[PATCH] D121531: [ELF] Implement --build-id={md5, sha1} with truncated BLAKE3

[Fangrui Song via Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGd3e5b6f7539b: [ELF] Implement --build-id={md5,sha1} with truncated BLAKE3 (authored by MaskRay).
Herald added a subscriber: StephenFan.

Changed prior to commit:
  https://reviews.llvm.org/D121531?vs=414873&id=417996#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121531/new/

https://reviews.llvm.org/D121531

Files:
  lld/ELF/Writer.cpp
  lld/test/ELF/build-id.s
  lld/test/ELF/partition-notes.s


Index: lld/test/ELF/partition-notes.s
===================================================================
--- lld/test/ELF/partition-notes.s
+++ lld/test/ELF/partition-notes.s
@@ -37,7 +37,7 @@
 // CHECK-NEXT:       Owner: GNU
 // CHECK-NEXT:       Data size:
 // CHECK-NEXT:       Type: NT_GNU_BUILD_ID (unique build ID bitstring)
-// CHECK-NEXT:       Build ID: bb5542bd74252653e286044980d602874d237ae0
+// CHECK-NEXT:       Build ID: ab81108a3d85b729980356331fddc2bfc4c10177{{$}}
 // CHECK-NEXT:     }
 // CHECK-NEXT:   }
 // CHECK-NEXT: ]
Index: lld/test/ELF/build-id.s
===================================================================
--- lld/test/ELF/build-id.s
+++ lld/test/ELF/build-id.s
@@ -69,11 +69,11 @@
 
 # MD5:      Contents of section .note.gnu.build-id:
 # MD5-NEXT: 04000000 10000000 03000000 474e5500  ............GNU.
-# MD5-NEXT: 7b00fd9e 054ceb4b 06f64d0e 482cb476
+# MD5-NEXT: dbf0bc13 b3ff11e9 fde6e17c 0304983c
 
 # SHA1:      Contents of section .note.gnu.build-id:
 # SHA1-NEXT: 04000000 14000000 03000000 474e5500  ............GNU.
-# SHA1-NEXT: 221a99da dd1d2bf3 05e48a91 dde8a0cb
+# SHA1-NEXT: 1215775f d3b60050 70afd970 e8a10972
 
 # UUID:      Contents of section .note.gnu.build-id:
 # UUID-NEXT: 04000000 10000000 03000000 474e5500  ............GNU.
@@ -89,11 +89,11 @@
 
 # SEPARATE:      Hex dump of section '.note.gnu.build-id':
 # SEPARATE-NEXT: 0x00200198 04000000 14000000 03000000 474e5500
-# SEPARATE-NEXT: 0x002001a8 96820adf d90d5470 0a0c32ff a88c4017
+# SEPARATE-NEXT: 0x002001a8 5cd067a4 2631c0fd 42029037 4b8e0938
 
 # RUN: ld.lld --build-id=sha1 --no-rosegment %t -o %t2
 # RUN: llvm-readelf -x .note.gnu.build-id %t2 | FileCheck --check-prefix=NORO %s
 
 # NORO:      Hex dump of section '.note.gnu.build-id':
 # NORO-NEXT: 0x00200160 04000000 14000000 03000000 474e5500
-# NORO-NEXT: 0x00200170 cf6d7b3a 0b3297c3 5b47c079 ce048349
+# NORO-NEXT: 0x00200170 a328cc99 45bfc3fc a9fc8615 37102f9d
Index: lld/ELF/Writer.cpp
===================================================================
--- lld/ELF/Writer.cpp
+++ lld/ELF/Writer.cpp
@@ -25,10 +25,9 @@
 #include "lld/Common/Filesystem.h"
 #include "lld/Common/Strings.h"
 #include "llvm/ADT/StringMap.h"
-#include "llvm/Support/MD5.h"
+#include "llvm/Support/BLAKE3.h"
 #include "llvm/Support/Parallel.h"
 #include "llvm/Support/RandomNumberGenerator.h"
-#include "llvm/Support/SHA1.h"
 #include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/xxhash.h"
 #include <climits>
@@ -2925,6 +2924,12 @@
   MutableArrayRef<uint8_t> output(buildId.get(), hashSize);
   llvm::ArrayRef<uint8_t> input{Out::bufferStart, size_t(fileSize)};
 
+  // Fedora introduced build ID as "approximation of true uniqueness across all
+  // binaries that might be used by overlapping sets of people". It does not
+  // need some security goals that some hash algorithms strive to provide, e.g.
+  // (second-)preimage and collision resistance. In practice people use 'md5'
+  // and 'sha1' just for different lengths. Implement them with the more
+  // efficient BLAKE3.
   switch (config->buildId) {
   case BuildIdKind::Fast:
     computeHash(output, input, [](uint8_t *dest, ArrayRef<uint8_t> arr) {
@@ -2933,12 +2938,12 @@
     break;
   case BuildIdKind::Md5:
     computeHash(output, input, [&](uint8_t *dest, ArrayRef<uint8_t> arr) {
-      memcpy(dest, MD5::hash(arr).data(), hashSize);
+      memcpy(dest, BLAKE3::hash<16>(arr).data(), hashSize);
     });
     break;
   case BuildIdKind::Sha1:
     computeHash(output, input, [&](uint8_t *dest, ArrayRef<uint8_t> arr) {
-      memcpy(dest, SHA1::hash(arr).data(), hashSize);
+      memcpy(dest, BLAKE3::hash<20>(arr).data(), hashSize);
     });
     break;
   case BuildIdKind::Uuid:


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D121531.417996.patch
Type: text/x-patch
Size: 3727 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220324/a0f53cd6/attachment.bin>