[lld] 0f24ffc - [lld/mac] Don't fold UNWIND_X86_64_MODE_STACK_IND unwind entries

[Nico Weber via llvm-commits]

Author: Nico Weber
Date: 2021-06-27T06:49:32-04:00
New Revision: 0f24ffcdfa9bb2b6380cedbb24f16d4ab9920dd7

URL: https://github.com/llvm/llvm-project/commit/0f24ffcdfa9bb2b6380cedbb24f16d4ab9920dd7
DIFF: https://github.com/llvm/llvm-project/commit/0f24ffcdfa9bb2b6380cedbb24f16d4ab9920dd7.diff

LOG: [lld/mac] Don't fold UNWIND_X86_64_MODE_STACK_IND unwind entries

libunwind uses unwind info to find the function address belonging
to the current instruction pointer. libunwind/src/CompactUnwinder.hpp's
step functions read functionStart for UNWIND_X86_64_MODE_STACK_IND
(and for nothing else), so these encodings need a dedicated entry
per function, so that the runtime can get the stacksize off the
`subq` instrunction in the function's prologue.

This matches ld64.

(CompactUnwinder.hpp from https://opensource.apple.com/source/libunwind/
also reads functionStart in a few more cases if `SUPPORT_OLD_BINARIES` is set,
but it defaults to 0, and ld64 seems to not worry about these additional
cases.)

Related upstream bug: https://crbug.com/1220175

Differential Revision: https://reviews.llvm.org/D104978

Added: 
    lld/test/MachO/compact-unwind-stack-ind.s

Modified: 
    lld/MachO/UnwindInfoSection.cpp

Removed: 
    


################################################################################
diff  --git a/lld/MachO/UnwindInfoSection.cpp b/lld/MachO/UnwindInfoSection.cpp
index 8ad71c04f866d..6e9f4ff92aa27 100644
--- a/lld/MachO/UnwindInfoSection.cpp
+++ b/lld/MachO/UnwindInfoSection.cpp
@@ -316,6 +316,31 @@ static void addEntriesForFunctionsWithoutUnwindInfo(
             markNoUnwindInfo(d);
 }
 
+static bool canFoldEncoding(compact_unwind_encoding_t encoding) {
+  // From compact_unwind_encoding.h:
+  //  UNWIND_X86_64_MODE_STACK_IND:
+  //  A "frameless" (RBP not used as frame pointer) function large constant
+  //  stack size.  This case is like the previous, except the stack size is too
+  //  large to encode in the compact unwind encoding.  Instead it requires that
+  //  the function contains "subq $nnnnnnnn,RSP" in its prolog.  The compact
+  //  encoding contains the offset to the nnnnnnnn value in the function in
+  //  UNWIND_X86_64_FRAMELESS_STACK_SIZE.
+  // Since this means the unwinder has to look at the `subq` in the function
+  // of the unwind info's unwind address, two functions that have identical
+  // unwind info can't be folded if it's using this encoding since both
+  // entries need unique addresses.
+  static_assert(UNWIND_X86_64_MODE_MASK == UNWIND_X86_MODE_MASK, "");
+  static_assert(UNWIND_X86_64_MODE_STACK_IND == UNWIND_X86_MODE_STACK_IND, "");
+  if ((target->cpuType == CPU_TYPE_X86_64 || target->cpuType == CPU_TYPE_X86) &&
+      (encoding & UNWIND_X86_64_MODE_MASK) == UNWIND_X86_64_MODE_STACK_IND) {
+    // FIXME: Consider passing in the two function addresses and getting
+    // their two stack sizes off the `subq` and only returning false if they're
+    // actually 
diff erent.
+    return false;
+  }
+  return true;
+}
+
 // Scan the __LD,__compact_unwind entries and compute the space needs of
 // __TEXT,__unwind_info and __TEXT,__eh_frame
 template <class Ptr> void UnwindInfoSectionImpl<Ptr>::finalize() {
@@ -377,7 +402,8 @@ template <class Ptr> void UnwindInfoSectionImpl<Ptr>::finalize() {
     while (++foldEnd < cuPtrVector.end() &&
            (*foldBegin)->encoding == (*foldEnd)->encoding &&
            (*foldBegin)->personality == (*foldEnd)->personality &&
-           (*foldBegin)->lsda == (*foldEnd)->lsda)
+           (*foldBegin)->lsda == (*foldEnd)->lsda &&
+           canFoldEncoding((*foldEnd)->encoding))
       ;
     *foldWrite++ = *foldBegin;
     foldBegin = foldEnd;

diff  --git a/lld/test/MachO/compact-unwind-stack-ind.s b/lld/test/MachO/compact-unwind-stack-ind.s
new file mode 100644
index 0000000000000..13d5e929d2dbf
--- /dev/null
+++ b/lld/test/MachO/compact-unwind-stack-ind.s
@@ -0,0 +1,54 @@
+# REQUIRES: x86
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin19.0.0 %s -o %t.o
+# RUN: %lld -arch x86_64 -dylib %t.o -o %t.dylib
+# RUN: llvm-objdump --macho --syms --unwind-info %t.dylib | FileCheck %s
+
+## Both _f and _g have the same compact unwind encoding,
+## but 
diff erent stack sizes. So their compact unwindings
+## can't be merged.
+# CHECK:  SYMBOL TABLE:
+# CHECK:  [[#%x,F:]] g  F __TEXT,__text _f
+# CHECK:  [[#%x,G:]] g  F __TEXT,__text _g
+# CHECK: Number of common encodings in array:       0x1
+# CHECK:  Common encodings: (count = 1)
+# CHECK:    encoding[0]: 0x03032000
+# CHECK:  Second level indices:
+# CHECK:    Second level index[0]:
+# CHECK:      [0]: function offset=0x[[#%.8x,F]], encoding[0]=0x03032000
+# CHECK:      [1]: function offset=0x[[#%.8x,G]], encoding[0]=0x03032000
+
+## Based on compiling
+##     int f() {
+##       char alloca[3260] = { 0 };
+##       return alloca[0];
+##     }
+##
+##     int g() {
+##       char alloca[2560] = { 0 };
+##       return alloca[0];
+##     }
+## with `-fomit-frame-pointer -fno-stack-protector -S`.
+.section __TEXT,__text,regular,pure_instructions
+.build_version macos, 10, 15 sdk_version 10, 15, 6
+
+.globl _f
+.p2align 4, 0x90
+_f:
+  .cfi_startproc
+  subq $3272, %rsp
+  .cfi_def_cfa_offset 3280
+  addq $3272, %rsp
+  retq
+  .cfi_endproc
+
+.globl _g
+.p2align 4, 0x90
+_g:
+  .cfi_startproc
+  subq $2568, %rsp
+  .cfi_def_cfa_offset 2576
+  addq $2568, %rsp
+  retq
+  .cfi_endproc
+
+.subsections_via_symbols