[CodeGenPrepare] Make sure instruction get from SunkAddrs is before MemoryInst

Function optimizeBlock may do optimizations on a block for multiple times.
In the first iteration of the loop, MemoryInst1 may generate a sunk
instruction and store it into SunkAddrs. In the second iteration of the loop,
MemoryInst2 may use the same address and then it can reuse the sunk
instruction stored in SunkAddrs, but MemoryInst2 may be before MemoryInst1
and the corresponding sunk instruction. In order to avoid use before def
error, we need to move the sunk instruction before MemoryInst2.

It fixes issue 138208.

Author: weiguozhi

llvm/lib/CodeGen/CodeGenPrepare.cpp

@@ -5913,6 +5913,9 @@ bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
   if (SunkAddr) {
     LLVM_DEBUG(dbgs() << "CGP: Reusing nonlocal addrmode: " << AddrMode
                       << " for " << *MemoryInst << "\n");
+    Instruction *AddrInst = dyn_cast<Instruction>(SunkAddr);
+    if (AddrInst && MemoryInst->comesBefore(AddrInst))
+      AddrInst->moveBefore(MemoryInst->getIterator());
     if (SunkAddr->getType() != Addr->getType()) {
       if (SunkAddr->getType()->getPointerAddressSpace() !=
               Addr->getType()->getPointerAddressSpace() &&

llvm/test/Transforms/CodeGenPrepare/X86/sink-addr-reuse.ll

@@ -0,0 +1,44 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -p 'require<profile-summary>,codegenprepare' -cgpp-huge-func=0 < %s | FileCheck %s
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-grtev4-linux-gnu"
+
+declare void @g(ptr)
+
+; %load and %load5 use the same address, %load5 is optimized first, %load is
+; optimized later and reuse the same address computation instruction. We must
+; make sure not to generate use before def error.
+
+define void @f(ptr %arg) {
+; CHECK-LABEL: define void @f(
+; CHECK-SAME: ptr [[ARG:%.*]]) {
+; CHECK-NEXT:  [[BB:.*:]]
+; CHECK-NEXT:    [[GETELEMENTPTR:%.*]] = getelementptr i8, ptr [[ARG]], i64 -64
+; CHECK-NEXT:    call void @g(ptr [[GETELEMENTPTR]])
+; CHECK-NEXT:    [[SUNKADDR1:%.*]] = getelementptr i8, ptr [[ARG]], i64 -64
+; CHECK-NEXT:    [[LOAD:%.*]] = load ptr, ptr [[SUNKADDR1]], align 8
+; CHECK-NEXT:    [[SUNKADDR:%.*]] = getelementptr i8, ptr [[ARG]], i64 -56
+; CHECK-NEXT:    [[LOAD4:%.*]] = load i32, ptr [[SUNKADDR]], align 8
+; CHECK-NEXT:    [[LOAD5:%.*]] = load ptr, ptr [[SUNKADDR1]], align 8
+; CHECK-NEXT:    [[TMP0:%.*]] = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 1, i32 0)
+; CHECK-NEXT:    [[MATH:%.*]] = extractvalue { i32, i1 } [[TMP0]], 0
+; CHECK-NEXT:    ret void
+;
+bb:
+  %getelementptr = getelementptr i8, ptr %arg, i64 -64
+  %getelementptr1 = getelementptr i8, ptr %arg, i64 -56
+  call void @g(ptr %getelementptr)
+  br label %bb3
+
+bb3:
+  %load = load ptr, ptr %getelementptr, align 8
+  %load4 = load i32, ptr %getelementptr1, align 8
+  %load5 = load ptr, ptr %getelementptr, align 8
+  %add = add i32 1, 0
+  %icmp = icmp eq i32 %add, 0
+  br i1 %icmp, label %bb7, label %bb7
+
+bb7:
+  ret void
+}