Devicetree
 help / color / mirror / Atom feed
* [PATCH 0/3] soc: mediatek: pwrap: mt6572 support + log level fixes
@ 2026-07-14 12:42 Roman Vivchar via B4 Relay
  2026-07-14 12:42 ` [PATCH 1/3] dt-bindings: soc: mediatek: pwrap: add mt6572 Roman Vivchar via B4 Relay
                   ` (2 more replies)
  0 siblings, 3 replies; 6+ messages in thread
From: Roman Vivchar via B4 Relay @ 2026-07-14 12:42 UTC (permalink / raw)
  To: Rob Herring, Krzysztof Kozlowski, Conor Dooley, Matthias Brugger,
	AngeloGioacchino Del Regno, Flora Fu, Alexandre Mergnat
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

This patch series adds support for the mt6572 pwrap.

All known mt6572 devices use mt6323 PMIC, which is already supported
by the upstream drivers. mt6572 also shares SoC-specific init with
mt2701.

Patch 1 adds dt-bindings compatible.
Patch 2 fixes improper log levels in the driver, improving UX when
debugging.
Patch 3 adds mt6572 support.

Tested on various mt6572 devices without any failures.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
Roman Vivchar (3):
      dt-bindings: soc: mediatek: pwrap: add mt6572
      soc: mediatek: pwrap: use correct log level
      soc: mediatek: pwrap: add mt6572 support

 .../bindings/soc/mediatek/mediatek,pwrap.yaml      |   1 +
 drivers/soc/mediatek/mtk-pmic-wrap.c               | 156 +++++++++++++++++----
 2 files changed, 129 insertions(+), 28 deletions(-)
---
base-commit: 8cd9520d35a6c38db6567e97dd93b1f11f185dc6
change-id: 20260712-6572-pwrap-4c91563cfd23

Best regards,
--  
Roman Vivchar <rva333@protonmail.com>



^ permalink raw reply	[flat|nested] 6+ messages in thread

* [PATCH 1/3] dt-bindings: soc: mediatek: pwrap: add mt6572
  2026-07-14 12:42 [PATCH 0/3] soc: mediatek: pwrap: mt6572 support + log level fixes Roman Vivchar via B4 Relay
@ 2026-07-14 12:42 ` Roman Vivchar via B4 Relay
  2026-07-14 12:42 ` [PATCH 2/3] soc: mediatek: pwrap: use correct log level Roman Vivchar via B4 Relay
  2026-07-14 12:42 ` [PATCH 3/3] soc: mediatek: pwrap: add mt6572 support Roman Vivchar via B4 Relay
  2 siblings, 0 replies; 6+ messages in thread
From: Roman Vivchar via B4 Relay @ 2026-07-14 12:42 UTC (permalink / raw)
  To: Rob Herring, Krzysztof Kozlowski, Conor Dooley, Matthias Brugger,
	AngeloGioacchino Del Regno, Flora Fu, Alexandre Mergnat
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

From: Roman Vivchar <rva333@protonmail.com>

Add a compatible string for the mt6572 SoC.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
 Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml b/Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml
index e7c4a3984c60..a3cf11153fba 100644
--- a/Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml
+++ b/Documentation/devicetree/bindings/soc/mediatek/mediatek,pwrap.yaml
@@ -31,6 +31,7 @@ properties:
       - items:
           - enum:
               - mediatek,mt2701-pwrap
+              - mediatek,mt6572-pwrap
               - mediatek,mt6765-pwrap
               - mediatek,mt6779-pwrap
               - mediatek,mt6795-pwrap

-- 
2.54.0



^ permalink raw reply related	[flat|nested] 6+ messages in thread

* [PATCH 2/3] soc: mediatek: pwrap: use correct log level
  2026-07-14 12:42 [PATCH 0/3] soc: mediatek: pwrap: mt6572 support + log level fixes Roman Vivchar via B4 Relay
  2026-07-14 12:42 ` [PATCH 1/3] dt-bindings: soc: mediatek: pwrap: add mt6572 Roman Vivchar via B4 Relay
@ 2026-07-14 12:42 ` Roman Vivchar via B4 Relay
  2026-07-14 12:53   ` sashiko-bot
  2026-07-14 12:42 ` [PATCH 3/3] soc: mediatek: pwrap: add mt6572 support Roman Vivchar via B4 Relay
  2 siblings, 1 reply; 6+ messages in thread
From: Roman Vivchar via B4 Relay @ 2026-07-14 12:42 UTC (permalink / raw)
  To: Rob Herring, Krzysztof Kozlowski, Conor Dooley, Matthias Brugger,
	AngeloGioacchino Del Regno, Flora Fu, Alexandre Mergnat
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

From: Roman Vivchar <rva333@protonmail.com>

Errors paths should be dev_err, not dev_dbg. Replace all dev_dbg in error
branches to have the correct log level. Also simplify dev_err and return
with dev_err_probe.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
 drivers/soc/mediatek/mtk-pmic-wrap.c | 45 ++++++++++++++----------------------
 1 file changed, 17 insertions(+), 28 deletions(-)

diff --git a/drivers/soc/mediatek/mtk-pmic-wrap.c b/drivers/soc/mediatek/mtk-pmic-wrap.c
index 0bcd85826375..a4b10b0a97cb 100644
--- a/drivers/soc/mediatek/mtk-pmic-wrap.c
+++ b/drivers/soc/mediatek/mtk-pmic-wrap.c
@@ -2475,10 +2475,9 @@ static int pwrap_probe(struct platform_device *pdev)
 	if (np->child)
 		of_slave_id = of_match_node(of_slave_match_tbl, np->child);
 
-	if (!of_slave_id) {
-		dev_dbg(&pdev->dev, "slave pmic should be defined in dts\n");
-		return -EINVAL;
-	}
+	if (!of_slave_id)
+		return dev_err_probe(&pdev->dev, -EINVAL,
+				     "slave pmic should be defined in dts\n");
 
 	wrp = devm_kzalloc(&pdev->dev, sizeof(*wrp), GFP_KERNEL);
 	if (!wrp)
@@ -2496,11 +2495,9 @@ static int pwrap_probe(struct platform_device *pdev)
 
 	if (HAS_CAP(wrp->master->caps, PWRAP_CAP_RESET)) {
 		wrp->rstc = devm_reset_control_get(wrp->dev, "pwrap");
-		if (IS_ERR(wrp->rstc)) {
-			ret = PTR_ERR(wrp->rstc);
-			dev_dbg(wrp->dev, "cannot get pwrap reset: %d\n", ret);
-			return ret;
-		}
+		if (IS_ERR(wrp->rstc))
+			return dev_err_probe(wrp->dev, PTR_ERR(wrp->rstc),
+					     "cannot get pwrap reset\n");
 	}
 
 	if (HAS_CAP(wrp->master->caps, PWRAP_CAP_BRIDGE)) {
@@ -2510,12 +2507,9 @@ static int pwrap_probe(struct platform_device *pdev)
 
 		wrp->rstc_bridge = devm_reset_control_get(wrp->dev,
 							  "pwrap-bridge");
-		if (IS_ERR(wrp->rstc_bridge)) {
-			ret = PTR_ERR(wrp->rstc_bridge);
-			dev_dbg(wrp->dev,
-				"cannot get pwrap-bridge reset: %d\n", ret);
-			return ret;
-		}
+		if (IS_ERR(wrp->rstc_bridge))
+			return dev_err_probe(wrp->dev, PTR_ERR(wrp->rstc_bridge),
+					     "cannot get pwrap-bridge reset\n");
 	}
 
 	ret = devm_clk_bulk_get_all_enabled(wrp->dev, &clk);
@@ -2535,10 +2529,8 @@ static int pwrap_probe(struct platform_device *pdev)
 	 */
 	if (!pwrap_readl(wrp, PWRAP_INIT_DONE2)) {
 		ret = pwrap_init(wrp);
-		if (ret) {
-			dev_dbg(wrp->dev, "init failed with %d\n", ret);
-			return ret;
-		}
+		if (ret)
+			return dev_err_probe(wrp->dev, ret, "init failed\n");
 	}
 
 	if (HAS_CAP(wrp->master->caps, PWRAP_CAP_ARB))
@@ -2548,10 +2540,9 @@ static int pwrap_probe(struct platform_device *pdev)
 	else
 		mask_done = PWRAP_STATE_INIT_DONE0;
 
-	if (!(pwrap_readl(wrp, PWRAP_WACS2_RDATA) & mask_done)) {
-		dev_dbg(wrp->dev, "initialization isn't finished\n");
-		return -ENODEV;
-	}
+	if (!(pwrap_readl(wrp, PWRAP_WACS2_RDATA) & mask_done))
+		return dev_err_probe(wrp->dev, -ENODEV,
+				     "initialization isn't finished\n");
 
 	/* Initialize watchdog, may not be done by the bootloader */
 	if (!HAS_CAP(wrp->master->caps, PWRAP_CAP_ARB))
@@ -2593,11 +2584,9 @@ static int pwrap_probe(struct platform_device *pdev)
 		return PTR_ERR(wrp->regmap);
 
 	ret = of_platform_populate(np, NULL, NULL, wrp->dev);
-	if (ret) {
-		dev_dbg(wrp->dev, "failed to create child devices at %pOF\n",
-				np);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(wrp->dev, ret,
+				     "failed to create child devices at %pOF\n", np);
 
 	return 0;
 }

-- 
2.54.0



^ permalink raw reply related	[flat|nested] 6+ messages in thread

* [PATCH 3/3] soc: mediatek: pwrap: add mt6572 support
  2026-07-14 12:42 [PATCH 0/3] soc: mediatek: pwrap: mt6572 support + log level fixes Roman Vivchar via B4 Relay
  2026-07-14 12:42 ` [PATCH 1/3] dt-bindings: soc: mediatek: pwrap: add mt6572 Roman Vivchar via B4 Relay
  2026-07-14 12:42 ` [PATCH 2/3] soc: mediatek: pwrap: use correct log level Roman Vivchar via B4 Relay
@ 2026-07-14 12:42 ` Roman Vivchar via B4 Relay
  2026-07-14 13:24   ` sashiko-bot
  2 siblings, 1 reply; 6+ messages in thread
From: Roman Vivchar via B4 Relay @ 2026-07-14 12:42 UTC (permalink / raw)
  To: Rob Herring, Krzysztof Kozlowski, Conor Dooley, Matthias Brugger,
	AngeloGioacchino Del Regno, Flora Fu, Alexandre Mergnat
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

From: Roman Vivchar <rva333@protonmail.com>

Add mt6572 registers and platform data for the pmic wrapper.
The mt2701 SoC-specific initialization function is used because they
share the same GPS_INTF settings.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
 drivers/soc/mediatek/mtk-pmic-wrap.c | 111 +++++++++++++++++++++++++++++++++++
 1 file changed, 111 insertions(+)

diff --git a/drivers/soc/mediatek/mtk-pmic-wrap.c b/drivers/soc/mediatek/mtk-pmic-wrap.c
index a4b10b0a97cb..4b8a5dc80a36 100644
--- a/drivers/soc/mediatek/mtk-pmic-wrap.c
+++ b/drivers/soc/mediatek/mtk-pmic-wrap.c
@@ -569,6 +569,96 @@ static const int mt2701_regs[] = {
 	[PWRAP_ADC_RDATA_ADDR2] =	0x154,
 };
 
+static const int mt6572_regs[] = {
+	[PWRAP_MUX_SEL] =		0x0,
+	[PWRAP_WRAP_EN] =		0x4,
+	[PWRAP_DIO_EN] =		0x8,
+	[PWRAP_SIDLY] =			0xc,
+	[PWRAP_OP_TYPE] =		0x10,
+	[PWRAP_MSB_FIRST] =		0x14,
+	[PWRAP_RDDMY] =			0x18,
+	[PWRAP_SI_CK_CON] =		0x1c,
+	[PWRAP_CSHEXT_WRITE] =		0x20,
+	[PWRAP_CSHEXT_READ] =		0x24,
+	[PWRAP_CSLEXT_START] =		0x28,
+	[PWRAP_CSLEXT_END] =		0x2c,
+	[PWRAP_STAUPD_PRD] =		0x30,
+	[PWRAP_STAUPD_GRPEN] =		0x34,
+	[PWRAP_STAUPD_MAN_TRIG] =	0x38,
+	[PWRAP_STAUPD_STA] =		0x3c,
+	[PWRAP_GPS_STA] =		0x40,
+	[PWRAP_WRAP_STA] =		0x44,
+	[PWRAP_HARB_INIT] =		0x48,
+	[PWRAP_HARB_HPRIO] =		0x4c,
+	[PWRAP_HIPRIO_ARB_EN] =		0x50,
+	[PWRAP_HARB_STA0] =		0x54,
+	[PWRAP_HARB_STA1] =		0x58,
+	[PWRAP_MAN_EN] =		0x5c,
+	[PWRAP_MAN_CMD] =		0x60,
+	[PWRAP_MAN_RDATA] =		0x64,
+	[PWRAP_MAN_VLDCLR] =		0x68,
+	[PWRAP_WACS0_EN] =		0x6c,
+	[PWRAP_INIT_DONE0] =		0x70,
+	[PWRAP_WACS0_CMD] =		0x74,
+	[PWRAP_WACS0_RDATA] =		0x78,
+	[PWRAP_WACS0_VLDCLR] =		0x7c,
+	[PWRAP_WACS1_EN] =		0x80,
+	[PWRAP_INIT_DONE1] =		0x84,
+	[PWRAP_WACS1_CMD] =		0x88,
+	[PWRAP_WACS1_RDATA] =		0x8c,
+	[PWRAP_WACS1_VLDCLR] =		0x90,
+	[PWRAP_WACS2_EN] =		0x94,
+	[PWRAP_INIT_DONE2] =		0x98,
+	[PWRAP_WACS2_CMD] =		0x9c,
+	[PWRAP_WACS2_RDATA] =		0xa0,
+	[PWRAP_WACS2_VLDCLR] =		0xa4,
+	[PWRAP_INT_EN] =		0xa8,
+	[PWRAP_INT_FLG_RAW] =		0xac,
+	[PWRAP_INT_FLG] =		0xb0,
+	[PWRAP_INT_CLR] =		0xb4,
+	[PWRAP_SIG_ADR] =		0xb8,
+	[PWRAP_SIG_MODE] =		0xbc,
+	[PWRAP_SIG_VALUE] =		0xc0,
+	[PWRAP_SIG_ERRVAL] =		0xc4,
+	[PWRAP_CRC_EN] =		0xc8,
+	[PWRAP_TIMER_EN] =		0xcc,
+	[PWRAP_TIMER_STA] =		0xd0,
+	[PWRAP_WDT_UNIT] =		0xd4,
+	[PWRAP_WDT_SRC_EN] =		0xd8,
+	[PWRAP_WDT_FLG] =		0xdc,
+	[PWRAP_DEBUG_INT_SEL] =		0xe0,
+	[PWRAP_DVFS_ADR0] =		0xe4,
+	[PWRAP_DVFS_WDATA0] =		0xe8,
+	[PWRAP_DVFS_ADR1] =		0xec,
+	[PWRAP_DVFS_WDATA1] =		0xf0,
+	[PWRAP_DVFS_ADR2] =		0xf4,
+	[PWRAP_DVFS_WDATA2] =		0xf8,
+	[PWRAP_DVFS_ADR3] =		0xfc,
+	[PWRAP_DVFS_WDATA3] =		0x100,
+	[PWRAP_DVFS_ADR4] =		0x104,
+	[PWRAP_DVFS_WDATA4] =		0x108,
+	[PWRAP_DVFS_ADR5] =		0x10c,
+	[PWRAP_DVFS_WDATA5] =		0x110,
+	[PWRAP_DVFS_ADR6] =		0x114,
+	[PWRAP_DVFS_WDATA6] =		0x118,
+	[PWRAP_DVFS_ADR7] =		0x11c,
+	[PWRAP_DVFS_WDATA7] =		0x120,
+	[PWRAP_CIPHER_KEY_SEL] =	0x124,
+	[PWRAP_CIPHER_IV_SEL] =		0x128,
+	[PWRAP_CIPHER_EN] =		0x12c,
+	[PWRAP_CIPHER_RDY] =		0x130,
+	[PWRAP_CIPHER_MODE] =		0x134,
+	[PWRAP_CIPHER_SWRST] =		0x138,
+	[PWRAP_DCM_EN] =		0x13c,
+	[PWRAP_DCM_DBC_PRD] =		0x140,
+	[PWRAP_ADC_CMD_ADDR] =		0x144,
+	[PWRAP_PWRAP_ADC_CMD] =		0x148,
+	[PWRAP_ADC_RDY_ADDR] =		0x14c,
+	[PWRAP_ADC_RDATA_ADDR1] =	0x150,
+	[PWRAP_ADC_RDATA_ADDR2] =	0x154,
+	[PWRAP_SW_RST] =		0x180,
+};
+
 static const int mt6765_regs[] = {
 	[PWRAP_MUX_SEL] =		0x0,
 	[PWRAP_WRAP_EN] =		0x4,
@@ -1314,6 +1404,7 @@ enum pmic_type {
 
 enum pwrap_type {
 	PWRAP_MT2701,
+	PWRAP_MT6572,
 	PWRAP_MT6765,
 	PWRAP_MT6779,
 	PWRAP_MT6795,
@@ -1733,6 +1824,11 @@ static void pwrap_init_chip_select_ext(struct pmic_wrapper *wrp, u8 hext_write,
 static int pwrap_common_init_reg_clock(struct pmic_wrapper *wrp)
 {
 	switch (wrp->master->type) {
+	case PWRAP_MT6572:
+		pwrap_writel(wrp, 0x8, PWRAP_RDDMY);
+		pwrap_write(wrp, wrp->slave->dew_regs[PWRAP_DEW_RDDMY_NO], 0x8);
+		pwrap_init_chip_select_ext(wrp, 5, 0, 0, 0);
+		break;
 	case PWRAP_MT6795:
 		if (wrp->slave->type == PMIC_MT6331) {
 			const u32 *dew_regs = wrp->slave->dew_regs;
@@ -1839,6 +1935,7 @@ static int pwrap_init_cipher(struct pmic_wrapper *wrp)
 		pwrap_writel(wrp, 1, PWRAP_CIPHER_START);
 		break;
 	case PWRAP_MT2701:
+	case PWRAP_MT6572:
 	case PWRAP_MT6765:
 	case PWRAP_MT6779:
 	case PWRAP_MT6795:
@@ -2277,6 +2374,19 @@ static const struct pmic_wrapper_type pwrap_mt2701 = {
 	.init_soc_specific = pwrap_mt2701_init_soc_specific,
 };
 
+static const struct pmic_wrapper_type pwrap_mt6572 = {
+	.regs = mt6572_regs,
+	.type = PWRAP_MT6572,
+	.arb_en_all = 0x1ff,
+	.int_en_all = 0x7ffffffd,
+	.int1_en_all = 0,
+	.spi_w = PWRAP_MAN_CMD_SPI_WRITE,
+	.wdt_src = PWRAP_WDT_SRC_MASK_ALL,
+	.caps = PWRAP_CAP_RESET | PWRAP_CAP_DCM,
+	.init_reg_clock = pwrap_common_init_reg_clock,
+	.init_soc_specific = pwrap_mt2701_init_soc_specific,
+};
+
 static const struct pmic_wrapper_type pwrap_mt6765 = {
 	.regs = mt6765_regs,
 	.type = PWRAP_MT6765,
@@ -2446,6 +2556,7 @@ static const struct pmic_wrapper_type pwrap_mt8186 = {
 
 static const struct of_device_id of_pwrap_match_tbl[] = {
 	{ .compatible = "mediatek,mt2701-pwrap", .data = &pwrap_mt2701 },
+	{ .compatible = "mediatek,mt6572-pwrap", .data = &pwrap_mt6572 },
 	{ .compatible = "mediatek,mt6765-pwrap", .data = &pwrap_mt6765 },
 	{ .compatible = "mediatek,mt6779-pwrap", .data = &pwrap_mt6779 },
 	{ .compatible = "mediatek,mt6795-pwrap", .data = &pwrap_mt6795 },

-- 
2.54.0



^ permalink raw reply related	[flat|nested] 6+ messages in thread

* Re: [PATCH 2/3] soc: mediatek: pwrap: use correct log level
  2026-07-14 12:42 ` [PATCH 2/3] soc: mediatek: pwrap: use correct log level Roman Vivchar via B4 Relay
@ 2026-07-14 12:53   ` sashiko-bot
  0 siblings, 0 replies; 6+ messages in thread
From: sashiko-bot @ 2026-07-14 12:53 UTC (permalink / raw)
  To: Roman Vivchar; +Cc: robh, conor+dt, devicetree

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Child devices created by `of_platform_populate()` are leaked upon probe failure or driver unbind, leading to a Use-After-Free.
--

--- Patch [2]: [PATCH 2/3] soc: mediatek: pwrap: use correct log level ---
commit 9e7d63641cf243186ed10eee942d5eeb9f4b6345
Author: Roman Vivchar <rva333@protonmail.com>

soc: mediatek: pwrap: use correct log level

This commit updates error handling in the mediatek pwrap driver to use
dev_err_probe instead of dev_dbg for error branches. It also simplifies
the returns by utilizing dev_err_probe.

> diff --git a/drivers/soc/mediatek/mtk-pmic-wrap.c b/drivers/soc/mediatek/mtk-pmic-wrap.c
> index 0bcd858263755..a4b10b0a97cbb 100644
> --- a/drivers/soc/mediatek/mtk-pmic-wrap.c
> +++ b/drivers/soc/mediatek/mtk-pmic-wrap.c

[ ... ]

> @@ -2593,11 +2584,9 @@ static int pwrap_probe(struct platform_device *pdev)
>  		return PTR_ERR(wrp->regmap);
>  
>  	ret = of_platform_populate(np, NULL, NULL, wrp->dev);
> -	if (ret) {
> -		dev_dbg(wrp->dev, "failed to create child devices at %pOF\n",
> -				np);
> -		return ret;
> -	}
> +	if (ret)
> +		return dev_err_probe(wrp->dev, ret,
> +				     "failed to create child devices at %pOF\n", np);

[Severity: High]
This is a pre-existing issue, but does this missing cleanup for
of_platform_populate() leave child devices registered if this fails
halfway through, or during driver unbind?

If a user unbinds the driver via sysfs, devres will automatically free
the parent driver's resources, including wrp->regmap. Since there is no
remove callback to call of_platform_depopulate(), the child devices
remain active. When these active child drivers subsequently attempt to
use their parent's freed regmap, could this result in a use-after-free?

Would it be safer to use devm_of_platform_populate() here instead to
ensure proper cleanup?

>  	return 0;
>  }

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260714-6572-pwrap-v1-0-d8e5a39cf7ef@protonmail.com?part=2

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [PATCH 3/3] soc: mediatek: pwrap: add mt6572 support
  2026-07-14 12:42 ` [PATCH 3/3] soc: mediatek: pwrap: add mt6572 support Roman Vivchar via B4 Relay
@ 2026-07-14 13:24   ` sashiko-bot
  0 siblings, 0 replies; 6+ messages in thread
From: sashiko-bot @ 2026-07-14 13:24 UTC (permalink / raw)
  To: Roman Vivchar; +Cc: robh, conor+dt, devicetree

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Unconditional dereference and access of `wrp->slave->dew_regs` in MT6572 clock initialization can cause a NULL pointer dereference or unintended PMIC register overwrite.
--

--- Patch [3]: [PATCH 3/3] soc: mediatek: pwrap: add mt6572 support ---
commit 27b1606815262a3356b161758ca5a4ebb413b4ab
Author: Roman Vivchar <rva333@protonmail.com>

soc: mediatek: pwrap: add mt6572 support

This commit adds mt6572 registers and platform data for the pmic wrapper.
It reuses the mt2701 SoC-specific initialization function since they share
the same GPS_INTF settings.

> diff --git a/drivers/soc/mediatek/mtk-pmic-wrap.c b/drivers/soc/mediatek/mtk-pmic-wrap.c
> index a4b10b0a97cbb..4b8a5dc80a36e 100644
> --- a/drivers/soc/mediatek/mtk-pmic-wrap.c
> +++ b/drivers/soc/mediatek/mtk-pmic-wrap.c

[ ... ]

> @@ -1733,6 +1824,11 @@ static void pwrap_init_chip_select_ext(struct pmic_wrapper *wrp, u8 hext_write,
>  static int pwrap_common_init_reg_clock(struct pmic_wrapper *wrp)
>  {
>  	switch (wrp->master->type) {
> +	case PWRAP_MT6572:
> +		pwrap_writel(wrp, 0x8, PWRAP_RDDMY);
> +		pwrap_write(wrp, wrp->slave->dew_regs[PWRAP_DEW_RDDMY_NO], 0x8);

[Severity: High]
Could this unconditionally dereference wrp->slave->dew_regs if the configured
slave PMIC doesn't populate it?

If the mediatek,mt6572-pwrap device node is configured with a PMIC that
doesn't populate dew_regs (like PMIC_MT6380), or leaves PWRAP_DEW_RDDMY_NO
uninitialized (like PMIC_MT6397), this array lookup could either
dereference a NULL pointer or evaluate to 0x0. 

This could lead to a kernel panic during driver probe or an unintended
SPI write of 0x8 to PMIC register 0x0.

Would it be safer to validate the slave PMIC type or check that dew_regs is
present before accessing it here, similar to how it is handled for
PWRAP_MT6795 below?

> +		pwrap_init_chip_select_ext(wrp, 5, 0, 0, 0);
> +		break;
>  	case PWRAP_MT6795:
>  		if (wrp->slave->type == PMIC_MT6331) {

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260714-6572-pwrap-v1-0-d8e5a39cf7ef@protonmail.com?part=3

^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2026-07-14 13:24 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-14 12:42 [PATCH 0/3] soc: mediatek: pwrap: mt6572 support + log level fixes Roman Vivchar via B4 Relay
2026-07-14 12:42 ` [PATCH 1/3] dt-bindings: soc: mediatek: pwrap: add mt6572 Roman Vivchar via B4 Relay
2026-07-14 12:42 ` [PATCH 2/3] soc: mediatek: pwrap: use correct log level Roman Vivchar via B4 Relay
2026-07-14 12:53   ` sashiko-bot
2026-07-14 12:42 ` [PATCH 3/3] soc: mediatek: pwrap: add mt6572 support Roman Vivchar via B4 Relay
2026-07-14 13:24   ` sashiko-bot

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox