Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [day] [month] [year] [list]
Date: Wed, 13 May 2015 13:24:30 +0200
From: Alex Dowad <alexinbeijing@...il.com>
To: musl@...ts.openwall.com
Subject: [PATCH v2] 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.
---

Dear Rich (and other interested parties),

Does the aswrap.sh script in this version look something like what you were
thinking of?

I have worked on the AWK script a bit more but need to test again to make
sure the latest amendments haven't broken anything.

Kind regards,
Alex Dowad


 Makefile               |   2 +-
 tools/add-cfi.awk.i386 | 169 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/aswrap.sh        |  15 +++++
 3 files changed, 185 insertions(+), 1 deletion(-)
 create mode 100644 tools/add-cfi.awk.i386
 create mode 100755 tools/aswrap.sh

diff --git a/Makefile b/Makefile
index 6559295..9aefd62 100644
--- a/Makefile
+++ b/Makefile
@@ -118,7 +118,7 @@ $(foreach s,$(wildcard src/*/$(ARCH)*/*.s),$(eval $(call mkasmdep,$(s))))
 	$(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $(dir $<)$(shell cat $<)
 
 %.o: $(ARCH)/%.s
-	$(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $<
+	tools/aswrap.sh $< $@ $(ARCH) "$(CC) $(CFLAGS_ALL_STATIC)"
 
 %.o: %.c $(GENH) $(IMPH)
 	$(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $<
diff --git a/tools/add-cfi.awk.i386 b/tools/add-cfi.awk.i386
new file mode 100644
index 0000000..63c8750
--- /dev/null
+++ b/tools/add-cfi.awk.i386
@@ -0,0 +1,169 @@
+# 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 callable from C
+  # (blindly emitting a '.cfi_startproc' at the beginning of each file and
+  #   '.cfi_endproc' at the end doesn't work)
+  in_function = 0
+}
+
+function hex2int(str) {
+  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 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_const2() {
+  # for instructions with 2 operands, get 2nd operand (assuming it is constant)
+  match($0, /,-?(0x[0-9a-fA-F]+|[0-9]+)/)
+  return parse_const(substr($0, RSTART+1, RLENGTH-1))
+}
+function parse_const(const) {
+  if (substr(const, 1, 1) == "-") {
+    if (substr(const, 2, 2) == "0x") {
+      return -hex2int(substr(const, 4, length(const)-3))
+    } else {
+      return const
+    }
+  } else {
+    if (substr(const, 1, 2) == "0x") {
+      return hex2int(substr(const, 3, length(const)-2))
+    } else {
+      return const
+    }
+  }
+}
+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, RLENGTH-1)
+}
+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, RLENGTH-2)
+}
+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+2, RLENGTH-2)
+}
+
+function adjust_sp_offset(delta) {
+  if (in_function) {
+    printf ".cfi_adjust_cfa_offset %d\n", delta
+  }
+}
+
+{ print }
+
+/\.type.*,@function/ {
+  if (in_function) {
+    print ".cfi_endproc"
+  }
+
+  print ".cfi_startproc"
+  in_function = 1
+
+  for (register in saved)
+    delete saved[register]
+  for (register in dirty)
+    delete dirty[register]
+}
+
+# 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?/ { adjust_sp_offset(4) }
+/popl?/  { adjust_sp_offset(-4) }
+/addl?\s+\$?-?(0x[0-9a-fA-F]+|[0-9]+),%esp/ { adjust_sp_offset(-get_const1()) }
+/subl?\s+\$?-?(0x[0-9a-fA-F]+|[0-9]+),%esp/ { adjust_sp_offset(get_const1()) }
+
+# TRACKING REGISTER VALUES FROM THE PREVIOUS STACK FRAME
+#
+/pushl?\s+%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?\s+%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($0, RSTART, RLENGTH-6))
+    } else {
+      offset = 0
+    }
+    if (!saved[register] && !dirty[register]) {
+      printf ".cfi_rel_offset %s,%d\n", register, offset
+      saved[register] = 1
+    }
+  }
+}
+
+# IF REGISTER VALUES ARE UNCEREMONIOUSLY TRASHED
+# ...then we want to know about it.
+#
+function trashed(register) {
+  if (in_function && !saved[register] && !dirty[register]) {
+    printf ".cfi_undefined %s\n", register
+  }
+  dirty[register] = 1
+}
+# this does NOT exhaustively check for all possible instructions which could
+# overwrite a register value inherited from the caller (just the common ones)
+# TODO: detect when ax/ah/al/etc. are trashed -- means eax is no longer usable either
+/mov.*,%e(ax|bx|cx|dx|si|di|bp)/  { trashed(get_reg2()) }
+/(add|addl|sub|subl|and|or|xor|lea|sal|sar|shl|shr)\s+%e(ax|bx|cx|dx|si|di|bp),/ {
+  trashed(get_reg1())
+}
+/i?mul\s+[^,]*$/                    { trashed("eax"); trashed("edx") }
+/i?mul\s+%e(ax|bx|cx|dx|si|di|bp),/ { trashed(get_reg1()) }
+/^(\w+:)?\s*i?div/                  { trashed("eax"); trashed("edx") }
+/(dec|inc|not|neg|pop)\s+%e(ax|bx|cx|dx|si|di|bp)/  { trashed(get_reg()) }
+/^(\w+:)\s*cpuid/ { trashed("eax"); trashed("ebx"); trashed("ecx"); trashed("edx") }
+
+END {
+  if (in_function) {
+    print ".cfi_endproc"
+  }
+}
\ No newline at end of file
diff --git a/tools/aswrap.sh b/tools/aswrap.sh
new file mode 100755
index 0000000..0afbd4e
--- /dev/null
+++ b/tools/aswrap.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# Run assembler to produce an object file, optionally applying other pre-processing steps
+input=$1
+output=$2
+arch=$3
+as=$4
+
+if [ -f "tools/add-cfi.awk.$arch" ]; then
+  tmpfile=$(mktemp -t musl-aswrap-XXXXXX)
+  awk -f tools/add-cfi.awk.$arch $input >$tmpfile
+  mv $tmpfile $tmpfile.s
+  input=$tmpfile.s
+fi
+
+$as -c -o $output $input
\ 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.