Revert "r226086 - Revert "r226071 - [RegisterCoalescer] Remove copies to reserved registers""

Reapply r226071 with fixes. Two fixes:

 1. We need to manually remove the old and create the new 'deaf defs'
    associated with physical register definitions when we move the definition of
    the physical register from the copy point to the point of the original vreg def.

    This problem was picked up by the machinstr verifier, and could trigger a
    verification failure on test/CodeGen/X86/2009-02-12-DebugInfoVLA.ll, so I've
    turned on the verifier in the tests.

 2. When moving the def point of the phys reg up, we need to make sure that it
    is neither defined nor read in between the two instructions. We don't, however,
    extend the live ranges of phys reg defs to cover uses, so just checking for
    live-range overlap between the pair interval and the phys reg aliases won't
    pick up reads. As a result, we manually iterate over the range and check for
    reads.

    A test soon to be committed to the PowerPC backend will test this change.

Original commit message:

[RegisterCoalescer] Remove copies to reserved registers

This allows the RegisterCoalescer to join "non-flipped" range pairs with a
physical destination register -- which allows the RegisterCoalescer to remove
copies like this:

<vreg> = something (maybe a load, for example)
... (things that don't use PHYSREG)
PHYSREG = COPY <vreg>

(with all of the restrictions normally applied by the RegisterCoalescer: having
compatible register classes, etc. )

Previously, the RegisterCoalescer handled only the opposite case (copying
*from* a physical register). I don't handle the problem fully here, but try to
get the common case where there is only one use of <vreg> (the COPY).

An upcoming commit to the PowerPC backend will make this pattern much more
common on PPC64/ELF systems.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@226200 91177308-0d34-0410-b5e6-96231b3b80d8

lib/CodeGen/RegisterCoalescer.cpp

@@ -1209,10 +1209,10 @@ bool RegisterCoalescer::canJoinPhys(const CoalescerPair &CP) {
   }
 
   LiveInterval &JoinVInt = LIS->getInterval(CP.getSrcReg());
-  if (CP.isFlipped() && JoinVInt.containsOneValue())
+  if (JoinVInt.containsOneValue())
     return true;
 
-  DEBUG(dbgs() << "\tCannot join defs into reserved register.\n");
+  DEBUG(dbgs() << "\tCannot join complex intervals into reserved register.\n");
   return false;
 }
 
@@ -1431,8 +1431,7 @@ bool RegisterCoalescer::joinReservedPhysReg(CoalescerPair &CP) {
   LiveInterval &RHS = LIS->getInterval(CP.getSrcReg());
   DEBUG(dbgs() << "\t\tRHS = " << RHS << '\n');
 
-  assert(CP.isFlipped() && RHS.containsOneValue() &&
-         "Invalid join with reserved register");
+  assert(RHS.containsOneValue() && "Invalid join with reserved register");
 
   // Optimization for reserved registers like ESP. We can only merge with a
   // reserved physreg if RHS has a single value that is a copy of CP.DstReg().
@@ -1453,7 +1452,50 @@ bool RegisterCoalescer::joinReservedPhysReg(CoalescerPair &CP) {
   // defs are there.
 
   // Delete the identity copy.
-  MachineInstr *CopyMI = MRI->getVRegDef(RHS.reg);
+  MachineInstr *CopyMI;
+  if (CP.isFlipped()) {
+    CopyMI = MRI->getVRegDef(RHS.reg);
+  } else {
+    if (!MRI->hasOneNonDBGUse(RHS.reg)) {
+      DEBUG(dbgs() << "\t\tMultiple vreg uses!\n");
+      return false;
+    }
+
+    MachineInstr *DestMI = MRI->getVRegDef(RHS.reg);
+    CopyMI = &*MRI->use_instr_nodbg_begin(RHS.reg);
+    const SlotIndex CopyRegIdx = LIS->getInstructionIndex(CopyMI).getRegSlot();
+    const SlotIndex DestRegIdx = LIS->getInstructionIndex(DestMI).getRegSlot();
+
+    // We checked above that there are no interfering defs of the physical
+    // register. However, for this case, where we indent to move up the def of
+    // the physical register, we also need to check for interfering uses.
+    SlotIndexes *Indexes = LIS->getSlotIndexes();
+    for (SlotIndex SI = Indexes->getNextNonNullIndex(DestRegIdx);
+         SI != CopyRegIdx; SI = Indexes->getNextNonNullIndex(SI)) {
+      MachineInstr *MI = LIS->getInstructionFromIndex(SI);
+      if (MI->readsRegister(CP.getDstReg(), TRI)) {
+        DEBUG(dbgs() << "\t\tInterference (read): " << *MI);
+        return false;
+      }
+    }
+
+    // We're going to remove the copy which defines a physical reserved
+    // register, so remove its valno, etc.
+    for (MCRegUnitIterator UI(CP.getDstReg(), TRI); UI.isValid(); ++UI) {
+      LiveRange &LR = LIS->getRegUnit(*UI);
+      VNInfo *OrigRegVNI = LR.getVNInfoAt(CopyRegIdx);
+      if (!OrigRegVNI)
+        continue;
+
+      DEBUG(dbgs() << "\t\tRemoving: " << CopyRegIdx << " from " << LR << "\n");
+      LR.removeSegment(CopyRegIdx, CopyRegIdx.getDeadSlot());
+      LR.removeValNo(OrigRegVNI);
+
+      // Create a new dead def at the new def location.
+      LR.createDeadDef(DestRegIdx, LIS->getVNInfoAllocator());
+    }
+  }
+  
   LIS->RemoveMachineInstrFromMaps(CopyMI);
   CopyMI->eraseFromParent();
 

test/CodeGen/ARM/dyn-stackalloc.ll

@@ -1,4 +1,4 @@
-; RUN: llc -mtriple=arm-eabi %s -o /dev/null
+; RUN: llc -mcpu=generic -mtriple=arm-eabi -verify-machineinstrs < %s | FileCheck %s
 
 %struct.comment = type { i8**, i32*, i32, i8* }
 %struct.info = type { i32, i32, i32, i32, i32, i32, i32, i8* }
@@ -7,6 +7,18 @@
 @str215 = external global [2 x i8]
 
 define void @t1(%struct.state* %v) {
+
+; Make sure we generate:
+;   sub	sp, sp, r1
+; instead of:
+;   sub	r1, sp, r1
+;   mov	sp, r1
+
+; CHECK-LABEL: @t1
+; CHECK: bic [[REG1:r[0-9]+]],
+; CHECK-NOT: sub r{{[0-9]+}}, sp, [[REG1]]
+; CHECK: sub sp, sp, [[REG1]]
+
   %tmp6 = load i32* null
   %tmp8 = alloca float, i32 %tmp6
   store i32 1, i32* null

test/CodeGen/X86/2009-02-12-DebugInfoVLA.ll

@@ -1,9 +1,19 @@
 ; RUN: llc < %s
-; RUN: llc < %s -march=x86-64
+; RUN: llc < %s -march=x86-64 -verify-machineinstrs | FileCheck %s
 ; PR3538
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 target triple = "i386-apple-darwin9"
 define signext i8 @foo(i8* %s1) nounwind ssp {
+
+; Make sure we generate:
+;  movq	-40(%rbp), %rsp
+; Instead of:
+;  movq	-40(%rbp), %rax
+;  movq	%rax, %rsp
+
+; CHECK-LABEL: @foo
+; CHECK: movq	-40(%rbp), %rsp
+
 entry:
   %s1_addr = alloca i8*                           ; <i8**> [#uses=2]
   %retval = alloca i32                            ; <i32*> [#uses=2]