Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date: Sat, 16 May 2015 15:54:31 +0200
From: Alex Dowad <alexinbeijing@...il.com>
To: musl@...ts.openwall.com
Subject: [PATCH] Build process uses script to add CFI directives to x86 asm

Some functions implemented in asm need to use EBP for purposes other than acting
as a frame pointer. (Notably, it is used for the 6th argument to syscalls with
6 arguments.) Without frame pointers, GDB can only show backtraces if it gets
CFI information from a .debug_frame or .eh_frame ELF section.

Rather than littering our asm with ugly .cfi directives, use an awk script to
insert them in the right places during the build process, so GDB can keep track of
where the current stack frame is relative to the stack pointer. This means GDB can
produce beautiful stack traces at any given point when single-stepping through asm
functions.

Additionally, when registers are saved on the stack and later overwritten, emit
.cfi directives so GDB will know where they were saved relative to the stack
pointer. This way, when you look back up the stack from within an asm function,
you can still reliably print the values of local variables in the caller.

If this awk script were to understand every possible wild and crazy contortion that
an asm programmer can do with the stack and registers, and always emit the exact
.cfi directives needed for GDB to know what the register values were in the
preceding stack frame, it would necessarily be as complex as a full x86 emulator.
That way lies madness.

Hence, we assume that the stack pointer will _only_ ever be adjusted using push/pop
or else add/sub with a constant. We do not attempt to detect every possible way that
a register value could be saved for later use, just the simple and common ways.

Thanks to Szabolcs Nagy for suggesting numerous improvements to this code.
---

Wash, rinse, and repeat...

configure script now checks whether debugging is enabled, whether the assembler
understands CFI directives, whether it understands '-x assembler', and whether
there the AWK script is present for the current arch.

aswrap.sh is gone -- the problem is that the arguments it wants (and the order it
  wants them in) is different from $(CC). So it's hard to use an AS_CMD variable
  as suggested by RF to run whichever command is appropriate.

Suggestions from shell/Makefile scripting wizards on how to do this better
  are appreciated!

The processed asm now contains .file and .loc directives, so when you debug it in
GDB, it will show you the original source file, and highlight the correct lines.

I haven't tested with busybox awk yet, just with GNU awk. If there are no further
  issues with the code, I will do that next.

Thanks,
Alex Dowad

 Makefile               |  10 ++-
 configure              |  13 ++++
 tools/add-cfi.awk.i386 | 207 +++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 229 insertions(+), 1 deletion(-)
 create mode 100644 tools/add-cfi.awk.i386

diff --git a/Makefile b/Makefile
index 6559295..6f17cc7 100644
--- a/Makefile
+++ b/Makefile
@@ -118,7 +118,11 @@ $(foreach s,$(wildcard src/*/$(ARCH)*/*.s),$(eval $(call mkasmdep,$(s))))
 	$(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $(dir $<)$(shell cat $<)
 
 %.o: $(ARCH)/%.s
+ifeq ($(ADD_CFI),yes)
+	LC_ALL=C awk -f tools/add-cfi.awk.$(ARCH) $< | $(CC) $(CFLAGS_ALL_STATIC) -x assembler -c -o $@ -
+else
 	$(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $<
+endif
 
 %.o: %.c $(GENH) $(IMPH)
 	$(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $<
@@ -127,7 +131,11 @@ $(foreach s,$(wildcard src/*/$(ARCH)*/*.s),$(eval $(call mkasmdep,$(s))))
 	$(CC) $(CFLAGS_ALL_SHARED) -c -o $@ $(dir $<)$(shell cat $<)
 
 %.lo: $(ARCH)/%.s
+ifeq ($(ADD_CFI),yes)
+	LC_ALL=C awk -f tools/add-cfi.awk.$(ARCH) $< | $(CC) $(CFLAGS_ALL_SHARED) -x assembler -c -o $@ -
+else
 	$(CC) $(CFLAGS_ALL_SHARED) -c -o $@ $<
+endif
 
 %.lo: %.c $(GENH) $(IMPH)
 	$(CC) $(CFLAGS_ALL_SHARED) -c -o $@ $<
diff --git a/configure b/configure
index 143dc92..72349a2 100755
--- a/configure
+++ b/configure
@@ -317,6 +317,18 @@ tryflag CFLAGS_MEMOPS -fno-tree-loop-distribute-patterns
 test "$debug" = yes && CFLAGS_AUTO=-g
 
 #
+# Preprocess asm files to add extra debugging information if debug is
+# enabled, our assembler supports the needed directives, and the
+# preprocessing script has been written for our architecture.
+#
+if (test "$debug" = yes) &&
+   (test -f "tools/add-cfi.awk.$ARCH") &&
+   (echo ".cfi_startproc\n.cfi_endproc" | $CC -x assembler -c -o /dev/null -)
+then
+  ADD_CFI=yes
+fi
+
+#
 # Possibly add a -O option to CFLAGS and select modules to optimize with
 # -O3 based on the status of --enable-optimize and provided CFLAGS.
 #
@@ -570,6 +582,7 @@ LDFLAGS = $LDFLAGS_AUTO $LDFLAGS
 CROSS_COMPILE = $CROSS_COMPILE
 LIBCC = $LIBCC
 OPTIMIZE_GLOBS = $OPTIMIZE_GLOBS
+ADD_CFI = $ADD_CFI
 EOF
 test "x$static" = xno && echo "STATIC_LIBS ="
 test "x$shared" = xno && echo "SHARED_LIBS ="
diff --git a/tools/add-cfi.awk.i386 b/tools/add-cfi.awk.i386
new file mode 100644
index 0000000..647b6a1
--- /dev/null
+++ b/tools/add-cfi.awk.i386
@@ -0,0 +1,207 @@
+# Insert GAS CFI directives ("control frame information") into x86-32 asm input
+#
+# CFI directives tell the assembler how to generate "stack frame" debug info
+# This information can tell a debugger (like gdb) how to find the current stack
+#   frame at any point in the program code, and how to find the values which
+#   various registers had at higher points in the call stack
+# With this information, the debugger can show a backtrace, and you can move up
+#   and down the call stack and examine the values of local variables
+
+BEGIN {
+  # don't put CFI data in the .eh_frame ELF section (which we don't keep)
+  print ".cfi_sections .debug_frame"
+
+  # only emit CFI directives inside a function
+  in_function = 0
+
+  # emit .loc directives with line numbers from original source
+  printf ".file 1 \"%s\"\n", ARGV[1]
+  line_number = 0
+}
+
+function hex2int(str,   i) {
+  str = tolower(str)
+
+  for (i = 1; i <= 16; i++) {
+    char = substr("0123456789abcdef", i, 1)
+    lookup[char] = i-1
+  }
+
+  result = 0
+  for (i = 1; i <= length(str); i++) {
+    result = result * 16
+    char   = substr(str, i, 1)
+    result = result + lookup[char]
+  }
+  return result
+}
+
+function parse_const(str) {
+  sign = sub(/^-/, "", str)
+  hex  = sub(/^0x/, "", str)
+  if (hex)
+    n = hex2int(str)
+  else
+    n = str+0
+  return sign ? -n : n
+}
+
+function get_const1() {
+  # for instructions with 2 operands, get 1st operand (assuming it is constant)
+  match($0, /-?(0x[0-9a-fA-F]+|[0-9]+),/)
+  return parse_const(substr($0, RSTART, RLENGTH-1))
+}
+function get_reg() {
+  # only use if you already know there is 1 and only 1 register
+  match($0, /%e(ax|bx|cx|dx|si|di|bp)/)
+  return substr($0, RSTART+1, 3)
+}
+function get_reg1() {
+  # for instructions with 2 operands, get 1st operand (assuming it is register)
+  match($0, /%e(ax|bx|cx|dx|si|di|bp),/)
+  return substr($0, RSTART+1, 3)
+}
+function get_reg2() {
+  # for instructions with 2 operands, get 2nd operand (assuming it is register)
+  match($0, /,%e(ax|bx|cx|dx|si|di|bp)/)
+  return substr($0, RSTART+RLENGTH-3, 3)
+}
+
+function adjust_sp_offset(delta) {
+  if (in_function)
+    printf ".cfi_adjust_cfa_offset %d\n", delta
+}
+
+{
+  line_number = line_number + 1
+
+  # clean the input up before doing anything else
+  # delete comments
+  gsub("/(#|//).*/", "")
+
+  # canonicalize whitespace
+  gsub(/\s+/, " ")
+  gsub(/ *, */, ",")
+  gsub(/ *: */, ": ")
+  gsub(/ $/, "")
+  gsub(/^ /, "")
+}
+
+# check for assembler directives which we care about
+/^\.section/ {
+  if (in_function) {
+    print ".cfi_endproc"
+    in_function = 0
+  }
+}
+/^\.globa?l\s+\w+/ {
+  globals[$2] = 1
+}
+# not interested in assembler directives beyond this, just pass them through
+/^\./ {
+  print
+  next
+}
+
+/^\w+:/ {
+  label = substr($1, 1, length($1)-1) # drop trailing :
+
+  if (globals[label]) {
+    if (in_function)
+      print ".cfi_endproc"
+
+    in_function = 1
+    print ".cfi_startproc"
+
+    for (register in saved)
+      delete saved[register]
+    for (register in dirty)
+      delete dirty[register]
+  }
+}
+
+/^$/ { next }
+
+{
+  printf ".loc 1 %d\n", line_number
+  print
+}
+
+# KEEPING UP WITH THE STACK POINTER
+# We do NOT attempt to understand foolish and ridiculous tricks like stashing
+#   the stack pointer and then using %esp as a scratch register, or bitshifting
+#   it or taking its square root or anything stupid like that.
+# %esp should only be adjusted by pushing/popping or adding/subtracting constants
+#
+/pushl?/ {
+  if (match($0, /\s+%(ax|bx|cx|dx|di|si|bp|sp)/))
+    adjust_sp_offset(2)
+  else
+    adjust_sp_offset(4)
+}
+/popl?/ {
+  if (match($0, /\s+%(ax|bx|cx|dx|di|si|bp|sp)/))
+    adjust_sp_offset(-2)
+  else
+    adjust_sp_offset(-4)
+}
+/addl? \$-?(0x[0-9a-fA-F]+|[0-9]+),%esp/ { adjust_sp_offset(-get_const1()) }
+/subl? \$-?(0x[0-9a-fA-F]+|[0-9]+),%esp/ { adjust_sp_offset(get_const1()) }
+
+# TRACKING REGISTER VALUES FROM THE PREVIOUS STACK FRAME
+#
+/pushl? %e(ax|bx|cx|dx|si|di|bp)/ { # don't match "push (%reg)"
+  # if a register is being pushed, and its value has not changed since the
+  #   beginning of this function, the pushed value can be used when printing
+  #   local variables at the next level up the stack
+  # emit '.cfi_rel_offset' for that
+
+  if (in_function) {
+    register = get_reg()
+    if (!saved[register] && !dirty[register]) {
+      printf ".cfi_rel_offset %s,0\n", register
+      saved[register] = 1
+    }
+  }
+}
+
+/movl? %e(ax|bx|cx|dx|si|di|bp),-?(0x[0-9a-fA-F]+|[0-9]+)?\(%esp\)/ {
+  if (in_function) {
+    register = get_reg()
+    if (match($0, /-?(0x[0-9a-fA-F]+|[0-9]+)\(%esp\)/)) {
+      offset = parse_const(substr($0, RSTART, RLENGTH-6))
+    } else {
+      offset = 0
+    }
+    if (!saved[register] && !dirty[register]) {
+      printf ".cfi_rel_offset %s,%d\n", register, offset
+      saved[register] = 1
+    }
+  }
+}
+
+# IF REGISTER VALUES ARE UNCEREMONIOUSLY TRASHED
+# ...then we want to know about it.
+#
+function trashed(register) {
+  if (in_function && !saved[register] && !dirty[register]) {
+    printf ".cfi_undefined %s\n", register
+  }
+  dirty[register] = 1
+}
+# this does NOT exhaustively check for all possible instructions which could
+# overwrite a register value inherited from the caller (just the common ones)
+/mov.*,%e(ax|bx|cx|dx|si|di|bp)/  { trashed(get_reg2()) }
+/(add|addl|sub|subl|and|or|xor|lea|sal|sar|shl|shr) %e(ax|bx|cx|dx|si|di|bp),/ {
+  trashed(get_reg1())
+}
+/i?mul [^,]*$/                    { trashed("eax"); trashed("edx") }
+/i?mul %e(ax|bx|cx|dx|si|di|bp),/ { trashed(get_reg1()) }
+/i?div/                           { trashed("eax"); trashed("edx") }
+/(dec|inc|not|neg|pop) %e(ax|bx|cx|dx|si|di|bp)/  { trashed(get_reg()) }
+/cpuid/ { trashed("eax"); trashed("ebx"); trashed("ecx"); trashed("edx") }
+
+END {
+  if (in_function)
+    print ".cfi_endproc"
+}
\ No newline at end of file
-- 
2.0.0.GIT

Powered by blists - more mailing lists

Your e-mail address:

Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.