adding support for new /sys interface (#55)

* adding support for new /sys interface
* fix(objdump): prefer -d instead of -D, some kernels crash objdump otherwise

spectre-meltdown-checker.sh

@@ -8,7 +8,7 @@
 #
 # Stephane Lesimple
 #
-VERSION=0.25
+VERSION=0.26
 
 # Script configuration
 show_usage()
@@ -33,7 +33,8 @@ show_usage()
 
 	Options:
 		--no-color			Don't use color codes
-		-v, --verbose			Increase verbosity level
+		--verbose, -v			Increase verbosity level
+		--no-sysfs			Don't use the /sys interface even if present
 		--batch text			Produce machine readable output, this is the default if --batch is specified alone
 		--batch json			Produce JSON output formatted for Puppet, Ansible, Chef...
 		--batch nrpe			Produce machine readable output formatted for NRPE
@@ -86,6 +87,7 @@ opt_variant1=0
 opt_variant2=0
 opt_variant3=0
 opt_allvariants=1
+opt_no_sysfs=0
 
 nrpe_critical=0
 nrpe_unknown=0
@@ -95,13 +97,13 @@ __echo()
 {
 	opt="$1"
 	shift
-	msg="$@"
+	_msg="$@"
 	if [ "$opt_no_color" = 1 ] ; then
 		# strip ANSI color codes
-		msg=$(/bin/echo -e  "$msg" | sed -r "s/\x1B\[([0-9]{1,2}(;[0-9]{1,2})?)?[m|K]//g")
+		_msg=$(/bin/echo -e  "$_msg" | sed -r "s/\x1B\[([0-9]{1,2}(;[0-9]{1,2})?)?[m|K]//g")
 	fi
 	# explicitely call /bin/echo to avoid shell builtins that might not take options
-	/bin/echo $opt -e "$msg"
+	/bin/echo $opt -e "$_msg"
 }
 
 _echo()
@@ -250,6 +252,9 @@ while [ -n "$1" ]; do
 	elif [ "$1" = "--no-color" ]; then
 		opt_no_color=1
 		shift
+	elif [ "$1" = "--no-sysfs" ]; then
+		opt_no_sysfs=1
+		shift
 	elif [ "$1" = "--batch" ]; then
 		opt_batch=1
 		opt_verbose=0
@@ -548,46 +553,83 @@ umount_debugfs()
 	fi
 }
 
+sys_interface_check()
+{
+	[ "$opt_live" = 1 -a "$opt_no_sysfs" = 0 -a -r "$1" ] || return 1
+	_info_nol "* Checking wheter we're safe according to the /sys interface: "
+	if grep -qi '^not affected' "$1"; then
+		# Not affected
+		status=OK
+		pstatus green YES "kernel confirms that your CPU is unaffected"
+	elif grep -qi '^mitigation' "$1"; then
+		# Mitigation: PTI
+		status=OK
+		pstatus green YES "kernel confirms that the mitigation is active"
+	elif grep -qi '^vulnerable' "$1"; then
+		# Vulnerable
+		status=VULN
+		pstatus red NO "kernel confirms your system is vulnerable"
+	else
+		status=UNK
+		pstatus yellow UNKNOWN "unknown value reported by kernel"
+	fi
+	msg=$(cat "$1")
+	return 0
+}
+
 ###################
 # SPECTRE VARIANT 1
 check_variant1()
 {
 	_info "\033[1;34mCVE-2017-5753 [bounds check bypass] aka 'Spectre Variant 1'\033[0m"
-	_info_nol "* Checking count of LFENCE opcodes in kernel: "
 
-	status=0
+	status=UNK
+	sys_interface_available=0
+	msg=''
+	if sys_interface_check "/sys/devices/system/cpu/vulnerabilities/spectre_v1"; then
+		# this kernel has the /sys interface, trust it over everything
+		sys_interface_available=1
+	else
+		# no /sys interface (or offline mode), fallback to our own ways
+		_info_nol "* Checking count of LFENCE opcodes in kernel: "
 		if [ -n "$vmlinux_err" ]; then
-		pstatus yellow UNKNOWN "$vmlinux_err"
+			msg="couldn't check ($vmlinux_err)"
+			status=UNK
+			pstatus yellow UNKNOWN
 		else
 			if ! which objdump >/dev/null 2>&1; then
-			pstatus yellow UNKNOWN "missing 'objdump' tool, please install it, usually it's in the binutils package"
+				msg="missing 'objdump' tool, please install it, usually it's in the binutils package"
+				status=UNK
+				pstatus yellow UNKNOWN
 			else
 				# here we disassemble the kernel and count the number of occurences of the LFENCE opcode
 				# in non-patched kernels, this has been empirically determined as being around 40-50
 				# in patched kernels, this is more around 70-80, sometimes way higher (100+)
 				# v0.13: 68 found in a 3.10.23-xxxx-std-ipv6-64 (with lots of modules compiled-in directly), which doesn't have the LFENCE patches,
 				# so let's push the threshold to 70.
-			# TODO LKML patch is starting to dump LFENCE in favor of the PAUSE opcode, we might need to check that (patch not stabilized yet)
+				nb_lfence=$(objdump -d "$vmlinux" | grep -wc lfence)
-			nb_lfence=$(objdump -D "$vmlinux" | grep -wc lfence)
 				if [ "$nb_lfence" -lt 70 ]; then
-				pstatus red NO "only $nb_lfence opcodes found, should be >= 70"
+					msg="only $nb_lfence opcodes found, should be >= 70, heuristic to be improved when official patches become available"
-				status=1
+					status=VULN
+					pstatus yellow UNKNOWN
 				else
-				pstatus green YES "$nb_lfence opcodes found, which is >= 70"
+					msg="$nb_lfence opcodes found, which is >= 70, heuristic to be improved when official patches become available"
-				status=2
+					status=OK
+					pstatus green YES
+				fi
 			fi
 		fi
 	fi
 
-	if ! is_cpu_vulnerable 1; then
+	# if we have the /sys interface, don't even check is_cpu_vulnerable ourselves, the kernel already does it
-		pvulnstatus CVE-2017-5753 OK "your CPU vendor reported your CPU model as not vulnerable"
+	if [ "$sys_interface_available" = 0 ] && ! is_cpu_vulnerable 1; then
-	else
+		# override status & msg in case CPU is not vulnerable after all
-		case "$status" in
+		msg="your CPU vendor reported your CPU model as not vulnerable"
-			0) pvulnstatus CVE-2017-5753 UNK "impossible to check ${vmlinux}";;
+		status=OK
-			1) pvulnstatus CVE-2017-5753 VULN 'heuristic to be improved when official patches become available';;
-			2) pvulnstatus CVE-2017-5753 OK 'heuristic to be improved when official patches become available';;
-		esac
 	fi
+
+	# report status
+	pvulnstatus CVE-2017-5753 "$status" "$msg"
 }
 
 ###################
@@ -595,6 +637,14 @@ check_variant1()
 check_variant2()
 {
 	_info "\033[1;34mCVE-2017-5715 [branch target injection] aka 'Spectre Variant 2'\033[0m"
+
+	status=UNK
+	sys_interface_available=0
+	msg=''
+	if sys_interface_check "/sys/devices/system/cpu/vulnerabilities/spectre_v2"; then
+		# this kernel has the /sys interface, trust it over everything
+		sys_interface_available=1
+	else
 		_info "* Mitigation 1"
 		_info_nol "*   Hardware (CPU microcode) support for mitigation: "
 		if [ ! -e /dev/cpu/0/msr ]; then
@@ -725,10 +775,15 @@ check_variant2()
 		else
 			pstatus yellow UNKNOWN "couldn't find your kernel image or System.map"
 		fi
+	fi
 
-	if ! is_cpu_vulnerable 2; then
+	# if we have the /sys interface, don't even check is_cpu_vulnerable ourselves, the kernel already does it
+	if [ "$sys_interface_available" = 0 ] && ! is_cpu_vulnerable 2; then
+		# override status & msg in case CPU is not vulnerable after all
 		pvulnstatus CVE-2017-5715 OK "your CPU vendor reported your CPU model as not vulnerable"
-	elif [ "$retpoline" = 1 -a "$retpoline_compiler" = 1 ]; then
+	elif [ -z "$msg" ]; then
+		# if msg is empty, sysfs check didn't fill it, rely on our own test
+		if [ "$retpoline" = 1 -a "$retpoline_compiler" = 1 ]; then
 			pvulnstatus CVE-2017-5715 OK "retpoline mitigate the vulnerability"
 		elif [ "$opt_live" = 1 ]; then
 			if [ "$ibrs_enabled" = 1 -o "$ibrs_enabled" = 2 ]; then
@@ -743,6 +798,9 @@ check_variant2()
 				pvulnstatus CVE-2017-5715 VULN "IBRS hardware + kernel support OR kernel with retpoline are needed to mitigate the vulnerability"
 			fi
 		fi
+	else
+		pvulnstatus CVE-2017-5715 "$status" "$msg"
+	fi
 }
 
 ########################
@@ -750,6 +808,14 @@ check_variant2()
 check_variant3()
 {
 	_info "\033[1;34mCVE-2017-5754 [rogue data cache load] aka 'Meltdown' aka 'Variant 3'\033[0m"
+
+	status=UNK
+	sys_interface_available=0
+	msg=''
+	if sys_interface_check "/sys/devices/system/cpu/vulnerabilities/meltdown"; then
+		# this kernel has the /sys interface, trust it over everything
+		sys_interface_available=1
+	else
 		_info_nol "* Kernel supports Page Table Isolation (PTI): "
 		kpti_support=0
 		kpti_can_tell=0
@@ -817,22 +883,31 @@ check_variant3()
 		else
 			pstatus blue N/A "can't verify if PTI is enabled in offline mode"
 		fi
+	fi
 
-	if ! is_cpu_vulnerable 3; then
+	# if we have the /sys interface, don't even check is_cpu_vulnerable ourselves, the kernel already does it
-		pvulnstatus CVE-2017-5754 OK "your CPU vendor reported your CPU model as not vulnerable"
+	cve='CVE-2017-5754'
-	elif [ "$opt_live" = 1 ]; then
+	if [ "$sys_interface_available" = 0 ] && ! is_cpu_vulnerable 3; then
+		# override status & msg in case CPU is not vulnerable after all
+		pvulnstatus $cve OK "your CPU vendor reported your CPU model as not vulnerable"
+	elif [ -z "$msg" ]; then
+		# if msg is empty, sysfs check didn't fill it, rely on our own test
+		if [ "$opt_live" = 1 ]; then
 			if [ "$kpti_enabled" = 1 ]; then
-			pvulnstatus CVE-2017-5754 OK "PTI mitigates the vulnerability"
+				pvulnstatus $cve OK "PTI mitigates the vulnerability"
 			else
-			pvulnstatus CVE-2017-5754 VULN "PTI is needed to mitigate the vulnerability"
+				pvulnstatus $cve VULN "PTI is needed to mitigate the vulnerability"
 			fi
 		else
 			if [ "$kpti_support" = 1 ]; then
-			pvulnstatus CVE-2017-5754 OK "offline mode: PTI will mitigate the vulnerability if enabled at runtime"
+				pvulnstatus $cve OK "offline mode: PTI will mitigate the vulnerability if enabled at runtime"
 			else
-			pvulnstatus CVE-2017-5754 VULN "PTI is needed to mitigate the vulnerability"
+				pvulnstatus $cve VULN "PTI is needed to mitigate the vulnerability"
 			fi
 		fi
+	else
+		pvulnstatus $cve "$status" "$msg"
+	fi
 }
 
 # now run the checks the user asked for