scripts/recordmcount.pl

   1 #!/usr/bin/perl -w
   2 # (c) 2008, Steven Rostedt <srostedt@redhat.com>
   3 # Licensed under the terms of the GNU GPL License version 2
   4 #
   5 # recordmcount.pl - makes a section called __mcount_loc that holds
   6 #                   all the offsets to the calls to mcount.
   7 #
   8 #
   9 # What we want to end up with is a section in vmlinux called
  10 # __mcount_loc that contains a list of pointers to all the
  11 # call sites in the kernel that call mcount. Later on boot up, the kernel
  12 # will read this list, save the locations and turn them into nops.
  13 # When tracing or profiling is later enabled, these locations will then
  14 # be converted back to pointers to some function.
  15 #
  16 # This is no easy feat. This script is called just after the original
  17 # object is compiled and before it is linked.
  18 #
  19 # The references to the call sites are offsets from the section of text
  20 # that the call site is in. Hence, all functions in a section that
  21 # has a call site to mcount, will have the offset from the beginning of
  22 # the section and not the beginning of the function.
  23 #
  24 # The trick is to find a way to record the beginning of the section.
  25 # The way we do this is to look at the first function in the section
  26 # which will also be the location of that section after final link.
  27 # e.g.
  28 #
  29 #  .section ".text.sched"
  30 #  .globl my_func
  31 #  my_func:
  32 #        [...]
  33 #        call mcount  (offset: 0x5)
  34 #        [...]
  35 #        ret
  36 #  other_func:
  37 #        [...]
  38 #        call mcount (offset: 0x1b)
  39 #        [...]
  40 #
  41 # Both relocation offsets for the mcounts in the above example will be
  42 # offset from .text.sched. If we make another file called tmp.s with:
  43 #
  44 #  .section __mcount_loc
  45 #  .quad  my_func + 0x5
  46 #  .quad  my_func + 0x1b
  47 #
  48 # We can then compile this tmp.s into tmp.o, and link it to the original
  49 # object.
  50 #
  51 # But this gets hard if my_func is not globl (a static function).
  52 # In such a case we have:
  53 #
  54 #  .section ".text.sched"
  55 #  my_func:
  56 #        [...]
  57 #        call mcount  (offset: 0x5)
  58 #        [...]
  59 #        ret
  60 #  .globl my_func
  61 #  other_func:
  62 #        [...]
  63 #        call mcount (offset: 0x1b)
  64 #        [...]
  65 #
  66 # If we make the tmp.s the same as above, when we link together with
  67 # the original object, we will end up with two symbols for my_func:
  68 # one local, one global.  After final compile, we will end up with
  69 # an undefined reference to my_func.
  70 #
  71 # Since local objects can reference local variables, we need to find
  72 # a way to make tmp.o reference the local objects of the original object
  73 # file after it is linked together. To do this, we convert the my_func
  74 # into a global symbol before linking tmp.o. Then after we link tmp.o
  75 # we will only have a single symbol for my_func that is global.
  76 # We can convert my_func back into a local symbol and we are done.
  77 #
  78 # Here are the steps we take:
  79 #
  80 # 1) Record all the local symbols by using 'nm'
  81 # 2) Use objdump to find all the call site offsets and sections for
  82 #    mcount.
  83 # 3) Compile the list into its own object.
  84 # 4) Do we have to deal with local functions? If not, go to step 8.
  85 # 5) Make an object that converts these local functions to global symbols
  86 #    with objcopy.
  87 # 6) Link together this new object with the list object.
  88 # 7) Convert the local functions back to local symbols and rename
  89 #    the result as the original object.
  90 #    End.
  91 # 8) Link the object with the list object.
  92 # 9) Move the result back to the original object.
  93 #    End.
  94 #
  95
  96 use strict;
  97
  98 my $P = $0;
  99 $P =~ s@.*/@@g;
 100
 101 my $V = '0.1';
 102
 103 if ($#ARGV < 6) {
 104         print "usage: $P arch objdump objcopy cc ld nm rm mv inputfile\n";
 105         print "version: $V\n";
 106         exit(1);
 107 }
 108
 109 my ($arch, $bits, $objdump, $objcopy, $cc,
 110     $ld, $nm, $rm, $mv, $inputfile) = @ARGV;
 111
 112 # Acceptable sections to record.
 113 my %text_sections = (
 114      ".text" => 1,
 115 );
 116
 117 $objdump = "objdump" if ((length $objdump) == 0);
 118 $objcopy = "objcopy" if ((length $objcopy) == 0);
 119 $cc = "gcc" if ((length $cc) == 0);
 120 $ld = "ld" if ((length $ld) == 0);
 121 $nm = "nm" if ((length $nm) == 0);
 122 $rm = "rm" if ((length $rm) == 0);
 123 $mv = "mv" if ((length $mv) == 0);
 124
 125 #print STDERR "running: $P '$arch' '$objdump' '$objcopy' '$cc' '$ld' " .
 126 #    "'$nm' '$rm' '$mv' '$inputfile'\n";
 127
 128 my %locals;             # List of local (static) functions
 129 my %weak;               # List of weak functions
 130 my %convert;            # List of local functions used that needs conversion
 131
 132 my $type;
 133 my $section_regex;      # Find the start of a section
 134 my $function_regex;     # Find the name of a function
 135                         #    (return offset and func name)
 136 my $mcount_regex;       # Find the call site to mcount (return offset)
 137
 138 if ($arch eq "x86") {
 139     if ($bits == 64) {
 140         $arch = "x86_64";
 141     } else {
 142         $arch = "i386";
 143     }
 144 }
 145
 146 if ($arch eq "x86_64") {
 147     $section_regex = "Disassembly of section\\s+(\\S+):";
 148     $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
 149     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
 150     $type = ".quad";
 151
 152     # force flags for this arch
 153     $ld .= " -m elf_x86_64";
 154     $objdump .= " -M x86-64";
 155     $objcopy .= " -O elf64-x86-64";
 156     $cc .= " -m64";
 157
 158 } elsif ($arch eq "i386") {
 159     $section_regex = "Disassembly of section\\s+(\\S+):";
 160     $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
 161     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
 162     $type = ".long";
 163
 164     # force flags for this arch
 165     $ld .= " -m elf_i386";
 166     $objdump .= " -M i386";
 167     $objcopy .= " -O elf32-i386";
 168     $cc .= " -m32";
 169
 170 } else {
 171     die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
 172 }
 173
 174 my $text_found = 0;
 175 my $read_function = 0;
 176 my $opened = 0;
 177 my $mcount_section = "__mcount_loc";
 178
 179 my $dirname;
 180 my $filename;
 181 my $prefix;
 182 my $ext;
 183
 184 if ($inputfile =~ m,^(.*)/([^/]*)$,) {
 185     $dirname = $1;
 186     $filename = $2;
 187 } else {
 188     $dirname = ".";
 189     $filename = $inputfile;
 190 }
 191
 192 if ($filename =~ m,^(.*)(\.\S),) {
 193     $prefix = $1;
 194     $ext = $2;
 195 } else {
 196     $prefix = $filename;
 197     $ext = "";
 198 }
 199
 200 my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s";
 201 my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o";
 202
 203 #
 204 # --globalize-symbols came out in 2.17, we must test the version
 205 # of objcopy, and if it is less than 2.17, then we can not
 206 # record local functions.
 207 my $use_locals = 01;
 208 my $local_warn_once = 0;
 209 my $found_version = 0;
 210
 211 open (IN, "$objcopy --version |") || die "error running $objcopy";
 212 while (<IN>) {
 213     if (/objcopy.*\s(\d+)\.(\d+)/) {
 214         my $major = $1;
 215         my $minor = $2;
 216
 217         $found_version = 1;
 218         if ($major < 2 ||
 219             ($major == 2 && $minor < 17)) {
 220             $use_locals = 0;
 221         }
 222         last;
 223     }
 224 }
 225 close (IN);
 226
 227 if (!$found_version) {
 228     print STDERR "WARNING: could not find objcopy version.\n" .
 229         "\tDisabling local function references.\n";
 230 }
 231
 232
 233 #
 234 # Step 1: find all the local (static functions) and weak symbols.
 235 #        't' is local, 'w/W' is weak (we never use a weak function)
 236 #
 237 open (IN, "$nm $inputfile|") || die "error running $nm";
 238 while (<IN>) {
 239     if (/^[0-9a-fA-F]+\s+t\s+(\S+)/) {
 240         $locals{$1} = 1;
 241     } elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) {
 242         $weak{$2} = $1;
 243     }
 244 }
 245 close(IN);
 246
 247 my @offsets;            # Array of offsets of mcount callers
 248 my $ref_func;           # reference function to use for offsets
 249 my $offset = 0;         # offset of ref_func to section beginning
 250
 251 ##
 252 # update_funcs - print out the current mcount callers
 253 #
 254 #  Go through the list of offsets to callers and write them to
 255 #  the output file in a format that can be read by an assembler.
 256 #
 257 sub update_funcs
 258 {
 259     return if ($#offsets < 0);
 260
 261     defined($ref_func) || die "No function to reference";
 262
 263     # A section only had a weak function, to represent it.
 264     # Unfortunately, a weak function may be overwritten by another
 265     # function of the same name, making all these offsets incorrect.
 266     # To be safe, we simply print a warning and bail.
 267     if (defined $weak{$ref_func}) {
 268         print STDERR
 269             "$inputfile: WARNING: referencing weak function" .
 270             " $ref_func for mcount\n";
 271         return;
 272     }
 273
 274     # is this function static? If so, note this fact.
 275     if (defined $locals{$ref_func}) {
 276
 277         # only use locals if objcopy supports globalize-symbols
 278         if (!$use_locals) {
 279             return;
 280         }
 281         $convert{$ref_func} = 1;
 282     }
 283
 284     # Loop through all the mcount caller offsets and print a reference
 285     # to the caller based from the ref_func.
 286     for (my $i=0; $i <= $#offsets; $i++) {
 287         if (!$opened) {
 288             open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
 289             $opened = 1;
 290             print FILE "\t.section $mcount_section,\"a\",\@progbits\n";
 291         }
 292         printf FILE "\t%s %s + %d\n", $type, $ref_func, $offsets[$i] - $offset;
 293     }
 294 }
 295
 296 #
 297 # Step 2: find the sections and mcount call sites
 298 #
 299 open(IN, "$objdump -dr $inputfile|") || die "error running $objdump";
 300
 301 my $text;
 302
 303 while (<IN>) {
 304     # is it a section?
 305     if (/$section_regex/) {
 306
 307         # Only record text sections that we know are safe
 308         if (defined($text_sections{$1})) {
 309             $read_function = 1;
 310         } else {
 311             $read_function = 0;
 312         }
 313         # print out any recorded offsets
 314         update_funcs() if ($text_found);
 315
 316         # reset all markers and arrays
 317         $text_found = 0;
 318         undef($ref_func);
 319         undef(@offsets);
 320
 321     # section found, now is this a start of a function?
 322     } elsif ($read_function && /$function_regex/) {
 323         $text_found = 1;
 324         $offset = hex $1;
 325         $text = $2;
 326
 327         # if this is either a local function or a weak function
 328         # keep looking for functions that are global that
 329         # we can use safely.
 330         if (!defined($locals{$text}) && !defined($weak{$text})) {
 331             $ref_func = $text;
 332             $read_function = 0;
 333         } else {
 334             # if we already have a function, and this is weak, skip it
 335             if (!defined($ref_func) || !defined($weak{$text})) {
 336                 $ref_func = $text;
 337             }
 338         }
 339     }
 340
 341     # is this a call site to mcount? If so, record it to print later
 342     if ($text_found && /$mcount_regex/) {
 343         $offsets[$#offsets + 1] = hex $1;
 344     }
 345 }
 346
 347 # dump out anymore offsets that may have been found
 348 update_funcs() if ($text_found);
 349
 350 # If we did not find any mcount callers, we are done (do nothing).
 351 if (!$opened) {
 352     exit(0);
 353 }
 354
 355 close(FILE);
 356
 357 #
 358 # Step 3: Compile the file that holds the list of call sites to mcount.
 359 #
 360 `$cc -o $mcount_o -c $mcount_s`;
 361
 362 my @converts = keys %convert;
 363
 364 #
 365 # Step 4: Do we have sections that started with local functions?
 366 #
 367 if ($#converts >= 0) {
 368     my $globallist = "";
 369     my $locallist = "";
 370
 371     foreach my $con (@converts) {
 372         $globallist .= " --globalize-symbol $con";
 373         $locallist .= " --localize-symbol $con";
 374     }
 375
 376     my $globalobj = $dirname . "/.tmp_gl_" . $filename;
 377     my $globalmix = $dirname . "/.tmp_mx_" . $filename;
 378
 379     #
 380     # Step 5: set up each local function as a global
 381     #
 382     `$objcopy $globallist $inputfile $globalobj`;
 383
 384     #
 385     # Step 6: Link the global version to our list.
 386     #
 387     `$ld -r $globalobj $mcount_o -o $globalmix`;
 388
 389     #
 390     # Step 7: Convert the local functions back into local symbols
 391     #
 392     `$objcopy $locallist $globalmix $inputfile`;
 393
 394     # Remove the temp files
 395     `$rm $globalobj $globalmix`;
 396
 397 } else {
 398
 399     my $mix = $dirname . "/.tmp_mx_" . $filename;
 400
 401     #
 402     # Step 8: Link the object with our list of call sites object.
 403     #
 404     `$ld -r $inputfile $mcount_o -o $mix`;
 405
 406     #
 407     # Step 9: Move the result back to the original object.
 408     #
 409     `$mv $mix $inputfile`;
 410 }
 411
 412 # Clean up the temp files
 413 `$rm $mcount_o $mcount_s`;
 414
 415 exit(0);