[AddressSanitizer] Instrument byval call arguments

Summary:
In the LLVM IR, "call" instructions read memory for each byval operand.
For example:

```
$ cat blah.c
struct foo { void *a, *b, *c; };
struct bar { struct foo foo; };
void func1(const struct foo);
void func2(struct bar *bar) { func1(bar->foo); }
$ [...]/bin/clang -S -flto -c blah.c -O2 ; cat blah.s
[...]
define dso_local void @func2(%struct.bar* %bar) local_unnamed_addr #0 {
entry:
  %foo = getelementptr inbounds %struct.bar, %struct.bar* %bar, i64 0, i32 0
  tail call void @func1(%struct.foo* byval(%struct.foo) align 8 %foo) rust-lang#2
  ret void
}
[...]
$ [...]/bin/clang -S -c blah.c -O2 ; cat blah.s
[...]
func2:                                  # @func2
[...]
        subq    $24, %rsp
[...]
        movq    16(%rdi), %rax
        movq    %rax, 16(%rsp)
        movups  (%rdi), %xmm0
        movups  %xmm0, (%rsp)
        callq   func1
        addq    $24, %rsp
[...]
        retq
```

Let ASAN instrument these hidden memory accesses.

This is patch 4/4 of a patch series:
https://reviews.llvm.org/D77616 [PATCH 1/4] [AddressSanitizer] Refactor ClDebug{Min,Max} handling
https://reviews.llvm.org/D77617 [PATCH 2/4] [AddressSanitizer] Split out memory intrinsic handling
https://reviews.llvm.org/D77618 [PATCH 3/4] [AddressSanitizer] Refactor: Permit >1 interesting operands per instruction
https://reviews.llvm.org/D77619 [PATCH 4/4] [AddressSanitizer] Instrument byval call arguments

Reviewers: kcc, glider

Reviewed By: glider

Subscribers: hiraditya, dexonsmith, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D77619

Author: thejh

llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp

@@ -213,6 +213,11 @@ static cl::opt<bool> ClInstrumentAtomics(
     cl::desc("instrument atomic instructions (rmw, cmpxchg)"), cl::Hidden,
     cl::init(true));
 
+static cl::opt<bool>
+    ClInstrumentByval("asan-instrument-byval",
+                      cl::desc("instrument byval call arguments"), cl::Hidden,
+                      cl::init(true));
+
 static cl::opt<bool> ClAlwaysSlowPath(
     "asan-always-slow-path",
     cl::desc("use instrumentation with slow path for all accesses"), cl::Hidden,
@@ -1414,6 +1419,14 @@ void AddressSanitizer::getInterestingMemoryOperands(
         Alignment = (unsigned)AlignmentConstant->getZExtValue();
       Value *Mask = CI->getOperand(2 + OpOffset);
       Interesting.emplace_back(I, OpOffset, IsWrite, Ty, Alignment, Mask);
+    } else {
+      for (unsigned ArgNo = 0; ArgNo < CI->getNumArgOperands(); ArgNo++) {
+        if (!ClInstrumentByval || !CI->isByValArgument(ArgNo) ||
+            ignoreAccess(CI->getArgOperand(ArgNo)))
+          continue;
+        Type *Ty = CI->getParamByValType(ArgNo);
+        Interesting.emplace_back(I, ArgNo, false, Ty, 1);
+      }
     }
   }
 }

llvm/lib/Transforms/Instrumentation/HWAddressSanitizer.cpp

@@ -97,6 +97,10 @@ static cl::opt<bool> ClInstrumentAtomics(
     cl::desc("instrument atomic instructions (rmw, cmpxchg)"), cl::Hidden,
     cl::init(true));
 
+static cl::opt<bool> ClInstrumentByval("hwasan-instrument-byval",
+                                       cl::desc("instrument byval arguments"),
+                                       cl::Hidden, cl::init(true));
+
 static cl::opt<bool> ClRecover(
     "hwasan-recover",
     cl::desc("Enable recovery mode (continue-after-error)."),
@@ -549,6 +553,14 @@ void HWAddressSanitizer::getInterestingMemoryOperands(
       return;
     Interesting.emplace_back(I, XCHG->getPointerOperandIndex(), true,
                              XCHG->getCompareOperand()->getType(), 0);
+  } else if (auto CI = dyn_cast<CallInst>(I)) {
+    for (unsigned ArgNo = 0; ArgNo < CI->getNumArgOperands(); ArgNo++) {
+      if (!ClInstrumentByval || !CI->isByValArgument(ArgNo) ||
+          ignoreAccess(CI->getArgOperand(ArgNo)))
+        continue;
+      Type *Ty = CI->getParamByValType(ArgNo);
+      Interesting.emplace_back(I, ArgNo, false, Ty, 1);
+    }
   }
 }
 

llvm/test/Instrumentation/AddressSanitizer/byval-args.ll

@@ -0,0 +1,18 @@
+; RUN: opt < %s -asan -S | FileCheck %s
+; Test that for call instructions, the by-value arguments are instrumented.
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+%struct.bar = type { %struct.foo }
+%struct.foo = type { i8*, i8*, i8* }
+define dso_local void @func2(%struct.foo* %foo) sanitize_address {
+; CHECK-LABEL: @func2
+  tail call void @func1(%struct.foo* byval(%struct.foo) align 8 %foo) #2
+; CHECK: call void @__asan_report_load
+  ret void
+; CHECK: ret void
+}
+declare dso_local void @func1(%struct.foo* byval(%struct.foo) align 8)
+
+!0 = !{i32 1, !"wchar_size", i32 4}