[DebugInfo] Re-instate LiveDebugVariables scope trimming

This patch reverts part of r362750 / D62650, which stopped
LiveDebugVariables from trimming leading variable location ranges down
to only covering those instructions that are in scope. I've observed some
circumstances where the number of DBG_VALUEs in a function can be
amplified in an un-necessary way, to cover more instructions that are
out of scope, leading to very slow compile times. Trimming the range
of instructions that the variables cover solves the slow compile times.

The specific problem that r362750 tries to fix is addressed by the
assignment to RStart that I've added. Any variable location that begins
at the first instruction of a block will now be considered to begin at the
start of the block. While these sound the same, the have different
SlotIndexes, and the register allocator may shoehorn additional
instructions in between the two. The test added in the past
(wrong_debug_loc_after_regalloc.ll) still works with this modification.

live-debug-variables.ll has a range trimmed to not cover the prologue of
the function, while dbg-addr-dse.ll has a DBG_VALUE sink past one
instruction with no DebugLoc, which is expected behaviour.

Differential Revision: https://reviews.llvm.org/D73691

Author: jmorse

llvm/lib/CodeGen/LiveDebugVariables.cpp

@@ -166,6 +166,10 @@ class UserValue {
   /// Map of slot indices where this value is live.
   LocMap locInts;
 
+  /// Set of interval start indexes that have been trimmed to the
+  /// lexical scope.
+  SmallSet<SlotIndex, 2> trimmedDefs;
+
   /// Insert a DBG_VALUE into MBB at Idx for LocNo.
   void insertDebugValue(MachineBasicBlock *MBB, SlotIndex StartIdx,
                         SlotIndex StopIdx, DbgValueLocation Loc, bool Spilled,
@@ -910,6 +914,11 @@ void UserValue::computeIntervals(MachineRegisterInfo &MRI,
     SlotIndex RStart = LIS.getInstructionIndex(*Range.first);
     SlotIndex REnd = LIS.getInstructionIndex(*Range.second);
 
+    // Variable locations at the first instruction of a block should be
+    // based on the block's SlotIndex, not the first instruction's index.
+    if (Range.first == Range.first->getParent()->begin())
+      RStart = LIS.getSlotIndexes()->getIndexBefore(*Range.first);
+
     // At the start of each iteration I has been advanced so that
     // I.stop() >= PrevEnd. Check for overlap.
     if (PrevEnd && I.start() < PrevEnd) {
@@ -922,7 +931,8 @@ void UserValue::computeIntervals(MachineRegisterInfo &MRI,
       ++I;
 
       // If the interval also overlaps the start of the "next" (i.e.
-      // current) range create a new interval for the remainder
+      // current) range create a new interval for the remainder (which
+      // may be further trimmed).
       if (RStart < IStop)
         I.insert(RStart, IStop, Loc);
     }
@@ -932,6 +942,13 @@ void UserValue::computeIntervals(MachineRegisterInfo &MRI,
     if (!I.valid())
       return;
 
+    if (I.start() < RStart) {
+      // Interval start overlaps range - trim to the scope range.
+      I.setStartUnchecked(RStart);
+      // Remember that this interval was trimmed.
+      trimmedDefs.insert(RStart);
+    }
+
     // The end of a lexical scope range is the last instruction in the
     // range. To convert to an interval we need the index of the
     // instruction after it.
@@ -1345,6 +1362,12 @@ void UserValue::emitDebugValues(VirtRegMap *VRM, LiveIntervals &LIS,
     bool Spilled = SpillIt != SpillOffsets.end();
     unsigned SpillOffset = Spilled ? SpillIt->second : 0;
 
+    // If the interval start was trimmed to the lexical scope insert the
+    // DBG_VALUE at the previous index (otherwise it appears after the
+    // first instruction in the range).
+    if (trimmedDefs.count(Start))
+      Start = Start.getPrevIndex();
+
     LLVM_DEBUG(dbgs() << "\t[" << Start << ';' << Stop << "):" << Loc.locNo());
     MachineFunction::iterator MBB = LIS.getMBBFromIndex(Start)->getIterator();
     SlotIndex MBBEnd = LIS.getMBBEndIdx(&*MBB);

llvm/test/DebugInfo/X86/dbg-addr-dse.ll

@@ -50,8 +50,8 @@ entry:
 }
 
 ; ASM-LABEL: f: # @f
-; ASM: #DEBUG_VALUE: f:x <- [DW_OP_plus_uconst [[OFF_X:[0-9]+]], DW_OP_deref] $rsp
-; ASM: movl    %ecx, [[OFF_X]](%rsp)
+; ASM: movl    %ecx, [[OFF_X:[0-9]+]](%rsp)
+; ASM: #DEBUG_VALUE: f:x <- [DW_OP_plus_uconst [[OFF_X]], DW_OP_deref] $rsp
 ; ASM: callq   escape
 ; ASM: #DEBUG_VALUE: f:x <- 1
 ; ASM: movl    $1, global(%rip)

llvm/test/DebugInfo/X86/live-debug-variables.ll

@@ -25,7 +25,7 @@
 ; CHECK:      .debug_loc contents:
 ; CHECK-NEXT: 0x00000000:
 ;   We currently emit an entry for the function prologue, too, which could be optimized away.
-; CHECK:              (0x0000000000000010, 0x0000000000000072): DW_OP_reg3 RBX
+; CHECK:              (0x0000000000000018, 0x0000000000000072): DW_OP_reg3 RBX
 ;   We should only have one entry inside the function.
 ; CHECK-NOT: :