[Bolt] Solving pie support issue (#65494)

Now PIE is default supported after clang 14. It cause parsing error when
using perf2bolt. The reason is the base address can not get correctly.
Fix the method of geting base address. If SegInfo.Alignment is not equal
to pagesize, alignDown(SegInfo.FileOffset, SegInfo.Alignment) can not
equal to FileOffset. So the SegInfo.FileOffset and FileOffset should be
aligned by SegInfo.Alignment first and then judge whether they are
equal.
The .text segment's offset from base address in VAS is aligned by
pagesize. So MMapAddress's offset from base address is
alignDown(SegInfo.Address, pagesize) instead of
alignDown(SegInfo.Address, SegInfo.Alignment). So the base address
calculate way should be changed.

Co-authored-by: Li Zhuohang <[email protected]>

Author: JohnLee1243

bolt/lib/Core/BinaryContext.cpp

@@ -1926,10 +1926,27 @@ BinaryContext::getBaseAddressForMapping(uint64_t MMapAddress,
   // Find a segment with a matching file offset.
   for (auto &KV : SegmentMapInfo) {
     const SegmentInfo &SegInfo = KV.second;
-    if (alignDown(SegInfo.FileOffset, SegInfo.Alignment) == FileOffset) {
-      // Use segment's aligned memory offset to calculate the base address.
-      const uint64_t MemOffset = alignDown(SegInfo.Address, SegInfo.Alignment);
-      return MMapAddress - MemOffset;
+    // FileOffset is got from perf event,
+    // and it is equal to alignDown(SegInfo.FileOffset, pagesize).
+    // If the pagesize is not equal to SegInfo.Alignment.
+    // FileOffset and SegInfo.FileOffset should be aligned first,
+    // and then judge whether they are equal.
+    if (alignDown(SegInfo.FileOffset, SegInfo.Alignment) ==
+        alignDown(FileOffset, SegInfo.Alignment)) {
+      // The function's offset from base address in VAS is aligned by pagesize
+      // instead of SegInfo.Alignment. Pagesize can't be got from perf events.
+      // However, The ELF document says that SegInfo.FileOffset should equal
+      // to SegInfo.Address, modulo the pagesize.
+      // Reference: https://refspecs.linuxfoundation.org/elf/elf.pdf
+
+      // So alignDown(SegInfo.Address, pagesize) can be calculated by:
+      // alignDown(SegInfo.Address, pagesize)
+      //   = SegInfo.Address - (SegInfo.Address % pagesize)
+      //   = SegInfo.Address - (SegInfo.FileOffset % pagesize)
+      //   = SegInfo.Address - SegInfo.FileOffset +
+      //     alignDown(SegInfo.FileOffset, pagesize)
+      //   = SegInfo.Address - SegInfo.FileOffset + FileOffset
+      return MMapAddress - (SegInfo.Address - SegInfo.FileOffset + FileOffset);
     }
   }
 

bolt/test/perf2bolt/Inputs/perf_test.c

@@ -0,0 +1,26 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+int add(int a, int b) { return a + b; }
+int minus(int a, int b) { return a - b; }
+int multiple(int a, int b) { return a * b; }
+int divide(int a, int b) {
+  if (b == 0)
+    return 0;
+  return a / b;
+}
+
+int main() {
+  int a = 16;
+  int b = 8;
+
+  for (int i = 1; i < 100000; i++) {
+    add(a, b);
+    minus(a, b);
+    multiple(a, b);
+    divide(a, b);
+  }
+
+  return 0;
+}

bolt/test/perf2bolt/Inputs/perf_test.lds

@@ -0,0 +1,13 @@
+SECTIONS {
+  . = SIZEOF_HEADERS;
+  .interp : { *(.interp) }
+  .note.gnu.build-id : { *(.note.gnu.build-id) }
+  . = 0x212e8;
+  .dynsym         : { *(.dynsym) }
+  . = 0x31860;
+  .text : { *(.text*) }
+  . = 0x41c20;
+  .fini_array : { *(.fini_array) }
+  . = 0x54e18;
+  .data : { *(.data) }
+}

bolt/test/perf2bolt/lit.local.cfg

@@ -0,0 +1,4 @@
+import shutil
+
+if shutil.which("perf") != None:
+    config.available_features.add("perf")

bolt/test/perf2bolt/perf_test.test

@@ -0,0 +1,17 @@
+# Check perf2bolt binary function which was compiled with pie
+
+REQUIRES: system-linux, perf
+
+RUN: %clang %S/Inputs/perf_test.c -fuse-ld=lld -Wl,--script=%S/Inputs/perf_test.lds -o %t
+RUN: perf record -e cycles:u -o %t2 -- %t
+RUN: perf2bolt %t -p=%t2 -o %t3 -nl -ignore-build-id 2>&1 | FileCheck %s
+
+CHECK-NOT: PERF2BOLT-ERROR
+CHECK-NOT: !! WARNING !! This high mismatch ratio indicates the input binary is probably not the same binary used during profiling collection.
+
+RUN: %clang %S/Inputs/perf_test.c -no-pie -fuse-ld=lld -o %t4
+RUN: perf record -e cycles:u -o %t5 -- %t4
+RUN: perf2bolt %t4 -p=%t5 -o %t6 -nl -ignore-build-id 2>&1 | FileCheck %s --check-prefix=CHECK-NO-PIE
+
+CHECK-NO-PIE-NOT: PERF2BOLT-ERROR
+CHECK-NO-PIE-NOT: !! WARNING !! This high mismatch ratio indicates the input binary is probably not the same binary used during profiling collection.

bolt/unittests/Core/BinaryContext.cpp

@@ -123,3 +123,24 @@ TEST_P(BinaryContextTester, BaseAddress) {
   BaseAddress = BC->getBaseAddressForMapping(0x7f13f5556000, 0x137a000);
   ASSERT_FALSE(BaseAddress.has_value());
 }
+
+TEST_P(BinaryContextTester, BaseAddress2) {
+  // Check that base address calculation is correct for a binary if the
+  // alignment in ELF file are different from pagesize.
+  // The segment layout is as follows:
+  BC->SegmentMapInfo[0] = SegmentInfo{0, 0x2177c, 0, 0x2177c, 0x10000};
+  BC->SegmentMapInfo[0x31860] =
+      SegmentInfo{0x31860, 0x370, 0x21860, 0x370, 0x10000};
+  BC->SegmentMapInfo[0x41c20] =
+      SegmentInfo{0x41c20, 0x1f8, 0x21c20, 0x1f8, 0x10000};
+  BC->SegmentMapInfo[0x54e18] =
+      SegmentInfo{0x54e18, 0x51, 0x24e18, 0x51, 0x10000};
+
+  std::optional<uint64_t> BaseAddress =
+      BC->getBaseAddressForMapping(0xaaaaea444000, 0x21000);
+  ASSERT_TRUE(BaseAddress.has_value());
+  ASSERT_EQ(*BaseAddress, 0xaaaaea413000ULL);
+
+  BaseAddress = BC->getBaseAddressForMapping(0xaaaaea444000, 0x11000);
+  ASSERT_FALSE(BaseAddress.has_value());
+}