riscv/arch_elf: Check for _HI20 relocation validity #11389
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
As pointed out in apache#11322 there is a hardware design issue in RISC-V that affects RV64 relocations. The problem is with how address bits are loaded into registers via lui / auipc and sign extension. If the hi20 relocation value happens to have its 32-bit sign bit set, i.e. value is 0x80000000 (but not negative! i.e. negative in 64-bit format) the relocation will fail, as the address is erroneously sign extended: 0x00000000_80000000 becomes 0xffffffff_80000000 which is not correct. Also, make sure the correct opcode is used with PCREL_HI20, it expects AUIPC (not LUI). The C compiler will never emit such code but when hand- writing assembly code this can happen.
|
@pkarashchenko this should now detect the issue discussed in #11322 . I still need to test a bit more but the code itself is ready for review. If I understood the problem description in the tickets you pointed out, the problem is exactly with 32-bit sign extension, so if the value is negative (in u64) the relocation works fine, but the singular exception is when the symbol value is positive but has the 32-bit sign bit set. Took a while to understand, and I'm not 100% sure I still do... |
|
Marking as draft so this does not get accidentally merged before I can run the tests |
|
@pkarashchenko it works. Test code as follows main.c: addr.S: Using badaddr Using goodaddr: Tested with rv-virt:knsh64, had to disable optimizations for main, as the compiler did not want to produce the erroneous code otherwise. |
xiaoxiang781216
approved these changes
Dec 14, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
As pointed out in #11322 there is a hardware design issue in RISC-V that affects RV64 relocations. The problem is with how address bits are loaded into registers via lui / auipc and sign extension.
If the hi20 relocation value happens to have its 32-bit sign bit set, i.e. value is 0x80000000 (but not negative! i.e. negative in 64-bit format) the relocation will fail, as the address is erroneously sign extended:
0x00000000_80000000 becomes 0xffffffff_80000000 which is not correct.
Also, make sure the correct opcode is used with PCREL_HI20, it expects AUIPC (not LUI). The C compiler will never emit such code but when hand- writing assembly code this can happen.
Impact
Fix two unlikely issues with risc-v elfloader
Testing
rv-virt:knsh64