Version 0.9.7.6 #136
Version 0.9.7.6 #136
Conversation
Compiles under TLS/SSL libraries in Ubuntu 20 "Focal Fossa"
Merge SSL branch (changed to compile under new SSL/TLS) back into master
…eys-ssl-only Merge ssl-only branch back into master branch; This commit will be tagged as Release v0.9.7.4
Development of TLS / SSL compatibility changes for latest Linux OS is merged back into master branch
v0.9.7.4 TLS / SSL Compatibility
This reverts commit 7a6d96d. Conflicts: src/key.h src/rpcprotocol.h
Conflicts: src/rpcserver.h
Conflicts: src/rpcserver.h
… a bit to the documentation.
…for the 0.9.7.5 release
…ihash and cryptonight blocks when "getheaders" are requested.
…nversion for the current and peak hashrate RPC calculations. Use a custom version of the bn.h header, with BN_ULONG set to uint64_t when the platform is 32 bit.
…ing factor (as is done on 64 bit machines, and should be done on 32 bit machines as well). Restore the openssl/bn.h includes.
…t, then use the max uint64_t as the uint64_t value. This is consistent with openssl's bignum
|
Overall looks good to me. The only concern is using I'll try to do a basic testing of this version when I find some time. |
|
Thanks for looking...The BigNum SSF calculation has an overflow issue that we thought about fixing earlier and it behaves differently on 32 bit vs 64 bit machines. As long as most miners are using 64 bit machines, there is no problem, but I want to make sure everything is compatible, so that's why I did that. The overflow behavior can be looked at positively also, since it causes the subsidy to 'jump around' when hashrate is close to peak hashrate (>97.6%), which can be good in preventing miners from sitting close to the peak and getting full reward without ever crossing the peak. By the way we tried contacting you on the email you put in your git commits, but no response. If you don't want to chat, that's ok, but we can if you want. |
It makes sense. I did a basic test and everything looks good.
Sorry, I missed it. I just replied. |
There was a problem hiding this comment.
Pull request overview
This pull request updates the secp256k1 library to version 0.9.7.6, addressing compilation errors and fixing a headers-first sync compatibility bug. The changes include new cryptographic implementation files, build system configurations, and mathematical verification scripts.
Key changes:
- Addition of complete secp256k1 library implementation files for field arithmetic, elliptic curve operations, and ECDSA
- Build system support via CMake and pkg-config
- Mathematical verification scripts using Sage for proving correctness of group operations
- Assembly optimizations for ARM32 architecture
Reviewed changes
Copilot reviewed 141 out of 224 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| src/secp256k1/src/field_10x26.h | Defines field element representation using 10 uint32_t limbs in base 2^26 |
| src/secp256k1/src/field.h | Generic interface for secp256k1 field element operations |
| src/secp256k1/src/ecmult_impl.h | Implementation of elliptic curve multiplication algorithms |
| src/secp256k1/src/ecmult_gen_impl.h | Generator point multiplication with blinding for timing attack protection |
| src/secp256k1/src/ecdsa_impl.h | ECDSA signature operations implementation |
| src/secp256k1/src/bench*.c/h | Benchmarking infrastructure and tests |
| src/secp256k1/src/CMakeLists.txt | CMake build configuration |
| src/secp256k1/sage/*.sage | Mathematical proofs for cryptographic operations |
| src/secp256k1/libsecp256k1.pc.in | pkg-config template |
| src/secp256k1/include/secp256k1_ecdh.h | ECDH module header |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| } secp256k1_fe_storage; | ||
|
|
||
| #define SECP256K1_FE_STORAGE_CONST(d7, d6, d5, d4, d3, d2, d1, d0) {{ (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }} | ||
| #define SECP256K1_FE_STORAGE_CONST_GET(d) d.n[7], d.n[6], d.n[5], d.n[4],d.n[3], d.n[2], d.n[1], d.n[0] |
There was a problem hiding this comment.
Missing space after comma between 'd.n[4]' and 'd.n[3]'. Add a space for consistency with the rest of the macro.
| return 0; | ||
| } | ||
| if (rlen != (size_t)(sigend - sig)) { | ||
| /* Tuple exceeds bounds or garage after tuple. */ |
There was a problem hiding this comment.
Corrected spelling of 'garage' to 'garbage'.
| /* Tuple exceeds bounds or garage after tuple. */ | |
| /* Tuple exceeds bounds or garbage after tuple. */ |
3 participants
This pull request fixes some compilation errors present in the current tip of the master branch, fixes a bug that affects headers-first sync compatibility, as well as numerous other improvements, which can be read in the release notes for 0.9.7.5 and 0.9.7.6.
This pull request prepares us for the next stage (v27.x+), i.e. the pull request by @jimmypound.