[llvm-size] Add --exclude-pagezero option for Mach-O to exclude __PAGEZERO size. (#159574)

Do not include the ``__PAGEZERO`` segment when calculating size information
for Mach-O files when `--exclude-pagezero` is used. The ``__PAGEZERO``
segment is a virtual memory region used for memory protection that does not
contribute to actual size, and excluding can provide a better representation of
actual size.

Fixes #86644

Author: rjmansfield

llvm/docs/CommandGuide/llvm-size.rst

@@ -41,6 +41,13 @@ OPTIONS
  as a separate section entry for ``sysv`` output. If not specified, these
  symbols are ignored.
 
+.. option:: --exclude-pagezero
+
+ Do not include the ``__PAGEZERO`` segment when calculating size information
+ for Mach-O files. The ``__PAGEZERO`` segment is a virtual memory region used
+ for memory protection that does not contribute to actual size, and excluding
+ can provide a better representation of actual size.
+
 .. option:: -d
 
  Equivalent to :option:`--radix` with a value of ``10``.

llvm/test/tools/llvm-size/macho-pagezero.test

@@ -0,0 +1,108 @@
+## Test the --exclude-pagezero option to skip __PAGEZERO segment in Mach-O files.
+
+# RUN: yaml2obj %s --docnum=1 -o %t-pagezero.o
+# RUN: llvm-size %t-pagezero.o | \
+# RUN:   FileCheck %s --check-prefix=NORMAL --match-full-lines
+# RUN: llvm-size --exclude-pagezero %t-pagezero.o | \
+# RUN:   FileCheck %s --check-prefix=SKIP --match-full-lines
+
+# RUN: yaml2obj %s --docnum=2 -o %t-pagezero32.o
+# RUN: llvm-size %t-pagezero32.o | \
+# RUN:   FileCheck %s --check-prefix=NORMAL --match-full-lines
+# RUN: llvm-size --exclude-pagezero %t-pagezero32.o | \
+# RUN:   FileCheck %s --check-prefix=SKIP --match-full-lines
+
+# NORMAL:__TEXT	__DATA	__OBJC	others	dec	hex
+# NORMAL-NEXT:20	100	0	4096	4216	1078
+
+# SKIP:__TEXT	__DATA	__OBJC	others	dec	hex
+# SKIP-NEXT:20	100	0	0	120	78
+
+--- !mach-o
+FileHeader:
+  magic:           0xFEEDFACF
+  cputype:         0x100000C
+  cpusubtype:      0x0
+  filetype:        0x2
+  ncmds:           3
+  sizeofcmds:      216
+  flags:           0x2000
+  reserved:        0x0
+LoadCommands:
+  - cmd:             LC_SEGMENT_64
+    cmdsize:         72
+    segname:         __PAGEZERO
+    vmaddr:          0x0
+    vmsize:          4096
+    fileoff:         0
+    filesize:        0
+    maxprot:         0
+    initprot:        0
+    nsects:          0
+    flags:           0
+  - cmd:             LC_SEGMENT_64
+    cmdsize:         72
+    segname:         __TEXT
+    vmaddr:          0x100000000
+    vmsize:          20
+    fileoff:         248
+    filesize:        20
+    maxprot:         7
+    initprot:        5
+    nsects:          0
+    flags:           0
+  - cmd:             LC_SEGMENT_64
+    cmdsize:         72
+    segname:         __DATA
+    vmaddr:          0x100001000
+    vmsize:          100
+    fileoff:         268
+    filesize:        100
+    maxprot:         7
+    initprot:        3
+    nsects:          0
+    flags:           0
+
+--- !mach-o
+FileHeader:
+  magic:           0xFEEDFACE
+  cputype:         0x7
+  cpusubtype:      0x3
+  filetype:        0x2
+  ncmds:           3
+  sizeofcmds:      168
+  flags:           0x2000
+LoadCommands:
+  - cmd:             LC_SEGMENT
+    cmdsize:         56
+    segname:         __PAGEZERO
+    vmaddr:          0x0
+    vmsize:          4096
+    fileoff:         0
+    filesize:        0
+    maxprot:         0
+    initprot:        0
+    nsects:          0
+    flags:           0
+  - cmd:             LC_SEGMENT
+    cmdsize:         56
+    segname:         __TEXT
+    vmaddr:          0x1000
+    vmsize:          20
+    fileoff:         196
+    filesize:        20
+    maxprot:         7
+    initprot:        5
+    nsects:          0
+    flags:           0
+  - cmd:             LC_SEGMENT
+    cmdsize:         56
+    segname:         __DATA
+    vmaddr:          0x2000
+    vmsize:          100
+    fileoff:         216
+    filesize:        100
+    maxprot:         7
+    initprot:        3
+    nsects:          0
+    flags:           0

llvm/tools/llvm-size/Opts.td

@@ -21,6 +21,9 @@ def grp_mach_o : OptionGroup<"kind">, HelpText<"OPTIONS (Mach-O specific)">;
 def arch_EQ : Joined<["--"], "arch=">, HelpText<"architecture(s) from a Mach-O file to dump">, Group<grp_mach_o>;
 def : Separate<["--", "-"], "arch">, Alias<arch_EQ>;
 def l : F<"l", "When format is darwin, use long format to include addresses and offsets">, Group<grp_mach_o>;
+def exclude_pagezero
+    : FF<"exclude-pagezero", "Do not include __PAGEZERO segment in totals">,
+      Group<grp_mach_o>;
 
 def : F<"A", "Alias for --format">, Alias<format_EQ>, AliasArgs<["sysv"]>;
 def : F<"B", "Alias for --format">, Alias<format_EQ>, AliasArgs<["berkeley"]>;

llvm/tools/llvm-size/llvm-size.cpp

@@ -79,6 +79,7 @@ static bool DarwinLongFormat;
 static RadixTy Radix = RadixTy::decimal;
 static bool TotalSizes;
 static bool HasMachOFiles = false;
+static bool ExcludePageZero = false;
 
 static std::vector<std::string> InputFilenames;
 
@@ -313,7 +314,7 @@ static void printDarwinSegmentSizes(MachOObjectFile *MachO) {
           total_data += Seg.vmsize;
         else if (SegmentName == "__OBJC")
           total_objc += Seg.vmsize;
-        else
+        else if (!ExcludePageZero || SegmentName != "__PAGEZERO")
           total_others += Seg.vmsize;
       }
     } else if (Load.C.cmd == MachO::LC_SEGMENT) {
@@ -339,7 +340,7 @@ static void printDarwinSegmentSizes(MachOObjectFile *MachO) {
           total_data += Seg.vmsize;
         else if (SegmentName == "__OBJC")
           total_objc += Seg.vmsize;
-        else
+        else if (!ExcludePageZero || SegmentName != "__PAGEZERO")
           total_others += Seg.vmsize;
       }
     }
@@ -914,6 +915,7 @@ int llvm_size_main(int argc, char **argv, const llvm::ToolContext &) {
 
   ELFCommons = Args.hasArg(OPT_common);
   DarwinLongFormat = Args.hasArg(OPT_l);
+  ExcludePageZero = Args.hasArg(OPT_exclude_pagezero);
   TotalSizes = Args.hasArg(OPT_totals);
   StringRef V = Args.getLastArgValue(OPT_format_EQ, "berkeley");
   if (V == "berkeley")