[WPD] Change Devirt Cutoff to use DebugCounter (#170009)

This removes the presence of global state from within the pass which is
blocking some efforts around test daemonization and is not good design
practice in general for LLVM. See

https://discourse.llvm.org/t/rfc-reducing-process-creation-overhead-in-llvm-regression-tests/88612/11
for more discussion.

This patch replaces the usage of global state with a DebugCounter, which
helps fix the global state problem and also increases the flexibility of
the option as now an explicit range can be passed.

Co-authored-by: Mingming Liu <[email protected]>

Author: boomanaiden154

llvm/lib/Transforms/IPO/WholeProgramDevirt.cpp

@@ -99,6 +99,7 @@
 #include "llvm/IR/ProfDataUtils.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
+#include "llvm/Support/DebugCounter.h"
 #include "llvm/Support/Errc.h"
 #include "llvm/Support/Error.h"
 #include "llvm/Support/FileSystem.h"
@@ -130,6 +131,8 @@ STATISTIC(NumUniqueRetVal, "Number of unique return value optimizations");
 STATISTIC(NumVirtConstProp1Bit,
           "Number of 1 bit virtual constant propagations");
 STATISTIC(NumVirtConstProp, "Number of virtual constant propagations");
+DEBUG_COUNTER(CallsToDevirt, "calls-to-devirt",
+              "Controls how many calls should be devirtualized.");
 
 namespace llvm {
 
@@ -219,14 +222,6 @@ static cl::opt<bool> WholeProgramDevirtKeepUnreachableFunction(
     cl::desc("Regard unreachable functions as possible devirtualize targets."),
     cl::Hidden, cl::init(true));
 
-/// If explicitly specified, the devirt module pass will stop transformation
-/// once the total number of devirtualizations reach the cutoff value. Setting
-/// this option to 0 explicitly will do 0 devirtualization.
-static cl::opt<unsigned> WholeProgramDevirtCutoff(
-    "wholeprogramdevirt-cutoff",
-    cl::desc("Max number of devirtualizations for devirt module pass"),
-    cl::init(0));
-
 /// Mechanism to add runtime checking of devirtualization decisions, optionally
 /// trapping or falling back to indirect call on any that are not correct.
 /// Trapping mode is useful for debugging undefined behavior leading to failures
@@ -377,9 +372,6 @@ VirtualCallTarget::VirtualCallTarget(GlobalValue *Fn, const TypeMemberInfo *TM)
 
 namespace {
 
-// Tracks the number of devirted calls in the IR transformation.
-static unsigned NumDevirtCalls = 0;
-
 // A slot in a set of virtual tables. The TypeID identifies the set of virtual
 // tables, and the ByteOffset is the offset in bytes from the address point to
 // the virtual function pointer.
@@ -1216,15 +1208,13 @@ void DevirtModule::applySingleImplDevirt(VTableSlotInfo &SlotInfo,
         continue;
 
       // Stop when the number of devirted calls reaches the cutoff.
-      if (WholeProgramDevirtCutoff.getNumOccurrences() > 0 &&
-          NumDevirtCalls >= WholeProgramDevirtCutoff)
-        return;
+      if (!DebugCounter::shouldExecute(CallsToDevirt))
+        continue;
 
       if (RemarksEnabled)
         VCallSite.emitRemark("single-impl",
                              TheFn->stripPointerCasts()->getName(), OREGetter);
       NumSingleImpl++;
-      NumDevirtCalls++;
       auto &CB = VCallSite.CB;
       assert(!CB.getCalledFunction() && "devirtualizing direct call?");
       IRBuilder<> Builder(&CB);

llvm/test/Transforms/WholeProgramDevirt/calls-to-devirt.ll

@@ -0,0 +1,81 @@
+; REQUIRES: asserts
+
+; Devirt calls debug counter is not explicitly set. Expect 3 remark messages.
+; RUN: opt -S -passes=wholeprogramdevirt -wholeprogramdevirt-summary-action=import \
+; RUN:   -pass-remarks=wholeprogramdevirt \
+; RUN:   -wholeprogramdevirt-read-summary=%S/Inputs/import-single-impl.yaml \
+; RUN:   -print-debug-counter-queries < %s  2>&1 \
+; RUN:   | grep "remark" | count 3
+; Devirt calls debug counter is set to 1. Expect one remark messages.
+; RUN: opt -S -passes=wholeprogramdevirt -wholeprogramdevirt-summary-action=import \
+; RUN:   -pass-remarks=wholeprogramdevirt -debug-counter=calls-to-devirt=0 \
+; RUN:   -wholeprogramdevirt-read-summary=%S/Inputs/import-single-impl.yaml \
+; RUN:   -print-debug-counter-queries < %s  2>&1 \
+; RUN:   | FileCheck --check-prefix=CHECK-SINGLE %s
+; Devirt calls debug counter is set outside the range of calls. Expect no remark message.
+; RUN: opt -S -passes=wholeprogramdevirt -wholeprogramdevirt-summary-action=import \
+; RUN:   -pass-remarks=wholeprogramdevirt -debug-counter=calls-to-devirt=9999 \
+; RUN:   -wholeprogramdevirt-read-summary=%S/Inputs/import-single-impl.yaml \
+; RUN:   -print-debug-counter-queries < %s 2>&1  \
+; RUN:   | FileCheck -implicit-check-not="remark" --check-prefix=CHECK-NONE %s
+
+; CHECK-SINGLE: DebugCounter calls-to-devirt=0 execute
+; CHECK-SINGLE: remark
+; CHECK-SINGLE-SAME: devirtualized a call
+; CHECK-SINGLE: DebugCounter calls-to-devirt=1 skip
+; CHECK-SINGLE: DebugCounter calls-to-devirt=2 skip
+
+; CHECK-NONE: DebugCounter calls-to-devirt=0 skip
+; CHECK-NONE: DebugCounter calls-to-devirt=1 skip
+; CHECK-NONE: DebugCounter calls-to-devirt=2 skip
+
+target datalayout = "e-p:64:64"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @call1(ptr %obj) #0 {
+  %vtable = load ptr, ptr %obj
+  %p = call i1 @llvm.type.test(ptr %vtable, metadata !"typeid1")
+  call void @llvm.assume(i1 %p)
+  %fptr = load ptr, ptr %vtable
+  %result = call i32 %fptr(ptr %obj, i32 1)
+  ret i32 %result
+}
+
+define i1 @call2(ptr %obj) #0 {
+  %vtable = load ptr, ptr %obj
+  %pair = call {ptr, i1} @llvm.type.checked.load(ptr %vtable, i32 8, metadata !"typeid2")
+  %fptr = extractvalue {ptr, i1} %pair, 0
+  %p = extractvalue {ptr, i1} %pair, 1
+  br i1 %p, label %cont, label %trap
+
+cont:
+  %result = call i1 %fptr(ptr %obj, i32 undef)
+  ret i1 %result
+
+trap:
+  call void @llvm.trap()
+  unreachable
+}
+
+define i1 @call3(ptr %obj) #0 {
+  %vtable = load ptr, ptr %obj
+  %pair = call {ptr, i1} @llvm.type.checked.load(ptr %vtable, i32 8, metadata !"typeid2")
+  %fptr = extractvalue {ptr, i1} %pair, 0
+  %p = extractvalue {ptr, i1} %pair, 1
+  br i1 %p, label %cont, label %trap
+
+cont:
+  %result = call i1 %fptr(ptr %obj, i32 3)
+  ret i1 %result
+
+trap:
+  call void @llvm.trap()
+  unreachable
+}
+
+declare void @llvm.assume(i1)
+declare void @llvm.trap()
+declare {ptr, i1} @llvm.type.checked.load(ptr, i32, metadata)
+declare i1 @llvm.type.test(ptr, metadata)
+
+attributes #0 = { "target-features"="+retpoline" }

llvm/test/Transforms/WholeProgramDevirt/import.ll

@@ -8,12 +8,6 @@
 ; RUN: opt -S -passes=wholeprogramdevirt -wholeprogramdevirt-summary-action=import -wholeprogramdevirt-read-summary=%S/Inputs/import-vcp-branch-funnel.yaml < %s | FileCheck --check-prefixes=CHECK,VCP,VCP-X86,VCP64,BRANCH-FUNNEL %s
 ; RUN: opt -S -passes=wholeprogramdevirt -wholeprogramdevirt-summary-action=import -wholeprogramdevirt-read-summary=%S/Inputs/import-branch-funnel.yaml < %s | FileCheck --check-prefixes=CHECK,BRANCH-FUNNEL,BRANCH-FUNNEL-NOVCP %s
 
-; Cutoff value is not explicitly set. Expect 3 remark messages.
-; RUN: opt -S -passes=wholeprogramdevirt -wholeprogramdevirt-summary-action=import -pass-remarks=wholeprogramdevirt -wholeprogramdevirt-read-summary=%S/Inputs/import-single-impl.yaml < %s  2>&1 | grep "single-impl" | count 3
-; Cutoff value is set to 1. Expect one remark messages.
-; RUN: opt -S -passes=wholeprogramdevirt -wholeprogramdevirt-summary-action=import -pass-remarks=wholeprogramdevirt -wholeprogramdevirt-cutoff=1  -wholeprogramdevirt-read-summary=%S/Inputs/import-single-impl.yaml < %s  2>&1 | grep "single-impl" | count 1
-; Cutoff value is explicitly set to zero. Expect no remark message.
-; RUN: opt -S -passes=wholeprogramdevirt -wholeprogramdevirt-summary-action=import -pass-remarks=wholeprogramdevirt -wholeprogramdevirt-cutoff=0  -wholeprogramdevirt-read-summary=%S/Inputs/import-single-impl.yaml < %s 2>&1  | FileCheck -implicit-check-not="remark" %s
 target datalayout = "e-p:64:64"
 target triple = "x86_64-unknown-linux-gnu"