[X86] Fix i386 struct and union parameter alignment

According to i386 System V ABI 2.1: Structures and unions assume the
alignment of their most strictly aligned component. But current
implementation always takes them as 4-byte aligned which will result
in incorrect code, e.g:

 1 #include <immintrin.h>
 2 typedef union {
 3         int d[4];
 4         __m128 m;
 5 } M128;
 6 extern void foo(int, ...);
 7 void test(void)
 8 {
 9   M128 a;
10   foo(1, a);
11   foo(1, a.m);
12 }

The first call (line 10) takes the second arg as 4-byte aligned while
the second call (line 11) takes the second arg as 16-byte aligned.
There is oxymoron for the alignment of the 2 calls because they should
be the same.

This patch fixes the bug by following i386 System V ABI and apply it to
Linux only since other System V OS (e.g Darwin, PS4 and FreeBSD) don't
want to spend any effort dealing with the ramifications of ABI breaks
at present.

Patch by Wei Xiao (wxiao3)

Differential Revision: https://reviews.llvm.org/D60748

llvm-svn: 361934

3 files changed, 48 insertions, 14 deletions

diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index 24b7b9f97f9..4b96aa13d00 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -1010,6 +1010,7 @@ class X86_32ABIInfo : public SwiftABIInfo {
   bool IsWin32StructABI;
   bool IsSoftFloatABI;
   bool IsMCUABI;
+  bool IsLinuxABI;
   unsigned DefaultNumRegisterParameters;
 
   static bool isRegisterSize(unsigned Size) {
@@ -1076,6 +1077,7 @@ public:
       IsWin32StructABI(Win32StructABI),
       IsSoftFloatABI(SoftFloatABI),
       IsMCUABI(CGT.getTarget().getTriple().isOSIAMCU()),
+      IsLinuxABI(CGT.getTarget().getTriple().isOSLinux()),
       DefaultNumRegisterParameters(NumRegisterParameters) {}
 
   bool shouldPassIndirectlyForSwift(ArrayRef<llvm::Type*> scalars,
@@ -1492,8 +1494,15 @@ unsigned X86_32ABIInfo::getTypeStackAlignInBytes(QualType Ty,
   if (Align <= MinABIStackAlignInBytes)
     return 0; // Use default alignment.
 
-  // On non-Darwin, the stack type alignment is always 4.
-  if (!IsDarwinVectorABI) {
+  if (IsLinuxABI) {
+    // i386 System V ABI 2.1: Structures and unions assume the alignment of their
+    // most strictly aligned component.
+    //
+    // Exclude other System V OS (e.g Darwin, PS4 and FreeBSD) since we don't
+    // want to spend any effort dealing with the ramifications of ABI breaks.
+    return Align;
+  } else if (!IsDarwinVectorABI) {
+    // On non-Darwin and non-Linux, the stack type alignment is always 4.
     // Set explicit alignment, since we may need to realign the top.
     return MinABIStackAlignInBytes;
   }
diff --git a/clang/test/CodeGen/x86_32-align-linux.c b/clang/test/CodeGen/x86_32-align-linux.c
new file mode 100644
index 00000000000..5fce3f5f295
--- /dev/null
+++ b/clang/test/CodeGen/x86_32-align-linux.c
@@ -0,0 +1,25 @@
+// RUN: %clang_cc1 -w -fblocks -ffreestanding -triple i386-pc-linux-gnu -emit-llvm -o %t %s
+// RUN: FileCheck < %t %s
+
+#include <immintrin.h>
+
+typedef union {
+        int d[4];
+        __m128 m;
+} M128;
+
+extern void foo(int, ...);
+
+M128 a;
+
+// CHECK-LABEL: define void @test
+// CHECK: entry:
+// CHECK: call void (i32, ...) @foo(i32 1, %union.M128* byval align 16
+// CHECK: call void (i32, ...) @foo(i32 1, <4 x float>
+
+void test(void)
+{
+  foo(1, a);
+  foo(1, a.m);
+}
+
diff --git a/clang/test/CodeGen/x86_32-arguments-linux.c b/clang/test/CodeGen/x86_32-arguments-linux.c
index 02eac51216a..3718980ba16 100644
--- a/clang/test/CodeGen/x86_32-arguments-linux.c
+++ b/clang/test/CodeGen/x86_32-arguments-linux.c
@@ -3,21 +3,21 @@
 
 // CHECK-LABEL: define void @f56(
 // CHECK: i8 signext %a0, %struct.s56_0* byval align 4 %a1,
-// CHECK: i64 %a2.coerce, %struct.s56_1* byval align 4,
-// CHECK: <1 x double> %a4, %struct.s56_2* byval align 4,
-// CHECK: <4 x i32> %a6, %struct.s56_3* byval align 4,
-// CHECK: <2 x double> %a8, %struct.s56_4* byval align 4,
-// CHECK: <8 x i32> %a10, %struct.s56_5* byval align 4,
-// CHECK: <4 x double> %a12, %struct.s56_6* byval align 4)
+// CHECK: i64 %a2.coerce, %struct.s56_1* byval align 8 %a3,
+// CHECK: <1 x double> %a4, %struct.s56_2* byval align 8 %a5,
+// CHECK: <4 x i32> %a6, %struct.s56_3* byval align 16 %a7,
+// CHECK: <2 x double> %a8, %struct.s56_4* byval align 16 %a9,
+// CHECK: <8 x i32> %a10, %struct.s56_5* byval align 32 %a11,
+// CHECK: <4 x double> %a12, %struct.s56_6* byval align 32 %a13)
 
 // CHECK: call void (i32, ...) @f56_0(i32 1,
 // CHECK: i32 %{{.*}}, %struct.s56_0* byval align 4 %{{[^ ]*}},
-// CHECK: i64 %{{[^ ]*}}, %struct.s56_1* byval align 4 %{{[^ ]*}},
-// CHECK: <1 x double> %{{[^ ]*}}, %struct.s56_2* byval align 4 %{{[^ ]*}},
-// CHECK: <4 x i32> %{{[^ ]*}}, %struct.s56_3* byval align 4 %{{[^ ]*}},
-// CHECK: <2 x double> %{{[^ ]*}}, %struct.s56_4* byval align 4 %{{[^ ]*}},
-// CHECK: <8 x i32> %{{[^ ]*}}, %struct.s56_5* byval align 4 %{{[^ ]*}},
-// CHECK: <4 x double> %{{[^ ]*}}, %struct.s56_6* byval align 4 %{{[^ ]*}})
+// CHECK: i64 %{{[^ ]*}}, %struct.s56_1* byval align 8 %{{[^ ]*}},
+// CHECK: <1 x double> %{{[^ ]*}}, %struct.s56_2* byval align 8 %{{[^ ]*}},
+// CHECK: <4 x i32> %{{[^ ]*}}, %struct.s56_3* byval align 16 %{{[^ ]*}},
+// CHECK: <2 x double> %{{[^ ]*}}, %struct.s56_4* byval align 16 %{{[^ ]*}},
+// CHECK: <8 x i32> %{{[^ ]*}}, %struct.s56_5* byval align 32 %{{[^ ]*}},
+// CHECK: <4 x double> %{{[^ ]*}}, %struct.s56_6* byval align 32 %{{[^ ]*}})
 // CHECK: }
 //
 // <rdar://problem/7964854> [i386] clang misaligns long double in structures