Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)

Summary:
 This is a resurrection of work first proposed and discussed in Aug 2015:
   http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
   http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html

 The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.

 This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.

 In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
   require that the alignments for source & dest be equal.

 For example, code which used to read:
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)

 Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.

s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g

 The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
   source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
        and those that use use MemIntrinsicInst::[get|set]Alignment() to use
        getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
        MemIntrinsicInst::[get|set]Alignment() methods.

Reviewers: pete, hfinkel, lhames, reames, bollu

Reviewed By: reames

Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits

Differential Revision: https://reviews.llvm.org/D41675

llvm-svn: 322965

10 files changed, 127 insertions, 40 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 27af4296552..1295b83fc6c 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -5017,6 +5017,8 @@ SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I, unsigned Intrinsic) {
       Align = 1; // @llvm.memcpy defines 0 and 1 to both mean no alignment.
     bool isVol = MCI.isVolatile();
     bool isTC = I.isTailCall() && isInTailCallPosition(&I, DAG.getTarget());
+    // FIXME: Support passing different dest/src alignments to the memcpy DAG
+    // node.
     SDValue MC = DAG.getMemcpy(getRoot(), sdl, Op1, Op2, Op3, Align, isVol,
                                false, isTC,
                                MachinePointerInfo(I.getArgOperand(0)),
@@ -5049,6 +5051,8 @@ SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I, unsigned Intrinsic) {
       Align = 1; // @llvm.memmove defines 0 and 1 to both mean no alignment.
     bool isVol = MMI.isVolatile();
     bool isTC = I.isTailCall() && isInTailCallPosition(&I, DAG.getTarget());
+    // FIXME: Support passing different dest/src alignments to the memmove DAG
+    // node.
     SDValue MM = DAG.getMemmove(getRoot(), sdl, Op1, Op2, Op3, Align, isVol,
                                 isTC, MachinePointerInfo(I.getArgOperand(0)),
                                 MachinePointerInfo(I.getArgOperand(1)));
diff --git a/llvm/lib/IR/AutoUpgrade.cpp b/llvm/lib/IR/AutoUpgrade.cpp
index bf96e772394..5d219995aed 100644
--- a/llvm/lib/IR/AutoUpgrade.cpp
+++ b/llvm/lib/IR/AutoUpgrade.cpp
@@ -22,6 +22,7 @@
 #include "llvm/IR/Function.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instruction.h"
+#include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Verifier.h"
@@ -522,6 +523,37 @@ static bool UpgradeIntrinsicFunction1(Function *F, Function *&NewFn) {
         return true;
       }
     }
+    // Updating the memory intrinsics (memcpy/memmove/memset) that have an
+    // alignment parameter to embedding the alignment as an attribute of
+    // the pointer args.
+    if (Name.startswith("memcpy.") && F->arg_size() == 5) {
+      rename(F);
+      // Get the types of dest, src, and len
+      ArrayRef<Type *> ParamTypes = F->getFunctionType()->params().slice(0, 3);
+      NewFn = Intrinsic::getDeclaration(F->getParent(), Intrinsic::memcpy,
+                                        ParamTypes);
+      return true;
+    }
+    if (Name.startswith("memmove.") && F->arg_size() == 5) {
+      rename(F);
+      // Get the types of dest, src, and len
+      ArrayRef<Type *> ParamTypes = F->getFunctionType()->params().slice(0, 3);
+      NewFn = Intrinsic::getDeclaration(F->getParent(), Intrinsic::memmove,
+                                        ParamTypes);
+      return true;
+    }
+    if (Name.startswith("memset.") && F->arg_size() == 5) {
+      rename(F);
+      // Get the types of dest, and len
+      const auto *FT = F->getFunctionType();
+      Type *ParamTypes[2] = {
+          FT->getParamType(0), // Dest
+          FT->getParamType(2)  // len
+      };
+      NewFn = Intrinsic::getDeclaration(F->getParent(), Intrinsic::memset,
+                                        ParamTypes);
+      return true;
+    }
     break;
   }
   case 'n': {
@@ -2198,14 +2230,17 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) {
     return;
   }
 
-  CallInst *NewCall = nullptr;
-  switch (NewFn->getIntrinsicID()) {
-  default: {
+  const auto &DefaultCase = [&NewFn, &CI]() -> void {
     // Handle generic mangling change, but nothing else
     assert(
         (CI->getCalledFunction()->getName() != NewFn->getName()) &&
         "Unknown function for CallInst upgrade and isn't just a name change");
     CI->setCalledFunction(NewFn);
+  };
+  CallInst *NewCall = nullptr;
+  switch (NewFn->getIntrinsicID()) {
+  default: {
+    DefaultCase();
     return;
   }
 
@@ -2346,6 +2381,35 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) {
     NewCall = Builder.CreateCall(NewFn, Args);
     break;
   }
+
+  case Intrinsic::memcpy:
+  case Intrinsic::memmove:
+  case Intrinsic::memset: {
+    // We have to make sure that the call signature is what we're expecting.
+    // We only want to change the old signatures by removing the alignment arg:
+    //  @llvm.mem[cpy|move]...(i8*, i8*, i[32|i64], i32, i1)
+    //    -> @llvm.mem[cpy|move]...(i8*, i8*, i[32|i64], i1)
+    //  @llvm.memset...(i8*, i8, i[32|64], i32, i1)
+    //    -> @llvm.memset...(i8*, i8, i[32|64], i1)
+    // Note: i8*'s in the above can be any pointer type
+    if (CI->getNumArgOperands() != 5) {
+      DefaultCase();
+      return;
+    }
+    // Remove alignment argument (3), and add alignment attributes to the
+    // dest/src pointers.
+    Value *Args[4] = {CI->getArgOperand(0), CI->getArgOperand(1),
+                      CI->getArgOperand(2), CI->getArgOperand(4)};
+    NewCall = Builder.CreateCall(NewFn, Args);
+    auto *MemCI = cast<MemIntrinsic>(NewCall);
+    // All mem intrinsics support dest alignment.
+    const ConstantInt *Align = cast<ConstantInt>(CI->getArgOperand(3));
+    MemCI->setDestAlignment(Align->getZExtValue());
+    // Memcpy/Memmove also support source alignment.
+    if (auto *MTI = dyn_cast<MemTransferInst>(MemCI))
+      MTI->setSourceAlignment(Align->getZExtValue());
+    break;
+  }
   }
   assert(NewCall && "Should have either set this variable or returned through "
                     "the default case");
diff --git a/llvm/lib/IR/IRBuilder.cpp b/llvm/lib/IR/IRBuilder.cpp
index 027c0255bce..99795f54138 100644
--- a/llvm/lib/IR/IRBuilder.cpp
+++ b/llvm/lib/IR/IRBuilder.cpp
@@ -15,6 +15,7 @@
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GlobalVariable.h"
+#include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Statepoint.h"
@@ -83,13 +84,16 @@ CreateMemSet(Value *Ptr, Value *Val, Value *Size, unsigned Align,
              bool isVolatile, MDNode *TBAATag, MDNode *ScopeTag,
              MDNode *NoAliasTag) {
   Ptr = getCastedInt8PtrValue(Ptr);
-  Value *Ops[] = { Ptr, Val, Size, getInt32(Align), getInt1(isVolatile) };
+  Value *Ops[] = {Ptr, Val, Size, getInt1(isVolatile)};
   Type *Tys[] = { Ptr->getType(), Size->getType() };
   Module *M = BB->getParent()->getParent();
   Value *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memset, Tys);
   
   CallInst *CI = createCallHelper(TheFn, Ops, this);
-  
+
+  if (Align > 0)
+    cast<MemSetInst>(CI)->setDestAlignment(Align);
+
   // Set the TBAA info if present.
   if (TBAATag)
     CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
@@ -99,7 +103,7 @@ CreateMemSet(Value *Ptr, Value *Val, Value *Size, unsigned Align,
  
   if (NoAliasTag)
     CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
- 
+
   return CI;
 }
 
@@ -107,16 +111,20 @@ CallInst *IRBuilderBase::
 CreateMemCpy(Value *Dst, Value *Src, Value *Size, unsigned Align,
              bool isVolatile, MDNode *TBAATag, MDNode *TBAAStructTag,
              MDNode *ScopeTag, MDNode *NoAliasTag) {
+  assert((Align == 0 || isPowerOf2_32(Align)) && "Must be 0 or a power of 2");
   Dst = getCastedInt8PtrValue(Dst);
   Src = getCastedInt8PtrValue(Src);
 
-  Value *Ops[] = { Dst, Src, Size, getInt32(Align), getInt1(isVolatile) };
+  Value *Ops[] = {Dst, Src, Size, getInt1(isVolatile)};
   Type *Tys[] = { Dst->getType(), Src->getType(), Size->getType() };
   Module *M = BB->getParent()->getParent();
   Value *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memcpy, Tys);
   
   CallInst *CI = createCallHelper(TheFn, Ops, this);
-  
+
+  if (Align > 0)
+    cast<MemCpyInst>(CI)->setAlignment(Align);
+
   // Set the TBAA info if present.
   if (TBAATag)
     CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
@@ -130,7 +138,7 @@ CreateMemCpy(Value *Dst, Value *Src, Value *Size, unsigned Align,
  
   if (NoAliasTag)
     CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
- 
+
   return CI;  
 }
 
@@ -154,8 +162,9 @@ CallInst *IRBuilderBase::CreateElementUnorderedAtomicMemCpy(
   CallInst *CI = createCallHelper(TheFn, Ops, this);
 
   // Set the alignment of the pointer args.
-  CI->addParamAttr(0, Attribute::getWithAlignment(CI->getContext(), DstAlign));
-  CI->addParamAttr(1, Attribute::getWithAlignment(CI->getContext(), SrcAlign));
+  auto *AMCI = cast<AtomicMemCpyInst>(CI);
+  AMCI->setDestAlignment(DstAlign);
+  AMCI->setSourceAlignment(SrcAlign);
 
   // Set the TBAA info if present.
   if (TBAATag)
@@ -178,16 +187,21 @@ CallInst *IRBuilderBase::
 CreateMemMove(Value *Dst, Value *Src, Value *Size, unsigned Align,
               bool isVolatile, MDNode *TBAATag, MDNode *ScopeTag,
               MDNode *NoAliasTag) {
+  assert((Align == 0 || isPowerOf2_32(Align)) && "Must be 0 or a power of 2");
   Dst = getCastedInt8PtrValue(Dst);
   Src = getCastedInt8PtrValue(Src);
-  
-  Value *Ops[] = { Dst, Src, Size, getInt32(Align), getInt1(isVolatile) };
+
+  Value *Ops[] = {Dst, Src, Size, getInt1(isVolatile)};
   Type *Tys[] = { Dst->getType(), Src->getType(), Size->getType() };
   Module *M = BB->getParent()->getParent();
   Value *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memmove, Tys);
   
   CallInst *CI = createCallHelper(TheFn, Ops, this);
-  
+
+  auto *MMI = cast<MemMoveInst>(CI);
+  if (Align > 0)
+    MMI->setAlignment(Align);
+
   // Set the TBAA info if present.
   if (TBAATag)
     CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index f7775be6961..b73f9dfe4d6 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -4048,18 +4048,23 @@ void Verifier::visitIntrinsicCallSite(Intrinsic::ID ID, CallSite CS) {
   case Intrinsic::memcpy:
   case Intrinsic::memmove:
   case Intrinsic::memset: {
-    ConstantInt *AlignCI = dyn_cast<ConstantInt>(CS.getArgOperand(3));
-    Assert(AlignCI,
-           "alignment argument of memory intrinsics must be a constant int",
-           CS);
     const auto *MI = cast<MemIntrinsic>(CS.getInstruction());
     auto IsValidAlignment = [&](unsigned Alignment) -> bool {
       return Alignment == 0 || isPowerOf2_32(Alignment);
     };
-    Assert(IsValidAlignment(MI->getAlignment()),
-           "alignment argument of memory intrinsics must be 0 or a power of 2",
+    Assert(IsValidAlignment(MI->getDestAlignment()),
+           "alignment of arg 0 of memory intrinsic must be 0 or a power of 2",
            CS);
-    Assert(isa<ConstantInt>(CS.getArgOperand(4)),
+    if (const auto *MTI = dyn_cast<MemTransferInst>(MI)) {
+      Assert(IsValidAlignment(MTI->getSourceAlignment()),
+             "alignment of arg 1 of memory intrinsic must be 0 or a power of 2",
+             CS);
+      // TODO: Remove this assert when we enhance IRBuilder API to create
+      //  memcpy/memmove with separate source & dest alignments.
+      Assert(MTI->getSourceAlignment() == MTI->getDestAlignment(),
+             "TEMPORARY: source and dest alignments must be the same");
+    }
+    Assert(isa<ConstantInt>(CS.getArgOperand(3)),
            "isvolatile argument of memory intrinsics must be a constant int",
            CS);
     break;
diff --git a/llvm/lib/Target/AArch64/AArch64FastISel.cpp b/llvm/lib/Target/AArch64/AArch64FastISel.cpp
index 022200986d2..59168aea91e 100644
--- a/llvm/lib/Target/AArch64/AArch64FastISel.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FastISel.cpp
@@ -3476,7 +3476,7 @@ bool AArch64FastISel::fastLowerIntrinsicCall(const IntrinsicInst *II) {
       return false;
 
     const char *IntrMemName = isa<MemCpyInst>(II) ? "memcpy" : "memmove";
-    return lowerCallTo(II, IntrMemName, II->getNumArgOperands() - 2);
+    return lowerCallTo(II, IntrMemName, II->getNumArgOperands() - 1);
   }
   case Intrinsic::memset: {
     const MemSetInst *MSI = cast<MemSetInst>(II);
@@ -3492,7 +3492,7 @@ bool AArch64FastISel::fastLowerIntrinsicCall(const IntrinsicInst *II) {
       // address spaces.
       return false;
 
-    return lowerCallTo(II, "memset", II->getNumArgOperands() - 2);
+    return lowerCallTo(II, "memset", II->getNumArgOperands() - 1);
   }
   case Intrinsic::sin:
   case Intrinsic::cos:
diff --git a/llvm/lib/Target/ARM/ARMFastISel.cpp b/llvm/lib/Target/ARM/ARMFastISel.cpp
index 60048d4453d..814236ce83c 100644
--- a/llvm/lib/Target/ARM/ARMFastISel.cpp
+++ b/llvm/lib/Target/ARM/ARMFastISel.cpp
@@ -2352,8 +2352,8 @@ bool ARMFastISel::SelectCall(const Instruction *I,
   for (ImmutableCallSite::arg_iterator i = CS.arg_begin(), e = CS.arg_end();
        i != e; ++i) {
     // If we're lowering a memory intrinsic instead of a regular call, skip the
-    // last two arguments, which shouldn't be passed to the underlying function.
-    if (IntrMemName && e-i <= 2)
+    // last argument, which shouldn't be passed to the underlying function.
+    if (IntrMemName && e - i <= 1)
       break;
 
     ISD::ArgFlagsTy Flags;
diff --git a/llvm/lib/Target/Mips/MipsFastISel.cpp b/llvm/lib/Target/Mips/MipsFastISel.cpp
index 8bbac3ed7cf..65dfbdc4564 100644
--- a/llvm/lib/Target/Mips/MipsFastISel.cpp
+++ b/llvm/lib/Target/Mips/MipsFastISel.cpp
@@ -1628,7 +1628,7 @@ bool MipsFastISel::fastLowerIntrinsicCall(const IntrinsicInst *II) {
     if (!MTI->getLength()->getType()->isIntegerTy(32))
       return false;
     const char *IntrMemName = isa<MemCpyInst>(II) ? "memcpy" : "memmove";
-    return lowerCallTo(II, IntrMemName, II->getNumArgOperands() - 2);
+    return lowerCallTo(II, IntrMemName, II->getNumArgOperands() - 1);
   }
   case Intrinsic::memset: {
     const MemSetInst *MSI = cast<MemSetInst>(II);
@@ -1637,7 +1637,7 @@ bool MipsFastISel::fastLowerIntrinsicCall(const IntrinsicInst *II) {
       return false;
     if (!MSI->getLength()->getType()->isIntegerTy(32))
       return false;
-    return lowerCallTo(II, "memset", II->getNumArgOperands() - 2);
+    return lowerCallTo(II, "memset", II->getNumArgOperands() - 1);
   }
   }
   return false;
diff --git a/llvm/lib/Target/X86/X86FastISel.cpp b/llvm/lib/Target/X86/X86FastISel.cpp
index 5dae485f4c9..cfd51e6e8a2 100644
--- a/llvm/lib/Target/X86/X86FastISel.cpp
+++ b/llvm/lib/Target/X86/X86FastISel.cpp
@@ -2726,7 +2726,7 @@ bool X86FastISel::fastLowerIntrinsicCall(const IntrinsicInst *II) {
     if (MCI->getSourceAddressSpace() > 255 || MCI->getDestAddressSpace() > 255)
       return false;
 
-    return lowerCallTo(II, "memcpy", II->getNumArgOperands() - 2);
+    return lowerCallTo(II, "memcpy", II->getNumArgOperands() - 1);
   }
   case Intrinsic::memset: {
     const MemSetInst *MSI = cast<MemSetInst>(II);
@@ -2741,7 +2741,7 @@ bool X86FastISel::fastLowerIntrinsicCall(const IntrinsicInst *II) {
     if (MSI->getDestAddressSpace() > 255)
       return false;
 
-    return lowerCallTo(II, "memset", II->getNumArgOperands() - 2);
+    return lowerCallTo(II, "memset", II->getNumArgOperands() - 1);
   }
   case Intrinsic::stackprotector: {
     // Emit code to store the stack guard onto the stack.
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 31dea892178..32821e6d9de 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -189,6 +189,7 @@ Instruction *InstCombiner::SimplifyMemTransfer(MemIntrinsic *MI) {
   unsigned MinAlign = std::min(DstAlign, SrcAlign);
   unsigned CopyAlign = MI->getAlignment();
 
+  // FIXME: Check & simplify source & dest alignments separately
   if (CopyAlign < MinAlign) {
     MI->setAlignment(MinAlign);
     return MI;
diff --git a/llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp b/llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp
index 5f6fa65abd1..9c90d27d6d5 100644
--- a/llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp
+++ b/llvm/lib/Transforms/Instrumentation/DataFlowSanitizer.cpp
@@ -1382,20 +1382,19 @@ void DFSanVisitor::visitMemTransferInst(MemTransferInst &I) {
   Value *LenShadow = IRB.CreateMul(
       I.getLength(),
       ConstantInt::get(I.getLength()->getType(), DFSF.DFS.ShadowWidth / 8));
-  Value *AlignShadow;
-  if (ClPreserveAlignment) {
-    AlignShadow = IRB.CreateMul(I.getAlignmentCst(),
-                                ConstantInt::get(I.getAlignmentType(),
-                                                 DFSF.DFS.ShadowWidth / 8));
-  } else {
-    AlignShadow = ConstantInt::get(I.getAlignmentType(),
-                                   DFSF.DFS.ShadowWidth / 8);
-  }
   Type *Int8Ptr = Type::getInt8PtrTy(*DFSF.DFS.Ctx);
   DestShadow = IRB.CreateBitCast(DestShadow, Int8Ptr);
   SrcShadow = IRB.CreateBitCast(SrcShadow, Int8Ptr);
-  IRB.CreateCall(I.getCalledValue(), {DestShadow, SrcShadow, LenShadow,
-                                      AlignShadow, I.getVolatileCst()});
+  auto *MTI = cast<MemTransferInst>(
+      IRB.CreateCall(I.getCalledValue(),
+                     {DestShadow, SrcShadow, LenShadow, I.getVolatileCst()}));
+  // FIXME: Set the source & dest alignments of MTI based on the separate
+  // source & dest alignments of I
+  if (ClPreserveAlignment) {
+    MTI->setAlignment(I.getAlignment() * (DFSF.DFS.ShadowWidth / 8));
+  } else {
+    MTI->setAlignment(DFSF.DFS.ShadowWidth / 8);
+  }
 }
 
 void DFSanVisitor::visitReturnInst(ReturnInst &RI) {