[Bolt] Fix address translation for KASLR kernel

bolt/lib/Core/BinaryContext.cpp

@@ -2024,6 +2024,10 @@ BinaryContext::getBaseAddressForMapping(uint64_t MMapAddress,
     // Only consider executable segments.
     if (!SegInfo.IsExecutable)
       continue;
+    // For Linux kernel perf files, SegInfo.FileOffset and FileOffset are
+    // irrelvent.
+    if (IsLinuxKernel)
+      return MMapAddress - SegInfo.Address;
     // FileOffset is got from perf event,
     // and it is equal to alignDown(SegInfo.FileOffset, pagesize).
     // If the pagesize is not equal to SegInfo.Alignment.

bolt/lib/Profile/DataAggregator.cpp

@@ -530,26 +530,18 @@ Error DataAggregator::preprocessProfile(BinaryContext &BC) {
   };
 
   if (BC.IsLinuxKernel) {
-    // Current MMap parsing logic does not work with linux kernel.
-    // MMap entries for linux kernel uses PERF_RECORD_MMAP
-    // format instead of typical PERF_RECORD_MMAP2 format.
-    // Since linux kernel address mapping is absolute (same as
-    // in the ELF file), we avoid parsing MMap in linux kernel mode.
-    // While generating optimized linux kernel binary, we may need
-    // to parse MMap entries.
-
     // In linux kernel mode, we analyze and optimize
     // all linux kernel binary instructions, irrespective
     // of whether they are due to system calls or due to
     // interrupts. Therefore, we cannot ignore interrupt
     // in Linux kernel mode.
     opts::IgnoreInterruptLBR = false;
-  } else {
-    prepareToParse("mmap events", MMapEventsPPI, ErrorCallback);
-    if (parseMMapEvents())
-      errs() << "PERF2BOLT: failed to parse mmap events\n";
   }
 
+  prepareToParse("mmap events", MMapEventsPPI, ErrorCallback);
+  if (parseMMapEvents())
+    errs() << "PERF2BOLT: failed to parse mmap events\n";
+
   prepareToParse("task events", TaskEventsPPI, ErrorCallback);
   if (parseTaskEvents())
     errs() << "PERF2BOLT: failed to parse task events\n";
@@ -1102,6 +1094,11 @@ ErrorOr<DataAggregator::PerfBranchSample> DataAggregator::parseBranchSample() {
     return make_error_code(errc::no_such_process);
   }
 
+  if (BC->IsLinuxKernel) {
+    // "-1" is the pid for the Linux kernel
+    MMapInfoIter = BinaryMMapInfo.find(-1);
+  }
+
   while (checkAndConsumeFS()) {
   }
 
@@ -1936,14 +1933,18 @@ DataAggregator::parseMMapEvent() {
   }
   StringRef Line = ParsingBuf.substr(0, LineEnd);
 
-  size_t Pos = Line.find("PERF_RECORD_MMAP2");
+  // This would match both PERF_RECORD_MMAP and PERF_RECORD_MMAP2
+  size_t Pos = Line.find("PERF_RECORD_MMAP");
   if (Pos == StringRef::npos) {
     consumeRestOfLine();
     return std::make_pair(StringRef(), ParsedInfo);
   }
 
   // Line:
   //   {<name> .* <sec>.<usec>: }PERF_RECORD_MMAP2 <pid>/<tid>: .* <file_name>
+  // Or:
+  //   {<name> .* <sec>.<usec>: }PERF_RECORD_MMAP <-1 | pid>/<tid>: .*
+  //   <file_name>
 
   const StringRef TimeStr =
       Line.substr(0, Pos).rsplit(':').first.rsplit(FieldSeparator).second;
@@ -1954,9 +1955,14 @@ DataAggregator::parseMMapEvent() {
 
   // Line:
   //   PERF_RECORD_MMAP2 <pid>/<tid>: [<hexbase>(<hexsize>) .*]: .* <file_name>
+  // Or:
+  //   PERF_RECORD_MMAP <-1 | pid>/<tid>: [<hexbase>(<hexsize>) .*]: .*
+  //   <file_name>
 
   StringRef FileName = Line.rsplit(FieldSeparator).second;
-  if (FileName.starts_with("//") || FileName.starts_with("[")) {
+  if (FileName == "[kernel.kallsyms]_text")
+    FileName = "[kernel.kallsyms]";
+  else if (FileName.starts_with("//") || FileName.starts_with("[")) {
     consumeRestOfLine();
     return std::make_pair(StringRef(), ParsedInfo);
   }
@@ -1983,8 +1989,11 @@ DataAggregator::parseMMapEvent() {
     return make_error_code(llvm::errc::io_error);
   }
 
-  const StringRef OffsetStr =
-      Line.split('@').second.ltrim().split(FieldSeparator).first;
+  const StringRef OffsetStr = Line.split('@')
+                                  .second.ltrim()
+                                  .split(FieldSeparator)
+                                  .first.split(']')
+                                  .first;
   if (OffsetStr.getAsInteger(0, ParsedInfo.Offset)) {
     reportError("expected mmaped page-aligned offset");
     Diag << "Found: " << OffsetStr << "in '" << Line << "'\n";
@@ -2008,7 +2017,8 @@ std::error_code DataAggregator::parseMMapEvents() {
       return EC;
 
     std::pair<StringRef, MMapInfo> FileMMapInfo = FileMMapInfoRes.get();
-    if (FileMMapInfo.second.PID == -1)
+    if (FileMMapInfo.first != "[kernel.kallsyms]" &&
+        FileMMapInfo.second.PID == -1)
       continue;
     if (FileMMapInfo.first == "(deleted)")
       continue;

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -530,8 +530,11 @@ Error RewriteInstance::discoverStorage() {
           Phdr.p_vaddr,  Phdr.p_memsz, Phdr.p_offset,
           Phdr.p_filesz, Phdr.p_align, ((Phdr.p_flags & ELF::PF_X) != 0)};
       if (BC->TheTriple->getArch() == llvm::Triple::x86_64 &&
-          Phdr.p_vaddr >= BinaryContext::KernelStartX86_64)
+          Phdr.p_vaddr >= BinaryContext::KernelStartX86_64) {
         BC->IsLinuxKernel = true;
+        BC->HasFixedLoadAddress = false;
+      }
+
       break;
     case ELF::PT_INTERP:
       BC->HasInterpHeader = true;
@@ -995,8 +998,13 @@ void RewriteInstance::discoverFileObjects() {
     }
 
     if (!Section->isText()) {
-      assert(SymbolType != SymbolRef::ST_Function &&
-             "unexpected function inside non-code section");
+      // In kernel, a function can live in a non-text section. For Example,
+      // lkdtm_rodata_do_nothing() in ./drivers/misc/lkdtm/rodata.c is in
+      // the rodata section.
+      if (!BC->IsLinuxKernel) {
+        assert(SymbolType != SymbolRef::ST_Function &&
+               "unexpected function inside non-code section");
+      }
       LLVM_DEBUG(dbgs() << "BOLT-DEBUG: rejecting as symbol is not in code\n");
       registerName(SymbolSize);
       continue;