[PATCH 0/9] Support ELE API in i.MX OCOTP NVMEM driver

[PATCH 0/9] Support ELE API in i.MX OCOTP NVMEM driver

[Frieder Schrempf]

The imx-ocotp-ele.c driver currently uses the limited FSB (fuseblock)
to access the fuse registers. In order to gain full read/write access
to all fuses, we need to use the Edgelock Secure Enclave firmware.

This patchset does:

* Add bindings to reference ELE device in OCOTP driver (patch 1)
* Add ELE API functions for accessing the fuses (patch 3)
* Let the OCOTP driver use the ELE API (patch 6)
* Extend the devicetree of the Kontron boards for using the ELE API (patch 9)

The rest of the patches contain cleanups that were implemented along
the way.

This was tested using the 'crucible' tool and through hexdump on the
nvmem device.

---
Frieder Schrempf (9):
      dt-bindings: nvmem: imx-ocotp: Add support for secure-enclave
      firmware: imx: ele: Fix indentation in ele_base_msg.h
      firmware: imx: ele: Add API functions for OCOTP fuse access
      nvmem: imx-ocotp-ele: Add keepout table for i.MX93
      nvmem: imx-ocotp-ele: Remove device-specific reg_read()
      nvmem: imx-ocotp-ele: Support the ELE API
      nvmem: imx-ocotp-ele: Remove the FUSE_ELE type
      nvmem: imx-ocotp-ele: Rename FSB access map
      arm64: dts: imx93-kontron: Enable ELE firmware driver

 .../devicetree/bindings/nvmem/imx-ocotp.yaml       |   4 +
 .../boot/dts/freescale/imx93-kontron-osm-s.dtsi    |  26 ++++
 drivers/firmware/imx/ele_base_msg.c                | 122 ++++++++++++++++++
 drivers/firmware/imx/ele_base_msg.h                |  22 ++--
 drivers/nvmem/imx-ocotp-ele.c                      | 137 ++++++++++++++++-----
 include/linux/firmware/imx/se_api.h                |   3 +
 6 files changed, 277 insertions(+), 37 deletions(-)
---
base-commit: 49e02880ec0a8c378e811bc9d85da188d7c6204c
change-id: 20260616-upstreaming-next-20260609-imx-ocotp-ele-a512ddf96b03

Best regards,
--  
Frieder Schrempf <frieder.schrempf@kontron.de>

[PATCH 1/9] dt-bindings: nvmem: imx-ocotp: Add support for secure-enclave

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

Some SoCs like the i.MX9 family allow full access to the fuses only
through the secure enclave firmware API. Add a property to reference
the secure enclave node and let the driver use the API.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml
index a8076d0e2737..14a6429f4a4c 100644
--- a/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml
+++ b/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml
@@ -53,6 +53,10 @@ properties:
   reg:
     maxItems: 1
 
+  secure-enclave:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description: A phandle to the secure enclave node
+
   clocks:
     maxItems: 1
 

-- 
2.54.0

Re: [PATCH 1/9] dt-bindings: nvmem: imx-ocotp: Add support for secure-enclave

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] The newly added `secure-enclave` property lacks a vendor prefix.
--

commit cf8315ecdb4e65137976e7833794688f5241f64e
Author: Frieder Schrempf <frieder.schrempf@kontron.de>

dt-bindings: nvmem: imx-ocotp: Add support for secure-enclave

Some SoCs like the i.MX9 family allow full access to the fuses only
through the secure enclave firmware API. Add a property to reference
the secure enclave node and let the driver use the API.

> diff --git a/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml
> index a8076d0e2737c..14a6429f4a4c0 100644
> --- a/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml
> +++ b/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml
> @@ -53,6 +53,10 @@ properties:
>    reg:
>      maxItems: 1
>  
> +  secure-enclave:

[Severity: Low]
Does this new property need a vendor prefix? Since this appears to be specific
to NXP/Freescale i.MX hardware for referencing the secure enclave firmware, it
should likely be named with an appropriate vendor prefix like
"fsl,secure-enclave" rather than as a standard generic property.

> +    $ref: /schemas/types.yaml#/definitions/phandle
> +    description: A phandle to the secure enclave node
> +
>    clocks:
>      maxItems: 1

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260616-upstreaming-next-20260609-imx-ocotp-ele-v1-0-cb7f3698c3e6@kontron.de?part=1

[PATCH 2/9] firmware: imx: ele: Fix indentation in ele_base_msg.h

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

The file uses mixed indentation characters. Use tabs everywhere.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 drivers/firmware/imx/ele_base_msg.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/firmware/imx/ele_base_msg.h b/drivers/firmware/imx/ele_base_msg.h
index 75e65e279193..1c5d6791b323 100644
--- a/drivers/firmware/imx/ele_base_msg.h
+++ b/drivers/firmware/imx/ele_base_msg.h
@@ -27,19 +27,19 @@
 #define ELE_GEN_KEY_BLOB_REQ		0xaf
 #define ELE_GET_FW_STATUS_REQ		0xc5
 #define ELE_XIP_DECRYPT_REQ		0xc6
-#define ELE_WRITE_FUSE                  0xd6
-#define ELE_DEV_ATTEST_REQ              0xdb
-#define ELE_WRITE_SHADOW_FUSE_REQ       0xf2
-#define ELE_READ_SHADOW_FUSE_REQ        0xf3
+#define ELE_WRITE_FUSE			0xd6
+#define ELE_DEV_ATTEST_REQ		0xdb
+#define ELE_WRITE_SHADOW_FUSE_REQ	0xf2
+#define ELE_READ_SHADOW_FUSE_REQ	0xf3
 
 #define ELE_GET_INFO_REQ		0xda
 #define ELE_GET_INFO_REQ_MSG_SZ		0x10
 #define ELE_GET_INFO_RSP_MSG_SZ		0x08
 
-#define MAX_UID_SIZE                     (16)
-#define DEV_GETINFO_ROM_PATCH_SHA_SZ     (32)
-#define DEV_GETINFO_FW_SHA_SZ            (32)
-#define DEV_GETINFO_OEM_SRKH_SZ          (64)
+#define MAX_UID_SIZE			(16)
+#define DEV_GETINFO_ROM_PATCH_SHA_SZ	(32)
+#define DEV_GETINFO_FW_SHA_SZ		(32)
+#define DEV_GETINFO_OEM_SRKH_SZ		(64)
 #define DEV_GETINFO_MIN_VER_MASK	0xff
 #define DEV_GETINFO_MAJ_VER_MASK	0xff00
 #define ELE_DEV_INFO_EXTRA_SZ		0x60

-- 
2.54.0

[PATCH 3/9] firmware: imx: ele: Add API functions for OCOTP fuse access

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

The ELE S400 API provides read and write access to the OCOTP fuse
registers. This adds the necessary API functions imx_se_read_fuse()
and imx_se_write_fuse() to be used by other drivers such as the
OCOTP S400 NVMEM driver.

This is ported from the downstream vendor kernel.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 drivers/firmware/imx/ele_base_msg.c | 122 ++++++++++++++++++++++++++++++++++++
 drivers/firmware/imx/ele_base_msg.h |   6 ++
 include/linux/firmware/imx/se_api.h |   3 +
 3 files changed, 131 insertions(+)

diff --git a/drivers/firmware/imx/ele_base_msg.c b/drivers/firmware/imx/ele_base_msg.c
index ec718d322abc..281d223aa144 100644
--- a/drivers/firmware/imx/ele_base_msg.c
+++ b/drivers/firmware/imx/ele_base_msg.c
@@ -8,6 +8,7 @@
 #include <linux/cleanup.h>
 #include <linux/completion.h>
 #include <linux/dma-mapping.h>
+#include <linux/firmware/imx/se_api.h>
 #include <linux/genalloc.h>
 
 #include "ele_base_msg.h"
@@ -303,3 +304,124 @@ int ele_debug_dump(struct se_if_priv *priv)
 
 	return ret;
 }
+
+static int ele_read_fuse(struct se_if_priv *priv, uint16_t fuse_id, u32 *value)
+{
+	struct se_api_msg *tx_msg __free(kfree) = NULL;
+	struct se_api_msg *rx_msg __free(kfree) = NULL;
+	int rx_msg_sz = ELE_READ_FUSE_RSP_MSG_SZ;
+	int ret = 0;
+
+	if (!priv)
+		return -EINVAL;
+
+	tx_msg = kzalloc(ELE_READ_FUSE_REQ_MSG_SZ, GFP_KERNEL);
+	if (!tx_msg)
+		return -ENOMEM;
+
+	rx_msg = kzalloc(rx_msg_sz, GFP_KERNEL);
+	if (!rx_msg)
+		return -ENOMEM;
+
+	ret = se_fill_cmd_msg_hdr(priv, (struct se_msg_hdr *)&tx_msg->header,
+				  ELE_READ_FUSE_REQ, ELE_READ_FUSE_REQ_MSG_SZ,
+				  true);
+	if (ret)
+		return ret;
+
+	tx_msg->data[0] = fuse_id;
+
+	ret = ele_msg_send_rcv(priv->priv_dev_ctx, tx_msg,
+			       ELE_READ_FUSE_REQ_MSG_SZ, rx_msg, rx_msg_sz);
+	if (ret < 0)
+		return ret;
+
+	ret = se_val_rsp_hdr_n_status(priv, rx_msg, ELE_READ_FUSE_REQ,
+				      rx_msg_sz, true);
+	if (ret)
+		return ret;
+
+	*value = rx_msg->data[1];
+
+	return 0;
+}
+
+/**
+ * imx_se_read_fuse() - API to request SE-FW to read the fuse value.
+ * @se_if_data: refs to data attached to the se interface.
+ * @fuse_id: fuse identifier to read.
+ * @value: unsigned integer array to store the fuse values.
+ *
+ * Secure enclave like EdgeLock Enclave, manages the fuses. This API
+ * requests the FW to read the fuses. FW responds with the read values.
+ *
+ * Context:
+ *
+ * Return value:
+ *   0,   means success.
+ *   < 0, means failure.
+ */
+int imx_se_read_fuse(void *se_if_data, uint16_t fuse_id, u32 *value)
+{
+	return ele_read_fuse((struct se_if_priv *)se_if_data, fuse_id, value);
+}
+EXPORT_SYMBOL_GPL(imx_se_read_fuse);
+
+static int ele_write_fuse(struct se_if_priv *priv, uint16_t fuse_id, u32 value)
+{
+	struct se_api_msg *tx_msg __free(kfree) = NULL;
+	struct se_api_msg *rx_msg __free(kfree) = NULL;
+	int ret = 0;
+
+	if (!priv)
+		return -EINVAL;
+
+	tx_msg = kzalloc(ELE_WRITE_FUSE_REQ_MSG_SZ, GFP_KERNEL);
+	if (!tx_msg)
+		return -ENOMEM;
+
+	rx_msg = kzalloc(ELE_WRITE_FUSE_RSP_MSG_SZ, GFP_KERNEL);
+	if (!rx_msg)
+		return -ENOMEM;
+
+	ret = se_fill_cmd_msg_hdr(priv, (struct se_msg_hdr *)&tx_msg->header,
+				  ELE_WRITE_FUSE, ELE_WRITE_FUSE_REQ_MSG_SZ,
+				  true);
+	if (ret)
+		return ret;
+
+	tx_msg->data[0] = (32 << 16) | (fuse_id << 5);
+	tx_msg->data[1] = value;
+
+	ret = ele_msg_send_rcv(priv->priv_dev_ctx, tx_msg,
+			       ELE_WRITE_FUSE_REQ_MSG_SZ, rx_msg,
+			       ELE_WRITE_FUSE_RSP_MSG_SZ);
+	if (ret < 0)
+		return ret;
+
+	ret = se_val_rsp_hdr_n_status(priv, rx_msg, ELE_WRITE_FUSE,
+				      ELE_WRITE_FUSE_RSP_MSG_SZ, true);
+
+	return ret;
+}
+
+/**
+ * imx_se_write_fuse() - API to request SE-FW to write to fuses.
+ * @se_if_data: refs to data attached to the se interface.
+ * @fuse_id: fuse identifier to write to.
+ * @value: unsigned integer value that to be written to the fuse.
+ *
+ * Secure enclave like EdgeLock Enclave, manages the fuses. This API
+ * requests the FW to write the fuse with the given value.
+ *
+ * Context:
+ *
+ * Return value:
+ *   0,   means success.
+ *   < 0, means failure.
+ */
+int imx_se_write_fuse(void *se_if_data, uint16_t fuse_id, u32 value)
+{
+	return ele_write_fuse((struct se_if_priv *)se_if_data, fuse_id, value);
+}
+EXPORT_SYMBOL_GPL(imx_se_write_fuse);
diff --git a/drivers/firmware/imx/ele_base_msg.h b/drivers/firmware/imx/ele_base_msg.h
index 1c5d6791b323..2af3ada2ad07 100644
--- a/drivers/firmware/imx/ele_base_msg.h
+++ b/drivers/firmware/imx/ele_base_msg.h
@@ -36,6 +36,12 @@
 #define ELE_GET_INFO_REQ_MSG_SZ		0x10
 #define ELE_GET_INFO_RSP_MSG_SZ		0x08
 
+#define ELE_READ_FUSE_REQ_MSG_SZ	(8)
+#define ELE_READ_FUSE_RSP_MSG_SZ	(12)
+
+#define ELE_WRITE_FUSE_REQ_MSG_SZ	(12)
+#define ELE_WRITE_FUSE_RSP_MSG_SZ	(12)
+
 #define MAX_UID_SIZE			(16)
 #define DEV_GETINFO_ROM_PATCH_SHA_SZ	(32)
 #define DEV_GETINFO_FW_SHA_SZ		(32)
diff --git a/include/linux/firmware/imx/se_api.h b/include/linux/firmware/imx/se_api.h
index b1c4c9115d7b..ed766b1d48f8 100644
--- a/include/linux/firmware/imx/se_api.h
+++ b/include/linux/firmware/imx/se_api.h
@@ -11,4 +11,7 @@
 #define SOC_ID_OF_IMX8ULP		0x084d
 #define SOC_ID_OF_IMX93			0x9300
 
+int imx_se_read_fuse(void *se_if_data, uint16_t fuse_id, u32 *value);
+int imx_se_write_fuse(void *se_if_data, uint16_t fuse_id, u32 value);
+
 #endif /* __SE_API_H__ */

-- 
2.54.0

Re: [PATCH 3/9] firmware: imx: ele: Add API functions for OCOTP fuse access

[sashiko-bot]

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

Pre-existing issues:
- [High] A timeout or interrupt during `ele_msg_send_rcv()` leaves a dangling pointer in the asynchronous mailbox callback state (`priv->waiting_rsp_clbk_hdl`), leading to a NULL pointer dereference and a Use-After-Free heap corruption upon a late firmware response.
--

commit d740730d233516ecbc0d56af8b1a5f692696bbf0
Author: Frieder Schrempf <frieder.schrempf@kontron.de>

firmware: imx: ele: Add API functions for OCOTP fuse access

This commit adds the ele_read_fuse() and ele_write_fuse() functions to the
ELE S400 API to provide read and write access to OCOTP fuse registers. These
are exposed via imx_se_read_fuse() and imx_se_write_fuse() for use by drivers
such as the OCOTP S400 NVMEM driver.

> diff --git a/drivers/firmware/imx/ele_base_msg.c b/drivers/firmware/imx/ele_base_msg.c
> index ec718d322abcd..281d223aa1447 100644
> --- a/drivers/firmware/imx/ele_base_msg.c
> +++ b/drivers/firmware/imx/ele_base_msg.c
[ ... ]
> @@ -303,3 +304,124 @@ int ele_debug_dump(struct se_if_priv *priv)
>  
>  	return ret;
>  }
> +
> +static int ele_read_fuse(struct se_if_priv *priv, uint16_t fuse_id, u32 *value)
> +{
> +	struct se_api_msg *tx_msg __free(kfree) = NULL;
> +	struct se_api_msg *rx_msg __free(kfree) = NULL;
> +	int rx_msg_sz = ELE_READ_FUSE_RSP_MSG_SZ;
> +	int ret = 0;
[ ... ]
> +	tx_msg->data[0] = fuse_id;
> +
> +	ret = ele_msg_send_rcv(priv->priv_dev_ctx, tx_msg,
> +			       ELE_READ_FUSE_REQ_MSG_SZ, rx_msg, rx_msg_sz);
> +	if (ret < 0)
> +		return ret;

[Severity: High]
This is a pre-existing issue, but will a late firmware response cause a
use-after-free here if ele_msg_send_rcv() times out or is interrupted?

If ele_msg_send_rcv() returns an error, it clears the dev_ctx but leaves the
dangling rx_msg pointer in the shared callback handle:

drivers/firmware/imx/ele_common.c:ele_msg_send_rcv() {
    ...
    if (priv->waiting_rsp_clbk_hdl.signal_rcvd) {
        err = -EINTR;
        priv->waiting_rsp_clbk_hdl.signal_rcvd = false;
    }
    priv->waiting_rsp_clbk_hdl.dev_ctx = NULL;
    
    return err;
}

Because rx_msg is managed with __free(kfree), it is immediately freed when
ele_read_fuse() returns on this error path.

If a late response arrives afterwards, se_if_rx_callback() will process it.
It first causes a NULL pointer dereference if dynamic debug is enabled:

drivers/firmware/imx/ele_common.c:se_if_rx_callback() {
    ...
    dev_dbg(dev, "Selecting resp waiter:%s ...",
            se_clbk_hdl->dev_ctx->devname);

Then it unconditionally copies the response into the freed rx_msg buffer:

    ...
    memcpy(se_clbk_hdl->rx_msg, msg, se_clbk_hdl->rx_msg_sz);
}

Does waiting_rsp_clbk_hdl need to be fully cleared (including setting rx_msg
and rx_msg_sz to zero) on error paths in ele_msg_send_rcv() to prevent this
memory corruption?

> +
> +	ret = se_val_rsp_hdr_n_status(priv, rx_msg, ELE_READ_FUSE_REQ,
> +				      rx_msg_sz, true);
> +	if (ret)
> +		return ret;
> +
> +	*value = rx_msg->data[1];
> +
> +	return 0;
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260616-upstreaming-next-20260609-imx-ocotp-ele-v1-0-cb7f3698c3e6@kontron.de?part=3

[PATCH 4/9] nvmem: imx-ocotp-ele: Add keepout table for i.MX93

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

Add an overall keepout table to describe which fuse registers are
invalid and not accessible. No functional changes intended.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 drivers/nvmem/imx-ocotp-ele.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
index a0d2985c6d03..dadec19ca252 100644
--- a/drivers/nvmem/imx-ocotp-ele.c
+++ b/drivers/nvmem/imx-ocotp-ele.c
@@ -34,6 +34,8 @@ struct ocotp_devtype_data {
 	u32 num_entry;
 	u32 flag;
 	nvmem_reg_read_t reg_read;
+	const struct nvmem_keepout *keepout;
+	unsigned int nkeepout;
 	struct ocotp_map_entry entry[];
 };
 
@@ -163,6 +165,12 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev)
 	priv->config.read_only = true;
 	priv->config.add_legacy_fixed_of_cells = true;
 	priv->config.fixup_dt_cell_info = imx_ocotp_fixup_dt_cell_info;
+
+	if (priv->data->nkeepout) {
+		priv->config.keepout = priv->data->keepout;
+		priv->config.nkeepout = priv->data->nkeepout;
+	}
+
 	mutex_init(&priv->lock);
 
 	nvmem = devm_nvmem_register(dev, &priv->config);
@@ -172,6 +180,14 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct nvmem_keepout imx93_ocotp_keepout[] = {
+	{.start = 208, .end = 252},
+	{.start = 256, .end = 512},
+	{.start = 576, .end = 728},
+	{.start = 732, .end = 752},
+	{.start = 756, .end = 1248},
+};
+
 static const struct ocotp_devtype_data imx93_ocotp_data = {
 	.reg_off = 0x8000,
 	.reg_read = imx_ocotp_reg_read,
@@ -185,6 +201,8 @@ static const struct ocotp_devtype_data imx93_ocotp_data = {
 		{ 188, 1, FUSE_ELE },
 		{ 312, 200, FUSE_FSB }
 	},
+	.keepout = imx93_ocotp_keepout,
+	.nkeepout = ARRAY_SIZE(imx93_ocotp_keepout),
 };
 
 static const struct ocotp_devtype_data imx94_ocotp_data = {

-- 
2.54.0

Re: [PATCH 4/9] nvmem: imx-ocotp-ele: Add keepout table for i.MX93

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Initialization of a flexible array member is not at the end of the initializer list, causing build errors.
--

commit d9179d39f1569f2fd5d16521edccfaa2096500c4
Author: Frieder Schrempf <frieder.schrempf@kontron.de>

nvmem: imx-ocotp-ele: Add keepout table for i.MX93

This commit adds an overall keepout table to describe which fuse
registers are invalid and inaccessible for the i.MX93.

> diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
> index a0d2985c6d030..dadec19ca2527 100644
> --- a/drivers/nvmem/imx-ocotp-ele.c
> +++ b/drivers/nvmem/imx-ocotp-ele.c
[ ... ]
> @@ -185,6 +201,8 @@ static const struct ocotp_devtype_data imx93_ocotp_data = {
>  		{ 188, 1, FUSE_ELE },
>  		{ 312, 200, FUSE_FSB }
>  	},
> +	.keepout = imx93_ocotp_keepout,
> +	.nkeepout = ARRAY_SIZE(imx93_ocotp_keepout),

[Severity: Low]
Does this cause a build failure? It looks like the designated initializers
for .keepout and .nkeepout are placed after the initialization of the flexible
array member .entry.

In C, flexible array members must be the last items initialized in a struct,
otherwise compilers like GCC will typically throw an "initialization of a
flexible array member not at end of struct" error.

Could these initializers be moved above the .entry initialization?

>  };
>  
>  static const struct ocotp_devtype_data imx94_ocotp_data = {

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260616-upstreaming-next-20260609-imx-ocotp-ele-v1-0-cb7f3698c3e6@kontron.de?part=4

[PATCH 5/9] nvmem: imx-ocotp-ele: Remove device-specific reg_read()

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

We only have a single implementation of the read hook. There is no
need to store it in the device data.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 drivers/nvmem/imx-ocotp-ele.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
index dadec19ca252..9d3f94e35508 100644
--- a/drivers/nvmem/imx-ocotp-ele.c
+++ b/drivers/nvmem/imx-ocotp-ele.c
@@ -33,7 +33,6 @@ struct ocotp_devtype_data {
 	u32 size;
 	u32 num_entry;
 	u32 flag;
-	nvmem_reg_read_t reg_read;
 	const struct nvmem_keepout *keepout;
 	unsigned int nkeepout;
 	struct ocotp_map_entry entry[];
@@ -158,7 +157,7 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev)
 	priv->config.id = NVMEM_DEVID_AUTO;
 	priv->config.owner = THIS_MODULE;
 	priv->config.size = priv->data->size;
-	priv->config.reg_read = priv->data->reg_read;
+	priv->config.reg_read = imx_ocotp_reg_read;
 	priv->config.word_size = 1;
 	priv->config.stride = 1;
 	priv->config.priv = priv;
@@ -190,7 +189,6 @@ static const struct nvmem_keepout imx93_ocotp_keepout[] = {
 
 static const struct ocotp_devtype_data imx93_ocotp_data = {
 	.reg_off = 0x8000,
-	.reg_read = imx_ocotp_reg_read,
 	.size = 2048,
 	.num_entry = 6,
 	.entry = {
@@ -207,7 +205,6 @@ static const struct ocotp_devtype_data imx93_ocotp_data = {
 
 static const struct ocotp_devtype_data imx94_ocotp_data = {
 	.reg_off = 0x8000,
-	.reg_read = imx_ocotp_reg_read,
 	.size = 3296, /* 103 Banks */
 	.num_entry = 10,
 	.entry = {
@@ -226,7 +223,6 @@ static const struct ocotp_devtype_data imx94_ocotp_data = {
 
 static const struct ocotp_devtype_data imx95_ocotp_data = {
 	.reg_off = 0x8000,
-	.reg_read = imx_ocotp_reg_read,
 	.size = 2048,
 	.num_entry = 12,
 	.entry = {

-- 
2.54.0

[PATCH 6/9] nvmem: imx-ocotp-ele: Support the ELE API

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

The fuses inside the Edgelock Secure Enclave are currently not
accessed via its API but through the FSB block which provides
limited access to some fuses.

The ELE API allows us to access all fuses with read/write
permissions. Therefore use it as primary method and only fall
back to the limited FSB if the ELE API is not available.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 drivers/nvmem/imx-ocotp-ele.c | 76 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 75 insertions(+), 1 deletion(-)

diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
index 9d3f94e35508..92cc061b9b34 100644
--- a/drivers/nvmem/imx-ocotp-ele.c
+++ b/drivers/nvmem/imx-ocotp-ele.c
@@ -6,10 +6,12 @@
  */
 
 #include <linux/device.h>
+#include <linux/firmware/imx/se_api.h>
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/nvmem-provider.h>
 #include <linux/of.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/if_ether.h>	/* ETH_ALEN */
@@ -44,6 +46,8 @@ struct imx_ocotp_priv {
 	struct nvmem_config config;
 	struct mutex lock;
 	const struct ocotp_devtype_data *data;
+	void *se_data;
+	struct platform_device *se_dev;
 };
 
 static enum fuse_type imx_ocotp_fuse_type(void *context, u32 index)
@@ -72,6 +76,7 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 	enum fuse_type type;
 	u32 *buf;
 	void *p;
+	int ret;
 	int i;
 	u8 skipbytes;
 
@@ -92,6 +97,19 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 	buf = p;
 
 	for (i = index; i < (index + count); i++) {
+		/*
+		 * All fuse registers can be read via ELE. If the SE device is
+		 * available, always prefer it.
+		 */
+		if (priv->se_data) {
+			ret = imx_se_read_fuse(priv->se_data, i, buf++);
+			if (ret) {
+				mutex_unlock(&priv->lock);
+				return ret;
+			}
+			continue;
+		}
+
 		type = imx_ocotp_fuse_type(context, i);
 		if (type == FUSE_INVALID || type == FUSE_ELE) {
 			*buf++ = 0;
@@ -113,6 +131,32 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 	return 0;
 };
 
+static int imx_ocotp_reg_write(void *context, unsigned int offset, void *val, size_t bytes)
+{
+	struct imx_ocotp_priv *priv = context;
+	u32 word = offset >> 2;
+	u32 *buf = val;
+	int ret;
+
+	/* allow only writing one complete OTP word at a time */
+	if ((bytes != 4) || (offset % 4 != 0))
+		return -EINVAL;
+
+	/*
+	 * The ELE API returns an error when writing an all-zero value. As
+	 * OTP fuse bits can not be switched from 1 to 0 anyway, skip these
+	 * values.
+	 */
+	if (!*buf)
+		return 0;
+
+	mutex_lock(&priv->lock);
+	ret = imx_se_write_fuse(priv->se_data, word, *buf);
+	mutex_unlock(&priv->lock);
+
+	return ret;
+}
+
 static int imx_ocotp_cell_pp(void *context, const char *id, int index,
 			     unsigned int offset, void *data, size_t bytes)
 {
@@ -136,11 +180,18 @@ static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem,
 	cell->read_post_process = imx_ocotp_cell_pp;
 }
 
+static void imx_ocotp_put_se_dev(void *data)
+{
+	platform_device_put(data);
+}
+
 static int imx_ele_ocotp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct imx_ocotp_priv *priv;
 	struct nvmem_device *nvmem;
+	struct device_node *np;
+	int ret;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -152,16 +203,36 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
+	np = of_parse_phandle(pdev->dev.of_node, "secure-enclave", 0);
+	if (!np) {
+		dev_info(&pdev->dev, "missing or invalid SE handle, using readonly FSB\n");
+	} else {
+		priv->se_dev = of_find_device_by_node(np);
+		of_node_put(np);
+		if (!priv->se_dev)
+			return dev_err_probe(&pdev->dev, -ENODEV, "failed to find SE device\n");
+
+		ret = devm_add_action_or_reset(&pdev->dev, imx_ocotp_put_se_dev,
+					       priv->se_dev);
+		if (ret)
+			return ret;
+
+		priv->se_data = platform_get_drvdata(priv->se_dev);
+		if (!priv->se_data)
+			return dev_err_probe(&pdev->dev, -EPROBE_DEFER,
+					     "SE device not ready\n");
+	}
+
 	priv->config.dev = dev;
 	priv->config.name = "ELE-OCOTP";
 	priv->config.id = NVMEM_DEVID_AUTO;
 	priv->config.owner = THIS_MODULE;
 	priv->config.size = priv->data->size;
 	priv->config.reg_read = imx_ocotp_reg_read;
+	priv->config.reg_write = imx_ocotp_reg_write;
 	priv->config.word_size = 1;
 	priv->config.stride = 1;
 	priv->config.priv = priv;
-	priv->config.read_only = true;
 	priv->config.add_legacy_fixed_of_cells = true;
 	priv->config.fixup_dt_cell_info = imx_ocotp_fixup_dt_cell_info;
 
@@ -170,6 +241,9 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev)
 		priv->config.nkeepout = priv->data->nkeepout;
 	}
 
+	if (!priv->se_data)
+		priv->config.read_only = true;
+
 	mutex_init(&priv->lock);
 
 	nvmem = devm_nvmem_register(dev, &priv->config);

-- 
2.54.0

Re: [PATCH 6/9] nvmem: imx-ocotp-ele: Support the ELE API

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] The dynamically allocated read buffer `p` is leaked when `imx_se_read_fuse()` returns an error in `imx_ocotp_reg_read()`.
- [High] Lack of unbind protection for the supplier Secure Enclave (`se_dev`) device leads to a potential Use-After-Free of its cached private data.
--

commit ce01a1e44e5619e1342b66aca8b1bf267d01e93e
Author: Frieder Schrempf <frieder.schrempf@kontron.de>

nvmem: imx-ocotp-ele: Support the ELE API

The fuses inside the Edgelock Secure Enclave are currently not accessed via
its API but through the FSB block which provides limited access to some
fuses. The ELE API allows us to access all fuses with read/write
permissions.

> diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
> index 9d3f94e35508f..92cc061b9b347 100644
> --- a/drivers/nvmem/imx-ocotp-ele.c
> +++ b/drivers/nvmem/imx-ocotp-ele.c

[ ... ]

> @@ -92,6 +97,19 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
>  	buf = p;
>  
>  	for (i = index; i < (index + count); i++) {
> +		/*
> +		 * All fuse registers can be read via ELE. If the SE device is
> +		 * available, always prefer it.
> +		 */
> +		if (priv->se_data) {
> +			ret = imx_se_read_fuse(priv->se_data, i, buf++);
> +			if (ret) {
> +				mutex_unlock(&priv->lock);
> +				return ret;

[Severity: High]
Does this error path leak the memory allocated for p earlier in the function?

The allocation happens here:

	p = kzalloc(num_bytes, GFP_KERNEL);
	if (!p)
		return -ENOMEM;

Returning directly here will bypass the kfree(p) at the end of the function.

> +			}
> +			continue;
> +		}
> +

[ ... ]

> @@ -152,16 +203,36 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev)
>  	if (IS_ERR(priv->base))
>  		return PTR_ERR(priv->base);
>  
> +	np = of_parse_phandle(pdev->dev.of_node, "secure-enclave", 0);
> +	if (!np) {
> +		dev_info(&pdev->dev, "missing or invalid SE handle, using readonly FSB\n");
> +	} else {
> +		priv->se_dev = of_find_device_by_node(np);
> +		of_node_put(np);
> +		if (!priv->se_dev)
> +			return dev_err_probe(&pdev->dev, -ENODEV, "failed to find SE device\n");
> +
> +		ret = devm_add_action_or_reset(&pdev->dev, imx_ocotp_put_se_dev,
> +					       priv->se_dev);
> +		if (ret)
> +			return ret;
> +
> +		priv->se_data = platform_get_drvdata(priv->se_dev);

[Severity: High]
Is there anything preventing the SE driver from being unbound via sysfs after we
cache its private data in priv->se_data here?

If the SE driver is unbound, its devres allocations (which likely include the
se_data) would be freed. Since we haven't established a device link
(e.g. using device_link_add) to enforce unbind ordering, we might be left
with a dangling pointer in priv->se_data.

Could this result in a use-after-free when imx_ocotp_reg_read() or
imx_ocotp_reg_write() later attempts to dereference priv->se_data?

> +		if (!priv->se_data)
> +			return dev_err_probe(&pdev->dev, -EPROBE_DEFER,
> +					     "SE device not ready\n");
> +	}
>

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260616-upstreaming-next-20260609-imx-ocotp-ele-v1-0-cb7f3698c3e6@kontron.de?part=6

[PATCH 7/9] nvmem: imx-ocotp-ele: Remove the FUSE_ELE type

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

There is no use in tracking the fuses that are only accessible via
ELE API and the current lists are incomplete. If the ELE API is
available it will be used as primary access method anyway, otherwise
the fuses not listed as accessible through the FSB can be considered
invalid.

No functional changes intended.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 drivers/nvmem/imx-ocotp-ele.c | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
index 92cc061b9b34..3d6fad149ed5 100644
--- a/drivers/nvmem/imx-ocotp-ele.c
+++ b/drivers/nvmem/imx-ocotp-ele.c
@@ -18,8 +18,7 @@
 
 enum fuse_type {
 	FUSE_FSB = BIT(0),
-	FUSE_ELE = BIT(1),
-	FUSE_ECC = BIT(2),
+	FUSE_ECC = BIT(1),
 	FUSE_INVALID = -1
 };
 
@@ -111,7 +110,7 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 		}
 
 		type = imx_ocotp_fuse_type(context, i);
-		if (type == FUSE_INVALID || type == FUSE_ELE) {
+		if (type == FUSE_INVALID) {
 			*buf++ = 0;
 			continue;
 		}
@@ -264,13 +263,9 @@ static const struct nvmem_keepout imx93_ocotp_keepout[] = {
 static const struct ocotp_devtype_data imx93_ocotp_data = {
 	.reg_off = 0x8000,
 	.size = 2048,
-	.num_entry = 6,
+	.num_entry = 2,
 	.entry = {
 		{ 0, 52, FUSE_FSB },
-		{ 63, 1, FUSE_ELE},
-		{ 128, 16, FUSE_ELE },
-		{ 182, 1, FUSE_ELE },
-		{ 188, 1, FUSE_ELE },
 		{ 312, 200, FUSE_FSB }
 	},
 	.keepout = imx93_ocotp_keepout,
@@ -280,7 +275,7 @@ static const struct ocotp_devtype_data imx93_ocotp_data = {
 static const struct ocotp_devtype_data imx94_ocotp_data = {
 	.reg_off = 0x8000,
 	.size = 3296, /* 103 Banks */
-	.num_entry = 10,
+	.num_entry = 9,
 	.entry = {
 		{ 0, 1, FUSE_FSB | FUSE_ECC },
 		{ 7, 1, FUSE_FSB | FUSE_ECC },
@@ -288,7 +283,6 @@ static const struct ocotp_devtype_data imx94_ocotp_data = {
 		{ 12, 24, FUSE_FSB },
 		{ 36, 2, FUSE_FSB  | FUSE_ECC },
 		{ 38, 14, FUSE_FSB },
-		{ 59, 1, FUSE_ELE },
 		{ 525, 2, FUSE_FSB | FUSE_ECC },
 		{ 528, 7, FUSE_FSB },
 		{ 536, 280, FUSE_FSB },
@@ -298,7 +292,7 @@ static const struct ocotp_devtype_data imx94_ocotp_data = {
 static const struct ocotp_devtype_data imx95_ocotp_data = {
 	.reg_off = 0x8000,
 	.size = 2048,
-	.num_entry = 12,
+	.num_entry = 9,
 	.entry = {
 		{ 0, 1, FUSE_FSB | FUSE_ECC },
 		{ 7, 1, FUSE_FSB | FUSE_ECC },
@@ -306,9 +300,6 @@ static const struct ocotp_devtype_data imx95_ocotp_data = {
 		{ 12, 24, FUSE_FSB },
 		{ 36, 2, FUSE_FSB  | FUSE_ECC },
 		{ 38, 14, FUSE_FSB },
-		{ 63, 1, FUSE_ELE },
-		{ 128, 16, FUSE_ELE },
-		{ 188, 1, FUSE_ELE },
 		{ 317, 2, FUSE_FSB | FUSE_ECC },
 		{ 320, 7, FUSE_FSB },
 		{ 328, 184, FUSE_FSB }

-- 
2.54.0

Re: [PATCH 7/9] nvmem: imx-ocotp-ele: Remove the FUSE_ELE type

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

Pre-existing issues:
- [Critical] ele_msg_send_rcv() fails to clear waiting_rsp_clbk_hdl.rx_msg on error/timeout paths, leading to heap corruption and NULL pointer dereference by the mailbox callback.
- [High] Missing kfree() on the error path in imx_ocotp_reg_read() causes a memory leak of the dynamically allocated read buffer.
- [High] Missing device link between the OCOTP driver and the Secure Enclave (SE) device creates a Use-After-Free risk for priv->se_data.
--

commit 59602650186437e4e8ff55bf4112fcec530ec2ab
Author: Frieder Schrempf <frieder.schrempf@kontron.de>

nvmem: imx-ocotp-ele: Remove the FUSE_ELE type

There is no use in tracking the fuses that are only accessible via
ELE API and the current lists are incomplete. If the ELE API is
available it will be used as primary access method anyway, otherwise
the fuses not listed as accessible through the FSB can be considered
invalid.

> diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
> index 92cc061b9b347..3d6fad149ed5d 100644
> --- a/drivers/nvmem/imx-ocotp-ele.c
> +++ b/drivers/nvmem/imx-ocotp-ele.c
[ ... ]
> @@ -111,7 +110,7 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
>  		}
>  
>  		type = imx_ocotp_fuse_type(context, i);
> -		if (type == FUSE_INVALID || type == FUSE_ELE) {
> +		if (type == FUSE_INVALID) {

[Severity: High]
This isn't a bug introduced by this patch, but looking at the earlier
part of imx_ocotp_reg_read() where the SE device is checked:

	if (priv->se_data) {
		ret = imx_se_read_fuse(priv->se_data, i, buf++);
		if (ret) {
			mutex_unlock(&priv->lock);
			return ret;
		}

Does this error path leak the dynamically allocated read buffer 'p'?

The function returns immediately without calling kfree(p). This could
allow repeated failing reads, such as from nvmem sysfs, to cause memory
exhaustion.

[ ... ]

[Severity: High]
This is a pre-existing issue, but looking at imx_ele_ocotp_probe() in
drivers/nvmem/imx-ocotp-ele.c:

	priv->se_data = platform_get_drvdata(priv->se_dev);
	if (!priv->se_data)
		return dev_err_probe(&pdev->dev, -EPROBE_DEFER,
				     "SE device not ready\n");

Is there a use-after-free risk here due to the missing device link?

The driver caches the SE device's driver data locally as priv->se_data
without establishing a device link (e.g., using device_link_add()).

If the Secure Enclave driver unbinds independently, its private data is
freed. Because this driver remains active, could it pass the dangling
priv->se_data pointer to imx_se_read_fuse() during a subsequent read
or write?

[Severity: Critical]
This is a pre-existing issue, but looking at ele_msg_send_rcv() in
drivers/firmware/imx/ele_common.c:

	err = ele_msg_send(dev_ctx, tx_msg, tx_msg_sz);
	if (err < 0)
		return err;

Could this error path leave a dangling pointer in the global state?

The function returns without clearing priv->waiting_rsp_clbk_hdl.rx_msg
or dev_ctx.

If a spurious response arrives later, se_if_rx_callback() copies data
into the freed rx_msg via memcpy(), which could cause heap corruption:

	dev_dbg(dev, "Selecting resp waiter:%s for mesg header:0x%x.",
		se_clbk_hdl->dev_ctx->devname, *(u32 *)header);
	...
	memcpy(se_clbk_hdl->rx_msg, msg, se_clbk_hdl->rx_msg_sz);

Additionally, if the message times out, dev_ctx is set to NULL but
rx_msg is not.

Would a delayed response crash in se_if_rx_callback() by dereferencing
se_clbk_hdl->dev_ctx->devname without checking if dev_ctx is NULL?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260616-upstreaming-next-20260609-imx-ocotp-ele-v1-0-cb7f3698c3e6@kontron.de?part=7

[PATCH 8/9] nvmem: imx-ocotp-ele: Rename FSB access map

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

The table is used to declare which fuse registers are accessible
through the FSB block. Name it accordingly to make this clearer for
the reader.

No functional changes intended.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 drivers/nvmem/imx-ocotp-ele.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
index 3d6fad149ed5..766b0d746f6c 100644
--- a/drivers/nvmem/imx-ocotp-ele.c
+++ b/drivers/nvmem/imx-ocotp-ele.c
@@ -32,11 +32,11 @@ struct ocotp_devtype_data {
 	u32 reg_off;
 	char *name;
 	u32 size;
-	u32 num_entry;
+	u32 num_fsb_map;
 	u32 flag;
 	const struct nvmem_keepout *keepout;
 	unsigned int nkeepout;
-	struct ocotp_map_entry entry[];
+	struct ocotp_map_entry fsb_map[];
 };
 
 struct imx_ocotp_priv {
@@ -56,12 +56,12 @@ static enum fuse_type imx_ocotp_fuse_type(void *context, u32 index)
 	u32 start, end;
 	int i;
 
-	for (i = 0; i < data->num_entry; i++) {
-		start = data->entry[i].start;
-		end = data->entry[i].start + data->entry[i].num;
+	for (i = 0; i < data->num_fsb_map; i++) {
+		start = data->fsb_map[i].start;
+		end = data->fsb_map[i].start + data->fsb_map[i].num;
 
 		if (index >= start && index < end)
-			return data->entry[i].type;
+			return data->fsb_map[i].type;
 	}
 
 	return FUSE_INVALID;
@@ -263,8 +263,8 @@ static const struct nvmem_keepout imx93_ocotp_keepout[] = {
 static const struct ocotp_devtype_data imx93_ocotp_data = {
 	.reg_off = 0x8000,
 	.size = 2048,
-	.num_entry = 2,
-	.entry = {
+	.num_fsb_map = 2,
+	.fsb_map = {
 		{ 0, 52, FUSE_FSB },
 		{ 312, 200, FUSE_FSB }
 	},
@@ -275,8 +275,8 @@ static const struct ocotp_devtype_data imx93_ocotp_data = {
 static const struct ocotp_devtype_data imx94_ocotp_data = {
 	.reg_off = 0x8000,
 	.size = 3296, /* 103 Banks */
-	.num_entry = 9,
-	.entry = {
+	.num_fsb_map = 9,
+	.fsb_map = {
 		{ 0, 1, FUSE_FSB | FUSE_ECC },
 		{ 7, 1, FUSE_FSB | FUSE_ECC },
 		{ 9, 3, FUSE_FSB | FUSE_ECC },
@@ -292,8 +292,8 @@ static const struct ocotp_devtype_data imx94_ocotp_data = {
 static const struct ocotp_devtype_data imx95_ocotp_data = {
 	.reg_off = 0x8000,
 	.size = 2048,
-	.num_entry = 9,
-	.entry = {
+	.num_fsb_map = 9,
+	.fsb_map = {
 		{ 0, 1, FUSE_FSB | FUSE_ECC },
 		{ 7, 1, FUSE_FSB | FUSE_ECC },
 		{ 9, 3, FUSE_FSB | FUSE_ECC },

-- 
2.54.0

[PATCH 9/9] arm64: dts: imx93-kontron: Enable ELE firmware driver

[Frieder Schrempf]

From: Frieder Schrempf <frieder.schrempf@kontron.de>

Add the ELE firmware API node and pass its handle to the OCOTP
driver. This allows us to gain read/write access to the OTP fuses.

Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
---
 .../boot/dts/freescale/imx93-kontron-osm-s.dtsi    | 26 ++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/arch/arm64/boot/dts/freescale/imx93-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx93-kontron-osm-s.dtsi
index c79b1df339db..c1da4b52c878 100644
--- a/arch/arm64/boot/dts/freescale/imx93-kontron-osm-s.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93-kontron-osm-s.dtsi
@@ -24,6 +24,15 @@ chosen {
 		stdout-path = &lpuart1;
 	};
 
+	firmware {
+		hsm0: secure-enclave {
+			compatible = "fsl,imx93-se-ele-hsm";
+			mbox-names = "tx", "rx";
+			mboxes = <&s4muap 0 0>, <&s4muap 1 0>;
+			memory-region = <&ele_memory>;
+		};
+	};
+
 	reg_usdhc2_vcc: regulator-usdhc2-vcc {
 		compatible = "regulator-fixed";
 		pinctrl-names = "default";
@@ -57,6 +66,19 @@ regulator-state-disk {
 			regulator-off-in-suspend;
 		};
 	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		ele_memory: ele-memory {
+			compatible = "shared-dma-pool";
+			alloc-ranges = <0 0x80000000 0 0x40000000>;
+			size = <0 0x100000>;
+			no-map;
+		};
+	};
 };
 
 &flexcan1 { /* OSM-S CAN_A */
@@ -253,6 +275,10 @@ &lpuart7 { /* OSM-S UART_A */
 	pinctrl-0 = <&pinctrl_lpuart7>;
 };
 
+&ocotp {
+	secure-enclave = <&hsm0>;
+};
+
 &tpm3 { /* OSM-S PWM_0 */
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_tpm3>;

-- 
2.54.0