From a8cf1a0352a080b62c3eee1d3aac213bf9d6b416 Mon Sep 17 00:00:00 2001
From: Amir Ayupov <aaupov@fb.com>
Date: Mon, 6 Apr 2026 14:41:21 -0700
Subject: [PATCH] [BOLT] Allow empty buildid in pre-aggregated profile
 addresses (#190675)

Allow `parseString()` to return an empty `StringRef` when the delimiter
appears at position 0. This enables parsing pre-aggregated profile
addresses with an omitted buildid but preserved colon (`:addr` format),
where the empty buildid corresponds to the main binary.

Previously, `parseString()` rejected zero-length fields by treating
`StringEnd == 0` the same as `StringRef::npos` (delimiter not found).
These are distinct situations: `npos` means no delimiter exists, while
`0` means the field before the delimiter is empty. The fix removes the
`StringEnd == 0` sub-condition so only the missing-delimiter case
errors.

The existing test for buildid-prefixed addresses is extended to also
verify that `:addr` input produces identical output to the plain-address
and non-empty-buildid variants.

Test Plan:
Added empty-buildid input file and extended
`pre-aggregated-perf-buildid.test` to run perf2bolt with `:addr` format
and diff the fdata output against the existing buildid-prefixed result.
---
 bolt/lib/Profile/DataReader.cpp                       | 3 +--
 bolt/test/X86/Inputs/pre-aggregated-buildid-empty.txt | 9 +++++++++
 bolt/test/X86/pre-aggregated-perf-buildid.test        | 8 ++++++++
 3 files changed, 18 insertions(+), 2 deletions(-)
 create mode 100644 bolt/test/X86/Inputs/pre-aggregated-buildid-empty.txt

diff --git a/bolt/lib/Profile/DataReader.cpp b/bolt/lib/Profile/DataReader.cpp
index ef4a65bb03b9..d3bea76daa5b 100644
--- a/bolt/lib/Profile/DataReader.cpp
+++ b/bolt/lib/Profile/DataReader.cpp
@@ -834,8 +834,7 @@ ErrorOr<StringRef> DataReader::parseString(char EndChar, bool EndNl) {
   size_t StringEnd = 0;
   do {
     StringEnd = ParsingBuf.find_first_of(EndChars, StringEnd);
-    if (StringEnd == StringRef::npos ||
-        (StringEnd == 0 && ParsingBuf[StringEnd] != '\\')) {
+    if (StringEnd == StringRef::npos) {
       reportError("malformed field");
       return make_error_code(llvm::errc::io_error);
     }
diff --git a/bolt/test/X86/Inputs/pre-aggregated-buildid-empty.txt b/bolt/test/X86/Inputs/pre-aggregated-buildid-empty.txt
new file mode 100644
index 000000000000..3cfe11a6510c
--- /dev/null
+++ b/bolt/test/X86/Inputs/pre-aggregated-buildid-empty.txt
@@ -0,0 +1,9 @@
+B deadbeefaabbccdd:7f36d18d60c0 :400bbc 2 0
+B :400ad1 :400e00 2 0
+B :400b10 :4005f0 1 0
+B :400bb7 :400610 1 0
+B :4005f0 cafebabe01234567:7f36d18f2ce0 1 0
+B :4011a0 :4011a9 33 4
+B :4011ad :401180 58 0
+F :401170 :4011b2 22
+B :400dae :400d90 1 0
diff --git a/bolt/test/X86/pre-aggregated-perf-buildid.test b/bolt/test/X86/pre-aggregated-perf-buildid.test
index 85c7c8b64f03..29ea0852a184 100644
--- a/bolt/test/X86/pre-aggregated-perf-buildid.test
+++ b/bolt/test/X86/pre-aggregated-perf-buildid.test
@@ -30,6 +30,14 @@ CHECK-FDATA: 1 usqrt 35 1 usqrt 39 0 22
 CHECK-FDATA: 1 usqrt 3d 1 usqrt 10 0 58
 CHECK-FDATA: 1 usqrt 3d 1 usqrt 3f 0 22
 
+## Test with empty buildid prefix on main binary addresses (`:addr` format).
+## An omitted buildid with a preserved colon should be treated as the main
+## binary. The output should be identical to the non-empty buildid version.
+RUN: perf2bolt %t.exe -o %t.fdata2 --pa \
+RUN:   -p %p/Inputs/pre-aggregated-buildid-empty.txt \
+RUN:   --profile-format=fdata 2>&1 | FileCheck %s --check-prefix=CHECK-BUILDID
+RUN: diff %t.fdata %t.fdata2
+
 ## Test YAML output with buildid-prefixed input.
 RUN: perf2bolt %t.exe -o %t.yaml --pa -p %p/Inputs/pre-aggregated-buildid.txt \
 RUN:   --profile-format=yaml --profile-use-dfs 2>&1