All .xdata sections are eligble for ICF

Summary:
Many small functions have identical unwind info because they push the
same sets of CSRs in the same order and have the same stack and prologue
size. The VC linker merges duplicate .xdata, and so should LLD.

This reduces the .xdata section size of clang.exe from 1.8MB to 94KB.

Reviewers: pcc, ruiu

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D40160

llvm-svn: 318547
This commit is contained in:
Reid Kleckner 2017-11-17 19:50:10 +00:00
parent dd01ddbe67
commit d99ac29a24
2 changed files with 100 additions and 3 deletions

View File

@ -73,12 +73,23 @@ uint32_t ICF::getHash(SectionChunk *C) {
// 2017) says that /opt:icf folds both functions and read-only data.
// Despite that, the MSVC linker folds only functions. We found
// a few instances of programs that are not safe for data merging.
// Therefore, we merge only functions just like the MSVC tool.
// Therefore, we merge only functions just like the MSVC tool. However, we merge
// identical .xdata sections, because the address of unwind information is
// insignificant to the user program and the Visual C++ linker does this.
bool ICF::isEligible(SectionChunk *C) {
// Non-comdat chunks, dead chunks, and writable chunks are not elegible.
bool Writable = C->getPermissions() & llvm::COFF::IMAGE_SCN_MEM_WRITE;
if (!C->isCOMDAT() || !C->isLive() || Writable)
return false;
// Code sections with external symbols are eligible.
bool Global = C->Sym && C->Sym->isExternal();
bool Executable = C->getPermissions() & llvm::COFF::IMAGE_SCN_MEM_EXECUTE;
bool Writable = C->getPermissions() & llvm::COFF::IMAGE_SCN_MEM_WRITE;
return C->isCOMDAT() && C->isLive() && Global && Executable && !Writable;
if (Global && Executable)
return true;
// .xdata unwind info sections are eligble.
return C->getSectionName().split('$').first == ".xdata";
}
// Split an equivalence class into smaller classes.

86
lld/test/COFF/icf-xdata.s Normal file
View File

@ -0,0 +1,86 @@
# RUN: llvm-mc %s -triple x86_64-windows-msvc -filetype=obj -o %t.obj
# RUN: lld-link %t.obj -dll -noentry -out:%t.dll
# RUN: llvm-readobj -sections %t.dll | FileCheck %s
# There shouldn't be much xdata, because all three .pdata entries (12 bytes
# each) should use the same .xdata unwind info.
# CHECK: Name: .pdata
# CHECK-NEXT: VirtualSize: 0x24
# CHECK: Name: .xdata
# CHECK-NEXT: VirtualSize: 0x8
.text
callee:
ret
.def xdata1;
.scl 2;
.type 32;
.endef
.section .text,"xr",one_only,xdata1
.globl xdata1 # -- Begin function xdata1
.p2align 4, 0x90
xdata1: # @xdata1
.seh_proc xdata1
# BB#0: # %entry
subq $40, %rsp
.seh_stackalloc 40
.seh_endprologue
callq callee
nop
addq $40, %rsp
jmp callee # TAILCALL
.seh_handlerdata
.section .text,"xr",one_only,xdata1
.seh_endproc
# -- End function
.def xdata2;
.scl 2;
.type 32;
.endef
.section .text,"xr",one_only,xdata2
.globl xdata2 # -- Begin function xdata2
.p2align 4, 0x90
xdata2: # @xdata2
.seh_proc xdata2
# BB#0: # %entry
subq $40, %rsp
.seh_stackalloc 40
.seh_endprologue
callq callee
callq callee
nop
addq $40, %rsp
jmp callee # TAILCALL
.seh_handlerdata
.section .text,"xr",one_only,xdata2
.seh_endproc
# -- End function
.def xdata3;
.scl 2;
.type 32;
.endef
.section .text,"xr",one_only,xdata3
.globl xdata3 # -- Begin function xdata3
.p2align 4, 0x90
xdata3: # @xdata3
.seh_proc xdata3
# BB#0: # %entry
subq $40, %rsp
.seh_stackalloc 40
.seh_endprologue
callq callee
callq callee
callq callee
nop
addq $40, %rsp
jmp callee # TAILCALL
.seh_handlerdata
.section .text,"xr",one_only,xdata3
.seh_endproc
# -- End function
.section .drectve,"yn"
.ascii " -export:xdata1"
.ascii " -export:xdata2"
.ascii " -export:xdata3"