Use 16 byte stack alignment for NaCl on ARM

NaCl's ARM ABI uses 16 byte stack alignment, so set that in
ARMSubtarget.cpp.

Using 16 byte alignment exposes an issue in code generation in which a
varargs function leaves a 4 byte gap between the values of r1-r3 saved
to the stack and the following arguments that were passed on the
stack.  (Previously, this code only needed to support 4 byte and 8
byte alignment.)

With this issue, llc generated:

varargs_func:
        sub     sp, sp, #16
        push    {lr}
        sub     sp, sp, #12
        add     r0, sp, #16   // Should be 20
        stm     r0, {r1, r2, r3}
        ldr     r0, .LCPI0_0  // Address of va_list
        add     r1, sp, #16
        str     r1, [r0]
        bl      external_func

Fix the bug by checking for "Align > 4".  Also simplify the code by
using OffsetToAlignment(), and update comments.

Differential Revision: http://llvm-reviews.chandlerc.com/D2677

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@201497 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 7 insertions, 6 deletions

diff --git a/lib/Target/ARM/ARMISelLowering.cpp b/lib/Target/ARM/ARMISelLowering.cpp
index 414922a69a..abf229b3c4 100644
--- a/lib/Target/ARM/ARMISelLowering.cpp
+++ b/lib/Target/ARM/ARMISelLowering.cpp
@@ -2756,11 +2756,11 @@ ARMTargetLowering::computeRegArea(CCState &CCInfo, MachineFunction &MF,
   ArgRegsSize = NumGPRs * 4;
 
   // If parameter is split between stack and GPRs...
-  if (NumGPRs && Align == 8 &&
+  if (NumGPRs && Align > 4 &&
       (ArgRegsSize < ArgSize ||
         InRegsParamRecordIdx >= CCInfo.getInRegsParamsCount())) {
-    // Add padding for part of param recovered from GPRs, so
-    // its last byte must be at address K*8 - 1.
+    // Add padding for part of param recovered from GPRs.  For example,
+    // if Align == 8, its last byte must be at address K*8 - 1.
     // We need to do it, since remained (stack) part of parameter has
     // stack alignment, and we need to "attach" "GPRs head" without gaps
     // to it:
@@ -2770,8 +2770,7 @@ ARMTargetLowering::computeRegArea(CCState &CCInfo, MachineFunction &MF,
     //
     ARMFunctionInfo *AFI = MF.getInfo<ARMFunctionInfo>();
     unsigned Padding =
-        ((ArgRegsSize + AFI->getArgRegsSaveSize() + Align - 1) & ~(Align-1)) -
-        (ArgRegsSize + AFI->getArgRegsSaveSize());
+        OffsetToAlignment(ArgRegsSize + AFI->getArgRegsSaveSize(), Align);
     ArgRegsSaveSize = ArgRegsSize + Padding;
   } else
     // We don't need to extend regs save size for byval parameters if they
diff --git a/lib/Target/ARM/ARMMachineFunctionInfo.h b/lib/Target/ARM/ARMMachineFunctionInfo.h
index 010edf33ce..216430b478 100644
--- a/lib/Target/ARM/ARMMachineFunctionInfo.h
+++ b/lib/Target/ARM/ARMMachineFunctionInfo.h
@@ -38,7 +38,7 @@ class ARMFunctionInfo : public MachineFunctionInfo {
 
   /// StByValParamsPadding - For parameter that is split between
   /// GPRs and memory; while recovering GPRs part, when
-  /// StackAlignment == 8, and GPRs-part-size mod 8 != 0,
+  /// StackAlignment > 4, and GPRs-part-size mod StackAlignment != 0,
   /// we need to insert gap before parameter start address. It allows to
   /// "attach" GPR-part to the part that was passed via stack.
   unsigned StByValParamsPadding;
diff --git a/lib/Target/ARM/ARMSubtarget.cpp b/lib/Target/ARM/ARMSubtarget.cpp
index a240d1916f..8c5847777e 100644
--- a/lib/Target/ARM/ARMSubtarget.cpp
+++ b/lib/Target/ARM/ARMSubtarget.cpp
@@ -210,6 +210,8 @@ void ARMSubtarget::resetSubtargetFeatures(StringRef CPU, StringRef FS) {
 
   if (isAAPCS_ABI())
     stackAlignment = 8;
+  if (isTargetNaCl())
+    stackAlignment = 16;
 
   UseMovt = hasV6T2Ops() && ArmUseMOVT;