From 66e493f81e8e27b4a498a6dac54d404c2333fa5e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20G=C3=B3rny?= <mgorny@moritz.systems>
Date: Sat, 3 Oct 2020 16:38:09 +0200
Subject: [PATCH] [asan] Stop instrumenting user-defined ELF sections

Do not instrument user-defined ELF sections (whose names resemble valid
C identifiers).  They may have special use semantics and modifying them
may break programs.  This is e.g. the case with NetBSD __link_set API
that expects these sections to store consecutive array elements.

Differential Revision: https://reviews.llvm.org/D76665
---
 .../Instrumentation/AddressSanitizer.cpp        |  8 ++++++++
 .../do-not-instrument-netbsd-link_set.ll        | 14 ++++++++++++++
 .../instrument-section-invalid-c-ident.ll       | 17 +++++++++++++++++
 3 files changed, 39 insertions(+)
 create mode 100644 llvm/test/Instrumentation/AddressSanitizer/do-not-instrument-netbsd-link_set.ll
 create mode 100644 llvm/test/Instrumentation/AddressSanitizer/instrument-section-invalid-c-ident.ll

diff --git a/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp b/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
index fd5eaada2febc..5902a2eb8374c 100644
--- a/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
@@ -1883,6 +1883,14 @@ bool ModuleAddressSanitizer::shouldInstrumentGlobal(GlobalVariable *G) const {
       return false;
     }
 
+    // Do not instrument user-defined sections (with names resembling
+    // valid C identifiers)
+    if (TargetTriple.isOSBinFormatELF()) {
+      if (std::all_of(Section.begin(), Section.end(),
+                      [](char c) { return llvm::isAlnum(c) || c == '_'; }))
+        return false;
+    }
+
     // On COFF, if the section name contains '$', it is highly likely that the
     // user is using section sorting to create an array of globals similar to
     // the way initialization callbacks are registered in .init_array and
diff --git a/llvm/test/Instrumentation/AddressSanitizer/do-not-instrument-netbsd-link_set.ll b/llvm/test/Instrumentation/AddressSanitizer/do-not-instrument-netbsd-link_set.ll
new file mode 100644
index 0000000000000..fd37d1357e87d
--- /dev/null
+++ b/llvm/test/Instrumentation/AddressSanitizer/do-not-instrument-netbsd-link_set.ll
@@ -0,0 +1,14 @@
+; This test checks that NetBSD link_set array elements remain consecutive.
+; RUN: opt < %s -asan -asan-module -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-netbsd"
+
+module asm ".hidden __stop_link_set_test_set"
+
+@data1 = dso_local global i32 1, align 4
+@data2 = dso_local global i32 2, align 4
+@__link_set_test_set_sym_data1 = internal constant i8* bitcast (i32* @data1 to i8*), section "link_set_test_set", align 8
+@__link_set_test_set_sym_data2 = internal constant i8* bitcast (i32* @data2 to i8*), section "link_set_test_set", align 8
+; CHECK: @__link_set_test_set_sym_data1 = internal constant i8*{{.*}}, section "link_set_test_set"
+; CHECK-NEXT: @__link_set_test_set_sym_data2 = internal constant i8*{{.*}}, section "link_set_test_set"
diff --git a/llvm/test/Instrumentation/AddressSanitizer/instrument-section-invalid-c-ident.ll b/llvm/test/Instrumentation/AddressSanitizer/instrument-section-invalid-c-ident.ll
new file mode 100644
index 0000000000000..a320f797a7137
--- /dev/null
+++ b/llvm/test/Instrumentation/AddressSanitizer/instrument-section-invalid-c-ident.ll
@@ -0,0 +1,17 @@
+; This test checks that sections with names not resembling valid C identifiers
+; are instrumented.
+; RUN: opt < %s -asan -asan-module -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-netbsd"
+
+module asm ".hidden invalid$c$name"
+
+@data1 = dso_local global i32 1, align 4
+@data2 = dso_local global i32 2, align 4
+@__invalid$c$name_sym_data1 = internal constant i8* bitcast (i32* @data1 to i8*), section "invalid$c$name", align 8
+@__invalid$c$name_sym_data2 = internal constant i8* bitcast (i32* @data2 to i8*), section "invalid$c$name", align 8
+; CHECK: @"__invalid$c$name_sym_data1" = internal constant{{.*}}, section "invalid$c$name", comdat
+; CHECK-NEXT: @"__invalid$c$name_sym_data2" = internal constant{{.*}}, section "invalid$c$name", comdat
+; CHECK: @"__asan_global___invalid$c$name_sym_data1"
+; CHECK-NEXT: @"__asan_global___invalid$c$name_sym_data2"