[regexp] Hoist LoadCurrentCharacterImpl

LoadCurrentCharacterImpl is implemented once in each of the eight
regexp-macro-assembler-<arch>.cc files. Aside from small differences
in comment wording, those eight implementations are identical. The
architecture-specific code for LoadCurrentCharacter is all in
LoadCurrentCharacterUnchecked.

This patch hoists the definition of LoadCurrentCharacterImpl into
NativeRegExpMacroAssembler and turns LoadCurrentCharacterUnchecked
into a virtual function.

Note: The arm64 version of LoadCurrentCharacterImpl contained the
following six-year-old comment, which I don't think is worth
preserving:

// TODO(pielan): Make sure long strings are caught before this, and
// not just asserted in debug mode.

R=jgruber@chromium.org

Bug: v8:10406
Change-Id: Ic81283ad3b618d6b06f4206fb77d30de617dccb7
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2140003
Commit-Queue: Jakob Gruber <jgruber@chromium.org>
Reviewed-by: Jakob Gruber <jgruber@chromium.org>
Cr-Commit-Position: refs/heads/master@{#67260}

src/regexp/arm/regexp-macro-assembler-arm.cc

@@ -945,25 +945,6 @@ RegExpMacroAssembler::IrregexpImplementation
   return kARMImplementation;
 }
 
-void RegExpMacroAssemblerARM::LoadCurrentCharacterImpl(int cp_offset,
-                                                       Label* on_end_of_input,
-                                                       bool check_bounds,
-                                                       int characters,
-                                                       int eats_at_least) {
-  // It's possible to preload a small number of characters when each success
-  // path requires a large number of characters, but not the reverse.
-  DCHECK_GE(eats_at_least, characters);
-
-  DCHECK(cp_offset < (1<<30));  // Be sane! (And ensure negation works)
-  if (check_bounds) {
-    if (cp_offset >= 0) {
-      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
-    } else {
-      CheckPosition(cp_offset, on_end_of_input);
-    }
-  }
-  LoadCurrentCharacterUnchecked(cp_offset, characters);
-}
 
 void RegExpMacroAssemblerARM::PopCurrentPosition() {
   Pop(current_input_offset());

src/regexp/arm/regexp-macro-assembler-arm.h

@@ -67,9 +67,8 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerARM
   virtual void IfRegisterLT(int reg, int comparand, Label* if_lt);
   virtual void IfRegisterEqPos(int reg, Label* if_eq);
   virtual IrregexpImplementation Implementation();
-  virtual void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
-                                        bool check_bounds, int characters,
-                                        int eats_at_least);
+  virtual void LoadCurrentCharacterUnchecked(int cp_offset,
+                                             int character_count);
   virtual void PopCurrentPosition();
   virtual void PopRegister(int register_index);
   virtual void PushBacktrack(Label* label);
@@ -127,10 +126,6 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerARM
 
   static const int kBacktrackConstantPoolSize = 4;
 
-  // Load a number of characters at the given offset from the
-  // current position, into the current-character register.
-  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
-
   // Check whether preemption has been requested.
   void CheckPreemption();
 

src/regexp/arm64/regexp-macro-assembler-arm64.cc

@@ -1131,28 +1131,6 @@ RegExpMacroAssembler::IrregexpImplementation
   return kARM64Implementation;
 }
 
-void RegExpMacroAssemblerARM64::LoadCurrentCharacterImpl(int cp_offset,
-                                                         Label* on_end_of_input,
-                                                         bool check_bounds,
-                                                         int characters,
-                                                         int eats_at_least) {
-  // It's possible to preload a small number of characters when each success
-  // path requires a large number of characters, but not the reverse.
-  DCHECK_GE(eats_at_least, characters);
-
-  // TODO(pielan): Make sure long strings are caught before this, and not
-  // just asserted in debug mode.
-  // Be sane! (And ensure that an int32_t can be used to index the string)
-  DCHECK(cp_offset < (1<<30));
-  if (check_bounds) {
-    if (cp_offset >= 0) {
-      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
-    } else {
-      CheckPosition(cp_offset, on_end_of_input);
-    }
-  }
-  LoadCurrentCharacterUnchecked(cp_offset, characters);
-}
 
 void RegExpMacroAssemblerARM64::PopCurrentPosition() {
   Pop(current_input_offset());

src/regexp/arm64/regexp-macro-assembler-arm64.h

@@ -73,9 +73,8 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerARM64
   virtual void IfRegisterLT(int reg, int comparand, Label* if_lt);
   virtual void IfRegisterEqPos(int reg, Label* if_eq);
   virtual IrregexpImplementation Implementation();
-  virtual void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
-                                        bool check_bounds, int characters,
-                                        int eats_at_least);
+  virtual void LoadCurrentCharacterUnchecked(int cp_offset,
+                                             int character_count);
   virtual void PopCurrentPosition();
   virtual void PopRegister(int register_index);
   virtual void PushBacktrack(Label* label);
@@ -139,10 +138,6 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerARM64
   // 16 registers.
   static const int kNumCachedRegisters = 16;
 
-  // Load a number of characters at the given offset from the
-  // current position, into the current-character register.
-  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
-
   // Check whether preemption has been requested.
   void CheckPreemption();
 

src/regexp/ia32/regexp-macro-assembler-ia32.cc

@@ -981,25 +981,6 @@ RegExpMacroAssembler::IrregexpImplementation
   return kIA32Implementation;
 }
 
-void RegExpMacroAssemblerIA32::LoadCurrentCharacterImpl(int cp_offset,
-                                                        Label* on_end_of_input,
-                                                        bool check_bounds,
-                                                        int characters,
-                                                        int eats_at_least) {
-  // It's possible to preload a small number of characters when each success
-  // path requires a large number of characters, but not the reverse.
-  DCHECK_GE(eats_at_least, characters);
-
-  DCHECK(cp_offset < (1<<30));  // Be sane! (And ensure negation works)
-  if (check_bounds) {
-    if (cp_offset >= 0) {
-      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
-    } else {
-      CheckPosition(cp_offset, on_end_of_input);
-    }
-  }
-  LoadCurrentCharacterUnchecked(cp_offset, characters);
-}
 
 void RegExpMacroAssemblerIA32::PopCurrentPosition() {
   Pop(edi);

src/regexp/ia32/regexp-macro-assembler-ia32.h

@@ -66,9 +66,8 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerIA32
   virtual void IfRegisterLT(int reg, int comparand, Label* if_lt);
   virtual void IfRegisterEqPos(int reg, Label* if_eq);
   virtual IrregexpImplementation Implementation();
-  virtual void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
-                                        bool check_bounds, int characters,
-                                        int eats_at_least);
+  virtual void LoadCurrentCharacterUnchecked(int cp_offset,
+                                             int character_count);
   virtual void PopCurrentPosition();
   virtual void PopRegister(int register_index);
   virtual void PushBacktrack(Label* label);
@@ -127,10 +126,6 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerIA32
   // Initial size of code buffer.
   static const int kRegExpCodeSize = 1024;
 
-  // Load a number of characters at the given offset from the
-  // current position, into the current-character register.
-  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
-
   // Check whether preemption has been requested.
   void CheckPreemption();
 

src/regexp/mips/regexp-macro-assembler-mips.cc

@@ -958,25 +958,6 @@ RegExpMacroAssembler::IrregexpImplementation
   return kMIPSImplementation;
 }
 
-void RegExpMacroAssemblerMIPS::LoadCurrentCharacterImpl(int cp_offset,
-                                                        Label* on_end_of_input,
-                                                        bool check_bounds,
-                                                        int characters,
-                                                        int eats_at_least) {
-  // It's possible to preload a small number of characters when each success
-  // path requires a large number of characters, but not the reverse.
-  DCHECK_GE(eats_at_least, characters);
-
-  DCHECK(cp_offset < (1<<30));  // Be sane! (And ensure negation works).
-  if (check_bounds) {
-    if (cp_offset >= 0) {
-      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
-    } else {
-      CheckPosition(cp_offset, on_end_of_input);
-    }
-  }
-  LoadCurrentCharacterUnchecked(cp_offset, characters);
-}
 
 void RegExpMacroAssemblerMIPS::PopCurrentPosition() {
   Pop(current_input_offset());

src/regexp/mips/regexp-macro-assembler-mips.h

@@ -67,9 +67,8 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerMIPS
   virtual void IfRegisterLT(int reg, int comparand, Label* if_lt);
   virtual void IfRegisterEqPos(int reg, Label* if_eq);
   virtual IrregexpImplementation Implementation();
-  virtual void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
-                                        bool check_bounds, int characters,
-                                        int eats_at_least);
+  virtual void LoadCurrentCharacterUnchecked(int cp_offset,
+                                             int character_count);
   virtual void PopCurrentPosition();
   virtual void PopRegister(int register_index);
   virtual void PushBacktrack(Label* label);
@@ -128,10 +127,6 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerMIPS
   // Initial size of code buffer.
   static const int kRegExpCodeSize = 1024;
 
-  // Load a number of characters at the given offset from the
-  // current position, into the current-character register.
-  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
-
   // Check whether preemption has been requested.
   void CheckPreemption();
 

src/regexp/mips64/regexp-macro-assembler-mips64.cc

@@ -994,25 +994,6 @@ RegExpMacroAssembler::IrregexpImplementation
   return kMIPSImplementation;
 }
 
-void RegExpMacroAssemblerMIPS::LoadCurrentCharacterImpl(int cp_offset,
-                                                        Label* on_end_of_input,
-                                                        bool check_bounds,
-                                                        int characters,
-                                                        int eats_at_least) {
-  // It's possible to preload a small number of characters when each success
-  // path requires a large number of characters, but not the reverse.
-  DCHECK_GE(eats_at_least, characters);
-
-  DCHECK(cp_offset < (1<<30));  // Be sane! (And ensure negation works).
-  if (check_bounds) {
-    if (cp_offset >= 0) {
-      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
-    } else {
-      CheckPosition(cp_offset, on_end_of_input);
-    }
-  }
-  LoadCurrentCharacterUnchecked(cp_offset, characters);
-}
 
 void RegExpMacroAssemblerMIPS::PopCurrentPosition() {
   Pop(current_input_offset());

src/regexp/mips64/regexp-macro-assembler-mips64.h

@@ -67,9 +67,8 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerMIPS
   virtual void IfRegisterLT(int reg, int comparand, Label* if_lt);
   virtual void IfRegisterEqPos(int reg, Label* if_eq);
   virtual IrregexpImplementation Implementation();
-  virtual void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
-                                        bool check_bounds, int characters,
-                                        int eats_at_least);
+  virtual void LoadCurrentCharacterUnchecked(int cp_offset,
+                                             int character_count);
   virtual void PopCurrentPosition();
   virtual void PopRegister(int register_index);
   virtual void PushBacktrack(Label* label);
@@ -133,10 +132,6 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerMIPS
   // Initial size of code buffer.
   static const int kRegExpCodeSize = 1024;
 
-  // Load a number of characters at the given offset from the
-  // current position, into the current-character register.
-  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
-
   // Check whether preemption has been requested.
   void CheckPreemption();
 

src/regexp/ppc/regexp-macro-assembler-ppc.cc

@@ -992,25 +992,6 @@ RegExpMacroAssemblerPPC::Implementation() {
   return kPPCImplementation;
 }
 
-void RegExpMacroAssemblerPPC::LoadCurrentCharacterImpl(int cp_offset,
-                                                       Label* on_end_of_input,
-                                                       bool check_bounds,
-                                                       int characters,
-                                                       int eats_at_least) {
-  // It's possible to preload a small number of characters when each success
-  // path requires a large number of characters, but not the reverse.
-  DCHECK_GE(eats_at_least, characters);
-
-  DCHECK(cp_offset < (1 << 30));  // Be sane! (And ensure negation works)
-  if (check_bounds) {
-    if (cp_offset >= 0) {
-      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
-    } else {
-      CheckPosition(cp_offset, on_end_of_input);
-    }
-  }
-  LoadCurrentCharacterUnchecked(cp_offset, characters);
-}
 
 void RegExpMacroAssemblerPPC::PopCurrentPosition() {
   Pop(current_input_offset());

src/regexp/ppc/regexp-macro-assembler-ppc.h

@@ -59,9 +59,8 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerPPC
   virtual void IfRegisterLT(int reg, int comparand, Label* if_lt);
   virtual void IfRegisterEqPos(int reg, Label* if_eq);
   virtual IrregexpImplementation Implementation();
-  virtual void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
-                                        bool check_bounds, int characters,
-                                        int eats_at_least);
+  virtual void LoadCurrentCharacterUnchecked(int cp_offset,
+                                             int character_count);
   virtual void PopCurrentPosition();
   virtual void PopRegister(int register_index);
   virtual void PushBacktrack(Label* label);
@@ -119,10 +118,6 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerPPC
   // Initial size of code buffer.
   static const int kRegExpCodeSize = 1024;
 
-  // Load a number of characters at the given offset from the
-  // current position, into the current-character register.
-  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
-
   // Check whether preemption has been requested.
   void CheckPreemption();
 

src/regexp/regexp-macro-assembler.cc

@@ -111,6 +111,24 @@ NativeRegExpMacroAssembler::NativeRegExpMacroAssembler(Isolate* isolate,
 
 NativeRegExpMacroAssembler::~NativeRegExpMacroAssembler() = default;
 
+void NativeRegExpMacroAssembler::LoadCurrentCharacterImpl(
+    int cp_offset, Label* on_end_of_input, bool check_bounds, int characters,
+    int eats_at_least) {
+  // It's possible to preload a small number of characters when each success
+  // path requires a large number of characters, but not the reverse.
+  DCHECK_GE(eats_at_least, characters);
+
+  DCHECK(base::IsInRange(cp_offset, kMinCPOffset, kMaxCPOffset));
+  if (check_bounds) {
+    if (cp_offset >= 0) {
+      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
+    } else {
+      CheckPosition(cp_offset, on_end_of_input);
+    }
+  }
+  LoadCurrentCharacterUnchecked(cp_offset, characters);
+}
+
 bool NativeRegExpMacroAssembler::CanReadUnaligned() {
   return FLAG_enable_regexp_unaligned_accesses && !slow_safe();
 }

src/regexp/regexp-macro-assembler.h

@@ -272,6 +272,13 @@ class NativeRegExpMacroAssembler: public RegExpMacroAssembler {
                                        const byte* input_end, int* output,
                                        int output_size, Isolate* isolate,
                                        JSRegExp regexp);
+  void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
+                                bool check_bounds, int characters,
+                                int eats_at_least) override;
+  // Load a number of characters at the given offset from the
+  // current position, into the current-character register.
+  virtual void LoadCurrentCharacterUnchecked(int cp_offset,
+                                             int character_count) = 0;
 };
 
 }  // namespace internal

src/regexp/s390/regexp-macro-assembler-s390.cc

@@ -983,26 +983,6 @@ RegExpMacroAssemblerS390::Implementation() {
   return kS390Implementation;
 }
 
-void RegExpMacroAssemblerS390::LoadCurrentCharacterImpl(int cp_offset,
-                                                        Label* on_end_of_input,
-                                                        bool check_bounds,
-                                                        int characters,
-                                                        int eats_at_least) {
-  // It's possible to preload a small number of characters when each success
-  // path requires a large number of characters, but not the reverse.
-  DCHECK_GE(eats_at_least, characters);
-
-  DCHECK(cp_offset < (1 << 30));  // Be sane! (And ensure negation works)
-  if (check_bounds) {
-    if (cp_offset >= 0) {
-      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
-    } else {
-      CheckPosition(cp_offset, on_end_of_input);
-    }
-  }
-  LoadCurrentCharacterUnchecked(cp_offset, characters);
-}
-
 void RegExpMacroAssemblerS390::PopCurrentPosition() {
   Pop(current_input_offset());
 }

src/regexp/s390/regexp-macro-assembler-s390.h

@@ -59,9 +59,7 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerS390
   virtual void IfRegisterLT(int reg, int comparand, Label* if_lt);
   virtual void IfRegisterEqPos(int reg, Label* if_eq);
   virtual IrregexpImplementation Implementation();
-  virtual void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
-                                        bool check_bounds, int characters,
-                                        int eats_at_least);
+  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
   virtual void PopCurrentPosition();
   virtual void PopRegister(int register_index);
   virtual void PushBacktrack(Label* label);
@@ -121,10 +119,6 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerS390
   // Initial size of code buffer.
   static const int kRegExpCodeSize = 1024;
 
-  // Load a number of characters at the given offset from the
-  // current position, into the current-character register.
-  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
-
   // Check whether preemption has been requested.
   void CheckPreemption();
 

src/regexp/x64/regexp-macro-assembler-x64.cc

@@ -1044,25 +1044,6 @@ RegExpMacroAssembler::IrregexpImplementation
   return kX64Implementation;
 }
 
-void RegExpMacroAssemblerX64::LoadCurrentCharacterImpl(int cp_offset,
-                                                       Label* on_end_of_input,
-                                                       bool check_bounds,
-                                                       int characters,
-                                                       int eats_at_least) {
-  // It's possible to preload a small number of characters when each success
-  // path requires a large number of characters, but not the reverse.
-  DCHECK_GE(eats_at_least, characters);
-
-  DCHECK(cp_offset < (1<<30));  // Be sane! (And ensure negation works)
-  if (check_bounds) {
-    if (cp_offset >= 0) {
-      CheckPosition(cp_offset + eats_at_least - 1, on_end_of_input);
-    } else {
-      CheckPosition(cp_offset, on_end_of_input);
-    }
-  }
-  LoadCurrentCharacterUnchecked(cp_offset, characters);
-}
 
 void RegExpMacroAssemblerX64::PopCurrentPosition() {
   Pop(rdi);

src/regexp/x64/regexp-macro-assembler-x64.h

@@ -59,9 +59,8 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerX64
   void IfRegisterLT(int reg, int comparand, Label* if_lt) override;
   void IfRegisterEqPos(int reg, Label* if_eq) override;
   IrregexpImplementation Implementation() override;
-  void LoadCurrentCharacterImpl(int cp_offset, Label* on_end_of_input,
-                                bool check_bounds, int characters,
-                                int eats_at_least) override;
+  void LoadCurrentCharacterUnchecked(int cp_offset,
+                                     int character_count) override;
   void PopCurrentPosition() override;
   void PopRegister(int register_index) override;
   void PushBacktrack(Label* label) override;
@@ -159,10 +158,6 @@ class V8_EXPORT_PRIVATE RegExpMacroAssemblerX64
   // Initial size of code buffer.
   static const int kRegExpCodeSize = 1024;
 
-  // Load a number of characters at the given offset from the
-  // current position, into the current-character register.
-  void LoadCurrentCharacterUnchecked(int cp_offset, int character_count);
-
   // Check whether preemption has been requested.
   void CheckPreemption();