Re: Issue using faddr2line on kernel modules

[Josh Poimboeuf <jpoimboe@redhat.com>]

On Wed, Jan 19, 2022 at 01:21:29PM -0800, Josh Poimboeuf wrote:
> > $ nm -n ./oops_tryv2.ko |grep -C5 do_the_work
> > 0000000000000000 r __func__.24215
> > 0000000000000000 r __param_bug_in_workq
> > 0000000000000000 D __this_module
> > 0000000000000000 r _note_7
> > 0000000000000000 T cleanup_module
> > 0000000000000000 t do_the_work
> > 0000000000000000 t do_the_work.cold
> > 0000000000000000 b gctx
> > 0000000000000000 T init_module
> > 0000000000000000 t try_oops_exit
> > 0000000000000000 t try_oops_init
> > 0000000000000008 b t1
> > $
> > 
> > BTW, here's the code:
> > https://github.com/PacktPublishing/Linux-Kernel-Debugging/tree/main/ch7/oops_tryv2
> 
> Ok, it looks like the symbols aren't sorted like the code expects.  I
> need to do a more robust fix.

Ok, please try this instead.  This takes a much more robust approach to
the function size calculation, using readelf to confine the symbol
search to the section matching the original symbol.

This actually has multiple fixes and cleanups, so it'll eventually be
split up into a patch set.

----

diff --git a/scripts/faddr2line b/scripts/faddr2line
index 6c6439f69a72..1acb68927977 100755
--- a/scripts/faddr2line
+++ b/scripts/faddr2line
@@ -97,10 +97,11 @@ __faddr2line() {
 	local dir_prefix=$3
 	local print_warnings=$4
 
+	local first=1
 	local func=${func_addr%+*}
 	local offset=${func_addr#*+}
 	offset=${offset%/*}
-	local size=
+	local user_size=
 	[[ $func_addr =~ "/" ]] && size=${func_addr#*/}
 
 	if [[ -z $func ]] || [[ -z $offset ]] || [[ $func = $func_addr ]]; then
@@ -110,73 +111,87 @@ __faddr2line() {
 	fi
 
 	# Go through each of the object's symbols which match the func name.
-	# In rare cases there might be duplicates.
-	file_end=$(${SIZE} -Ax $objfile | awk '$1 == ".text" {print $2}')
+	# In rare cases there might be duplicates, in which case we print both.
 	while read symbol; do
 		local fields=($symbol)
-		local sym_base=0x${fields[0]}
-		local sym_type=${fields[1]}
-		local sym_end=${fields[3]}
-
-		# calculate the size
-		local sym_size=$(($sym_end - $sym_base))
-		if [[ -z $sym_size ]] || [[ $sym_size -le 0 ]]; then
-			warn "bad symbol size: base: $sym_base end: $sym_end"
+		local sym_addr=0x${fields[1]}
+		local sym_size=${fields[2]}
+		local sym_sec=${fields[6]}
+
+		# Get the section size:
+		local 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: $sym_sec"
 			DONE=1
 			return
 		fi
-		sym_size=0x$(printf %x $sym_size)
 
-		# calculate the address
-		local addr=$(($sym_base + $offset))
-		if [[ -z $addr ]] || [[ $addr = 0 ]]; then
-			warn "bad address: $sym_base + $offset"
+		# Calculate the symbol size:
+		#
+		# We can't use the ELF size, because kallsyms also includes the
+		# padding bytes in its size calculation.  For kallsyms, the
+		# size calculation is the distance between the symbol and the
+		# next symbol in a sorted list.
+		local size=$(${READELF} --symbols --wide $objfile |
+			awk -v sec=$sym_sec '$7 == sec' |
+			sort --key=2 |
+			awk --bignum -v sym_addr=${sym_addr#0x} -v sym_size=${sym_size} -v sym_name=${func} -v sec_size=${sec_size} \
+				'$2 == sym_addr && $3 == sym_size && $8 == sym_name { found = 1; next } \
+				found == 1 { size = strtonum("0x" $2) - strtonum("0x" sym_addr); if (size < sym_size) next; found = 2; print size; exit } \
+				END { if (found == 1) print strtonum(sec_size) }')
+
+		if [[ -z $size ]]; then
+			warn "bad symbol size: addr: $sym_addr"
 			DONE=1
 			return
 		fi
-		addr=0x$(printf %x $addr)
 
-		# weed out non-function symbols
-		if [[ $sym_type != t ]] && [[ $sym_type != T ]]; then
-			[[ $print_warnings = 1 ]] &&
-				echo "skipping $func address at $addr due to non-function symbol of type '$sym_type'"
-			continue
+		# Calculate the specified address:
+		local addr=$(($sym_addr + $offset))
+		if [[ -z $addr ]] || [[ $addr = 0 ]]; then
+			warn "bad address: $sym_addr + $offset"
+			DONE=1
+			return
 		fi
+		addr=0x$(printf %x $addr)
 
-		# if the user provided a size, make sure it matches the symbol's size
-		if [[ -n $size ]] && [[ $size -ne $sym_size ]]; then
+		# If the user provided a size, make sure it matches the symbol's size:
+		if [[ -n $user_size ]] && [[ $user_size -ne $size ]]; then
 			[[ $print_warnings = 1 ]] &&
-				echo "skipping $func address at $addr due to size mismatch ($size != $sym_size)"
+				echo "skipping $func address at $addr due to size mismatch ($user_size != $size)"
 			continue;
 		fi
 
-		# make sure the provided offset is within the symbol's range
-		if [[ $offset -gt $sym_size ]]; then
+		# Make sure the provided offset is within the symbol's range:
+		if [[ $offset -gt $size ]]; then
 			[[ $print_warnings = 1 ]] &&
-				echo "skipping $func address at $addr due to size mismatch ($offset > $sym_size)"
+				echo "skipping $func address at $addr due to size mismatch ($offset > $size)"
 			continue
 		fi
 
-		# separate multiple entries with a blank line
-		[[ $FIRST = 0 ]] && echo
-		FIRST=0
+		# In case of duplicates, separate multiple entries with a blank line:
+		[[ $first = 0 ]] && echo
+		first=0
 
-		# pass real address to addr2line
-		echo "$func+$offset/$sym_size:"
-		local file_lines=$(${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;")
-		[[ -z $file_lines ]] && return
+		# Pass full address to addr2line:
+		echo "$func+$offset/$size:"
+		local output=$(${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;")
+		[[ -z $output ]] && continue
 
 		if [[ $LIST = 0 ]]; then
-			echo "$file_lines" | while read -r line
+			echo "$output" | while read -r line
 			do
 				echo $line
 			done
 			DONE=1;
-			return
+			continue
 		fi
 
-		# show each line with context
-		echo "$file_lines" | while read -r line
+		# If --list was specified, show each line with context:
+		echo "$output" | while read -r line
 		do
 			echo
 			echo $line
@@ -189,7 +204,7 @@ __faddr2line() {
 
 		DONE=1
 
-	done < <(${NM} -n $objfile | awk -v fn=$func -v end=$file_end '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, "0x"$1 } END {if (found == 1) print line, end; }')
+	done < <(${READELF} --symbols --wide $objfile | awk -v fn=$func '$4 == "FUNC" && $8 == fn')
 }
 
 [[ $# -lt 2 ]] && usage