All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 0/3] nvmem: mtk-efuse: mt6572 support
@ 2026-07-15 14:27 ` Roman Vivchar
  0 siblings, 0 replies; 9+ messages in thread
From: Roman Vivchar via B4 Relay @ 2026-07-15 14:27 UTC (permalink / raw)
  To: Srinivas Kandagatla, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley, Matthias Brugger, AngeloGioacchino Del Regno,
	Andrew-CT Chen, Lala Lin
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

This patch series adds MediaTek mt6572 efuse support. Unlike newer SoCs,
its efuse controller doesn't work properly with 8-bit reads, leading to
invalid data with current mtk-efuse driver implementation.

This behavior can be observed with devmem (0x10009174 and 0x10009178 are
thermal calibration cells):
~ # devmem 0x10009174 32
0x00CDD4CD
~ # devmem 0x10009178 32
0x0F76865D
~ # devmem 0x10009174 8
0xCD
~ # devmem 0x10009175 8
0x00
~ # devmem 0x10009176 8
0x00
~ # devmem 0x10009177 8
0x00
~ # devmem 0x10009178 8
0x5D
~ # devmem 0x10009179 8
0x00
~ # devmem 0x1000917a 8
0x00
~ # devmem 0x1000917b 8
0x00

Patch 1 adds dt-bindings compatible for the mt6572,
Patch 2 adds platform data option to use aligned 32-bit reads instead
of plain readb().
Patch 3 adds platform data for mt6572 SoC.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
Roman Vivchar (3):
      dt-bindings: nvmem: mediatek: efuse: add mt6572
      nvmem: mtk-efuse: add support for 32-bit aligned reads
      nvmem: mtk-efuse: add mt6572 support

 .../devicetree/bindings/nvmem/mediatek,efuse.yaml  |  1 +
 drivers/nvmem/mtk-efuse.c                          | 37 ++++++++++++++++++++--
 2 files changed, 35 insertions(+), 3 deletions(-)
---
base-commit: 8cd9520d35a6c38db6567e97dd93b1f11f185dc6
change-id: 20260710-6572-nvmem-eb98c7a73351

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



^ permalink raw reply	[flat|nested] 9+ messages in thread

* [PATCH 0/3] nvmem: mtk-efuse: mt6572 support
@ 2026-07-15 14:27 ` Roman Vivchar
  0 siblings, 0 replies; 9+ messages in thread
From: Roman Vivchar @ 2026-07-15 14:27 UTC (permalink / raw)
  To: Srinivas Kandagatla, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley, Matthias Brugger, AngeloGioacchino Del Regno,
	Andrew-CT Chen, Lala Lin
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

This patch series adds MediaTek mt6572 efuse support. Unlike newer SoCs,
its efuse controller doesn't work properly with 8-bit reads, leading to
invalid data with current mtk-efuse driver implementation.

This behavior can be observed with devmem (0x10009174 and 0x10009178 are
thermal calibration cells):
~ # devmem 0x10009174 32
0x00CDD4CD
~ # devmem 0x10009178 32
0x0F76865D
~ # devmem 0x10009174 8
0xCD
~ # devmem 0x10009175 8
0x00
~ # devmem 0x10009176 8
0x00
~ # devmem 0x10009177 8
0x00
~ # devmem 0x10009178 8
0x5D
~ # devmem 0x10009179 8
0x00
~ # devmem 0x1000917a 8
0x00
~ # devmem 0x1000917b 8
0x00

Patch 1 adds dt-bindings compatible for the mt6572,
Patch 2 adds platform data option to use aligned 32-bit reads instead
of plain readb().
Patch 3 adds platform data for mt6572 SoC.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
Roman Vivchar (3):
      dt-bindings: nvmem: mediatek: efuse: add mt6572
      nvmem: mtk-efuse: add support for 32-bit aligned reads
      nvmem: mtk-efuse: add mt6572 support

 .../devicetree/bindings/nvmem/mediatek,efuse.yaml  |  1 +
 drivers/nvmem/mtk-efuse.c                          | 37 ++++++++++++++++++++--
 2 files changed, 35 insertions(+), 3 deletions(-)
---
base-commit: 8cd9520d35a6c38db6567e97dd93b1f11f185dc6
change-id: 20260710-6572-nvmem-eb98c7a73351

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


^ permalink raw reply	[flat|nested] 9+ messages in thread

* [PATCH 1/3] dt-bindings: nvmem: mediatek: efuse: add mt6572
  2026-07-15 14:27 ` Roman Vivchar
@ 2026-07-15 14:27   ` Roman Vivchar
  -1 siblings, 0 replies; 9+ messages in thread
From: Roman Vivchar via B4 Relay @ 2026-07-15 14:27 UTC (permalink / raw)
  To: Srinivas Kandagatla, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley, Matthias Brugger, AngeloGioacchino Del Regno,
	Andrew-CT Chen, Lala Lin
  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 efuse controller.

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

diff --git a/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml b/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml
index f9323b3ecfc8..269e2b09f5c8 100644
--- a/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml
+++ b/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml
@@ -44,6 +44,7 @@ properties:
 
       - items:
           - enum:
+              - mediatek,mt6572-efuse
               - mediatek,mt7622-efuse
               - mediatek,mt7623-efuse
               - mediatek,mt7981-efuse

-- 
2.54.0



^ permalink raw reply related	[flat|nested] 9+ messages in thread

* [PATCH 1/3] dt-bindings: nvmem: mediatek: efuse: add mt6572
@ 2026-07-15 14:27   ` Roman Vivchar
  0 siblings, 0 replies; 9+ messages in thread
From: Roman Vivchar @ 2026-07-15 14:27 UTC (permalink / raw)
  To: Srinivas Kandagatla, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley, Matthias Brugger, AngeloGioacchino Del Regno,
	Andrew-CT Chen, Lala Lin
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

Add a compatible string for the mt6572 SoC efuse controller.

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

diff --git a/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml b/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml
index f9323b3ecfc8..269e2b09f5c8 100644
--- a/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml
+++ b/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml
@@ -44,6 +44,7 @@ properties:
 
       - items:
           - enum:
+              - mediatek,mt6572-efuse
               - mediatek,mt7622-efuse
               - mediatek,mt7623-efuse
               - mediatek,mt7981-efuse

-- 
2.54.0


^ permalink raw reply related	[flat|nested] 9+ messages in thread

* [PATCH 2/3] nvmem: mtk-efuse: add support for 32-bit aligned reads
  2026-07-15 14:27 ` Roman Vivchar
@ 2026-07-15 14:27   ` Roman Vivchar
  -1 siblings, 0 replies; 9+ messages in thread
From: Roman Vivchar via B4 Relay @ 2026-07-15 14:27 UTC (permalink / raw)
  To: Srinivas Kandagatla, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley, Matthias Brugger, AngeloGioacchino Del Regno,
	Andrew-CT Chen, Lala Lin
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

From: Roman Vivchar <rva333@protonmail.com>

Some MediaTek SoCs, such as mt6572, don't support 8-bit reads, leading
to zeroes or garbage data. 32-bit aligned reads must be used instead.

Introduce an 'needs_aligned_read' field to the platform data to enforce
32-bit aligned register access. All reads will be performed by reading
4-byte words and masking them.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
 drivers/nvmem/mtk-efuse.c | 31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c
index af953e1d9230..1462f2760818 100644
--- a/drivers/nvmem/mtk-efuse.c
+++ b/drivers/nvmem/mtk-efuse.c
@@ -4,6 +4,7 @@
  * Author: Andrew-CT Chen <andrew-ct.chen@mediatek.com>
  */
 
+#include <linux/align.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -14,10 +15,12 @@
 
 struct mtk_efuse_pdata {
 	bool uses_post_processing;
+	bool needs_aligned_read;
 };
 
 struct mtk_efuse_priv {
 	void __iomem *base;
+	const struct mtk_efuse_pdata *data;
 };
 
 static int mtk_reg_read(void *context,
@@ -28,6 +31,26 @@ static int mtk_reg_read(void *context,
 	u8 *val = _val;
 	int i;
 
+	if (priv->data->needs_aligned_read) {
+		u32 pos, shift, val32;
+
+		for (i = 0; i < bytes; i++, val++) {
+			pos = reg + i;
+
+			/*
+			 * Read on 32-bit word boundary or if it's the first
+			 * iteration
+			 */
+			if (i == 0 || IS_ALIGNED(pos, 4))
+				val32 = readl(priv->base + (pos & ~3));
+
+			shift = (pos & 3) * 8;
+			*val = (val32 >> shift) & 0xff;
+		}
+
+		return 0;
+	}
+
 	for (i = 0; i < bytes; i++, val++)
 		*val = readb(addr + i);
 
@@ -67,7 +90,6 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	struct nvmem_device *nvmem;
 	struct nvmem_config econfig = {};
 	struct mtk_efuse_priv *priv;
-	const struct mtk_efuse_pdata *pdata;
 	struct platform_device *socinfo;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -78,7 +100,8 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
-	pdata = device_get_match_data(dev);
+	priv->data = device_get_match_data(dev);
+
 	econfig.add_legacy_fixed_of_cells = true;
 	econfig.stride = 1;
 	econfig.word_size = 1;
@@ -86,7 +109,7 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	econfig.size = resource_size(res);
 	econfig.priv = priv;
 	econfig.dev = dev;
-	if (pdata->uses_post_processing)
+	if (priv->data->uses_post_processing)
 		econfig.fixup_dt_cell_info = &mtk_efuse_fixup_dt_cell_info;
 	nvmem = devm_nvmem_register(dev, &econfig);
 	if (IS_ERR(nvmem))
@@ -103,10 +126,12 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 
 static const struct mtk_efuse_pdata mtk_mt8186_efuse_pdata = {
 	.uses_post_processing = true,
+	.needs_aligned_read = false,
 };
 
 static const struct mtk_efuse_pdata mtk_efuse_pdata = {
 	.uses_post_processing = false,
+	.needs_aligned_read = false,
 };
 
 static const struct of_device_id mtk_efuse_of_match[] = {

-- 
2.54.0



^ permalink raw reply related	[flat|nested] 9+ messages in thread

* [PATCH 2/3] nvmem: mtk-efuse: add support for 32-bit aligned reads
@ 2026-07-15 14:27   ` Roman Vivchar
  0 siblings, 0 replies; 9+ messages in thread
From: Roman Vivchar @ 2026-07-15 14:27 UTC (permalink / raw)
  To: Srinivas Kandagatla, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley, Matthias Brugger, AngeloGioacchino Del Regno,
	Andrew-CT Chen, Lala Lin
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

Some MediaTek SoCs, such as mt6572, don't support 8-bit reads, leading
to zeroes or garbage data. 32-bit aligned reads must be used instead.

Introduce an 'needs_aligned_read' field to the platform data to enforce
32-bit aligned register access. All reads will be performed by reading
4-byte words and masking them.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
 drivers/nvmem/mtk-efuse.c | 31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c
index af953e1d9230..1462f2760818 100644
--- a/drivers/nvmem/mtk-efuse.c
+++ b/drivers/nvmem/mtk-efuse.c
@@ -4,6 +4,7 @@
  * Author: Andrew-CT Chen <andrew-ct.chen@mediatek.com>
  */
 
+#include <linux/align.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -14,10 +15,12 @@
 
 struct mtk_efuse_pdata {
 	bool uses_post_processing;
+	bool needs_aligned_read;
 };
 
 struct mtk_efuse_priv {
 	void __iomem *base;
+	const struct mtk_efuse_pdata *data;
 };
 
 static int mtk_reg_read(void *context,
@@ -28,6 +31,26 @@ static int mtk_reg_read(void *context,
 	u8 *val = _val;
 	int i;
 
+	if (priv->data->needs_aligned_read) {
+		u32 pos, shift, val32;
+
+		for (i = 0; i < bytes; i++, val++) {
+			pos = reg + i;
+
+			/*
+			 * Read on 32-bit word boundary or if it's the first
+			 * iteration
+			 */
+			if (i == 0 || IS_ALIGNED(pos, 4))
+				val32 = readl(priv->base + (pos & ~3));
+
+			shift = (pos & 3) * 8;
+			*val = (val32 >> shift) & 0xff;
+		}
+
+		return 0;
+	}
+
 	for (i = 0; i < bytes; i++, val++)
 		*val = readb(addr + i);
 
@@ -67,7 +90,6 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	struct nvmem_device *nvmem;
 	struct nvmem_config econfig = {};
 	struct mtk_efuse_priv *priv;
-	const struct mtk_efuse_pdata *pdata;
 	struct platform_device *socinfo;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -78,7 +100,8 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
-	pdata = device_get_match_data(dev);
+	priv->data = device_get_match_data(dev);
+
 	econfig.add_legacy_fixed_of_cells = true;
 	econfig.stride = 1;
 	econfig.word_size = 1;
@@ -86,7 +109,7 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	econfig.size = resource_size(res);
 	econfig.priv = priv;
 	econfig.dev = dev;
-	if (pdata->uses_post_processing)
+	if (priv->data->uses_post_processing)
 		econfig.fixup_dt_cell_info = &mtk_efuse_fixup_dt_cell_info;
 	nvmem = devm_nvmem_register(dev, &econfig);
 	if (IS_ERR(nvmem))
@@ -103,10 +126,12 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 
 static const struct mtk_efuse_pdata mtk_mt8186_efuse_pdata = {
 	.uses_post_processing = true,
+	.needs_aligned_read = false,
 };
 
 static const struct mtk_efuse_pdata mtk_efuse_pdata = {
 	.uses_post_processing = false,
+	.needs_aligned_read = false,
 };
 
 static const struct of_device_id mtk_efuse_of_match[] = {

-- 
2.54.0


^ permalink raw reply related	[flat|nested] 9+ messages in thread

* [PATCH 3/3] nvmem: mtk-efuse: add mt6572 support
  2026-07-15 14:27 ` Roman Vivchar
@ 2026-07-15 14:27   ` Roman Vivchar
  -1 siblings, 0 replies; 9+ messages in thread
From: Roman Vivchar via B4 Relay @ 2026-07-15 14:27 UTC (permalink / raw)
  To: Srinivas Kandagatla, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley, Matthias Brugger, AngeloGioacchino Del Regno,
	Andrew-CT Chen, Lala Lin
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

From: Roman Vivchar <rva333@protonmail.com>

Add a platform data struct for the efuse controller.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
 drivers/nvmem/mtk-efuse.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c
index 1462f2760818..a79434608465 100644
--- a/drivers/nvmem/mtk-efuse.c
+++ b/drivers/nvmem/mtk-efuse.c
@@ -124,6 +124,11 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct mtk_efuse_pdata mtk_mt6572_efuse_pdata = {
+	.uses_post_processing = false,
+	.needs_aligned_read = true,
+};
+
 static const struct mtk_efuse_pdata mtk_mt8186_efuse_pdata = {
 	.uses_post_processing = true,
 	.needs_aligned_read = false,
@@ -135,6 +140,7 @@ static const struct mtk_efuse_pdata mtk_efuse_pdata = {
 };
 
 static const struct of_device_id mtk_efuse_of_match[] = {
+	{ .compatible = "mediatek,mt6572-efuse", .data = &mtk_mt6572_efuse_pdata },
 	{ .compatible = "mediatek,mt8173-efuse", .data = &mtk_efuse_pdata },
 	{ .compatible = "mediatek,mt8186-efuse", .data = &mtk_mt8186_efuse_pdata },
 	{ .compatible = "mediatek,efuse", .data = &mtk_efuse_pdata },

-- 
2.54.0



^ permalink raw reply related	[flat|nested] 9+ messages in thread

* [PATCH 3/3] nvmem: mtk-efuse: add mt6572 support
@ 2026-07-15 14:27   ` Roman Vivchar
  0 siblings, 0 replies; 9+ messages in thread
From: Roman Vivchar @ 2026-07-15 14:27 UTC (permalink / raw)
  To: Srinivas Kandagatla, Rob Herring, Krzysztof Kozlowski,
	Conor Dooley, Matthias Brugger, AngeloGioacchino Del Regno,
	Andrew-CT Chen, Lala Lin
  Cc: devicetree, linux-kernel, linux-arm-kernel, linux-mediatek,
	Roman Vivchar

Add a platform data struct for the efuse controller.

Signed-off-by: Roman Vivchar <rva333@protonmail.com>
---
 drivers/nvmem/mtk-efuse.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c
index 1462f2760818..a79434608465 100644
--- a/drivers/nvmem/mtk-efuse.c
+++ b/drivers/nvmem/mtk-efuse.c
@@ -124,6 +124,11 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct mtk_efuse_pdata mtk_mt6572_efuse_pdata = {
+	.uses_post_processing = false,
+	.needs_aligned_read = true,
+};
+
 static const struct mtk_efuse_pdata mtk_mt8186_efuse_pdata = {
 	.uses_post_processing = true,
 	.needs_aligned_read = false,
@@ -135,6 +140,7 @@ static const struct mtk_efuse_pdata mtk_efuse_pdata = {
 };
 
 static const struct of_device_id mtk_efuse_of_match[] = {
+	{ .compatible = "mediatek,mt6572-efuse", .data = &mtk_mt6572_efuse_pdata },
 	{ .compatible = "mediatek,mt8173-efuse", .data = &mtk_efuse_pdata },
 	{ .compatible = "mediatek,mt8186-efuse", .data = &mtk_mt8186_efuse_pdata },
 	{ .compatible = "mediatek,efuse", .data = &mtk_efuse_pdata },

-- 
2.54.0


^ permalink raw reply related	[flat|nested] 9+ messages in thread

* Re: [PATCH 3/3] nvmem: mtk-efuse: add mt6572 support
  2026-07-15 14:27   ` Roman Vivchar
  (?)
@ 2026-07-15 14:45   ` sashiko-bot
  -1 siblings, 0 replies; 9+ messages in thread
From: sashiko-bot @ 2026-07-15 14:45 UTC (permalink / raw)
  To: Roman Vivchar; +Cc: conor+dt, devicetree, robh

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

Pre-existing issues:
- [High] Incorrect string comparison logic erroneously matches any nvmem cell name that is a prefix of 'gpu-speedbin'.
--

--- Patch [3]: [PATCH 3/3] nvmem: mtk-efuse: add mt6572 support ---
commit 2c71c19eb8895343bae32ea1c4c07b25c01cd56c
Author: Roman Vivchar <rva333@protonmail.com>

    nvmem: mtk-efuse: add mt6572 support
    
    Add a platform data struct for the efuse controller.

> diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c
> index 1462f27608184..a794346084658 100644
> --- a/drivers/nvmem/mtk-efuse.c
> +++ b/drivers/nvmem/mtk-efuse.c
> @@ -124,6 +124,11 @@ static int mtk_efuse_probe(struct platform_device *pdev)
>  	return 0;
>  }
>  
> +static const struct mtk_efuse_pdata mtk_mt6572_efuse_pdata = {
> +	.uses_post_processing = false,

[Severity: High]
This isn't a bug introduced by this patch, but there is a pre-existing issue
with the post-processing logic in this driver.

Looking at mtk_efuse_fixup_dt_cell_info(), the string comparison logic
erroneously matches any nvmem cell name that is a prefix of "gpu-speedbin":

drivers/nvmem/mtk-efuse.c:mtk_efuse_fixup_dt_cell_info() {
    ...
	if (cell->nbits <= 3 &&
	    strncmp(cell->name, "gpu-speedbin", min(sz, strlen("gpu-speedbin"))) == 0)
		cell->read_post_process = mtk_efuse_gpu_speedbin_pp;
    ...
}

Because strncmp() uses min(strlen(cell->name), strlen("gpu-speedbin")) for
the comparison length, it restricts the comparison to the shorter length.

If a device tree defines a cell with a name that is a substring of
"gpu-speedbin" (e.g., "gpu" or "gpu-speed") and has 3 or fewer bits, this
will evaluate to 0.

This incorrectly applies the post-processing fixup to completely unrelated
cells, which could cause silent data corruption.

Would it be possible to change this comparison to prevent short-prefix
matches?

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-6572-nvmem-v1-0-9c13be99d077@protonmail.com?part=3

^ permalink raw reply	[flat|nested] 9+ messages in thread

end of thread, other threads:[~2026-07-15 14:45 UTC | newest]

Thread overview: 9+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-15 14:27 [PATCH 0/3] nvmem: mtk-efuse: mt6572 support Roman Vivchar via B4 Relay
2026-07-15 14:27 ` Roman Vivchar
2026-07-15 14:27 ` [PATCH 1/3] dt-bindings: nvmem: mediatek: efuse: add mt6572 Roman Vivchar via B4 Relay
2026-07-15 14:27   ` Roman Vivchar
2026-07-15 14:27 ` [PATCH 2/3] nvmem: mtk-efuse: add support for 32-bit aligned reads Roman Vivchar via B4 Relay
2026-07-15 14:27   ` Roman Vivchar
2026-07-15 14:27 ` [PATCH 3/3] nvmem: mtk-efuse: add mt6572 support Roman Vivchar via B4 Relay
2026-07-15 14:27   ` Roman Vivchar
2026-07-15 14:45   ` 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.