Manual RPMB Provisioning Script for Colibri iMX7D
Based on your hardware information (Colibri iMX7D 1GB eMMC V1.1B with BSP 7.5.0-devel), I can see you’re working with an eMMC-based module that supports RPMB functionality.
Understanding RPMB on Your Module
Your Colibri iMX7D has eMMC storage with a dedicated RPMB (Replay Protected Memory Block) area (1). The RPMB area is a vendor-specific area that uses underlying storage technology more reliable than the user area (1).
Manual Provisioning Considerations
Unfortunately, the available documentation doesn’t include specific manual provisioning scripts for RPMB key programming. However, based on the community discussion about OP-TEE support on iMX7D (2), manual porting and configuration of OP-TEE for the Colibri iMX7D requires significant low-level configuration work.
Key Technical Details for Your Module
For the Colibri iMX7D, you can access the eMMC information through U-Boot (3). The U-Boot console allows you to interact with the eMMC device and examine its configuration (3).
eMMC Device Structure
Your module’s eMMC has the following structure (1):
eMMC boot area:
- Raw partition - U-Boot bootloader and environment, Toradex factory configuration block (1)
- Raw partition - RPMB area for storing sensitive data such as authentication keys (1)
eMMC user area:
- FAT32 partition - Kernel and device tree (1)
- EXT-4 partition - Root file system (1)
Recommendation
Given the complexity and the one-time nature of RPMB key programming, I strongly recommend using the factory/production image approach rather than manual scripting. The community discussion (2) shows that even basic OP-TEE porting for iMX7D requires extensive manual configuration work.
For manual provisioning scripts specific to your setup, you may need to consult the OP-TEE documentation directly or work with the low-level eMMC commands through U-Boot, but this carries significant risk since RPMB key programming can only be performed once per device.
Would you like me to help you set up the two-image approach instead, which would be much safer for your production deployment?
Best regards, Toradex AI Assistant.
Did you like my answer?

If I answered your question, please tick the “Solution” checkbox.
For follow-up questions to me, please use @ToradexAI in your post.