[InlineSpiller] Fix a crash due to lack of forward progress from remat (try 2)

This is a recommit of r335091 Add more test cases for deopt-operands via regalloc, and r335077 [InlineSpiller] Fix a crash due to lack of forward progress from remat specifically for STATEPOINT.  They were reverted due to a crash.

This change includes the text of both original changes, but also includes three aditional pieces:
1) A bug fix for the observed crash.  I had failed to record the failed remat value as live which resulted in an instruction being deleted which still had uses.  With the machine verifier, this is caught quickly.  Without it, we fail in StackSlotColoring due to an empty live interval from LiveStack.
2) A test case which demonstrates the fix for (1).  See @test11.
3) A control flag which defaults to disabling this for the moment.  Once I've run more extensive validaton, I will switch the default and then remove this flag.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@353871 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/InlineSpiller.cpp b/lib/CodeGen/InlineSpiller.cpp
index 7f89adfab7565525bf45531afa3b2a196472c9a7..647168b1c33eb2d459be012a03e5d54ea201c5cf 100644 (file)
--- a/lib/CodeGen/InlineSpiller.cpp
+++ b/lib/CodeGen/InlineSpiller.cpp
@@ -75,6 +75,10 @@ STATISTIC(NumRemats,          "Number of rematerialized defs for spilling");
 
 static cl::opt<bool> DisableHoisting("disable-spill-hoist", cl::Hidden,
                                      cl::desc("Disable inline spill hoisting"));
+static cl::opt<bool>
+RestrictStatepointRemat("restrict-statepoint-remat",
+                       cl::init(false), cl::Hidden,
+                       cl::desc("Restrict remat for statepoint operands"));
 
 namespace {
 
@@ -214,6 +218,7 @@ private:
   void eliminateRedundantSpills(LiveInterval &LI, VNInfo *VNI);
 
   void markValueUsed(LiveInterval*, VNInfo*);
+  bool canGuaranteeAssignmentAfterRemat(unsigned VReg, MachineInstr &MI);
   bool reMaterializeFor(LiveInterval &, MachineInstr &MI);
   void reMaterializeAll();
 
@@ -513,6 +518,28 @@ void InlineSpiller::markValueUsed(LiveInterval *LI, VNInfo *VNI) {
   } while (!WorkList.empty());
 }
 
+bool InlineSpiller::canGuaranteeAssignmentAfterRemat(unsigned VReg,
+                                                     MachineInstr &MI) {
+  if (!RestrictStatepointRemat)
+    return true;
+  // Here's a quick explanation of the problem we're trying to handle here:
+  // * There are some pseudo instructions with more vreg uses than there are
+  //   physical registers on the machine.
+  // * This is normally handled by spilling the vreg, and folding the reload
+  //   into the user instruction.  (Thus decreasing the number of used vregs
+  //   until the remainder can be assigned to physregs.)
+  // * However, since we may try to spill vregs in any order, we can end up
+  //   trying to spill each operand to the instruction, and then rematting it
+  //   instead.  When that happens, the new live intervals (for the remats) are
+  //   expected to be trivially assignable (i.e. RS_Done).  However, since we
+  //   may have more remats than physregs, we're guaranteed to fail to assign
+  //   one.
+  // At the moment, we only handle this for STATEPOINTs since they're the only
+  // psuedo op where we've seen this.  If we start seeing other instructions
+  // with the same problem, we need to revisit this.
+  return (MI.getOpcode() != TargetOpcode::STATEPOINT);
+}
+
 /// reMaterializeFor - Attempt to rematerialize before MI instead of reloading.
 bool InlineSpiller::reMaterializeFor(LiveInterval &VirtReg, MachineInstr &MI) {
   // Analyze instruction
@@ -568,6 +595,14 @@ bool InlineSpiller::reMaterializeFor(LiveInterval &VirtReg, MachineInstr &MI) {
     return true;
   }
 
+  // If we can't guarantee that we'll be able to actually assign the new vreg,
+  // we can't remat.
+  if (!canGuaranteeAssignmentAfterRemat(VirtReg.reg, MI)) {
+    markValueUsed(&VirtReg, ParentVNI);
+    LLVM_DEBUG(dbgs() << "\tcannot remat for " << UseIdx << '\t' << MI);
+    return false;
+  }
+
   // Allocate a new register for the remat.
   unsigned NewVReg = Edit->createFrom(Original);
 

diff --git a/test/CodeGen/X86/statepoint-live-in.ll b/test/CodeGen/X86/statepoint-live-in.ll
index 69affe2a9fcbe0efb16cf62a2518c9fb3d4a42ea..242f03fc3887e8eb7dd078ad7ddda6077b589293 100644 (file)
--- a/test/CodeGen/X86/statepoint-live-in.ll
+++ b/test/CodeGen/X86/statepoint-live-in.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -verify-machineinstrs -O3 < %s | FileCheck %s
+; RUN: llc -verify-machineinstrs -O3 -restrict-statepoint-remat < %s | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.11.0"
 
@@ -128,6 +128,460 @@ entry:
   ret void
 }
 
+; A variant of test7 where values are not directly foldable from stack slots.
+define void @test7(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p, i32 %q, i32 %r, i32 %s, i32 %t, i32 %u, i32 %v, i32 %w, i32 %x, i32 %y, i32 %z) gc "statepoint-example" {
+; The code for this is terrible, check simply for correctness for the moment
+; CHECK-LABEL: test7:
+; CHECK:       ## %bb.0: ## %entry
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    pushq %r15
+; CHECK-NEXT:    .cfi_def_cfa_offset 24
+; CHECK-NEXT:    pushq %r14
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    pushq %r13
+; CHECK-NEXT:    .cfi_def_cfa_offset 40
+; CHECK-NEXT:    pushq %r12
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 56
+; CHECK-NEXT:    subq $88, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 144
+; CHECK-NEXT:    .cfi_offset %rbx, -56
+; CHECK-NEXT:    .cfi_offset %r12, -48
+; CHECK-NEXT:    .cfi_offset %r13, -40
+; CHECK-NEXT:    .cfi_offset %r14, -32
+; CHECK-NEXT:    .cfi_offset %r15, -24
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl %edi, %edi
+; CHECK-NEXT:    movl %esi, %esi
+; CHECK-NEXT:    movl %edx, %edx
+; CHECK-NEXT:    movl %ecx, %ecx
+; CHECK-NEXT:    movl %r8d, %r8d
+; CHECK-NEXT:    movl %r9d, %r9d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, (%rsp) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %ebp
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r13d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r12d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r15d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r14d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %ebx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r11d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r10d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    callq _bar ## 88-byte Folded Reload
+; CHECK-NEXT:  Ltmp8:
+; CHECK-NEXT:    addq $88, %rsp
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    popq %r12
+; CHECK-NEXT:    popq %r13
+; CHECK-NEXT:    popq %r14
+; CHECK-NEXT:    popq %r15
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    retq
+entry:
+  %a64 = zext i32 %a to i64
+  %b64 = zext i32 %b to i64
+  %c64 = zext i32 %c to i64
+  %d64 = zext i32 %d to i64
+  %e64 = zext i32 %e to i64
+  %f64 = zext i32 %f to i64
+  %g64 = zext i32 %g to i64
+  %h64 = zext i32 %h to i64
+  %i64 = zext i32 %i to i64
+  %j64 = zext i32 %j to i64
+  %k64 = zext i32 %k to i64
+  %l64 = zext i32 %l to i64
+  %m64 = zext i32 %m to i64
+  %n64 = zext i32 %n to i64
+  %o64 = zext i32 %o to i64
+  %p64 = zext i32 %p to i64
+  %q64 = zext i32 %q to i64
+  %r64 = zext i32 %r to i64
+  %s64 = zext i32 %s to i64
+  %t64 = zext i32 %t to i64
+  %u64 = zext i32 %u to i64
+  %v64 = zext i32 %v to i64
+  %w64 = zext i32 %w to i64
+  %x64 = zext i32 %x to i64
+  %y64 = zext i32 %y to i64
+  %z64 = zext i32 %z to i64
+  %statepoint_token1 = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 2882400000, i32 0, void ()* @bar, i32 0, i32 2, i32 0, i32 26, i64 %a64, i64 %b64, i64 %c64, i64 %d64, i64 %e64, i64 %f64, i64 %g64, i64 %h64, i64 %i64, i64 %j64, i64 %k64, i64 %l64, i64 %m64, i64 %n64, i64 %o64, i64 %p64, i64 %q64, i64 %r64, i64 %s64, i64 %t64, i64 %u64, i64 %v64, i64 %w64, i64 %x64, i64 %y64, i64 %z64)
+  ret void
+}
+
+; a variant of test7 with mixed types chosen to exercise register aliases
+define void @test8(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p, i32 %q, i32 %r, i32 %s, i32 %t, i32 %u, i32 %v, i32 %w, i32 %x, i32 %y, i32 %z) gc "statepoint-example" {
+; The code for this is terrible, check simply for correctness for the moment
+; CHECK-LABEL: test8:
+; CHECK:       ## %bb.0: ## %entry
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    pushq %r15
+; CHECK-NEXT:    .cfi_def_cfa_offset 24
+; CHECK-NEXT:    pushq %r14
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    pushq %r13
+; CHECK-NEXT:    .cfi_def_cfa_offset 40
+; CHECK-NEXT:    pushq %r12
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 56
+; CHECK-NEXT:    subq $72, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 128
+; CHECK-NEXT:    .cfi_offset %rbx, -56
+; CHECK-NEXT:    .cfi_offset %r12, -48
+; CHECK-NEXT:    .cfi_offset %r13, -40
+; CHECK-NEXT:    .cfi_offset %r14, -32
+; CHECK-NEXT:    .cfi_offset %r15, -24
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movl %r9d, %r10d
+; CHECK-NEXT:    movl %r8d, %r9d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, (%rsp) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %ebp
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r13d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r12d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r15d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r14d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %ebx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r11d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %r8d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    callq _bar ## 72-byte Folded Reload
+; CHECK-NEXT:  Ltmp9:
+; CHECK-NEXT:    addq $72, %rsp
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    popq %r12
+; CHECK-NEXT:    popq %r13
+; CHECK-NEXT:    popq %r14
+; CHECK-NEXT:    popq %r15
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    retq
+entry:
+  %a8 = trunc i32 %a to i8
+  %b8 = trunc i32 %b to i8
+  %c8 = trunc i32 %c to i8
+  %d8 = trunc i32 %d to i8
+  %e16 = trunc i32 %e to i16
+  %f16 = trunc i32 %f to i16
+  %g16 = trunc i32 %g to i16
+  %h16 = trunc i32 %h to i16
+  %i64 = zext i32 %i to i64
+  %j64 = zext i32 %j to i64
+  %k64 = zext i32 %k to i64
+  %l64 = zext i32 %l to i64
+  %m64 = zext i32 %m to i64
+  %n64 = zext i32 %n to i64
+  %o64 = zext i32 %o to i64
+  %p64 = zext i32 %p to i64
+  %q64 = zext i32 %q to i64
+  %r64 = zext i32 %r to i64
+  %s64 = zext i32 %s to i64
+  %t64 = zext i32 %t to i64
+  %u64 = zext i32 %u to i64
+  %v64 = zext i32 %v to i64
+  %w64 = zext i32 %w to i64
+  %x64 = zext i32 %x to i64
+  %y64 = zext i32 %y to i64
+  %z64 = zext i32 %z to i64
+  %statepoint_token1 = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 2882400000, i32 0, void ()* @bar, i32 0, i32 2, i32 0, i32 26, i8 %a8, i8 %b8, i8 %c8, i8 %d8, i16 %e16, i16 %f16, i16 %g16, i16 %h16, i64 %i64, i64 %j64, i64 %k64, i64 %l64, i64 %m64, i64 %n64, i64 %o64, i64 %p64, i64 %q64, i64 %r64, i64 %s64, i64 %t64, i64 %u64, i64 %v64, i64 %w64, i64 %x64, i64 %y64, i64 %z64)
+  ret void
+}
+
+; Test perfect forwarding of argument registers and stack slots to the
+; deopt bundle uses
+define void @test9(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p, i32 %q, i32 %r, i32 %s, i32 %t, i32 %u, i32 %v, i32 %w, i32 %x, i32 %y, i32 %z) gc "statepoint-example" {
+; CHECK-LABEL: test9:
+; CHECK:       ## %bb.0: ## %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    callq _bar
+; CHECK-NEXT:  Ltmp10:
+; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    retq
+
+entry:
+  %statepoint_token1 = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 2882400000, i32 0, void ()* @bar, i32 0, i32 2, i32 0, i32 26, i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p, i32 %q, i32 %r, i32 %s, i32 %t, i32 %u, i32 %v, i32 %w, i32 %x, i32 %y, i32 %z)
+  ret void
+}
+
+; Test enough folding of argument slots when we have one call which clobbers
+; registers before a second which needs them - i.e. we must do something with
+; arguments originally passed in registers
+define void @test10(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p, i32 %q, i32 %r, i32 %s, i32 %t, i32 %u, i32 %v, i32 %w, i32 %x, i32 %y, i32 %z) gc "statepoint-example" {
+; FIXME (minor): It would be better to just spill (and fold reload) for
+; argument registers then spill and fill all the CSRs.
+; CHECK-LABEL: test10:
+; CHECK:       ## %bb.0: ## %entry
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    pushq %r15
+; CHECK-NEXT:    .cfi_def_cfa_offset 24
+; CHECK-NEXT:    pushq %r14
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    pushq %r13
+; CHECK-NEXT:    .cfi_def_cfa_offset 40
+; CHECK-NEXT:    pushq %r12
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 56
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
+; CHECK-NEXT:    .cfi_offset %rbx, -56
+; CHECK-NEXT:    .cfi_offset %r12, -48
+; CHECK-NEXT:    .cfi_offset %r13, -40
+; CHECK-NEXT:    .cfi_offset %r14, -32
+; CHECK-NEXT:    .cfi_offset %r15, -24
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movl %r9d, %r15d
+; CHECK-NEXT:    movl %r8d, %r14d
+; CHECK-NEXT:    movl %ecx, %r12d
+; CHECK-NEXT:    movl %edx, %r13d
+; CHECK-NEXT:    movl %esi, %ebx
+; CHECK-NEXT:    movl %edi, %ebp
+; CHECK-NEXT:    callq _bar
+; CHECK-NEXT:  Ltmp11:
+; CHECK-NEXT:    callq _bar
+; CHECK-NEXT:  Ltmp12:
+; CHECK-NEXT:    addq $8, %rsp
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    popq %r12
+; CHECK-NEXT:    popq %r13
+; CHECK-NEXT:    popq %r14
+; CHECK-NEXT:    popq %r15
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    retq
+
+entry:
+  %statepoint_token1 = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 2882400000, i32 0, void ()* @bar, i32 0, i32 2, i32 0, i32 26, i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p, i32 %q, i32 %r, i32 %s, i32 %t, i32 %u, i32 %v, i32 %w, i32 %x, i32 %y, i32 %z)
+  %statepoint_token2 = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 2882400000, i32 0, void ()* @bar, i32 0, i32 2, i32 0, i32 26, i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p, i32 %q, i32 %r, i32 %s, i32 %t, i32 %u, i32 %v, i32 %w, i32 %x, i32 %y, i32 %z)
+  ret void
+}
+
+; Check that we can remat some uses of a def despite not remating before the
+; statepoint user.
+define i64 @test11(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h, i32 %i, i32 %j, i32 %k, i32 %l, i32 %m, i32 %n, i32 %o, i32 %p, i32 %q, i32 %r, i32 %s, i32 %t, i32 %u, i32 %v, i32 %w, i32 %x, i32 %y, i32 %z) gc "statepoint-example" {
+; FIXME: The codegen for this is correct, but horrible.  Lots of room for
+; improvement if we so desire.
+; CHECK-LABEL: test11:
+; CHECK:       ## %bb.0: ## %entry
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    pushq %r15
+; CHECK-NEXT:    .cfi_def_cfa_offset 24
+; CHECK-NEXT:    pushq %r14
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    pushq %r13
+; CHECK-NEXT:    .cfi_def_cfa_offset 40
+; CHECK-NEXT:    pushq %r12
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 56
+; CHECK-NEXT:    subq $168, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 224
+; CHECK-NEXT:    .cfi_offset %rbx, -56
+; CHECK-NEXT:    .cfi_offset %r12, -48
+; CHECK-NEXT:    .cfi_offset %r13, -40
+; CHECK-NEXT:    .cfi_offset %r14, -32
+; CHECK-NEXT:    .cfi_offset %r15, -24
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl %edi, %ebx
+; CHECK-NEXT:    movl %esi, %r15d
+; CHECK-NEXT:    movl %edx, %r12d
+; CHECK-NEXT:    movl %ecx, %r13d
+; CHECK-NEXT:    movl %r8d, %ebp
+; CHECK-NEXT:    movl %r9d, %r14d
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
+; CHECK-NEXT:    callq _bar ## 160-byte Folded Reload
+; CHECK-NEXT:  Ltmp13:
+; CHECK-NEXT:    addq %r15, %rbx
+; CHECK-NEXT:    addq %r12, %rbx
+; CHECK-NEXT:    addq %r13, %rbx
+; CHECK-NEXT:    addq %rbp, %rbx
+; CHECK-NEXT:    addq %r14, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    addq %rax, %rbx
+; CHECK-NEXT:    movq %rbx, %rax
+; CHECK-NEXT:    addq $168, %rsp
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    popq %r12
+; CHECK-NEXT:    popq %r13
+; CHECK-NEXT:    popq %r14
+; CHECK-NEXT:    popq %r15
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    retq
+
+entry:
+  %a64 = zext i32 %a to i64
+  %b64 = zext i32 %b to i64
+  %c64 = zext i32 %c to i64
+  %d64 = zext i32 %d to i64
+  %e64 = zext i32 %e to i64
+  %f64 = zext i32 %f to i64
+  %g64 = zext i32 %g to i64
+  %h64 = zext i32 %h to i64
+  %i64 = zext i32 %i to i64
+  %j64 = zext i32 %j to i64
+  %k64 = zext i32 %k to i64
+  %l64 = zext i32 %l to i64
+  %m64 = zext i32 %m to i64
+  %n64 = zext i32 %n to i64
+  %o64 = zext i32 %o to i64
+  %p64 = zext i32 %p to i64
+  %q64 = zext i32 %q to i64
+  %r64 = zext i32 %r to i64
+  %s64 = zext i32 %s to i64
+  %t64 = zext i32 %t to i64
+  %u64 = zext i32 %u to i64
+  %v64 = zext i32 %v to i64
+  %w64 = zext i32 %w to i64
+  %x64 = zext i32 %x to i64
+  %y64 = zext i32 %y to i64
+  %z64 = zext i32 %z to i64
+  call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 2882400000, i32 0, void ()* @bar, i32 0, i32 2, i64 0, i64 26, i64 %a64, i64 %b64, i64 %c64, i64 %d64, i64 %e64, i64 %f64, i64 %g64, i64 %h64, i64 %i64, i64 %j64, i64 %k64, i64 %l64, i64 %m64, i64 %n64, i64 %o64, i64 %p64, i64 %q64, i64 %r64, i64 %s64, i64 %t64, i64 %u64, i64 %v64, i64 %w64, i64 %x64, i64 %y64, i64 %z64)
+  %addab = add i64 %a64, %b64
+  %addc = add i64 %addab, %c64
+  %addd = add i64 %addc, %d64
+  %adde = add i64 %addd, %e64
+  %addf = add i64 %adde, %f64
+  %addg = add i64 %addf, %g64
+  %addh = add i64 %addg, %h64
+  %addi = add i64 %addh, %i64
+  %addj = add i64 %addi, %j64
+  %addk = add i64 %addj, %k64
+  %addl = add i64 %addk, %l64
+  %addm = add i64 %addl, %m64
+  %addn = add i64 %addm, %n64
+  %addo = add i64 %addn, %o64
+  %addp = add i64 %addo, %p64
+  %addq = add i64 %addp, %q64
+  %addr = add i64 %addq, %r64
+  %adds = add i64 %addr, %s64
+  %addt = add i64 %adds, %t64
+  %addu = add i64 %addt, %u64
+  %addv = add i64 %addu, %v64
+  %addw = add i64 %addv, %w64
+  %addx = add i64 %addw, %x64
+  %addy = add i64 %addx, %y64
+  %addz = add i64 %addy, %z64
+  ret i64 %addz
+}
+
 
 ; CHECK: Ltmp0-_test1
 ; CHECK:      .byte    1