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, $objdump, $objcopy, $cc, $ld, $nm, $rm, $mv, $inputfile) = @ARGV;
 110
 111 $objdump = "objdump" if ((length $objdump) == 0);
 112 $objcopy = "objcopy" if ((length $objcopy) == 0);
 113 $cc = "gcc" if ((length $cc) == 0);
 114 $ld = "ld" if ((length $ld) == 0);
 115 $nm = "nm" if ((length $nm) == 0);
 116 $rm = "rm" if ((length $rm) == 0);
 117 $mv = "mv" if ((length $mv) == 0);
 118
 119 #print STDERR "running: $P '$arch' '$objdump' '$objcopy' '$cc' '$ld' " .
 120 #    "'$nm' '$rm' '$mv' '$inputfile'\n";
 121
 122 my %locals;             # List of local (static) functions
 123 my %weak;               # List of weak functions
 124 my %convert;            # List of local functions used that needs conversion
 125
 126 my $type;
 127 my $section_regex;      # Find the start of a section
 128 my $function_regex;     # Find the name of a function
 129                         #    (return offset and func name)
 130 my $mcount_regex;       # Find the call site to mcount (return offset)
 131
 132 if ($arch eq "x86_64") {
 133     $section_regex = "Disassembly of section";
 134     $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
 135     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
 136     $type = ".quad";
 137
 138     # force flags for this arch
 139     $ld .= " -m elf_x86_64";
 140     $objdump .= " -M x86-64";
 141     $objcopy .= " -O elf64-x86-64";
 142     $cc .= " -m64";
 143
 144 } elsif ($arch eq "i386") {
 145     $section_regex = "Disassembly of section";
 146     $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
 147     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
 148     $type = ".long";
 149
 150     # force flags for this arch
 151     $ld .= " -m elf_i386";
 152     $objdump .= " -M i386";
 153     $objcopy .= " -O elf32-i386";
 154     $cc .= " -m32";
 155
 156 } else {
 157     die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
 158 }
 159
 160 my $text_found = 0;
 161 my $read_function = 0;
 162 my $opened = 0;
 163 my $mcount_section = "__mcount_loc";
 164
 165 my $dirname;
 166 my $filename;
 167 my $prefix;
 168 my $ext;
 169
 170 if ($inputfile =~ m,^(.*)/([^/]*)$,) {
 171     $dirname = $1;
 172     $filename = $2;
 173 } else {
 174     $dirname = ".";
 175     $filename = $inputfile;
 176 }
 177
 178 if ($filename =~ m,^(.*)(\.\S),) {
 179     $prefix = $1;
 180     $ext = $2;
 181 } else {
 182     $prefix = $filename;
 183     $ext = "";
 184 }
 185
 186 my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s";
 187 my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o";
 188
 189 #
 190 # Step 1: find all the local (static functions) and weak symbols.
 191 #        't' is local, 'w/W' is weak (we never use a weak function)
 192 #
 193 open (IN, "$nm $inputfile|") || die "error running $nm";
 194 while (<IN>) {
 195     if (/^[0-9a-fA-F]+\s+t\s+(\S+)/) {
 196         $locals{$1} = 1;
 197     } elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) {
 198         $weak{$2} = $1;
 199     }
 200 }
 201 close(IN);
 202
 203 my @offsets;            # Array of offsets of mcount callers
 204 my $ref_func;           # reference function to use for offsets
 205 my $offset = 0;         # offset of ref_func to section beginning
 206
 207 ##
 208 # update_funcs - print out the current mcount callers
 209 #
 210 #  Go through the list of offsets to callers and write them to
 211 #  the output file in a format that can be read by an assembler.
 212 #
 213 sub update_funcs
 214 {
 215     return if ($#offsets < 0);
 216
 217     defined($ref_func) || die "No function to reference";
 218
 219     # A section only had a weak function, to represent it.
 220     # Unfortunately, a weak function may be overwritten by another
 221     # function of the same name, making all these offsets incorrect.
 222     # To be safe, we simply print a warning and bail.
 223     if (defined $weak{$ref_func}) {
 224         print STDERR
 225             "$inputfile: WARNING: referencing weak function" .
 226             " $ref_func for mcount\n";
 227         return;
 228     }
 229
 230     # is this function static? If so, note this fact.
 231     if (defined $locals{$ref_func}) {
 232         $convert{$ref_func} = 1;
 233     }
 234
 235     # Loop through all the mcount caller offsets and print a reference
 236     # to the caller based from the ref_func.
 237     for (my $i=0; $i <= $#offsets; $i++) {
 238         if (!$opened) {
 239             open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
 240             $opened = 1;
 241             print FILE "\t.section $mcount_section,\"a\",\@progbits\n";
 242         }
 243         printf FILE "\t%s %s + %d\n", $type, $ref_func, $offsets[$i] - $offset;
 244     }
 245 }
 246
 247 #
 248 # Step 2: find the sections and mcount call sites
 249 #
 250 open(IN, "$objdump -dr $inputfile|") || die "error running $objdump";
 251
 252 my $text;
 253
 254 while (<IN>) {
 255     # is it a section?
 256     if (/$section_regex/) {
 257         $read_function = 1;
 258         # print out any recorded offsets
 259         update_funcs() if ($text_found);
 260
 261         # reset all markers and arrays
 262         $text_found = 0;
 263         undef($ref_func);
 264         undef(@offsets);
 265
 266     # section found, now is this a start of a function?
 267     } elsif ($read_function && /$function_regex/) {
 268         $text_found = 1;
 269         $offset = hex $1;
 270         $text = $2;
 271
 272         # if this is either a local function or a weak function
 273         # keep looking for functions that are global that
 274         # we can use safely.
 275         if (!defined($locals{$text}) && !defined($weak{$text})) {
 276             $ref_func = $text;
 277             $read_function = 0;
 278         } else {
 279             # if we already have a function, and this is weak, skip it
 280             if (!defined($ref_func) || !defined($weak{$text})) {
 281                 $ref_func = $text;
 282             }
 283         }
 284     }
 285
 286     # is this a call site to mcount? If so, record it to print later
 287     if ($text_found && /$mcount_regex/) {
 288         $offsets[$#offsets + 1] = hex $1;
 289     }
 290 }
 291
 292 # dump out anymore offsets that may have been found
 293 update_funcs() if ($text_found);
 294
 295 # If we did not find any mcount callers, we are done (do nothing).
 296 if (!$opened) {
 297     exit(0);
 298 }
 299
 300 close(FILE);
 301
 302 #
 303 # Step 3: Compile the file that holds the list of call sites to mcount.
 304 #
 305 `$cc -o $mcount_o -c $mcount_s`;
 306
 307 my @converts = keys %convert;
 308
 309 #
 310 # Step 4: Do we have sections that started with local functions?
 311 #
 312 if ($#converts >= 0) {
 313     my $globallist = "";
 314     my $locallist = "";
 315
 316     foreach my $con (@converts) {
 317         $globallist .= " --globalize-symbol $con";
 318         $locallist .= " --localize-symbol $con";
 319     }
 320
 321     my $globalobj = $dirname . "/.tmp_gl_" . $filename;
 322     my $globalmix = $dirname . "/.tmp_mx_" . $filename;
 323
 324     #
 325     # Step 5: set up each local function as a global
 326     #
 327     `$objcopy $globallist $inputfile $globalobj`;
 328
 329     #
 330     # Step 6: Link the global version to our list.
 331     #
 332     `$ld -r $globalobj $mcount_o -o $globalmix`;
 333
 334     #
 335     # Step 7: Convert the local functions back into local symbols
 336     #
 337     `$objcopy $locallist $globalmix $inputfile`;
 338
 339     # Remove the temp files
 340     `$rm $globalobj $globalmix`;
 341
 342 } else {
 343
 344     my $mix = $dirname . "/.tmp_mx_" . $filename;
 345
 346     #
 347     # Step 8: Link the object with our list of call sites object.
 348     #
 349     `$ld -r $inputfile $mcount_o -o $mix`;
 350
 351     #
 352     # Step 9: Move the result back to the original object.
 353     #
 354     `$mv $mix $inputfile`;
 355 }
 356
 357 # Clean up the temp files
 358 `$rm $mcount_o $mcount_s`;
 359
 360 exit(0);