[ELF] --time-trace: Trace "Write sections"

[MaskRay]

Summary

writeSections is typically a bottleneck.
This was used to track down the following bottlenecks:

• Output section .rela.dyn (9115d75117b57115fe45153e5f38f2c444c0cd91)
• Output section .debug_str (3aae04c744b03eb3eec7376f9d34fa3e42f8d108)
• posix_fallocate is slow for Linux tmpfs: D115957

[ikudrin]

LGTM

lld/ELF/OutputSections.cpp

else if (size == 4)
     write32(buf, data);
   else if (size == 8)
     write64(buf, data);
   else
     llvm_unreachable("unsupported Size argument");
 }
 
 template <class ELFT> void OutputSection::writeTo(uint8_t *buf) {
+  llvm::TimeTraceScope timeScope("Write sections", name);
   if (type == SHT_NOBITS)
     return;
 
   // If --compress-debug-section is specified and if this is a debug section,
   // we've already compressed section contents. If that's the case,
   // just write it down.
   if (!compressedData.empty()) {
     memcpy(buf, zDebugHeader.data(), zDebugHeader.size());

lld/ELF/Writer.cpp

for (Partition &part : partitions) {
     if (last && (last->p_flags & PF_X))
       last->p_memsz = last->p_filesz =
           alignTo(last->p_filesz, config->maxPageSize);
   }
 }
 
 // Write section contents to a mmap'ed file.
 template <class ELFT> void Writer<ELFT>::writeSections() {
+  llvm::TimeTraceScope timeScope("Write sections");
+
   // In -r or --emit-relocs mode, write the relocation sections first as in
   // ELf_Rel targets we might find out that we need to modify the relocated
   // section while doing it.
   for (OutputSection *sec : outputSections)
     if (sec->type == SHT_REL || sec->type == SHT_RELA)
       sec->writeTo<ELFT>(Out::bufferStart + sec->offset);
 
   for (OutputSection *sec : outputSections)