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 $objdump = "objdump" if ((length $objdump) == 0);
 113 $objcopy = "objcopy" if ((length $objcopy) == 0);
 114 $cc = "gcc" if ((length $cc) == 0);
 115 $ld = "ld" if ((length $ld) == 0);
 116 $nm = "nm" if ((length $nm) == 0);
 117 $rm = "rm" if ((length $rm) == 0);
 118 $mv = "mv" if ((length $mv) == 0);
 119
 120 #print STDERR "running: $P '$arch' '$objdump' '$objcopy' '$cc' '$ld' " .
 121 #    "'$nm' '$rm' '$mv' '$inputfile'\n";
 122
 123 my %locals;             # List of local (static) functions
 124 my %weak;               # List of weak functions
 125 my %convert;            # List of local functions used that needs conversion
 126
 127 my $type;
 128 my $section_regex;      # Find the start of a section
 129 my $function_regex;     # Find the name of a function
 130                         #    (return offset and func name)
 131 my $mcount_regex;       # Find the call site to mcount (return offset)
 132
 133 if ($arch eq "x86") {
 134     if ($bits == 64) {
 135         $arch = "x86_64";
 136     } else {
 137         $arch = "i386";
 138     }
 139 }
 140
 141 if ($arch eq "x86_64") {
 142     $section_regex = "Disassembly of section";
 143     $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
 144     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
 145     $type = ".quad";
 146
 147     # force flags for this arch
 148     $ld .= " -m elf_x86_64";
 149     $objdump .= " -M x86-64";
 150     $objcopy .= " -O elf64-x86-64";
 151     $cc .= " -m64";
 152
 153 } elsif ($arch eq "i386") {
 154     $section_regex = "Disassembly of section";
 155     $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
 156     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
 157     $type = ".long";
 158
 159     # force flags for this arch
 160     $ld .= " -m elf_i386";
 161     $objdump .= " -M i386";
 162     $objcopy .= " -O elf32-i386";
 163     $cc .= " -m32";
 164
 165 } else {
 166     die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
 167 }
 168
 169 my $text_found = 0;
 170 my $read_function = 0;
 171 my $opened = 0;
 172 my $mcount_section = "__mcount_loc";
 173
 174 my $dirname;
 175 my $filename;
 176 my $prefix;
 177 my $ext;
 178
 179 if ($inputfile =~ m,^(.*)/([^/]*)$,) {
 180     $dirname = $1;
 181     $filename = $2;
 182 } else {
 183     $dirname = ".";
 184     $filename = $inputfile;
 185 }
 186
 187 if ($filename =~ m,^(.*)(\.\S),) {
 188     $prefix = $1;
 189     $ext = $2;
 190 } else {
 191     $prefix = $filename;
 192     $ext = "";
 193 }
 194
 195 my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s";
 196 my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o";
 197
 198 #
 199 # --globalize-symbols came out in 2.17, we must test the version
 200 # of objcopy, and if it is less than 2.17, then we can not
 201 # record local functions.
 202 my $use_locals = 01;
 203 my $local_warn_once = 0;
 204 my $found_version = 0;
 205
 206 open (IN, "$objcopy --version |") || die "error running $objcopy";
 207 while (<IN>) {
 208     if (/objcopy.*\s(\d+)\.(\d+)/) {
 209         my $major = $1;
 210         my $minor = $2;
 211
 212         $found_version = 1;
 213         if ($major < 2 ||
 214             ($major == 2 && $minor < 17)) {
 215             $use_locals = 0;
 216         }
 217         last;
 218     }
 219 }
 220 close (IN);
 221
 222 if (!$found_version) {
 223     print STDERR "WARNING: could not find objcopy version.\n" .
 224         "\tDisabling local function references.\n";
 225 }
 226
 227
 228 #
 229 # Step 1: find all the local (static functions) and weak symbols.
 230 #        't' is local, 'w/W' is weak (we never use a weak function)
 231 #
 232 open (IN, "$nm $inputfile|") || die "error running $nm";
 233 while (<IN>) {
 234     if (/^[0-9a-fA-F]+\s+t\s+(\S+)/) {
 235         $locals{$1} = 1;
 236     } elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) {
 237         $weak{$2} = $1;
 238     }
 239 }
 240 close(IN);
 241
 242 my @offsets;            # Array of offsets of mcount callers
 243 my $ref_func;           # reference function to use for offsets
 244 my $offset = 0;         # offset of ref_func to section beginning
 245
 246 ##
 247 # update_funcs - print out the current mcount callers
 248 #
 249 #  Go through the list of offsets to callers and write them to
 250 #  the output file in a format that can be read by an assembler.
 251 #
 252 sub update_funcs
 253 {
 254     return if ($#offsets < 0);
 255
 256     defined($ref_func) || die "No function to reference";
 257
 258     # A section only had a weak function, to represent it.
 259     # Unfortunately, a weak function may be overwritten by another
 260     # function of the same name, making all these offsets incorrect.
 261     # To be safe, we simply print a warning and bail.
 262     if (defined $weak{$ref_func}) {
 263         print STDERR
 264             "$inputfile: WARNING: referencing weak function" .
 265             " $ref_func for mcount\n";
 266         return;
 267     }
 268
 269     # is this function static? If so, note this fact.
 270     if (defined $locals{$ref_func}) {
 271
 272         # only use locals if objcopy supports globalize-symbols
 273         if (!$use_locals) {
 274             return;
 275         }
 276         $convert{$ref_func} = 1;
 277     }
 278
 279     # Loop through all the mcount caller offsets and print a reference
 280     # to the caller based from the ref_func.
 281     for (my $i=0; $i <= $#offsets; $i++) {
 282         if (!$opened) {
 283             open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
 284             $opened = 1;
 285             print FILE "\t.section $mcount_section,\"a\",\@progbits\n";
 286         }
 287         printf FILE "\t%s %s + %d\n", $type, $ref_func, $offsets[$i] - $offset;
 288     }
 289 }
 290
 291 #
 292 # Step 2: find the sections and mcount call sites
 293 #
 294 open(IN, "$objdump -dr $inputfile|") || die "error running $objdump";
 295
 296 my $text;
 297
 298 while (<IN>) {
 299     # is it a section?
 300     if (/$section_regex/) {
 301         $read_function = 1;
 302         # print out any recorded offsets
 303         update_funcs() if ($text_found);
 304
 305         # reset all markers and arrays
 306         $text_found = 0;
 307         undef($ref_func);
 308         undef(@offsets);
 309
 310     # section found, now is this a start of a function?
 311     } elsif ($read_function && /$function_regex/) {
 312         $text_found = 1;
 313         $offset = hex $1;
 314         $text = $2;
 315
 316         # if this is either a local function or a weak function
 317         # keep looking for functions that are global that
 318         # we can use safely.
 319         if (!defined($locals{$text}) && !defined($weak{$text})) {
 320             $ref_func = $text;
 321             $read_function = 0;
 322         } else {
 323             # if we already have a function, and this is weak, skip it
 324             if (!defined($ref_func) || !defined($weak{$text})) {
 325                 $ref_func = $text;
 326             }
 327         }
 328     }
 329
 330     # is this a call site to mcount? If so, record it to print later
 331     if ($text_found && /$mcount_regex/) {
 332         $offsets[$#offsets + 1] = hex $1;
 333     }
 334 }
 335
 336 # dump out anymore offsets that may have been found
 337 update_funcs() if ($text_found);
 338
 339 # If we did not find any mcount callers, we are done (do nothing).
 340 if (!$opened) {
 341     exit(0);
 342 }
 343
 344 close(FILE);
 345
 346 #
 347 # Step 3: Compile the file that holds the list of call sites to mcount.
 348 #
 349 `$cc -o $mcount_o -c $mcount_s`;
 350
 351 my @converts = keys %convert;
 352
 353 #
 354 # Step 4: Do we have sections that started with local functions?
 355 #
 356 if ($#converts >= 0) {
 357     my $globallist = "";
 358     my $locallist = "";
 359
 360     foreach my $con (@converts) {
 361         $globallist .= " --globalize-symbol $con";
 362         $locallist .= " --localize-symbol $con";
 363     }
 364
 365     my $globalobj = $dirname . "/.tmp_gl_" . $filename;
 366     my $globalmix = $dirname . "/.tmp_mx_" . $filename;
 367
 368     #
 369     # Step 5: set up each local function as a global
 370     #
 371     `$objcopy $globallist $inputfile $globalobj`;
 372
 373     #
 374     # Step 6: Link the global version to our list.
 375     #
 376     `$ld -r $globalobj $mcount_o -o $globalmix`;
 377
 378     #
 379     # Step 7: Convert the local functions back into local symbols
 380     #
 381     `$objcopy $locallist $globalmix $inputfile`;
 382
 383     # Remove the temp files
 384     `$rm $globalobj $globalmix`;
 385
 386 } else {
 387
 388     my $mix = $dirname . "/.tmp_mx_" . $filename;
 389
 390     #
 391     # Step 8: Link the object with our list of call sites object.
 392     #
 393     `$ld -r $inputfile $mcount_o -o $mix`;
 394
 395     #
 396     # Step 9: Move the result back to the original object.
 397     #
 398     `$mv $mix $inputfile`;
 399 }
 400
 401 # Clean up the temp files
 402 `$rm $mcount_o $mcount_s`;
 403
 404 exit(0);