From f30f9cb6eaee0f364619f47c3ad76066c0907dc6 Mon Sep 17 00:00:00 2001
From: sinan <sinan.lin@linux.alibaba.com>
Date: Wed, 7 Aug 2024 18:02:42 +0800
Subject: [PATCH] [BOLT] Skip PLT search for zero-value weak reference symbols
 (#69136)

Take a common weak reference pattern for example
```
    __attribute__((weak)) void undef_weak_fun();

      if (&undef_weak_fun)
        undef_weak_fun();
```

In this case, an undefined weak symbol `undef_weak_fun` has an address
of zero, and Bolt incorrectly changes the relocation for the
corresponding symbol to symbol@PLT, leading to incorrect runtime
behavior.

(cherry picked from commit 6c8933e1a095028d648a5a26aecee0f569304dd0)
---
 bolt/lib/Rewrite/RewriteInstance.cpp          | 11 +++++-
 .../AArch64/update-weak-reference-symbol.s    | 34 +++++++++++++++++++
 2 files changed, 44 insertions(+), 1 deletion(-)
 create mode 100644 bolt/test/AArch64/update-weak-reference-symbol.s

diff --git a/bolt/lib/Rewrite/RewriteInstance.cpp b/bolt/lib/Rewrite/RewriteInstance.cpp
index 33ebae3b6e6de2..45d594ef3fa6f5 100644
--- a/bolt/lib/Rewrite/RewriteInstance.cpp
+++ b/bolt/lib/Rewrite/RewriteInstance.cpp
@@ -2143,6 +2143,14 @@ bool RewriteInstance::analyzeRelocation(
   if (!Relocation::isSupported(RType))
     return false;
 
+  auto IsWeakReference = [](const SymbolRef &Symbol) {
+    Expected<uint32_t> SymFlagsOrErr = Symbol.getFlags();
+    if (!SymFlagsOrErr)
+      return false;
+    return (*SymFlagsOrErr & SymbolRef::SF_Undefined) &&
+           (*SymFlagsOrErr & SymbolRef::SF_Weak);
+  };
+
   const bool IsAArch64 = BC->isAArch64();
 
   const size_t RelSize = Relocation::getSizeForType(RType);
@@ -2174,7 +2182,8 @@ bool RewriteInstance::analyzeRelocation(
     // Section symbols are marked as ST_Debug.
     IsSectionRelocation = (cantFail(Symbol.getType()) == SymbolRef::ST_Debug);
     // Check for PLT entry registered with symbol name
-    if (!SymbolAddress && (IsAArch64 || BC->isRISCV())) {
+    if (!SymbolAddress && !IsWeakReference(Symbol) &&
+        (IsAArch64 || BC->isRISCV())) {
       const BinaryData *BD = BC->getPLTBinaryDataByName(SymbolName);
       SymbolAddress = BD ? BD->getAddress() : 0;
     }
diff --git a/bolt/test/AArch64/update-weak-reference-symbol.s b/bolt/test/AArch64/update-weak-reference-symbol.s
new file mode 100644
index 00000000000000..600a06b8b6d8fd
--- /dev/null
+++ b/bolt/test/AArch64/update-weak-reference-symbol.s
@@ -0,0 +1,34 @@
+// This test checks whether BOLT can correctly handle relocations against weak symbols.
+
+// RUN: %clang %cflags -Wl,-z,notext -shared -Wl,-q %s -o %t.so
+// RUN: llvm-bolt %t.so -o %t.so.bolt
+// RUN: llvm-nm -n %t.so.bolt > %t.out.txt
+// RUN: llvm-objdump -dj .rodata %t.so.bolt >> %t.out.txt
+// RUN: FileCheck %s --input-file=%t.out.txt
+
+# CHECK: w func_1
+# CHECK: {{0+}}[[#%x,ADDR:]] W func_2
+
+# CHECK: {{.*}} <.rodata>:
+# CHECK-NEXT: {{.*}} .word 0x00000000
+# CHECK-NEXT: {{.*}} .word 0x00000000
+# CHECK-NEXT: {{.*}} .word 0x{{[0]+}}[[#ADDR]]
+# CHECK-NEXT: {{.*}} .word 0x00000000
+
+	.text
+	.weak	func_2
+	.weak	func_1
+	.global	wow
+	.type	wow, %function
+wow:
+	bl func_1
+	bl func_2
+	ret
+	.type   func_2, %function
+func_2:
+	ret
+	.section	.rodata
+.LC0:
+	.xword	func_1
+.LC1:
+	.xword	func_2