+ 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 void apple_spmi_irq_handler(struct irq_desc *desc)
+{
+ struct apple_spmi *spmi = irq_desc_get_handler_data(desc);
+ struct irq_chip *chip = irq_desc_get_chip(desc);
+ bool handled = false;
+ unsigned long val, offset, bit;
+
+ chained_irq_enter(chip, desc);
+ val = readl(spmi->regs + SPMI_IRQ_ACK_BASE + (SPMI_IRQ_NOTIFY / 32) * 4);
+ if (val & BIT(SPMI_IRQ_NOTIFY % 32)) {
+ apple_spmi_irq_ack_raw(spmi, SPMI_IRQ_NOTIFY);
+ complete(&spmi->fifo_rx);
+ handled = true;
+ }
+
+ for (offset = 0; offset < SPMI_NUM_PERIPHERAL_IRQS / 8; 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)];
+ for_each_set_bit(bit, &val, 64) {
+ generic_handle_domain_irq(spmi->irqd, offset * 8 + bit);
+ handled = true;
+ }
+ }
+ if (!handled)
+ handle_bad_irq(desc);
+ chained_irq_exit(chip, desc);
+}
+
+static void apple_spmi_teardown_irq(void *data)
+{
+ struct apple_spmi *spmi = data;
+
+ for (size_t offset = 0; offset < SPMI_NUM_IRQS / 8; offset += 4)
+ writel(0, spmi->regs + SPMI_IRQ_MASK_BASE + offset);
+
+ synchronize_irq(spmi->irq);
+ irq_set_chained_handler_and_data(spmi->irq, NULL, NULL);
+}
+
+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_NUM_IRQS / 8; 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);
+
+ ret = devm_add_action(&pdev->dev, apple_spmi_teardown_irq, spmi);
+ if (ret)
+ return ret;
+
+ irq_set_chained_handler_and_data(spmi->irq, apple_spmi_irq_handler, spmi);
+ apple_spmi_irq_unmask_raw(spmi, SPMI_IRQ_NOTIFY);
+ spmi->notify_irq = true;
+
+ return 0;
+}
+
static int apple_spmi_probe(struct platform_device *pdev)
{
struct apple_spmi *spmi;
@@ -200,6 +444,8 @@ 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);
+ platform_set_drvdata(pdev, spmi);
spmi->regs = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(spmi->regs))
@@ -211,6 +457,15 @@ static int apple_spmi_probe(struct platform_device *pdev)
ctrl->write_cmd = spmi_write_cmd;
ctrl->cmd = spmi_cmd;
+ spmi->irq = platform_get_irq_optional(pdev, 0);
+ if (spmi->irq < 0 && spmi->irq != -ENXIO)
+ return spmi->irq;
+ if (spmi->irq >= 0) {
+ ret = apple_spmi_init_irq(pdev, spmi, spmi->irq);
+ if (ret)
+ return ret;
+ }
+
ret = devm_spmi_controller_add(&pdev->dev, ctrl);
if (ret)
return dev_err_probe(&pdev->dev, ret,
--
2.55.0
^ permalink raw reply related [flat|nested] 11+ messages in thread
* Re: [PATCH v7 4/6] spmi: apple: Implement remaining commands
2026-08-18 18:32 ` [PATCH v7 4/6] spmi: apple: Implement remaining commands Sasha Finkelstein
@ 2026-08-18 18:44 ` sashiko-bot
0 siblings, 0 replies; 11+ messages in thread
From: sashiko-bot @ 2026-08-18 18:44 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: devicetree, robh, conor+dt
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Replacing bitwise shifts with `memcpy()` into/from a `u32` variable combined with `writel()` and `readl()` for FIFO transfers introduces byte-swapping data corruption on big-endian architectures.
--
--- Patch [4]: [PATCH v7 4/6] spmi: apple: Implement remaining commands ---
commit 0955662fb587593fe5c8969de75412be27a01533
Author: Alba Mendez <me@alba.sh>
spmi: apple: Implement remaining commands
Add support for zero write and power management commands.
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> index b1c127cf5f441..9843dc871d6c7 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -86,6 +85,14 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
>
> writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
>
> + while (i < len_wr) {
> + j = min_t(size_t, sizeof(spmi_cmd), len_wr - i);
> + spmi_cmd = 0;
> + memcpy(&spmi_cmd, buf_wr + i, j);
> + writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
> + i += j;
> + }
> +
[Severity: High]
Will this combination of memcpy() and writel() cause data corruption on
big-endian architectures?
On big-endian systems, memcpy() will store the first byte of the stream into
the lowest memory address of the u32, making it the most-significant byte.
When writel() is called, it will apply cpu_to_le32(), swapping the bytes and
sending them to the hardware in reverse order. Does this loop need to use
writesl() or explicit bitwise shifts instead?
> ret = apple_spmi_wait_rx_not_empty(ctrl);
[ ... ]
> @@ -101,11 +109,9 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> 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);
> - i += 1;
> - }
> + j = min_t(size_t, sizeof(spmi_cmd), len_rd - i);
> + memcpy(buf_rd + i, &rsp, j);
> + i += j;
> }
[Severity: High]
Can this sequence of readl() and memcpy() read zero-padding instead of valid
data for partial reads on big-endian systems?
When readl() byte-swaps the incoming hardware register value on big-endian
CPUs, the lowest bytes end up at the highest memory addresses. Since memcpy()
copies from the lowest memory address first, a partial read will copy the
zero-padded upper bytes instead of the actual data. Should this use readsl()
or the previous bitwise extraction logic to preserve portability?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260818-t603x-spmi-v7-0-dafebe6e7739@chaosmail.tech?part=4
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH v7 2/6] spmi: apple: Validate FIFO state
2026-08-18 18:32 ` [PATCH v7 2/6] spmi: apple: Validate FIFO state Sasha Finkelstein
@ 2026-08-18 18:44 ` sashiko-bot
0 siblings, 0 replies; 11+ messages in thread
From: sashiko-bot @ 2026-08-18 18:44 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: devicetree, conor+dt, robh
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
New issues:
- [Medium] Instantaneous check of RX_FIFO_EMPTY randomly aborts valid multi-word reads if the hardware streams data.
Pre-existing issues:
- [High] Missing controller-level lock allows concurrent operations to corrupt SPMI bus transactions and race on prev_fail.
--
--- Patch [2]: [PATCH v7 2/6] spmi: apple: Validate FIFO state ---
commit b638b8c461a5028b5eb344197adecba7ccd922ba
Author: Alba Mendez <me@alba.sh>
spmi: apple: Validate FIFO state
This commit adds checks to validate the FIFO state before reading reply data
and after a command completes. It introduces a prev_fail flag and flushes
the FIFO before executing new commands if previous operations failed.
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -67,6 +71,11 @@ static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> u8 i;
> int ret;
>
> + if (spmi->prev_fail) {
[Severity: High]
This isn't a bug introduced by this patch, but does this missing
controller-level lock allow concurrent operations to corrupt SPMI bus
transactions?
Since the SPMI subsystem exposes this controller to all its children and
does not natively serialize read_cmd or write_cmd operations, multiple
threads could invoke spmi_read_cmd() simultaneously. This would lead to
concurrent modifications of spmi->prev_fail and shared hardware registers
without mutual exclusion.
> + writel(SPMI_ACT_FIFO_FLUSH, spmi->regs + SPMI_ACT_REG);
> + spmi->prev_fail = false;
> + }
> +
> writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
[ ... ]
> @@ -78,6 +87,12 @@ 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) {
> + spmi->prev_fail = true;
> + dev_err_ratelimited(&ctrl->dev,
> + "FIFO lacks reply data, controller stuck?\n");
> + return -EIO;
> + }
[Severity: Medium]
Could this instantaneous check of SPMI_RX_FIFO_EMPTY spuriously abort valid
multi-word reads?
In a multi-word read transaction, the CPU might outrun the SPMI bus after
reading the first word. If the hardware streams data and hasn't buffered
the next word yet, the CPU will immediately see SPMI_RX_FIFO_EMPTY and
return -EIO instead of waiting for the next word to arrive.
> rsp = readl(spmi->regs + SPMI_RSP_REG);
> i = 0;
[ ... ]
> @@ -97,6 +117,11 @@ static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> size_t i = 0, j;
> int ret;
>
> + if (spmi->prev_fail) {
[Severity: High]
This is a pre-existing issue, but can concurrent calls to spmi_write_cmd()
race on spmi->prev_fail and hardware state?
Similar to spmi_read_cmd(), this modifies shared hardware state and
spmi->prev_fail without serialization.
> + writel(SPMI_ACT_FIFO_FLUSH, spmi->regs + SPMI_ACT_REG);
> + spmi->prev_fail = false;
> + }
> +
> writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260818-t603x-spmi-v7-0-dafebe6e7739@chaosmail.tech?part=2
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH v7 3/6] spmi: apple: check transaction status
2026-08-18 18:32 ` [PATCH v7 3/6] spmi: apple: check transaction status Sasha Finkelstein
@ 2026-08-18 18:46 ` sashiko-bot
0 siblings, 0 replies; 11+ messages in thread
From: sashiko-bot @ 2026-08-18 18:46 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:
Pre-existing issues:
- [High] Missing serialization lock in SPMI controller commands causing data races and hardware state corruption.
--
--- Patch [3]: [PATCH v7 3/6] spmi: apple: check transaction status ---
commit 203a0d3a4ce6927effa9895d6d8b8a19c020f6cd
Author: Alba Mendez <me@alba.sh>
spmi: apple: check transaction status
This commit adds checks for parity errors and missing command ACKs in the
Apple SPMI controller driver.
> diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
> index 15721cb41d5c8..b1c127cf5f441 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -66,7 +74,7 @@ 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;
[Severity: High]
This is a pre-existing issue, but does spmi_read_cmd() in
drivers/spmi/spmi-apple-controller.c need a lock to prevent data races?
The SPMI core subsystem does not serialize these calls, expecting the
controller driver to handle mutual exclusion. If multiple threads access
distinct SPMI devices on the same bus simultaneously, could their register
accesses interleave?
This could potentially corrupt the hardware state, commands, and FIFO data
since the sequence of writing to SPMI_CMD_REG, waiting for the FIFO, and
reading the result is performed without a controller-level lock.
[ ... ]
> @@ -114,6 +125,7 @@ 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;
[Severity: High]
This is a pre-existing issue, but does spmi_write_cmd() in
drivers/spmi/spmi-apple-controller.c also require serialization?
Similar to spmi_read_cmd(), data is packed and written to the shared command
register without acquiring a lock. Could this lead to interleaved register
accesses and hardware state corruption if invoked concurrently by multiple
threads or interrupt handlers?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260818-t603x-spmi-v7-0-dafebe6e7739@chaosmail.tech?part=3
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [PATCH v7 6/6] spmi: apple: Add interrupt functionality
2026-08-18 18:32 ` [PATCH v7 6/6] spmi: apple: Add interrupt functionality Sasha Finkelstein
@ 2026-08-18 18:46 ` sashiko-bot
0 siblings, 0 replies; 11+ messages in thread
From: sashiko-bot @ 2026-08-18 18:46 UTC (permalink / raw)
To: Sasha Finkelstein; +Cc: robh, conor+dt, devicetree
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [High] Spurious completions during timeout recovery cause subsequent commands to fail with -EIO.
- [High] Using a 64-bit `readq` on a 32-bit peripheral register array causes a bus fault (SError) on Apple SoCs.
- [Medium] Incorrect use of register accessors (`writel`/`readl`) with `memcpy()` for FIFO access causes byte reversal on big-endian architectures.
--
--- Patch [6]: [PATCH v7 6/6] spmi: apple: Add interrupt functionality ---
commit ed584cbe528c0915b9974fbcae3310e9b639b962
Author: Alba Mendez <me@alba.sh>
spmi: apple: Add interrupt functionality
Add support for interrupts sent by slave devices and use IRQ for
RX FIFO if possible, as that 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 fabccd25aa0da..2390174452ab4 100644
> --- a/drivers/spmi/spmi-apple-controller.c
> +++ b/drivers/spmi/spmi-apple-controller.c
[ ... ]
> @@ -84,8 +165,10 @@ static int spmi_raw_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, u16 param,
>
> if (spmi->prev_fail) {
> writel(SPMI_ACT_FIFO_FLUSH, spmi->regs + SPMI_ACT_REG);
> + apple_spmi_irq_ack_raw(spmi, SPMI_IRQ_NOTIFY);
> spmi->prev_fail = false;
> }
> + reinit_completion(&spmi->fifo_rx);
>
> writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
[Severity: High]
Can a delayed interrupt cause spurious completions here?
If a previous command times out, apple_spmi_wait_rx_not_empty() returns
-ETIMEDOUT and sets prev_fail = true.
On the next command, spmi_raw_cmd() executes the recovery path and then calls
reinit_completion(). If a delayed interrupt arrives concurrently and the
IRQ handler calls complete() after reinit_completion() has executed, the next
command's wait_for_completion_timeout() could return immediately before the
actual reply is ready. This would lead to an -EIO failure.
Does the recovery path need to synchronize with the IRQ handler to prevent
this?
[Severity: Medium]
Does using writel() and readl() with memcpy() later in this function cause
byte reversal on big-endian architectures?
When spmi_raw_cmd() handles payload data:
drivers/spmi/spmi-apple-controller.c:spmi_raw_cmd() {
...
while (i < len_wr) {
j = min_t(size_t, sizeof(spmi_cmd), len_wr - i);
spmi_cmd = 0;
memcpy(&spmi_cmd, buf_wr + i, j);
writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
i += j;
}
...
}
Using memcpy() to copy data to or from a u32 variable followed by writel()
or readl() causes implicit byte-swapping on big-endian CPUs. While Apple
SoCs run in little-endian mode, this could corrupt data during SPMI transfers
if the driver is compiled and run on a big-endian system (e.g., during
COMPILE_TEST).
Should this use stream-oriented accessors like writesl() and readsl() to
ensure consistent endianness?
[ ... ]
> +static void apple_spmi_irq_handler(struct irq_desc *desc)
> +{
> + struct apple_spmi *spmi = irq_desc_get_handler_data(desc);
> + struct irq_chip *chip = irq_desc_get_chip(desc);
> + bool handled = false;
> + unsigned long val, offset, bit;
> +
> + chained_irq_enter(chip, desc);
> + val = readl(spmi->regs + SPMI_IRQ_ACK_BASE + (SPMI_IRQ_NOTIFY / 32) * 4);
> + if (val & BIT(SPMI_IRQ_NOTIFY % 32)) {
> + apple_spmi_irq_ack_raw(spmi, SPMI_IRQ_NOTIFY);
> + complete(&spmi->fifo_rx);
> + handled = true;
> + }
> +
> + for (offset = 0; offset < SPMI_NUM_PERIPHERAL_IRQS / 8; offset += sizeof(val)) {
> + val = readq(spmi->regs + SPMI_IRQ_ACK_BASE + offset);
[Severity: High]
Does reading a 32-bit peripheral register using a 64-bit readq() cause a bus
fault on Apple SoCs?
Apple SoC peripheral fabrics strictly enforce MMIO access widths. Issuing a
64-bit read to the 32-bit SPMI_IRQ_ACK_BASE registers generates a Synchronous
External Abort (SError), resulting in a kernel panic when a peripheral
interrupt fires.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260818-t603x-spmi-v7-0-dafebe6e7739@chaosmail.tech?part=6
^ permalink raw reply [flat|nested] 11+ messages in thread
end of thread, other threads:[~2026-08-18 18:46 UTC | newest]
Thread overview: 11+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-08-18 18:32 [PATCH v7 0/6] spmi: apple: Additional commands and interrupt support Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 1/6] dt-bindings: spmi: apple,spmi: Add t603x and t8122 Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 2/6] spmi: apple: Validate FIFO state Sasha Finkelstein
2026-08-18 18:44 ` sashiko-bot
2026-08-18 18:32 ` [PATCH v7 3/6] spmi: apple: check transaction status Sasha Finkelstein
2026-08-18 18:46 ` sashiko-bot
2026-08-18 18:32 ` [PATCH v7 4/6] spmi: apple: Implement remaining commands Sasha Finkelstein
2026-08-18 18:44 ` sashiko-bot
2026-08-18 18:32 ` [PATCH v7 5/6] spmi: apple: lock around FIFOs Sasha Finkelstein
2026-08-18 18:32 ` [PATCH v7 6/6] spmi: apple: Add interrupt functionality Sasha Finkelstein
2026-08-18 18:46 ` sashiko-bot
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.