Index: lib/Target/PowerPC/PPCBranchSelector.cpp
===================================================================
--- lib/Target/PowerPC/PPCBranchSelector.cpp
+++ lib/Target/PowerPC/PPCBranchSelector.cpp
@@ -25,6 +25,7 @@
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Target/TargetMachine.h"
+#include <algorithm>
 using namespace llvm;
 
 #define DEBUG_TYPE "ppc-branch-select"
@@ -189,10 +190,39 @@
         } else {
           // Otherwise, add the size of the blocks between this block and the
           // dest to the number of bytes left in this block.
-          BranchSize = -MBBStartOffset;
+          unsigned StartBlock = MBB.getNumber();
+          BranchSize = BlockSizes[StartBlock].first - MBBStartOffset;
 
-          for (unsigned i = MBB.getNumber(), e = Dest->getNumber(); i != e; ++i)
+          unsigned MaxAlign = 2;
+          MaxAlign = std::max(MaxAlign, Dest->getAlignment());
+          for (unsigned i = StartBlock+1, e = Dest->getNumber(); i != e; ++i) {
             BranchSize += BlockSizes[i].first;
+            MaxAlign = std::max(MaxAlign,
+                                Fn.getBlockNumbered(i)->getAlignment());
+          }
+
+          // We tend to over estimate code size due to large alignment and
+          // inline assembly. Usually it causes larger computed branch offset.
+          // But sometimes it may also causes smaller computed branch offset
+          // than actual branch offset. If the offset is close to the limit of
+          // encoding, it may cause problem at run time.
+          // Following is a simplified example.
+          //
+          //              actual        estimated
+          //              address        address
+          //    ...
+          //   bne Far      100            10c
+          //   .p2align 4
+          //   Near:        110            110
+          //    ...
+          //   Far:        8108           8108
+          //
+          //   Actual offset:    0x8108 - 0x100 = 0x8008
+          //   Computed offset:  0x8108 - 0x10c = 0x7ffc
+          //
+          // The computed offset is at most ((1 << alignment) - 4) bytes smaller
+          // than actual offset. So we add this number to the offset for safety.
+          BranchSize += (1 << MaxAlign) - 4;
         }
 
         // If this branch is in range, ignore it.