linux-stable/scripts/faddr2line
Will Deacon 60fd39af33 scripts/faddr2line: Skip over mapping symbols in output from readelf
Mapping symbols emitted in the readelf output can confuse the
'faddr2line' symbol size calculation, resulting in the erroneous
rejection of valid offsets. This is especially prevalent when building
an arm64 kernel with CONFIG_CFI_CLANG=y, where most functions are
prefixed with a 32-bit data value in a '$d.n' section. For example:

447538: ffff800080014b80   548 FUNC    GLOBAL DEFAULT    2 do_one_initcall
   104: ffff800080014c74     0 NOTYPE  LOCAL  DEFAULT    2 $x.73
   106: ffff800080014d30     0 NOTYPE  LOCAL  DEFAULT    2 $x.75
   111: ffff800080014da4     0 NOTYPE  LOCAL  DEFAULT    2 $d.78
   112: ffff800080014da8     0 NOTYPE  LOCAL  DEFAULT    2 $x.79
    36: ffff800080014de0   200 FUNC    LOCAL  DEFAULT    2 run_init_process

Adding a warning to do_one_initcall() results in:

  | WARNING: CPU: 0 PID: 1 at init/main.c:1236 do_one_initcall+0xf4/0x260

Which 'faddr2line' refuses to accept:

$ ./scripts/faddr2line vmlinux do_one_initcall+0xf4/0x260
skipping do_one_initcall address at 0xffff800080014c74 due to size mismatch (0x260 != 0x224)
no match for do_one_initcall+0xf4/0x260

Filter out these entries from readelf using a shell reimplementation of
is_mapping_symbol(), so that the size of a symbol is calculated as a
delta to the next symbol present in ksymtab.

Suggested-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20231002165750.1661-4-will@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
2023-10-23 08:36:46 -07:00

313 lines
8.6 KiB
Bash
Executable file

#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
#
# Translate stack dump function offsets.
#
# addr2line doesn't work with KASLR addresses. This works similarly to
# addr2line, but instead takes the 'func+0x123' format as input:
#
# $ ./scripts/faddr2line ~/k/vmlinux meminfo_proc_show+0x5/0x568
# meminfo_proc_show+0x5/0x568:
# meminfo_proc_show at fs/proc/meminfo.c:27
#
# If the address is part of an inlined function, the full inline call chain is
# printed:
#
# $ ./scripts/faddr2line ~/k/vmlinux native_write_msr+0x6/0x27
# native_write_msr+0x6/0x27:
# arch_static_branch at arch/x86/include/asm/msr.h:121
# (inlined by) static_key_false at include/linux/jump_label.h:125
# (inlined by) native_write_msr at arch/x86/include/asm/msr.h:125
#
# The function size after the '/' in the input is optional, but recommended.
# It's used to help disambiguate any duplicate symbol names, which can occur
# rarely. If the size is omitted for a duplicate symbol then it's possible for
# multiple code sites to be printed:
#
# $ ./scripts/faddr2line ~/k/vmlinux raw_ioctl+0x5
# raw_ioctl+0x5/0x20:
# raw_ioctl at drivers/char/raw.c:122
#
# raw_ioctl+0x5/0xb1:
# raw_ioctl at net/ipv4/raw.c:876
#
# Multiple addresses can be specified on a single command line:
#
# $ ./scripts/faddr2line ~/k/vmlinux type_show+0x10/45 free_reserved_area+0x90
# type_show+0x10/0x2d:
# type_show at drivers/video/backlight/backlight.c:213
#
# free_reserved_area+0x90/0x123:
# free_reserved_area at mm/page_alloc.c:6429 (discriminator 2)
set -o errexit
set -o nounset
usage() {
echo "usage: faddr2line [--list] <object file> <func+offset> <func+offset>..." >&2
exit 1
}
warn() {
echo "$1" >&2
}
die() {
echo "ERROR: $1" >&2
exit 1
}
UTIL_SUFFIX=""
if [[ "${LLVM:-}" == "" ]]; then
UTIL_PREFIX=${CROSS_COMPILE:-}
else
UTIL_PREFIX=llvm-
if [[ "${LLVM}" == *"/" ]]; then
UTIL_PREFIX=${LLVM}${UTIL_PREFIX}
elif [[ "${LLVM}" == "-"* ]]; then
UTIL_SUFFIX=${LLVM}
fi
fi
READELF="${UTIL_PREFIX}readelf${UTIL_SUFFIX}"
ADDR2LINE="${UTIL_PREFIX}addr2line${UTIL_SUFFIX}"
AWK="awk"
GREP="grep"
command -v ${AWK} >/dev/null 2>&1 || die "${AWK} isn't installed"
command -v ${READELF} >/dev/null 2>&1 || die "${READELF} isn't installed"
command -v ${ADDR2LINE} >/dev/null 2>&1 || die "${ADDR2LINE} isn't installed"
# Try to figure out the source directory prefix so we can remove it from the
# addr2line output. HACK ALERT: This assumes that start_kernel() is in
# init/main.c! This only works for vmlinux. Otherwise it falls back to
# printing the absolute path.
find_dir_prefix() {
local objfile=$1
local start_kernel_addr=$(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' |
${AWK} '$8 == "start_kernel" {printf "0x%s", $2}')
[[ -z $start_kernel_addr ]] && return
local file_line=$(${ADDR2LINE} -e $objfile $start_kernel_addr)
[[ -z $file_line ]] && return
local prefix=${file_line%init/main.c:*}
if [[ -z $prefix ]] || [[ $prefix = $file_line ]]; then
return
fi
DIR_PREFIX=$prefix
return 0
}
__faddr2line() {
local objfile=$1
local func_addr=$2
local dir_prefix=$3
local print_warnings=$4
local sym_name=${func_addr%+*}
local func_offset=${func_addr#*+}
func_offset=${func_offset%/*}
local user_size=
local file_type
local is_vmlinux=0
[[ $func_addr =~ "/" ]] && user_size=${func_addr#*/}
if [[ -z $sym_name ]] || [[ -z $func_offset ]] || [[ $sym_name = $func_addr ]]; then
warn "bad func+offset $func_addr"
DONE=1
return
fi
# vmlinux uses absolute addresses in the section table rather than
# section offsets.
local file_type=$(${READELF} --file-header $objfile |
${AWK} '$1 == "Type:" { print $2; exit }')
if [[ $file_type = "EXEC" ]] || [[ $file_type == "DYN" ]]; then
is_vmlinux=1
fi
# Go through each of the object's symbols which match the func name.
# In rare cases there might be duplicates, in which case we print all
# matches.
while read line; do
local fields=($line)
local sym_addr=0x${fields[1]}
local sym_elf_size=${fields[2]}
local sym_sec=${fields[6]}
local sec_size
local sec_name
# Get the section size:
sec_size=$(${READELF} --section-headers --wide $objfile |
sed 's/\[ /\[/' |
${AWK} -v sec=$sym_sec '$1 == "[" sec "]" { print "0x" $6; exit }')
if [[ -z $sec_size ]]; then
warn "bad section size: section: $sym_sec"
DONE=1
return
fi
# Get the section name:
sec_name=$(${READELF} --section-headers --wide $objfile |
sed 's/\[ /\[/' |
${AWK} -v sec=$sym_sec '$1 == "[" sec "]" { print $2; exit }')
if [[ -z $sec_name ]]; then
warn "bad section name: section: $sym_sec"
DONE=1
return
fi
# Calculate the symbol size.
#
# Unfortunately we can't use the ELF size, because kallsyms
# also includes the padding bytes in its size calculation. For
# kallsyms, the size calculation is the distance between the
# symbol and the next symbol in a sorted list.
local sym_size
local cur_sym_addr
local found=0
while read line; do
local fields=($line)
cur_sym_addr=0x${fields[1]}
local cur_sym_elf_size=${fields[2]}
local cur_sym_name=${fields[7]:-}
# is_mapping_symbol(cur_sym_name)
if [[ ${cur_sym_name} =~ ^(\.L|L0|\$) ]]; then
continue
fi
if [[ $cur_sym_addr = $sym_addr ]] &&
[[ $cur_sym_elf_size = $sym_elf_size ]] &&
[[ $cur_sym_name = $sym_name ]]; then
found=1
continue
fi
if [[ $found = 1 ]]; then
sym_size=$(($cur_sym_addr - $sym_addr))
[[ $sym_size -lt $sym_elf_size ]] && continue;
found=2
break
fi
done < <(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' | ${AWK} -v sec=$sym_sec '$7 == sec' | sort --key=2)
if [[ $found = 0 ]]; then
warn "can't find symbol: sym_name: $sym_name sym_sec: $sym_sec sym_addr: $sym_addr sym_elf_size: $sym_elf_size"
DONE=1
return
fi
# If nothing was found after the symbol, assume it's the last
# symbol in the section.
[[ $found = 1 ]] && sym_size=$(($sec_size - $sym_addr))
if [[ -z $sym_size ]] || [[ $sym_size -le 0 ]]; then
warn "bad symbol size: sym_addr: $sym_addr cur_sym_addr: $cur_sym_addr"
DONE=1
return
fi
sym_size=0x$(printf %x $sym_size)
# Calculate the address from user-supplied offset:
local addr=$(($sym_addr + $func_offset))
if [[ -z $addr ]] || [[ $addr = 0 ]]; then
warn "bad address: $sym_addr + $func_offset"
DONE=1
return
fi
addr=0x$(printf %x $addr)
# If the user provided a size, make sure it matches the symbol's size:
if [[ -n $user_size ]] && [[ $user_size -ne $sym_size ]]; then
[[ $print_warnings = 1 ]] &&
echo "skipping $sym_name address at $addr due to size mismatch ($user_size != $sym_size)"
continue;
fi
# Make sure the provided offset is within the symbol's range:
if [[ $func_offset -gt $sym_size ]]; then
[[ $print_warnings = 1 ]] &&
echo "skipping $sym_name address at $addr due to size mismatch ($func_offset > $sym_size)"
continue
fi
# In case of duplicates or multiple addresses specified on the
# cmdline, separate multiple entries with a blank line:
[[ $FIRST = 0 ]] && echo
FIRST=0
echo "$sym_name+$func_offset/$sym_size:"
# Pass section address to addr2line and strip absolute paths
# from the output:
local args="--functions --pretty-print --inlines --exe=$objfile"
[[ $is_vmlinux = 0 ]] && args="$args --section=$sec_name"
local output=$(${ADDR2LINE} $args $addr | sed "s; $dir_prefix\(\./\)*; ;")
[[ -z $output ]] && continue
# Default output (non --list):
if [[ $LIST = 0 ]]; then
echo "$output" | while read -r line
do
echo $line
done
DONE=1;
continue
fi
# For --list, show each line with its corresponding source code:
echo "$output" | while read -r line
do
echo
echo $line
n=$(echo $line | sed 's/.*:\([0-9]\+\).*/\1/g')
n1=$[$n-5]
n2=$[$n+5]
f=$(echo $line | sed 's/.*at \(.\+\):.*/\1/g')
${AWK} 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") { if (NR=='$n') printf(">%d<", NR); else printf(" %d ", NR); printf("\t%s\n", $0)}' $f
done
DONE=1
done < <(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' | ${AWK} -v fn=$sym_name '$8 == fn')
}
[[ $# -lt 2 ]] && usage
objfile=$1
LIST=0
[[ "$objfile" == "--list" ]] && LIST=1 && shift && objfile=$1
[[ ! -f $objfile ]] && die "can't find objfile $objfile"
shift
${READELF} --section-headers --wide $objfile | ${GREP} -q '\.debug_info' || die "CONFIG_DEBUG_INFO not enabled"
DIR_PREFIX=supercalifragilisticexpialidocious
find_dir_prefix $objfile
FIRST=1
while [[ $# -gt 0 ]]; do
func_addr=$1
shift
# print any matches found
DONE=0
__faddr2line $objfile $func_addr $DIR_PREFIX 0
# if no match was found, print warnings
if [[ $DONE = 0 ]]; then
__faddr2line $objfile $func_addr $DIR_PREFIX 1
warn "no match for $func_addr"
fi
done