diff options
| -rw-r--r-- | Makefile | 12 | ||||
| -rwxr-xr-x | configure | 17 | ||||
| -rw-r--r-- | tools/add-cfi.i386.awk | 227 |
3 files changed, 254 insertions, 2 deletions
@@ -119,11 +119,19 @@ $(dir $(patsubst %/,%,$(dir $(1))))$(notdir $(1:.s=.o)): $(1) endef $(foreach s,$(wildcard src/*/$(ARCH)*/*.s),$(eval $(call mkasmdep,$(s)))) +# Choose invocation of assembler to be used +# $(1) is input file, $(2) is output file, $(3) is assembler flags +ifeq ($(ADD_CFI),yes) + AS_CMD = LC_ALL=C awk -f tools/add-cfi.$(ARCH).awk $< | $(CC) -x assembler -c -o $@ - +else + AS_CMD = $(CC) -c -o $@ $< +endif + %.o: $(ARCH)$(ASMSUBARCH)/%.sub $(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $(dir $<)$(shell cat $<) %.o: $(ARCH)/%.s - $(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $< + $(AS_CMD) $(CFLAGS_ALL_STATIC) %.o: %.c $(GENH) $(IMPH) $(CC) $(CFLAGS_ALL_STATIC) -c -o $@ $< @@ -132,7 +140,7 @@ $(foreach s,$(wildcard src/*/$(ARCH)*/*.s),$(eval $(call mkasmdep,$(s)))) $(CC) $(CFLAGS_ALL_SHARED) -c -o $@ $(dir $<)$(shell cat $<) %.lo: $(ARCH)/%.s - $(CC) $(CFLAGS_ALL_SHARED) -c -o $@ $< + $(AS_CMD) $(CFLAGS_ALL_SHARED) %.lo: %.c $(GENH) $(IMPH) $(CC) $(CFLAGS_ALL_SHARED) -c -o $@ $< @@ -351,6 +351,22 @@ tryflag CFLAGS_MEMOPS -fno-tree-loop-distribute-patterns test "$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. +# +printf "checking whether we should preprocess assembly to add debugging information... " +if fnmatch '-g*|*\ -g*' "$CFLAGS_AUTO $CFLAGS" && + test -f "tools/add-cfi.$ARCH.awk" && + printf ".file 1 \"srcfile.s\"\n.line 1\n.cfi_startproc\n.cfi_endproc" | $CC -g -x assembler -c -o /dev/null 2>/dev/null - +then + ADD_CFI=yes +else + ADD_CFI=no +fi +printf "%s\n" "$ADD_CFI" + +# # Possibly add a -O option to CFLAGS and select modules to optimize with # -O3 based on the status of --enable-optimize and provided CFLAGS. # @@ -606,6 +622,7 @@ LIBCC = $LIBCC OPTIMIZE_GLOBS = $OPTIMIZE_GLOBS ALL_TOOLS = $tools TOOL_LIBS = $tool_libs +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.i386.awk b/tools/add-cfi.i386.awk new file mode 100644 index 00000000..4a4a3b63 --- /dev/null +++ b/tools/add-cfi.i386.awk @@ -0,0 +1,227 @@ +# 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 + + # used to detect "call label; label:" trick + called = "" +} + +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(/[ \t]+/, " ") # mawk doesn't understand \s + gsub(/ *, */, ",") + gsub(/ *: */, ": ") + gsub(/ $/, "") + gsub(/^ /, "") +} + +# check for assembler directives which we care about +/^\.(section|data|text)/ { + # a .cfi_startproc/.cfi_endproc pair should be within the same section + # otherwise, clang will choke when generating ELF output + if (in_function) { + print ".cfi_endproc" + in_function = 0 + } +} +/^\.type [a-zA-Z0-9_]+,\@function/ { + functions[substr($2, 1, length($2)-10)] = 1 +} +# not interested in assembler directives beyond this, just pass them through +/^\./ { + print + next +} + +/^[a-zA-Z0-9_]+:/ { + label = substr($1, 1, length($1)-1) # drop trailing : + + if (called == label) { + # note adjustment of stack pointer from "call label; label:" + adjust_sp_offset(4) + } + + if (functions[label]) { + if (in_function) + print ".cfi_endproc" + + in_function = 1 + print ".cfi_startproc" + + for (register in saved) + delete saved[register] + for (register in dirty) + delete dirty[register] + } + + # an instruction may follow on the same line, so continue processing +} + +/^$/ { next } + +{ + called = "" + 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, / %(ax|bx|cx|dx|di|si|bp|sp)/)) + adjust_sp_offset(2) + else + adjust_sp_offset(4) +} +/popl?/ { + if (match($0, / %(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()) } + +/call/ { + if (match($0, /call [0-9]+f/)) # "forward" label + called = substr($0, RSTART+5, RLENGTH-6) + else if (match($0, /call [0-9a-zA-Z_]+/)) + called = substr($0, RSTART+5, RLENGTH-5) +} + +# 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" +} |