[MemCpyOpt] fix incorrect handling of lifetime markers (#143782)

Having lifetime markers should only increase the information available
to LLVM, but it would instead rely on the callback to entirely give up
if it encountered a lifetime marker that wasn't full size, but
sub-optimal lifetime markers are not supposed to be forbidding
optimizations that would otherwise apply if they were either absent or
optimal. This pass wasn't tracking GEP offsets either, so it wasn't
quite correctly handled either, although earlier sub-optimal checks
that this size is the same as the alloca test made this safe in the
past, and unlikely to have encountered anything else in the past.

Author: vtjnash

llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp

@@ -1593,11 +1593,8 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
             // since both llvm.lifetime.start and llvm.lifetime.end intrinsics
             // practically fill all the bytes of the alloca with an undefined
             // value, although conceptually marked as alive/dead.
-            int64_t Size = cast<ConstantInt>(UI->getOperand(0))->getSExtValue();
-            if (Size < 0 || Size == DestSize) {
-              LifetimeMarkers.push_back(UI);
-              continue;
-            }
+            LifetimeMarkers.push_back(UI);
+            continue;
           }
           AAMetadataInstrs.insert(UI);
 
@@ -1614,9 +1611,8 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
     return true;
   };
 
-  // Check that dest has no Mod/Ref, from the alloca to the Store, except full
-  // size lifetime intrinsics. And collect modref inst for the reachability
-  // check.
+  // Check that dest has no Mod/Ref, from the alloca to the Store. And collect
+  // modref inst for the reachability check.
   ModRefInfo DestModRef = ModRefInfo::NoModRef;
   MemoryLocation DestLoc(DestAlloca, LocationSize::precise(Size));
   SmallVector<BasicBlock *, 8> ReachabilityWorklist;

llvm/test/Transforms/MemCpyOpt/stack-move.ll

@@ -1649,20 +1649,13 @@ loop_exit:
   ret void
 }
 
-; Tests that failure because partial-sized lifetimes are counted as mod.
+; Tests that partial-sized lifetimes are not inhibiting the optimizer
 define void @partial_lifetime() {
 ; CHECK-LABEL: define void @partial_lifetime() {
-; CHECK-NEXT:    [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
-; CHECK-NEXT:    [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4
-; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 12, ptr captures(none) [[SRC]])
-; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 3, ptr captures(none) [[DEST]])
-; CHECK-NEXT:    store [[STRUCT_FOO]] { i32 10, i32 20, i32 30 }, ptr [[SRC]], align 4
-; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @use_nocapture(ptr captures(none) [[SRC]])
-; CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DEST]], ptr align 4 [[SRC]], i64 12, i1 false)
-; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 3, ptr captures(none) [[SRC]])
+; CHECK-NEXT:    [[DEST:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
+; CHECK-NEXT:    store [[STRUCT_FOO]] { i32 10, i32 20, i32 30 }, ptr [[DEST]], align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @use_nocapture(ptr captures(none) [[DEST]])
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @use_nocapture(ptr captures(none) [[DEST]])
-; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 12, ptr captures(none) [[SRC]])
-; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 12, ptr captures(none) [[DEST]])
 ; CHECK-NEXT:    ret void
 ;
   %src = alloca %struct.Foo, align 4